JP4728229B2 - Behavior analysis device - Google Patents

Description

  The present invention relates to a behavior analysis apparatus, and more particularly to a technology for analyzing a behavior of a moving object in a space by position detection using a technology such as wireless communication.

In recent years, fierce service competition has developed in the retail industry, especially large stores. Each retailer is working on the issue of how to provide customers with added value not found in other stores, as well as reducing costs from all angles in order to lower the selling price of goods. Customer needs are diversified, and how to respond to such needs, provide accurate product information at the right time, and arrange sales floors and product lineups that meet customer needs. Directly linked to efficiency.
JP 2003-223548 A

  One of the tools that capture the diversified needs of customers is the POS (Point Of Sales) system. The POS system can collect statistics on sales of products and purchasers based on data input to the cash register of the retail store. However, although “goods that can be sold” and “goods that cannot be sold” are found in the POS data, it is difficult to specify the cause related to the customer's behavior such as “why it sells” or “why it cannot sell”. Therefore, it is difficult to determine whether a product that cannot be sold has a problem with the product itself or simply a problem with the display method, and it is difficult to take appropriate measures.

  On the other hand, in order to promote sales promotion, it is necessary not only to analyze customer behavior in stores, but also to improve employee efficiency, and employee behavior analysis using IT technology is realized with high accuracy. Can be an effective tool across all industries. Various data that can be used for marketing can be obtained by analyzing human behavior in other businesses and applications.

  The present invention has been made under the above background, and an object of the present invention is to provide useful information by analyzing the behavior of a moving object in space.

  In order to solve the above-described problem, a behavior analysis device according to an aspect of the present invention acquires a position information indicating a position of a moving body that changes with time in a predetermined real space and a time information indicating a positioning timing thereof. An acquisition unit, a space acquisition unit that acquires spatial information representing the real space as a position in the virtual space, and a movement path of the moving body in the real space on the virtual space based on the position information, the time information, and the spatial information. The relationship between the route acquisition unit that generates the route information indicated by the position, the speed acquisition unit that generates the velocity information indicating the moving speed of the moving body based on the position information and the time information, and the moving path and the moving speed of the moving body A pattern storage unit for storing a plurality of behavior pattern data in which different behavior patterns are defined as behavior types based on the path information, speed information, and a plurality of behavior pattern data Based on data provided and determines the pattern determining section for determining behavior of the moving object matches one of the types of behavior patterns, and an output processing unit that outputs a result of the determination, the.

  Here, “mobile” refers to, for example, a customer who visits a store, a shopping cart or a basket of the customer, a store employee, a visitor or employee in an entertainment facility such as a theme park, or a player in a competition space. Indicates a person moving in space or an accessory. In “behavior pattern data”, the type of behavior pattern of a moving object in the entire predetermined space is defined, and the type of behavior pattern of the moving object in each of a plurality of areas included in the predetermined space is defined. Any of them may be used. According to this aspect, since not only the moving path of the moving body in the space but also the moving speed thereof is acquired, it takes time to simply pass through the sales floor and consider purchasing the product even if the same moving path is, for example, a store space. Can be distinguished. Therefore, it is possible to accurately estimate the behavior of a person such as the purchase behavior of a customer or the behavior of an employee, and the factors of such behavior.

  The space acquisition unit acquires, as space information, each coordinate for specifying the arrangement of a plurality of regions included in the real space on the virtual space, and the route acquisition unit determines the movement path of the moving object in the real space in the virtual space. The route information shown in the above position is generated together with information on which of the plurality of areas the moving body has passed, and the speed acquisition unit, as speed information, the average speed of the moving body in all of the plurality of areas, Information indicating at least one of the average speed of the moving body in each of the plurality of areas and the instantaneous speed of the moving body is generated, and the pattern determination unit relates to which of the plurality of areas the moving body has passed. The match of the action pattern may be determined based on the route information including the information, the speed information, and the plurality of action pattern data.

  The position acquisition unit acquires position information indicating the position of a moving body in a space in a predetermined store as a real space and its time information, and the space acquisition unit displays the arrangement of a plurality of sales floors included in the store on a virtual space. Each coordinate for specifying is acquired as spatial information, and the route acquisition unit displays route information indicating the moving route of the moving object in the space in the store by the position in the virtual space, and the moving object is a plurality of sales floors. The speed acquisition unit generates, as speed information, the average speed of the mobile body in all of the sales floor areas, the average speed of the mobile body in each of the sales floor areas, and the speed of the mobile body. Information indicating at least one of the instantaneous velocities is generated, and the pattern determination unit includes route information and speed information including information on which of the plurality of sales floors the mobile object has passed. The coincidence of behavior patterns on the basis of the fine plurality of action pattern data may be determined. In this case, since a customer's action can be analyzed for every sales floor, the exact useful information leading to sales promotion can be obtained for every sales floor or goods.

  This behavior analysis device uses at least one of a plurality of wireless communication devices installed at different positions in real space, as intensity information indicating the strength of radio waves transmitted or received by a communication device possessed by a mobile object. And a position recognizing unit that generates position information and time information indicating the position of the moving body based on the intensity information. Here, the “wireless communication apparatus” may be a wireless base station also called a so-called access point. In this case, position information and time information can be acquired using wireless LAN technology that is widely used as hardware, and behavior of a moving object such as a customer who has visited the store can be analyzed at a relatively low cost. The “communication device possessed by the mobile body” is mainly assumed to be a wireless LAN terminal, but may be realized by an IC tag (RFID) incorporating a wireless function.

  This behavior analysis device transmits a radio wave between at least one of a plurality of wireless communication devices installed at different positions in a real space and a wireless communication medium possessed by a mobile object, and then transmits the wireless radio wave. You may further provide the position recognition part which produces | generates the positional information and time information which show the position of a moving body based on the length of time until one side receives the radio wave as a reply by the other which received the electromagnetic wave. The “wireless communication device” and the “wireless communication medium possessed by the moving body” here are also the same as described above, and may be a wireless LAN or an IC tag.

  In this behavior analysis device, an IC tag or a wireless communication device possessed by a mobile body communicates with any of a plurality of wireless communication devices or a plurality of IC tags installed at different positions in real space. A position recognizing unit that generates position information and time information indicating the position of the moving body based on whether the moving object is located may be further provided.

  The behavior analysis apparatus specifies an image acquisition unit that acquires an image captured from a predetermined angle in real space, and an object that moves between a plurality of images acquired by the image acquisition unit as a moving object. A position recognition unit that generates position information and time information of the moving body by recognizing the position of the object in the space. The “imaging” referred to here may be special imaging using reflected waves when ultrasonic waves, microwaves, infrared rays, electromagnetic waves or the like are applied to an object in addition to imaging using a CCD sensor or a CMOS sensor. .

  The pattern determination unit may acquire data indicating purchase contents of a customer who is a mobile body, and may estimate a factor of purchase quality based on the data indicating the purchase contents and the type of matching behavior pattern. For example, you may acquire the data which show the purchase content of a customer using POS data. Since it is considered that there is a correlation between the degree of sales of the product and the behavior pattern of the customer, the cause of good sales and the reason of poor sales can be grasped relatively easily by combining the two.

  The pattern determination unit determines the position of the settlement area where the customer stayed for product purchase and the date and time of product purchase based on the route information, and displays data indicating purchase contents corresponding to the position of the settlement area and the date and time of product purchase. The acquired data may be associated with the route information.

  The pattern determination unit is based on route information, speed information, and a matching behavior pattern type, and attribute pattern data in which route information, speed information, and behavior pattern type conditions are defined for each customer attribute. You may estimate the attribute of the customer who is a moving body. In some cases, there is a high correlation between customer attributes and behavior patterns, and by making such relationships data beforehand as attribute pattern data, it is relatively easy to estimate customer attributes according to behavior patterns. Can do.

  The pattern determination unit acquires the attribute of the customer as a mobile object, stores the determined behavior pattern in advance in the pattern storage unit as attribute pattern data associated with the attribute, and stores the attribute pattern stored in the pattern storage unit By referring to the data, an attribute of a customer whose attribute is not known may be estimated.

  A product information storage unit that stores information that can be provided to the customer regarding the product to be sold in association with the sales floor of the product and the type of behavior pattern, and can be provided to a customer who is a mobile object according to the type of matching behavior pattern And an information distribution unit that transmits information to a communication device held by the customer. Since the current state can be estimated from the current position of the customer and the behavior pattern of the customer, it is possible to lead to sales promotion and sales efficiency of the product by actively distributing information that matches the position and state. .

  The plurality of action pattern data stored in the pattern storage unit is compared with the first pattern indicating the case where the sales floor area is passed as a type of the purchase behavior of the customer who is a moving object in the determination target sales area, compared with the sales area. For each sales area, the second pattern indicating the case where the product is purchased or considered after being stopped for a short time, and the third pattern indicating the case where the product stays for a long time in one sales area. A criterion for at least one of acceleration / deceleration is determined in advance, and the pattern determination unit determines which of the first pattern, the second pattern, and the third pattern the customer's behavior as a moving object matches. You may judge. The “stop” here may include a case where the vehicle stays to such an extent that it is substantially regarded as a stop, or a case where the traveling speed is much lower than the average speed. As a reference regarding “acceleration / deceleration”, for example, presence or absence of sudden deceleration may be determined. Thereby, a customer's purchasing behavior can be estimated accurately.

  The pattern determination unit calculates a stay time from entry to exit each time a mobile object enters each of a plurality of sales floor areas, and the mobile object that has purchased a product based on data indicating route information and purchase details Identify the sales area of the purchased product, and specify the staying time of the moving body in the sales area as the staying time at the time of purchasing the product, and for each of the multiple sales areas, daily or time The actual shortest time and the longest time for each band are specified, and the average shortest time obtained by averaging the actual shortest time over a plurality of days or a plurality of time periods is calculated for each sales area, and this is used as the first pattern. The first threshold value for distinguishing the second pattern is stored in the pattern storage unit in a form corresponding to the sales area, and each sales area has a plurality of days or a plurality of days. An average longest time obtained by averaging the substantial longest time over the interband is calculated and stored in the pattern storage unit as a second threshold value for distinguishing the second pattern from the third pattern. When the staying time in a certain sales floor area of a mobile object to be determined falls below a first threshold value associated with the sales floor area, it is determined that the behavior pattern of the mobile body matches the first pattern with respect to the sales floor area. If the staying time in a certain sales area of a moving object subject to action pattern determination is equal to or greater than the first threshold value associated with the sales area and falls below the second threshold value, the sales area It is determined that the behavior pattern of the moving object matches the second pattern with respect to the area, and the stay time in a certain sales area for the moving object that is the target of the action pattern Behavior pattern of the mobile with respect to the second of the sales area the case of equal to or more than the threshold value associated with the field region may be determined to match the third pattern.

  Here, “when the value falls below the first threshold value” as the determination criterion of the first pattern does not mean that the values near the first threshold value are strictly distinguished. It may also be determined that the first pattern matches the first threshold value or the first threshold value is within a predetermined range. Similarly, the determination criterion of the second pattern is “when it is equal to or higher than the first threshold value and below the second threshold value”, and the determination criterion of the third pattern is “the second threshold value. The case of “below” does not mean that the values near the respective threshold values are strictly distinguished. In addition, “substantially shortest time” and “substantially longest time” are intended to exclude abnormal values that are extremely short or long, and have a plurality of values related to the stay time specified in one day. Of these, for example, the shortest time and the longest time, excluding values in the range of 10% above and below, may be set as the actual shortest time and longest time, respectively.

  The “plurality of days” may be specified by, for example, a day of the week, may be specified by a combination of a month and a day of the week, or may be specified by a way of dividing a weekday and a holiday. “Multiple time zones” may be specified by, for example, only the time zone, may be specified by a combination of day of the week and time zone, may be specified by a combination of month, day of the week, and time zone, It may be specified by a combination of a method for dividing weekdays and holidays and a time zone.

  When the pattern determination unit represents the relationship between the staying time in the sales area and the number of customers who stayed for each sales floor area, among the customers whose staying time is shorter than the first time value, the customer who purchased the product in the sales floor area A time value that makes the ratio between the total and the total number of customers who did not purchase products in the sales area a predetermined ratio is identified as a first time value for each day or time zone, and there are multiple time values for each sales area. An average value of first time values over a day or a plurality of time zones is calculated and stored in the pattern storage unit as a first threshold value for distinguishing between the first pattern and the second pattern. When the relationship between the staying time in that area and the number of customers staying is expressed, the total of the customers who purchased products in the sales area among the customers whose staying time is longer than the second time value, and the purchase of goods in the sales area Sum of customers who did not have A time value at which the percentage of the product becomes a predetermined rate is specified as a second time value for each day or every time zone, and the average value of the second time values over a plurality of days or a plurality of time zones for each sales area Is calculated and stored in the pattern storage unit as a second threshold value for distinguishing the second pattern from the third pattern. If the first threshold value associated with the sales area falls below the first threshold, it is determined that the behavior pattern of the moving object matches the first pattern with respect to the sales area, and there is a certain sales area for the moving object whose behavior pattern is to be determined. When the staying time in is greater than or equal to the first threshold value associated with the sales floor area and falls below the second threshold value, the behavior pattern of the mobile object for the sales floor area is the second If it is determined that it matches the turn and the staying time in the sales area of the mobile object that is the target of the action pattern determination is greater than or equal to the second threshold value associated with the sales area, the mobile object is related to the sales area. It may be determined that the behavior pattern matches the third pattern.

  The pattern determination unit determines whether the customer who is a moving body is at least one of the flow line distance from the store entry to the store exit in the entire space in the store, the store entry time, the stay time, the average speed, and the total number of stops. Are classified into a plurality of segments, the first threshold value and the second threshold value are calculated for each segment and stored in the pattern storage unit. After determining whether it corresponds to any of the flow line distance from store entry to store exit, store entry time, stay time, average speed, and total number of stops in the entire store space The first pattern, the second pattern, or the third pattern may be determined based on the first threshold value and the second threshold value corresponding to the corresponding segment. .

  The pattern determination unit categorizes the behavior of the moving customer as the first pattern and the second pattern and the third pattern, and calculates the ratio of product purchase in each pattern. The reference value for estimating the factor of whether or not the product is purchased may be determined.

  In this case, the presence or absence of the customer's interest in the product can be estimated for each sales area based on which pattern matches. For example, if it matches the first pattern, it can be estimated that there is no interest in the products in the sales area, and if it matches the second pattern or the third pattern, it can be estimated that there is interest in the products in the sales area. Based on such interests, you can estimate whether you did not purchase because you were not interested as a factor that did not purchase the product, or whether you did not purchase it despite being interested, It is possible to estimate factors such as whether it was based or impulse purchase, and useful marketing information can be obtained.

  The pattern determination unit determines the number of purchases or the purchase amount of the product with respect to the number of times of any of the first pattern, the second pattern, and the third pattern for each sales floor area as a factor of the quality of purchase by a customer who is a mobile object. Alternatively, the number of times of the first pattern, the second pattern, and the third pattern may be calculated. Thereby, the factor of a customer's purchase quality can be estimated accurately.

  Note that any combination of the above-described constituent elements, and those in which the constituent elements and expressions of the present invention are mutually replaced between methods, apparatuses, systems, and the like are also effective as an aspect of the present invention.

  ADVANTAGE OF THE INVENTION According to this invention, useful information can be provided by analyzing the action of the moving body in space.

It is a functional block diagram which shows the structure of a customer behavior analysis system. It is a figure which shows typically the relationship between the classification | category based on a customer's state, and the number of purchasers. It is a figure which shows the external appearance of a shopping cart. It is a figure which shows typically the sales floor arrangement in the store on the virtual space defined by the spatial information. It is a figure which shows typically the sales area which was hierarchized. It is a figure which shows typically the example of the movement path | route of the shopping cart in a sales area. It is a functional block diagram which shows the structure of the customer behavior analysis system in Example 2. It is a functional block diagram which shows the structure of the customer behavior analysis system in Example 3. It is a functional block diagram which shows the structure of the customer behavior analysis system in Example 4. The image which image | photographed a certain sales floor area from the bird's-eye view is illustrated. It is a figure which shows typically the photography condition of the sales floor image in FIG. 10 from the side. It is the figure which applied the cylindrical body model to the sales floor image of FIG. It is a figure which shows typically the method of detecting the same moving body in the overlapping imaging | photography range. It is a figure which shows typically the example of the imaging range of each camera in a shop. It is a functional block diagram which shows the structure of the customer behavior analysis system in Example 5. It is a functional block diagram which shows the structure of the customer behavior analysis system in Example 6. It is a figure which shows the relationship between the stay time in a sales area, and the number of customers. It is a figure which shows the example of a screen which displays as a list the length of time for every action state of an employee.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 10 Customer behavior analysis system, 20 Customer behavior analysis apparatus, 22 Communication part, 24 Strength acquisition part, 26 Position recognition part, 28 Position information storage part, 30 Position acquisition part, 32 Speed acquisition part, 34 Path | route acquisition part, 36 Space acquisition Unit, 38 spatial information storage unit, 40 data setting unit, 42 pattern determination unit, 44 behavior pattern data storage unit, 46 determination result storage unit, 48 output processing unit, 50 information distribution unit, 56 display unit, 58 product information storage unit , 60 shopping cart, 62 liquid crystal display device for cart.

Example 1
Even if it is possible to grasp “sellable products” and “unsellable products” by referring to data indicating purchase contents such as POS data, the purchase factors such as “why sell” and “why cannot sell” It is difficult to identify. According to the system of this embodiment, it is possible to grasp the intention of the customer at the sales floor and the process of purchasing the product based on statistical data, and objectively guess the interest and interest of each customer for the product at the sales floor. You can get useful marketing information.

  FIG. 1 is a functional block diagram showing the configuration of the customer behavior analysis system. The customer behavior analysis system 10 includes a first access point 12, a second access point 14, a third access point 16 that are a plurality of wireless LAN base stations, and a customer behavior analysis device 20. The “plurality of wireless LAN base stations” are provided with at least three access points for positioning using the strength of the radio wave between the mobile body and each base station. In the present embodiment, three access points including the first access point 12, the second access point 14, and the third access point 16 are illustrated, but actually four according to the size of the store and the sales area. The above access points may be used.

  Here, for example, IEEE802.11a / b / g is used as the wireless LAN system. The first access point 12, the second access point 14, and the third access point 16 communicate with each other via a wireless LAN via a communication device provided in the customer's shopping cart via the antenna, and also via the LAN 18. Data is transmitted to and received from the behavior analysis device 20. The customer behavior analysis apparatus 20 acquires POS data as data indicating purchase contents from the POS server 19 via the LAN 18. The POS data includes information related to customer purchases. The POS server 19 is connected to a plurality of cash registers (not shown), and acquires information related to customer purchases such as the product name or product ID, the number, the sales price, the sales date and time, and the customer ID sold from each cash register. The customer ID may be, for example, the ID of a membership card issued to the customer. In this case, the POS server 19 does not acquire a customer ID from a customer who does not own the membership card.

  The customer behavior analysis device 20 includes a communication unit 22, an intensity acquisition unit 24, a position recognition unit 26, a position information storage unit 28, a position acquisition unit 30, a speed acquisition unit 32, a route acquisition unit 34, a space acquisition unit 36, and a spatial information storage. Unit 38, data setting unit 40, pattern determination unit 42, behavior pattern data storage unit 44, determination result storage unit 46, output processing unit 48, information distribution unit 50, operation input unit 52, control unit 54, display unit 56, product An information storage unit 58 is provided. The communication unit 22 transmits / receives data to / from the first access point 12, the second access point 14, the third access point 16, and the POS server 19 via the LAN 18.

  The strength acquisition unit 24 receives data indicating the radio field strength from the first access point 12, the second access point 14, and the third access point 16 via the communication unit 22. This radio wave intensity is the intensity of radio waves transmitted / received to / from a communication device provided in a shopping cart used by a customer. Each shopping cart communicator transmits data indicating the intensity of radio waves transmitted to and received from the first access point 12, the second access point 14, and the third access point 16 to the first access point 12, the second access point 12, and the second access point 12. Transmit to at least one of the access point 14 and the third access point 16, and this is acquired by the strength acquisition unit 24 via any one of the first access point 12, the second access point 14, and the third access point 16. . The position recognition unit 26 recognizes the position of the shopping cart from the difference in radio wave intensity from the same shopping cart received by the strength acquisition unit 24 from the first access point 12, the second access point 14, and the third access point 16. . That is, the position recognition unit 26 obtains the distance from each access point to the shopping cart based on the radio wave intensity received from each access point, and recognizes the point where the distance intersects as the current position of the shopping cart. The position recognizing unit 26 generates position information that is the current position of the customer that changes with time in the store and time information that indicates the timing at which the position information is measured, and stores the position information in the position information storage unit 28. This position information indicates the relative position of the shopping cart with respect to the three access points, and is represented by, for example, three-dimensional coordinates (x, y, z). Further, it may be expressed as (x, y, z, t) together with time information, or may be expressed by two-dimensional coordinates (x, y) or (x, y, t). The location information of the three access points is set in advance based on information input from the administrator. That is, at the time of installation of each access point, the manager inputs the approximate position via the operation input unit 52, and the position recognition unit 26 corrects the input value based on the radio wave intensity between the access points to accurately The position information is recognized, and the position information is stored in the position information storage unit 28.

  The position acquisition unit 30 acquires, from the position information storage unit 28, position information and time information of a shopping cart used by a customer who has made a purchase in the store or who is shopping. That is, the position acquisition unit 30 acquires position information and time information continuously measured from when the customer enters the shop and starts using the shopping cart until the use of the shopping cart ends.

  The speed acquisition unit 32 generates speed information indicating the moving speed of the customer based on the position information and the time information. For example, the speed acquisition unit 32 includes an average speed, a maximum speed, and an average number of stops for all shopping carts, an average speed from the start of use to the end of use for each shopping cart, a maximum speed, and the number of stops, an average speed for each sales area, The maximum speed, the average number of stops, the average speed for each sales area for each shopping cart, the maximum speed, the number of stops, and the speed of the shopping cart currently in use are calculated. Flow line distance from start to use of shopping cart throughout store, entrance time, stay time, average speed or average speed excluding third pattern, total number of stops, sales floor determined to match first pattern The combination or permutation of the areas, the combination or permutation of the sales floor areas determined to match the second pattern, the combination or permutation of the sales floor areas determined to match the third pattern, and Classify customers into multiple customer segments. For example, it may be classified into high speed, medium speed, and low speed based on an arbitrary speed. In this case, for example, customers who are slow on average such as the elderly and physically handicapped customers and customers who are fast on average such as young people are separated in terms of data. Can be increased. Parameters such as a minimum value, a maximum value, an average value, and a threshold value, which will be described later, are calculated for each customer segment, and behavior pattern determination and customer attribute estimation are processed for each customer segment. However, as a modification, parameters such as minimum value, maximum value, average value, and threshold value are calculated for the entire customer, not for each customer segment, and behavior pattern determination and customer attribute estimation are performed based on the parameters. It may be processed. In addition, as the “average speed” here, an average speed in a period excluding a “freeze” state described later is also calculated.

  The space acquisition unit 36 acquires space information representing the space in the store by the position in the virtual space. In the spatial information, coordinates indicating the overall area of the store and coordinates for specifying the arrangement of a plurality of sales floors included therein are defined in the virtual space. The positions of the first access point 12, the second access point 14, and the third access point 16 are also determined in the spatial information. Based on the position information, time information, and space information, the route acquisition unit 34 generates route information that indicates the movement route of the customer in the space in the store by the position in the virtual space. The route acquisition unit 34 generates route information together with information regarding which of the plurality of sales floor areas the customer has passed. In this way, the route information is generated in units of sales floor areas, and all routes from the start of use to the end of use can be recognized by connecting the route information for one shopping cart in time series.

  The behavior pattern data storage unit 44 stores a plurality of behavior pattern data in which different behavior patterns are defined as types of purchase behavior based on the relationship between the movement route and the movement speed of the customer. The types of purchasing behavior defined in the plurality of behavior pattern data are “passing”, which is the first pattern that passes through the sales floor area without showing the behavior of the purchase examination such as stoppage or sudden deceleration, for example. There is “active” which is a second pattern in which goods are stopped for a short time and goods are put into a shopping cart or at least considering the purchase of goods. In the plurality of behavior pattern data, an average stay time, an average travel speed, whether or not the cart is stopped, and whether or not there is a sudden deceleration is determined in advance for each sales floor area for various purchasing behaviors. The plurality of behavior pattern data is determined for each sales floor area, and the pattern determination unit 42 periodically or irregularly calculates the average staying time and average travel speed in each sales floor area, and calculates the average value. Based on this, the plurality of behavior pattern data stored in the behavior pattern data storage unit 44 is updated. Since the criteria for distinguishing the behavior patterns differ depending on the product configuration and arrangement for each sales floor area, the standards are frequently updated for each sales floor area to reflect changes in the product configuration and arrangement in the discrimination of the behavior patterns. The pattern determination unit 42 stores in the determination result storage unit 46 the determination result indicating whether the customer's behavior matches one of passing, active, and freeze with the sales area. The pattern determination unit 42 stores, in the determination result storage unit 46, combinations or permutations of sales floor areas in which customer behavior matches the passing, combinations or permutations of sales floor areas that match actively, and combinations or permutations of sales floor areas that match the freeze. Store.

  The pattern determination unit 42 determines which of the behavior pattern types the customer's purchase behavior matches based on the route information, the speed information, and the plurality of behavior pattern data. The pattern determination unit 42 acquires POS data as data indicating purchase contents from the POS server 19 via the communication unit 22 and uses the POS data as information for determining the purchase behavior of the customer. The POS data includes information related to the purchase of the customer such as the product name or product ID, the number of purchases, the purchase price, the purchase date and time, the customer ID, and the settlement area ID, and information related to the customer. The customer ID is identification information given to identify the customer. For example, the customer ID is registered in a membership card, and the ID is input via the cash register at the time of payment. Note that the customer ID is not included in the POS data regarding the customer who does not own the membership card. The settlement area ID is identification information given in advance for each cash register in order to distinguish a plurality of cash registers. The position coordinates of a plurality of settlement areas in which each cash register is installed are determined in the spatial information, and each is associated with a settlement area ID in advance. The pattern determination unit 42 associates the POS data with the route information based on the purchase date / time, the settlement area ID, and the route information. That is, the route information records when the settlement area is passed, and the POS data is associated with the path information with reference to the purchase date and time and the settlement area ID included in the POS data.

  The pattern determination unit 42 extracts the customer ID from the POS data, and acquires the customer attribute from the POS server 19 based on the customer ID. As a modified example, customer attribute data itself may be included in the POS data. The customer attribute is an element that can distinguish the type of customer, such as gender and age group, and can influence the behavior. The pattern determination unit 42 stores the behavior pattern determined to match the behavior pattern data storage unit 44 in association with the type of customer attribute. Then, the pattern determination unit 42 estimates the attribute of the customer whose attribute is not known by referring to the correspondence relationship between the behavior pattern and the attribute stored in the behavior pattern data storage unit 44. The pattern determination unit 42 estimates the purchase behavior of the customer based on information regarding which of the plurality of sales floors the customer has passed and the type of matching behavior pattern. Details of the determination method and the estimation method by the pattern determination unit 42 will be described later. The determination result and estimation result of the pattern determination unit 42 are stored in the determination result storage unit 46.

  The output processing unit 48 outputs the determination result stored in the determination result storage unit 46 through the display unit 56 or the communication unit 22. That is, the output processing unit 48 displays the determination result on the screen of the display unit 56 and transmits the determination result to the outside via the communication unit 22. The merchandise information storage unit 58 stores information that can be provided to the customer regarding the merchandise to be sold in association with the sales floor of the merchandise and the type of action pattern. The information distribution unit 50 sends information that can be provided to the customer according to the type of the customer's behavior pattern determined by the pattern determination unit 42 to the output processing unit 48, and the output processing unit 48 stores the information in the customer's shopping cart. The data is transmitted to the provided liquid crystal display device or POS server 19. The operation input unit 52 receives an operation by an administrator of the customer behavior analysis system 10, and the control unit 54 controls each unit of the customer behavior analysis device 20 based on the operation.

Hereinafter, a behavior pattern determination method and a purchase behavior estimation method by the pattern determination unit 42 will be described. Two examples are given as behavior pattern determination methods. One is (A) a method of judging according to the time from entry to exit of the sales floor area and whether it is stopped or suddenly decelerated in the sales floor area, and the other is (B) to the sales floor area. This is a method of judging only by the staying time from entering to leaving.
In the case of (A), the following five patterns are defined as the plurality of behavior pattern data.
(1) Passing ... The stay time from entry to exit in the sales area is less than X seconds and there is no stop or sudden deceleration. (2) Active ... The stay time from entry to exit in the sales area is X More than a second and less than Y seconds, or the stay time from entry to exit in the sales area is less than X seconds, or there is a sudden slowdown. (3) Freeze ... The stay time from entry to exit in the sales area Y seconds or more (4) Refreeze: Repeat freeze in the same sales area (5) Repassing: Repeat the same sales area: Here, the pattern determination unit 42 exits from entering the sales area. Is calculated for each sales area, and the actual minimum value of the day or the time zone is XX [seconds], and the actual maximum value of the day or the time zone is YY [seconds]. . Here, a substantial minimum value for a cart that has purchased a product in the sales area, a substantial minimum value for a cart that has stopped or suddenly decelerated in the sales area, and a stop or rapid deceleration in the sales area. Then, the administrator selects either a practical minimum value for the cart from which the product was purchased, or a value set by the system administrator, and the selected value is XX [seconds of the day or the time period] ]. In addition, the actual maximum value for carts that purchased products in the sales area, the actual maximum value for carts that stopped or suddenly decelerated in the sales area, and stopped or suddenly decelerated in the sales area The administrator selects either the actual maximum value for the cart from which the product was purchased above, or a value set by the system administrator, and the selected value is YY [seconds] for the day or the time zone. And The pattern determination unit 42 averages the substantial minimum value XX and the substantial maximum value YY over a plurality of days or a plurality of time periods, and obtains an average value X [seconds] and an average value Y [seconds]. These average values X and Y serve as a threshold value as a reference for distinguishing between passing, active and freezing. Note that XX, YY, X, and Y may be calculated for each day of the week in addition to the calculation for each day or each time zone.

In the case of (B), the following five patterns are defined as the plurality of behavior pattern data.
(1) Passing: Stay time from entry to exit in the sales area is less than X seconds (2) Active: Stay time from entry to exit in the sales area is less than Y seconds (3) Freeze ・ ・ ・ Stay time from entry to exit of the sales area over Y seconds (4) Refreeze ... Repeat freeze in the same sales area (5) Repassing ... Repeat the same sales area Here, the pattern determination unit 42 calculates the stay time taken from the entry to the exit of the sales area for each sales area, and the actual minimum value of the day or the time zone is set to XX [seconds]. Let YY [seconds] be the substantial maximum value of the time period. Here, a substantial minimum value for a cart that has purchased a product in the sales area, a substantial minimum value for a cart that has stopped or suddenly decelerated in the sales area, and a stop or rapid deceleration in the sales area. Then, the administrator selects either a practical minimum value for the cart from which the product was purchased, or a value set by the system administrator, and the selected value is XX [seconds of the day or the time period] ]. In addition, the actual maximum value for carts that purchased products in the sales area, the actual maximum value for carts that stopped or suddenly decelerated in the sales area, and stopped or suddenly decelerated in the sales area The administrator selects either the actual maximum value for the cart from which the product was purchased above, or a value set by the system administrator, and the selected value is YY [seconds] for the day or the time zone. And The pattern determination unit 42 averages the substantial minimum value XX and the substantial maximum value YY over a plurality of days or a plurality of time periods, and obtains an average value X [seconds] and an average value Y [seconds]. These average values X and Y serve as a threshold value as a reference for distinguishing between passing, active and freezing.

  The pattern determination unit 42 determines for each sales floor area whether the movement of the shopping cart matches (1) to (5). In the case of (1), it is presumed that the sales area has simply been passed, and in the case of (2), it is presumed that a product in the sales area has been purchased or at least purchased. In the case of (3), it is estimated that although there is a strong interest in the product in the sales area, the product is not found or purchase is lost. In the case of (4), it is presumed that the purchase is lost due to repeated freezes. In the case of (5), it is estimated that the more repeated the passing, the more lost or the product cannot be found. As described above, the pattern determination unit 42 can estimate the purchase behavior of the customer if the behavior pattern type is known.

  The pattern determination unit 42 determines the traveling direction, the moving speed, and whether or not there is a stop for each shopping cart based on the position information and the time information. The pattern determination unit 42 can determine whether the sales area has been entered in the forward direction or the reverse direction based on the traveling direction. Further, the pattern determination unit 42 can determine whether or not the customer is in a hurry based on the moving speed of the shopping cart. Further, the pattern determination unit 42 can determine whether the customer has decided on a product or shopping based on the speed of the shopping cart, the presence or absence of sudden deceleration, and the presence or absence of a stop.

  The pattern determination unit 42 estimates the attribute of the customer based on the customer's behavior pattern or purchase behavior. For example, on Saturdays, Sundays, and holidays, a customer whose movement speed is slow and whose average residence time in each sales area is relatively long is extracted, and the customer is estimated to be “family”. Further, in stores that handle merchandise other than groceries such as clothing and miscellaneous goods, customers who pass through most or all of the sales areas for men, women, and children are estimated as “family families”. Thus, the pattern determination unit 42 may make different determinations according to the day of the week, the time zone, and the sales floor. The pattern determination unit 42 determines the number of passing / freezing sales areas with respect to the number of sales areas where the number, ratio, and time of passing and freezing exceed a predetermined abnormal value standard, for example, the number of sales areas that have passed from entering the store to leaving the store. It may be determined that a moving object whose ratio is higher than a predetermined reference is a suspicious person. Moreover, you may determine with a suspicious person the moving body in which the freeze time in a specific sales area is longer than a predetermined abnormal value, or the moving body with the number of times of freezing more than a predetermined abnormal value. Also, the flow line distance from entry to exit, entry time, stay time, average speed or average speed excluding the third pattern, total number of stops, combination or permutation of sales floor areas determined to match the passing, When at least one of the combination or permutation of the sales area determined to match the active and the combination or permutation of the sales area determined to match the freeze corresponds to the predetermined abnormal condition, the pattern determination unit 42 The mobile body is determined to be a suspicious person. For example, a suspicious person is a moving body that has a very long time of staying in the store for several hours, or a moving body that has a long distance such that the flow line distance in the store far exceeds the normal time. May be determined. Moreover, you may determine with a suspicious person the mobile body whose average speed is slower than a predetermined | prescribed abnormal value, and the mobile body whose average speed is faster than a predetermined | prescribed abnormal value. The output processing unit 48 may transmit the determination result of the suspicious person, for example, to a terminal carried by a guard.

  Next, the pattern determination unit 42 estimates a factor of the good or bad sales of the product using the total of the customer behavior patterns and the determination result regarding the purchase behavior. For example, the pattern determination unit 42 can compare the product sales ability of each sales floor area from a plurality of cut points. The customer's actions in each sales floor area and the process of purchasing the product are tabulated as “performance indicators” for each sales floor area and compared with past tabulations or between different sales floors. Compare aggregates. The comparison result is stored in the output processing unit 48. For example, the number of sales and purchases in each sales floor area, the area of the sales floor area, the number of passing carts, the number of active traffic carts, the number of freeze traffic carts, the total cart stay time, the total number of cart stops, Count and compare numbers divided by density. The output processing unit 48 reads the comparison result from the determination result storage unit 46 and causes the display unit 56 to display the comparison result.

  Details of the analysis will be described below. For each sales area, the pattern determination unit 42 first selects (1-1) the number of purchases, (1-2) the purchase price, (1-3) the number of passing, the number of actives, and the number of freezes from entering the store to leaving the store. Purchase probability as a ratio of the number of purchases, (1-4) Purchase probability as a ratio of the number of purchases to the number of stops, (1-5) Average speed, (1-6) Stay time, (1-7) From entering the store The flow line distance to the store exit, (1-8) customer attributes, (1-9) number of stops, (1-10) passing ratio, active ratio, and freeze ratio are calculated. Here, the “passing ratio” is, for example, the ratio of the number of passing times to the sum of the number of passing times, the number of active times, and the number of freezing times. Similarly, the “active ratio” is, for example, the ratio of the number of active times to the sum of the number of passing times, the number of active times, and the number of freeze times, and the “freeze ratio” is, for example, the sum of the number of times of passing, active times, and freeze times Percentage of freezes.

  The pattern determination unit 42 totals the information (1-1) to (1-10) for each shopping cart for all customers, and classifies or compares the following elements as cut points according to user requests. The elements of the classification are, for example, (1-A) sales area, (1-B) time and day of the week, (1-C) average speed, (1-D) dwell time, (1-E) traffic line distance, (1 -F) Customer attributes, (1-G) Number of stops, (1-H) Purchase amount, Number of purchases. The output processing unit 48 is a graph in which any one of (1-A) to (1-H) is taken on the x axis and any one of the information (1-1) to (1-10) is taken on the y axis. Is output to the display unit 56 or the like. The user selects the elements on the x-axis and the y-axis.

  The pattern determination unit 42 also determines (2-1) the number of traffic, that is, the number of customers, (2-2) the number of purchases, (2-3) the purchase price, (2-4) the passing ratio, and the active ratio for each sales area. , Freeze ratio, (2-5) purchase probability as the ratio of the number of purchases to each of the number of passing, active number, and freeze, (2-6) purchase probability as the ratio of the number of purchases to the number of stoppages, (2-7) ) Average speed, (2-8) Average stay time, (2-9) Average traffic line distance from entry to the sales area, (2-10) Customer attribute, (2-11) Average stop count, 2-12) Area information of the sales area, (2-13) Shopping cart density in the sales area, and (2-14) purchased product information are calculated.

  The pattern determination unit 42 classifies or compares each information of (2-1) to (2-14) for each sales floor area with the following elements as the cut points according to the user's request. The elements of the classification are, for example, (2-A) customer status divided by passing, active, and freeze, (2-B) sales area, (2-C) time and day of the week, (2-D) leaving the store. Average speed until (2-E) stay time from entry to exit, (2-F) traffic distance from entry to sales area, (2-G) customer attributes, (2-H) Stop count, (2-I) purchase price, purchase count, (2-J) purchased product. The output processing unit 48 is a graph in which any one of (2-A) to (2-J) is taken on the x-axis and any one of the information (2-1) to (2-14) is taken on the y-axis. Is output to the display unit 56 or the like. The user selects the elements on the x-axis and the y-axis.

  FIG. 2 schematically shows the relationship between the classification based on the customer state and the number of purchasers. The pattern determination unit 42 determines the number of passing times, the number of active times, the number of active times, the tendency of the product purchase such as whether the customer often immediately decides to purchase the product for each sales floor area, Judge based on the number of freezes. As an example, the total number of times a product is purchased for each sales area, the number of passing, the number of active times, and the number of freezes are aggregated for the entire customer. In the figure, the number 130 of prospective purchasers is the sum of the number of active times and the number of freezes in a certain sales area, and is positioned as at least the number of customers who are interested in products in that sales area and have entered. The actual purchaser number 132 is the number of customers who have actually purchased a product in the sales area calculated based on the POS data. The number of customers 136, which is a portion where the circle of the prospective purchaser number 130 and the actual purchaser number 132 overlap, is the number of customers who have actually purchased from the customers who are interested in the sales area. The number of customers 134 is the number of customers who are interested in the sales area but have not actually purchased. If there are many, the number of customers is out of stock, poor quality, low product power, It can be estimated that negative factors such as high prices exist at the sales floor. On the other hand, the number of customers 138 is the number of customers who were in a passing state that was not scheduled to purchase, and it can be estimated that there are positive factors such as impulse purchases and the need for goods on the spot. In this way, the existence of negative factors and positive factors can be revealed for each sales area, and measures to reduce negative factors and to increase positive factors can be taken according to the results.

  The pattern determination unit 42 may calculate the following performance index. For example, a is the number of customers 134 who are interested in the sales floor but have not been purchased, and a is the number of customers 136 who are interested in the sales floor and have made a purchase. If c is the number of customers who have reached 138, and d is the number of customers 139 who are not interested in the sales floor and have not been purchased, b / (a + b) is connected to the purchase of interested customers (a + b). If the rate is high, the quality and price of the product can be highly evaluated. c / (b + c) is the rate of customers (b + c) who were originally not interested in the sales floor. If this rate is high, store advertisements, product placement, campaigns, etc. can be highly evaluated. c / (c + d) is the rate of purchase among customers (c + d) who were not interested in the sales floor. If this rate is high, the in-store advertisement, product arrangement, etc. can be highly evaluated. a / (a + d) is the rate of customers who did not purchase at the sales floor and were originally interested in the sales floor. If this ratio is high, the potential customer needs of the sales floor are highly evaluated. be able to.

  The pattern determination unit 42 estimates the cause of a poorly sold product. For example, the pattern determination unit 42 estimates that there is a problem with the shelf allocation and the arrangement method when the number of passing is relatively large in the sales area where the poor-selling product is displayed, and information indicating that is used as the determination result. The result is stored in the determination result storage unit 46. For example, when the number of purchases is relatively small compared to the number of active times and the number of freezing times, the pattern determining unit 42 estimates that there is a problem with the assortment, the product power, and the product price, and determines the information indicating that as the determination result Store in the storage unit 46. In addition, instead of the purchase history such as sales and the number of purchases, the factor of purchase quality may be determined based on the number of stoppages of the shopping cart in each sales area. The number of stoppages in the shopping cart is included not only when the product is purchased but also when it is not actually purchased but at least when it is considered for purchase. It is done.

  The pattern determination unit 42 can also analyze the effects of special sales campaigns and leaflets performed on specific products and specific sales area. Although the quality of sales itself can be determined from POS data, it is difficult to determine the quality of sales from the POS data. According to the present embodiment, it is possible to estimate the factor of sales quality based on the behavior pattern of the customer. For example, before and after the campaign or flyer, the pattern determination unit 42 does not increase the number of visitors to the sales floor advertised by the campaign or flyer or the number of interested customers (a + b) or increases the value of c so much. If not, it can be determined that the campaign and flyers were not very effective. If the number of visitors to the sales floor or the number of interested customers (a + b) has increased, but the purchase probability for the number of interested customers (a + b) has decreased and does not lead to a significant increase in sales, a campaign or flyer Although it was effective, it can be judged that sales did not increase due to problems with product strength and product price. As described above, the pattern determination unit 42 determines the effect of the campaign or the flyer based on the number of times of passing, the number of active times, the number of times of freezing in the sales area of the product advertised with the special sale product or the flyer, and the number of purchases and the purchase price for each number of times. And the factors can be determined.

  Next, the pattern determination unit 42 monitors the behavior of the shopping cart in real time for the customer who is currently shopping. Each performance index is displayed on the display unit 56 by the output processing unit 48. The manager can grasp the performance index for each sales floor area in real time while looking at the screen of the display unit 56, find a sales floor with poor performance, and respond immediately. For example, when the average value of the number of “active” carts for a certain sales area does not change from normal, but the display unit 56 indicates that the sales growth is worse than normal, the products in the sales area are not fresh. It can be inferred that there are problems such as high product prices.

  The information distribution unit 50 sends information for introducing the products displayed in the sales area to the output processing unit 48 according to the sales area where the shopping cart is currently located. The output processing unit 48 transmits the information received from the information distribution unit 50 to the shopping cart via the wireless LAN, and transmits it to the POS server 19 via the LAN 18. The information distribution unit 50 acquires product information corresponding to the type of customer behavior pattern from the product information storage unit 58 and sends the product information to the output processing unit 48. For example, information that introduces a product may be sent as information for a customer in a frozen state or information about a customer who is passing, or store guide map data may be sent as information for a customer who is lost. Good.

  As another method of providing information introducing products to the customer, the pattern determination unit 42 refers to the POS data and the purchase history of the customer, and matches the type of the purchase route information, speed information, and behavior pattern with the purchase content. The information distribution unit 50 may determine the information content and the providing method based on the determination. Based on the POS data received from the POS server 19, the pattern determination unit 42 acquires the customer ID and purchase details of the customer who stays in the checkout area, and associates it with the customer's route information as a purchase history as the purchase history. Store. After the storage in the determination result storage unit 46, when the same customer visits the store again, the pattern determination unit 42 reads the purchase history of the customer based on the customer ID from the determination result storage unit 46, and analyzes the behavior of the customer. . The customer ID may be acquired, for example, by reading it from a member card to a shopping cart at the start of shopping, or by reading from the member card in the checkout area at the time of payment. In these cases, the information distribution unit 50 may send the information to the cash register in the checkout area and print it on the customer's receipt. If the customer's e-mail address is registered in advance, the information is distributed by e-mail. May be.

  Examples of information to be printed on receipts and information distributed by e-mail are shown below. For example, if the pattern determination unit 42 determines that the frequency of visiting a specific sales area has suddenly decreased with respect to a customer with a relatively high frequency of visiting the store, it is assumed that a product in that sales area has been purchased at another store. be able to. In that case, the information distribution part 50 distributes the data of the discount coupon regarding the goods of the sales area, or the data of the sales promotion advertisement regarding the goods of the sales area to the customer. When the pattern determination unit 42 determines that a customer who has stayed in the same sales area for a relatively long time, that is, a customer who has been active or frozen, has not purchased a product in that sales area, the product in the sales area or We can guess that we were not convinced of the price. In that case, the information distribution unit 50 provides the customer with discount coupon data related to products in the sales area or sales promotion advertisement data related to products in the sales area. When the pattern determination unit 42 determines that the number of purchased items is small despite the relatively long flow line distance or the staying time in the store, the information distribution unit 50 provides a discount ticket for the entire product of the store. Providing the customer with promotional data about the data or the entire store product. When the pattern determination unit 42 determines that the number of purchased items in the sales area is small even though the stay time is relatively long in the specific sales area, the information distribution unit 50 discounts the product in the sales area. The ticket data or sales promotion advertisement data relating to the products in the sales area is provided to the customer. When the pattern determination unit 42 determines that the customer has a short traffic distance because the date has been short since the membership card was issued, the information distribution unit 50 provides the customer with discount coupon data on the products in the entire store or Providing sales promotion data for all products in the store. Customers who become active or frozen at special sales floors where promotional campaigns are held are presumed to be interested in the theme of the campaign. For such a customer, the information distribution unit 50 provides discount coupon data related to the target product of the same campaign or sales promotion advertisement data related to the product.

  The information distribution unit 50 provides information related to a sales promotion campaign of other products or related products, for example, to a customer who purchased a product targeted for the campaign during a specific sales promotion campaign as information to be distributed by e-mail. May be. As a method for displaying information on the liquid crystal display device of the shopping cart, for example, when the time spent staying in the same sales area has passed a predetermined time, the information distribution unit 50 immediately provides sales promotion information regarding the products in the sales area Alternatively, sales promotion information regarding products in the sales area may be provided to customers who have passed the same sales area more than a predetermined number of times. The information for sales promotion transmitted to the customer may be information relating to a product on the sales floor that the customer did not pass or a product on the sales floor that the customer passed through.

  FIG. 3 shows the appearance of the shopping cart. The shopping cart 60 includes a cart liquid crystal display device 62. This cart liquid crystal display device 62 has a built-in wireless LAN communication function, and communicates with the first access point 12, the second access point 14, and the third access point 16 in the store via the cart antenna 64. The cart liquid crystal display device 62 acquires the intensity of radio waves transmitted and received between the first access point 12, the second access point 14, and the third access point 16. The cart liquid crystal display device 62 includes a liquid crystal display unit, and displays information related to the product received from the customer behavior analysis device 20 on the liquid crystal display unit.

  FIG. 4 schematically shows the sales floor arrangement in the store on the virtual space defined in the spatial information. In this store, there are sales floors for products classified as “vegetables”, “fruits”, “meat”, “fresh fish”, “confectionery / dry foods”, “retorts / condiments”, “dairy products”, and “beverages”. The area through which the customer can pass is composed of an entrance area 70, a first sales area 72 to an eleventh sales area 92, a first settlement area 94 to a sixth settlement area 104, and an exit area 106. The arrangement and coordinates of each of these areas Is defined in spatial information.

  The entrance area 70 is an area through which a customer starts shopping at this store, and a shopping cart is prepared in this area in advance and serves as a movement start point. The first sales floor area 72 and the second sales floor area 74 are areas adjacent to the entrance area 70, the first sales floor area 72 is associated with the “vegetable” sales floor, and the second sales floor area 74 and the fourth sales floor area 78 are Corresponds to the “fruit” sales floor. The third sales floor area 76 is associated with the “meat” sales floor, and the fifth sales floor area 80 and the sixth sales floor area 82 are associated with the “confectionery / dried food” sales floor. The ninth sales floor area 88 is associated with the “fresh fish” sales floor, and the seventh sales floor area 84 and the eighth sales floor area 86 are associated with the “retort / condiment” sales floor. The tenth sales area 90 is associated with the “dairy” sales area, and the eleventh sales area 92 is associated with the “beverage” sales area.

  The first settlement area 94, the second settlement area 96, the third settlement area 98, the fourth settlement area 100, the fifth settlement area 102, and the sixth settlement area 104 are the first cash register, the second cash register, the third cash register, and the third cash register, respectively. Corresponding to 4 cash register, 5 cash register, and 6 cash register. For example, route information about a shopping cart that has passed through the first checkout area 94 is associated with the POS data recorded by the first cash register at the passing time. The exit area 106 is an area where the customer passes when finishing shopping at the store, and serves as a shopping cart movement end point. Note that, in both the entrance area 70 and the exit area 106, it is regarded as entering a store when it passes in the direction from the outside of the store to the inside of the store, and it is regarded as exiting when it passes in the direction from the inside of the store to the outside of the store.

  FIG. 5 schematically shows a hierarchical sales area. FIG. 4 shows an example in which the sales floor areas are not hierarchized, but in this figure, one sales floor area is subdivided into a plurality of sub sales floor areas, and the relationship between the sales floor areas is hierarchized. For example, when the sales area 120 is a clothing sales area and is divided into a plurality of brands, the sales area 120 that is the “clothing sales area” is changed to “A brand” “B brand” “C brand” “D It is divided into a plurality of sub-sale areas 122, 124, 126, 128 called “brand”. The pattern determination unit 42 not only aggregates the behavior patterns for the sales floor area 120 but also totals the behavior patterns for the plurality of sub sales floor areas 122, 124, 126, and 128. It can be estimated in detail.

  On the other hand, the relationship between the sales floor areas may be hierarchized in the same manner as in the example of FIG. 5 by setting a section to be a higher area including a plurality of sales floor areas. In this case, not only the behavior pattern judgment result in each sales floor area, but also the behavior pattern judgment result in the upper hierarchy section is obtained, so more diversified judgment results and estimations such as overall results and partial results The result can be obtained.

  FIG. 6 schematically shows an example of the movement route of the shopping cart in the sales area. The sales floor area 110 in this figure is a horizontally long quadrangular area, and the shopping cart enters the sales floor area 110 from the left side, moves back and forth several times within the sales floor area 110, and once out of the sales floor area 110 from the right side. Get out. Thereafter, a moving route is shown in which the sales area 110 is entered again from the right side of the sales area 110 and after a while, the moving area exits the sales area 110 from the right side again.

  Depending on the sales area, the correct traveling direction may be determined in advance depending on the arrangement, and the route information generated by the route acquisition unit 34 indicates whether the shopping cart has entered in the forward direction or the reverse direction. Recorded in correspondence with the sales area. In addition, once you enter the sales area from entering the store area, you will enter without being active or frozen, and after you become active or frozen in that sales area, you will once enter the sales area. When it goes to the checkout area without being active or frozen, it is recorded in the determination result by the pattern determination unit 42 that the shopping cart has gone “directly” to the sales area.

  Next, the contents of each table generated by the pattern determination unit 42 will be described. First, the pattern determination unit 42 records position information and time information representing customer behavior from entering a store to leaving a store as a position attribute table for each shopping cart. In the location attribute table, the date and time of entry, entrance course [order course, reverse course, direct], checkout method [yes / no], exit course [order course, reverse course], checkout cash register number, The date and time of payment and the traffic distance, which is the total travel distance from entering the store to leaving the store, is recorded. The number of times, average cart stop time, and maximum cart stop time are recorded. Note that the pattern determination unit 42 determines that the shopping cart is stopped when the movement of the shopping cart is within a predetermined radius range. For example, when the moving range from a certain positioning point is continuously within a predetermined radius range, the pattern determining unit 42 regards this as “stopped”. Further, for example, when the state of staying within a predetermined radius range from the previous positioning point measured one second before continues for a predetermined time or longer, the pattern determination unit 42 regards this as “stopped”. May be.

  In the position attribute table, the number of passing times, the passing average time, the minimum passing time, the longest passing time, and the number of passing sales areas are further recorded as parameters relating to passing.

  In the position attribute table, the number of active times, the active average time, the active shortest time, the active longest time, and the number of active sales areas are further recorded as parameters relating to the active. In the position attribute table, the number of freezes, the average freeze time, the minimum freeze time, the longest freeze time, and the number of freeze sales areas are further recorded as freeze parameters.

  The pattern determination unit 42 records the history of behavior in the sales area that has been passed as a cart behavior history table for each shopping cart. The cart action history table includes the sales area name, entry date / time, exit date / time, state name (passing, active, freeze), flow line distance from the store to the sales floor, average speed, maximum speed, number of stops, average stop time, The maximum stop time, the number of purchased products, and the total purchase price are recorded. In addition, when a certain shopping cart passes the same sales area several times, the record of an individual cart action history is produced | generated for every passage.

  The pattern determination unit 42 records the state in each sales area as a sales area area attribute table for each sales area and each time zone. The sales area location attribute table includes the number of passing states, the average time of the passing state, the shortest time of the passing state, the longest time of the passing state, the average number of stoppages of the passing state, and the average of the passing state in one sales space and time zone. The purchase amount and the average number of purchases in the passing state are recorded. The sales area area attribute table includes the number of active states, the average time of active states, the shortest time of active states, the longest time of active states, the average number of stoppages of active states, and the average of active states Purchase amount, average number of active purchases, number of freezes, average time for freezes, minimum time for freezes, maximum time for freezes, average number of freezes for freezes, average purchases for freezes, The average number of purchases is further recorded. In addition, for all customers who have passed through the sales area for each time period, the average flow line distance, minimum flow line distance, and maximum flow line distance from entry to the sales area, and all customers who have purchased products in the sales area Flow line average distance from entry to exit, minimum flow line distance, maximum flow line distance, average flow line distance from entry to exit for all customers who have stopped in the sales area, minimum flow line The distance and maximum flow line distance are further recorded.

  The sales floor area position attribute table includes the average travel time, shortest travel time, longest travel time of customers who have purchased products in the sales floor area, average travel time, shortest travel time, longest travel of customers who have stopped in the sales floor area. The average travel time, the shortest travel time, and the longest travel time when the product is purchased after stopping at the sales area are further recorded. XX and YY of the day or time zone and X and Y applied to the day or time zone are also recorded.

The pattern determination unit 42 can estimate the following items by combining the purchase history based on the POS data and the customer's behavior pattern.
(1) The pattern determination unit 42 calculates the number of purchases per stop for each sales area from the formula (number of purchases / number of stops). Since it is considered that there is a strong correlation between the stoppage of the shopping cart and the purchase / non-purchase of the product, it can be estimated that there is a problem in the assortment and the product power if the number of purchases per stop is relatively small.
(2) The pattern determination unit 42 calculates the number of purchases per shopping cart pass (passing, active, freeze) per sales area. If the number of purchases per pass is relatively small, factors such as inappropriate merchandise arrangement, poor merchandise appeal, and improper advertisement content and advertisement arrangement on the sales floor are estimated. )
(3) The pattern determination unit 42 calculates the number of purchases and the purchase amount per shopping cart that is “passing” for each sales area. If the number of purchases and the purchase price are large, it can be estimated that attractive products are easily arranged.
(4) The pattern determination unit 42 calculates the number of purchases and the purchase amount per shopping cart that is “active” for each sales area. If the number of purchases and the purchase price are low, factors such as inappropriate product placement, low product appeal, and high product prices are estimated.
(5) The pattern determination unit 42 calculates the number of purchases and the purchase amount per shopping cart that is “frozen” for each sales area. If the number of purchases and the purchase price are low, it is estimated that there is a possibility that the product has been missed due to improper product placement or out of stock despite high demand.
(6) The pattern determination unit 42 calculates the number of purchases and the purchase amount per shopping cart that is “refreeze” for each sales area. If the number of purchases and the purchase price are low, it is estimated that there is a problem such as improper product arrangement or out of stock.
(7) The pattern determination unit 42 calculates the number of shopping carts that have left the store without purchasing anything in “active” despite being “directly”. In this case, it is presumed that the product was out of stock.
(8) The pattern determination unit 42 calculates the number of shopping carts that have left the store without purchasing anything despite being “directly” and “freezing”. In this case, it is estimated that the assortment was insufficient.
(9) The pattern determination unit 42 calculates the number of shopping carts that have moved in the “forward direction” and left the store without purchasing anything. In this case, problems such as product selection, product quality, and product placement in the entire store are estimated.
(10) If the pattern determination unit 42 once becomes “freeze” in a certain sales area, then enters the same sales area again and becomes “active” or “freeze”. The customer presumes that the product has been returned or has not been purchased.

  Next, the pattern determination unit 42 estimates the customer's attributes and state based on the customer's behavior pattern and purchase behavior. Specifically, (1) day of the week and time zone [weekdays, holidays, 11:00 to 17:00, etc.], (2) entrance course [forward course, reverse course, direct], (3) presence / absence of payment [ None], (4) Closed course [forward course, reverse course], (5) Store stay time [High, Middle, Low], (6) Average speed or average speed during periods excluding freeze state [High, Middle , Low], (7) Cart stop frequency [High, Middle, Low], (8) Average cart stop time [High, Middle, Low], (9) Passing frequency, (10) Active frequency [High, Middle, Low] ], (11) Freeze frequency [High, Middle, Low], (12) Refreeze probability [High, Middle, Low], (13) Repassing probability [H gh, Middle, Low], (14) A combination or permutation of the sales area that has become active or frozen [does it contain at least six of food, confectionery, meat, fresh fish, vegetables, dairy products, dried food, seasonings] (15) Conditions for each item such as the total flow line distance from entry to exit are defined as attribute pattern data for each attribute and stored in the behavior pattern data storage unit 44. The pattern determination unit 42 estimates the customer attributes as follows with reference to the attribute pattern data. Here, in (2) the entrance course and (4) the exit course, it is determined whether or not the entrance course and exit course assumed in advance are traced accordingly. (12) The refreezing probability is obtained by (number of times of freezing) / (number of sales area that has become frozen). (13) The re-passing probability is obtained by (number of times of passing) / (number of sales area that has been passed). Here, the “passing frequency” is the number of times of passing per hour, and the passing frequency × the stay time in the store = the number of times of passing.

  For example, in the case of the attribute of “shopping with family on holidays”, (1) is “holidays, 11:00 to 17:00”, (2) is “order course”, (3) is “paid”, and (4) is “Order Course”, (5) as “High”, (6) as “Low, Middle”, (7) as “High”, (10) as “High”, (11) as “High”, (12) As “Middle, High”, (13) as “Middle, High”, and (14) as “active sales floor, food, confectionery, meat, fresh fish, vegetables, dairy products, dried food, seasonings, etc. 6 regions are included ”, and“ High ”is defined as (15). If the customer's behavior pattern or purchase behavior is applicable to the above conditions, the pattern determination unit 42 estimates that the customer's attribute is “shopping with family on holidays”. Note that “High”, “Middle”, and “Low” correspond to, for example, a case where the distribution of customers is divided into three equal parts.

(Example 2)
In this embodiment, between a customer who is a mobile body and a plurality of wireless LAN base stations, the time from when one transmits a radio wave to the time when a return radio wave is received from the other is measured. Position based on the difference in length of time measured at the station. This is different from the first embodiment in which the position of the moving body is detected using the difference in radio wave intensity at each base station. Hereinafter, the difference from the first embodiment will be mainly described, and the description of the common points will be omitted.

  FIG. 7 is a functional block diagram illustrating the configuration of the customer behavior analysis system according to the second embodiment. The customer behavior analysis system 10 is different from the customer behavior analysis system 10 in the first embodiment including the strength acquisition unit 24 in that it includes a time value acquisition unit 140. First, after a plurality of wireless LAN base stations, for example, the first access point 12, the second access point 14, and the third access point 16 within the wireless communication range of the communication device provided in the shopping cart transmit a wireless signal, The time until the wireless signal as a reply is received from the communication device is measured, and the time value is transmitted to the customer behavior analysis system 10. The wireless communication system used in the present embodiment may be UWB (Ultra Wide Band). The time value acquisition unit 140 acquires the time value of the time required for transmission / reception with the shopping cart from each base station. The position recognition unit 26 calculates the distance between each base station and the shopping cart from the time value, calculates the position of the shopping cart based on the distance from at least three base stations, and generates position information. Time information indicating the time at which is calculated is generated. The position detection method may be a TOA (Time of Arrival) method or a TDOA (Time Difference of Arrival) method. The position information and time information are stored in the position information storage unit 28. The position information and time information of the shopping cart can be detected by the above method as in the first embodiment, and the same analysis as in the first embodiment can be performed based on this. In addition, you may detect which shopping cart is used by detecting ID of the wireless LAN communication apparatus with which the customer's shopping cart was equipped.

(Example 3)
In this embodiment, an IC tag is embedded in a shopping cart, a shopping cart, a membership card, a mobile phone, a portable terminal, etc. possessed by a customer, and a plurality of reader / writers are used as a wireless communication device capable of wirelessly communicating with the IC tag. It is done. The position of the customer is detected by information indicating to which reader / writer the IC tag communicates wirelessly. For example, a large number of reader / writers are installed in a store, each has a unique communication area, and the position of the customer is determined by detecting which reader / writer's communication area the IC tag held by the customer passes through. judge. This is different from the first embodiment in which the position of the moving body is detected using the difference in radio wave intensity at each base station. Hereinafter, the difference from the first embodiment will be mainly described, and the description of the common points will be omitted.

  FIG. 8 is a functional block diagram illustrating the configuration of the customer behavior analysis system according to the third embodiment. The first reader / writer 142, the second reader / writer 144, and the third reader / writer 146 transmit received information indicating that to the customer behavior analysis system 10 when a customer who has an IC tag passes through each communication area. To do. The reception information acquisition unit 148 acquires reception information from the first reader / writer 142, the second reader / writer 144, and the third reader / writer 146. The position recognizing unit 26 generates position information indicating the position of the customer who has the IC tag depending on from which reader / writer the received information is acquired, and also generates time information indicating the timing, and sends it to the position information storage unit 28. Store. According to the above method, the customer position information and time information can be detected as in the first embodiment, and the same analysis as in the first embodiment can be performed based on this. In addition, you may detect which shopping cart etc. are used by detecting ID of IC tag embedded in possessions, such as a customer's shopping cart.

Example 4
The customer behavior analysis system 10 in this embodiment is connected to the first camera 152, the second camera 154, and the third camera 156, and includes a reception information acquisition unit 148. In this embodiment, a plurality of areas included in a target space are continuously photographed from a predetermined angle such as a bird's-eye view with a plurality of cameras, and an object moving from a color change in the obtained plurality of continuous images. Is detected and the position of the object is recognized. This is different from the first embodiment in which the position of the moving body is detected using the difference in radio wave intensity at each base station. Hereinafter, the difference from the first embodiment will be mainly described, and the description of the common points will be omitted.

  FIG. 9 is a functional block diagram illustrating the configuration of the customer behavior analysis system according to the fourth embodiment. At each sales floor area in the store, at least one camera is installed so that it can shoot from a predetermined angle such as an overhead view. The first camera 152, the second camera 154, and the third camera 156 are examples of cameras that can be taken from a bird's-eye view. The first camera 152, the second camera 154, and the third camera 156 continuously shoot the sales area, which is the respective shooting area, from an overhead view. A plurality of continuous images taken by the first camera 152, the second camera 154, and the third camera 156 are transmitted to the customer behavior analysis system 10 as needed. The image acquisition unit 150 acquires continuous images from the first camera 152, the second camera 154, and the third camera 156. The position recognizing unit 26 detects a moving object from continuous images, recognizes the position of the moving object, generates position information, generates time information indicating the time, and sends each of the time information to the position information storage unit 28. Store. According to the above method, the customer position information and time information can be detected as in the first embodiment, and the same analysis as in the first embodiment can be performed based on this.

  FIG. 10 illustrates an image of a certain sales floor area taken from an overhead view. If the sales floor image 180 in the figure is captured in a plane, the image of the customer as a moving object appears obliquely except when the customer is directly under the camera. As a result, customers other than the head and shoulders are not shown for the customers directly under the camera, whereas the whole body is shown not only for the head and shoulders for the customers who are shown obliquely. Not only does it look completely different depending on the customer's position, but the head is closer to the camera than the feet, so it appears larger, making it difficult to accurately grasp the customer's position. Here, according to the conventional position detection technique, first, a rectangular frame 183 that is inscribed by the moving body 182 is set on the sales floor image 180, and the frame center point 184 of the rectangular frame 183 is regarded as the position of the moving body 182. . However, as shown in the figure, the actual position of the moving body 182 should be originally the foot position 186, and the frame center point 184 is shifted from the foot position 186.

  FIG. 11 schematically shows the shooting situation of the sales floor image 180 in FIG. 10 from the side. A camera 204 is installed on the ceiling 200, and the camera 204 captures the direction of the floor surface 202. The moving body 182 walking on the floor 202 is moving in the direction from the image center point 188 to the end. When the camera 204 captures its appearance, the shooting angle of the moving body 182 is not vertical but oblique as shown in the figure. Therefore, assuming that the floor 202 is the sales floor image 180, the moving body 182 is projected obliquely onto the area 206. Therefore, the moving body 182 appears wider than when it is photographed vertically from directly above, and the center point of the width is far from the actual position of the moving body 182. In addition, since the portion closer to the camera 204 is larger, the head of the customer, which is the moving body 182, is larger than the feet.

  FIG. 12 is a diagram in which a cylindrical body model is applied to the sales floor image of FIG. In the sales floor image 180 in this figure, the moving body 182 shown in the sales floor image 180 in FIG. Hereinafter, processing of the position recognition unit 26 that detects the position of the moving object by replacing the moving object image with the cylindrical object will be described. The position recognition unit 26 sets a cylinder axis 194 that is a straight line connecting the image center point 188 and the frame center point 184 of the quadrangular frame 183, and sets a cylinder body 192 having the cylinder axis 194 as an axis. For example, 50 cm is set as the radius in the real world of the bottom surface 196 of the cylindrical body 192. Since the appearance and size of the cylindrical body 192 change depending on the distance, the bottom surface 196 is calculated to be drawn with an ellipse having a major axis radius corresponding to 50 cm in the sales floor image 180. An arbitrary value can be set for the radius of the ellipse. The bottom surface 196 is set at a position where the bottom surface center point 190 is placed on the cylindrical shaft 194 and the circumferential line thereof is in contact with the quadrangular frame 183. The upper surface 198 of the cylindrical body 192 is drawn as an ellipse having a size such that its center point is placed on the cylindrical axis 194 and its circumferential line abuts on the rectangular frame 183. As shown in FIG. 11, since the moving body 182 looks larger at the head than at the feet, the cylindrical body 192 is set such that the upper surface 198 is larger than the bottom surface 196 as shown in FIG. 12. The bottom surface center point 190 is regarded as the foot position of the moving body 182. Thereby, even when the moving body is photographed obliquely, the position recognition unit 26 can acquire more accurate position information. In this figure, the process of detecting the position of the foot without any image correction has been described. However, even if the position of the foot is detected after correcting the difference in size due to aberration or perspective of the sales floor image 180 in advance. Good. In that case, in particular, the sales floor image 180 may be corrected so that the bottom surface 196 changes from an ellipse to a perfect circle. Since the aberration correction method is known, its description is omitted.

  The position recognition unit 26 assigns an ID to the detected moving body, and recognizes position information and position detection time in association with the ID. The position recognition unit 26 continues to assign the same ID to the moving object as long as the same moving object is continuously recognized from the images in the same sales area. The position information that is initially recognized is the position coordinates of the frame center point 184 of the quadrangular frame 183 shown in FIG. A straight line connecting the image center point 188 and the frame center point 184 is assumed as the cylinder axis 194. A cylindrical body 192 having a bottom surface 196 corresponding to a radius of 50 cm in contact with the quadrangular frame 183 on the cylindrical axis 194 is closer to the image center point 188 than the frame center point 184 and has an upper surface 198 in contact with the quadrangular frame 183 on the opposite side. Set. At this time, the relative coordinates of the bottom surface center point 190 of the bottom surface 196 are detected as position information of the moving body.

  The position recognition unit 26 detects a moving body in the image for each camera. Since different IDs are assigned to each camera even for the same moving object, the position recognition unit 26 determines the correspondence of IDs for the same moving object based on the arrangement relationship of the images from the cameras. Thereby, the position recognition part 26 recognizes the flow line in the store of each moving body.

  Here, when the shooting ranges partially overlap between adjacent cameras, there is a possibility that a moving body that has entered the overlapping area is simultaneously displayed on two images. In that case, the number of IDs generated from the overlapping area is a multiple of two. All IDs displayed in the overlapping area are divided into pairs, the distance between the moving bodies in the pair is calculated, and the distances of each pair are summed. Next, the combinations of the pairs are changed and the distances of the respective pairs are summed in the same manner. A combination having the smallest total distance among all combinations that can be considered as such a pair combination is an optimal combination, and the mobile bodies of each pair are determined to be the same mobile body.

  FIG. 13 schematically shows a method for detecting the same moving object in overlapping imaging ranges. The first image 262 and the second image 264 each have an overlapping region 260 because the imaging ranges partially overlap. In the example of this figure, one moving body is shown in an area other than the overlapping area 260 of the first image 262, whereas four moving bodies 252 to 258 are shown in the overlapping area 260. Since the overlapping area 260 is a part where the imaging ranges of two images overlap, the number of moving bodies appearing in this area is a multiple of two. Therefore, in the second moving body 252, the third moving body 254, the fourth moving body 256, and the fifth moving body 258 reflected in the overlapping area 260, two moving bodies are actually doubled and recognized as four. It ’s just that.

  Here, the position recognizing unit 26 divides the moving body shown in the overlapping area 260 into a plurality of pairs, and determines how to divide the pair that has the smallest value when the total value of the distances is calculated for each pair. In the example of this figure, these moving bodies are arranged at substantially equal intervals in the order of the second moving body 252, the third moving body 254, the fourth moving body 256, and the fifth moving body 258. Therefore, if the pair is divided into a pair of the second moving body 252 and the third moving body 254 and a pair of the fourth moving body 256 and the fifth moving body 258, the total distance is minimized. In addition, since it is grasped in advance that the moving bodies appearing in the same image are separate moving bodies, for example, in this figure, the second moving body 252 and the fourth moving body 256 are not paired. 254 and the fifth moving body 258 are not paired.

  As a supplementary determination method, the position recognizing unit 26 moves from the position of the first moving body 250 to the positions of the second to fifth moving bodies 252 to 258, the moving direction, and the speed to the position of the first moving body 250. Then, any difference in the moving direction is calculated, and the method of dividing the pair that has the smallest total value when the total difference value is calculated for a plurality of pairs is further determined. In addition, the position recognition unit 26 calculates a total value of values obtained by arbitrarily combining some of the parameters such as the distance between the moving objects, the speed of the moving objects, and the moving direction, and the total value is minimized. You may determine how to divide a pair.

  In addition, although the comparison of the moving bodies by the above calculation has been described on the assumption that the imaging ranges are partially overlapped, the position recognition unit 26 performs the above calculation and comparison without overlapping the imaging ranges. You may process with the image of an adjacent camera. In that case, the position recognizing unit 26 recognizes the moving direction of the moving body from the obtained flow line of the moving body, and recognizes the correspondence relationship between the IDs of the moving body between the images in the imaging range adjacent to the moving direction. Thereby, even if the cameras are somewhat separated from each other, it is possible to maintain the correspondence relationship of the moving bodies, and it is possible to reduce the number of cameras installed and keep the cost low. Moreover, even when the positional relationship of a plurality of moving bodies is switched between images, the corresponding moving body can be accurately recognized by the difference in speed and moving direction.

  FIG. 14 schematically shows an example of the shooting range of each camera in the store. Here, three shooting ranges are illustrated. The first shooting range 320 and the second shooting range 322 are shooting ranges corresponding to the first image 262 and the second image 264 in FIG. The first imaging range 320 and the second imaging range 322 have a positional relationship aligned with each other, and their coordinate axes are parallel. On the other hand, the second shooting range 322 and the third shooting range 324 are not parallel in coordinate axes, and the third shooting range 324 is inclined with respect to the second shooting range 322. Thus, even if the coordinate axes of the shooting ranges are not parallel, the position recognition unit 26 converts the coordinates in the image of each shooting range into absolute coordinates that are the spatial coordinates of the entire store, so The position can be recognized.

(Example 5)
The customer behavior analysis system 10 in the present embodiment is connected to the first ultrasonic acquisition device 270, the second ultrasonic acquisition device 272, and the third ultrasonic acquisition device 274, and includes a reception information acquisition unit 148. The first ultrasonic acquisition device 270, the second ultrasonic acquisition device 272, and the third ultrasonic acquisition device 274 acquire ultrasonic waves sent from a moving body in a plurality of areas included in a target space, and the ultrasonic waves The position of the moving body is detected based on the reception angle. It is assumed that each moving body includes an ultrasonic transmitter. For example, the mobile is a customer's shopping cart in the store, and the shopping cart includes an ultrasonic transmitter. As described above, the customer behavior analysis system 10 according to the present embodiment is different from the customer behavior analysis system 10 according to the first embodiment that detects the position of the moving body using the difference in radio wave intensity at each base station. Hereinafter, the difference from the first embodiment will be mainly described, and the description of the common points will be omitted.

  FIG. 15 is a functional block diagram illustrating the configuration of the customer behavior analysis system according to the fifth embodiment. In each of a plurality of sales floor areas in the store, at least one ultrasonic acquisition device is installed at a high place such as a ceiling. The first ultrasonic acquisition device 270, the second ultrasonic acquisition device 272, and the third ultrasonic acquisition device 274 in this figure are examples of ultrasonic acquisition devices installed on the ceiling, respectively. Receive continuously. The first ultrasonic acquisition device 270, the second ultrasonic acquisition device 272, and the third ultrasonic acquisition device 274 transmit the reception angle of the received ultrasonic waves to the reception information acquisition unit 148. The position recognition unit 26 detects a moving body from the reception angle of ultrasonic waves, recognizes the position of the moving body, generates position information, generates time information indicating the time, and stores each position information. Store in the unit 28. Since the method for detecting the reception angle of the ultrasonic wave and the method for detecting the position of the moving body based on the reception angle are known, the description thereof is omitted.

(Example 6)
In the present embodiment, a geomagnetic sensor and an acceleration sensor are mounted on a shopping cart of a customer as a mobile body, and a flow line from the vicinity of the entrance of the store can be recognized by tracking the geomagnetic sensor and the acceleration sensor. Direction information, which is the detection result of the traveling direction by the geomagnetic sensor, and acceleration information, which is the detection result of the acceleration by the acceleration sensor, are transmitted to the customer behavior analysis system 10 by the wireless communication device mounted on the shopping cart. The customer behavior analysis system 10 recognizes the flow line of the customer traced from the store entrance based on the direction information and acceleration information received from the shopping cart. The customer behavior analysis system 10 does not always need to receive direction information and acceleration information from the shopping cart, and all direction information and acceleration information indicating a flow line from the entrance to the payment area when the shopping cart reaches the payment area. Are received together. Therefore, at least one base station in the store is sufficient to receive information from the shopping cart by wireless communication. Thus, since the customer behavior analysis system 10 in the present embodiment detects information on the position by the sensor on the mobile body side, the first embodiment detects the position of the mobile body using the difference in radio wave intensity at each base station. Different from the customer behavior analysis system 10. Hereinafter, the difference from the first embodiment will be mainly described, and the description of the common points will be omitted.

  Correction points may be provided at a plurality of locations in the store. An IC tag is installed at each correction point. When the moving body reaches the communication area of each IC tag, the position recognition unit 26 rewrites the position information of the moving body at that time with a predetermined value indicating the position of the correction point. As a result, the position recognition base point based on the direction information and the acceleration information is irregularly corrected, so that position recognition with less error is realized.

  FIG. 16 is a functional block diagram illustrating the configuration of the customer behavior analysis system according to the sixth embodiment. At least one base station is installed in the store. The access point 280 in this figure is an example of a base station installed in a store, receives direction information and acceleration information from a sales area or a settlement area, and transmits these to the reception information acquisition unit 148. Based on the direction information and the acceleration information, the position recognizing unit 26 recognizes a moving line of the moving body based on the position of the store entrance that is a detection start point, generates position information, and time information indicating the time Are stored in the position information storage unit 28. The position recognition unit 26 may further store the direction information and acceleration information received from the reception information acquisition unit 148 in the position information storage unit 28. The speed acquisition unit 32 may calculate the speed of the moving body by integrating the acceleration information stored in the position information storage unit 28.

(Example 7)
In a present Example, the specific determination method of the action pattern by the pattern determination part 42 is demonstrated, and description common to Examples 1-6 is abbreviate | omitted.

  FIG. 17 shows the relationship between the staying time in the sales area and the number of customers. The relationship between the staying time and the number of customers in the sales area shown in this figure is merely an example, but it is presumed that the relationship is generally as shown in this figure. The horizontal axis indicates the staying time of customers in a certain sales area, and the vertical axis indicates the number of customers. The number of staying customers 160 indicates the number of customers for each staying time in a certain sales area in one day, and the number of purchased customers 162 indicates the number of customers who have actually purchased a product in the sales floor area out of the number of customers for each staying time. . As shown in the figure, the total number of customers is greater for customers with a relatively short stay, and less for customers with a longer stay. The number of customers who purchased the product is smaller as the staying time is shorter, but the number of customers increases as the staying time becomes longer, and the number of customers starts to decrease as the staying time becomes longer.

  The area of the first range 164 indicates the total number of customers who have not purchased a product in the sales area among customers whose stay time is shorter than the first time value XX [seconds]. The area of the second range 166 indicates the total number of customers who have purchased items in the sales area among customers whose stay time is shorter than the first time value XX. The area of the third range 168 indicates the total number of customers who have not purchased a product in the sales area among customers whose stay time is longer than the second time value YY [seconds]. The area of the fourth range 170 indicates the total number of customers who have purchased products in the sales area among customers whose stay time is longer than the second time value YY.

  The first time value XX is a value such that the area ratio between the first range 164 and the second range 166 is a predetermined ratio. That is, the first time value XX is a value such that a ratio of customers who have not purchased a product and customers who have purchased a product among customers whose stay time is shorter than that value is a predetermined rate. The area ratio between the first range 164 and the second range 166 is, for example, 10: 1, and is set to an optimum value based on experiments and verification.

  The second time value YY is a value such that the area ratio between the third range 168 and the fourth range 170 is a predetermined ratio. That is, the second time value YY is a value such that a ratio of customers who have not purchased a product and customers who have purchased a product among customers whose stay time is longer than that value is a predetermined rate. The area ratio between the third range 168 and the fourth range 170 is, for example, 1: 1, and is set to an optimum value based on experiments and verification.

(Example 8)
The customer behavior analysis system 10 in the present embodiment is common to other embodiments in that any one of the position detection methods in the first to sixth embodiments is adopted as a basic configuration. It differs from the other embodiments in that it analyzes employee behavior. For example, when the position detection method of the first to third embodiments is adopted, each employee carries a wireless communication device or an IC tag, and the position is recognized by communication with the base station or reader / writer on the customer behavior analysis system 10 side. Is done. When the position detection method according to the fourth embodiment is employed, the position of the employee is recognized through an image captured by the camera. When the position detection method of the fifth embodiment is employed, the position of the employee is recognized through transmission / reception of ultrasonic waves. When the position detection method of the sixth embodiment is adopted, the position of the employee is recognized through the detection results of the geomagnetic sensor and the acceleration sensor. In addition, in order to identify an employee, it is particularly preferable to employ the position detection methods according to the first to third embodiments. Hereinafter, differences from the first to sixth embodiments will be mainly described, and description of common points will be omitted.

  In the present embodiment, the pattern determination unit 42 can calculate the values of the following parameters based on the route information and display them on the screen. For example, for each employee, the pattern determination unit 42 enters a store, leaves a store, traffic flow distance from store to store, number of stops from store to store, stop from store to store. Calculate time. The pattern determination unit 42 can also calculate the stay time, the number of stops, and the stop time for each sales area for each employee. The values of these parameters are displayed on the screen through the operation of the administrator.

The pattern determination unit 42 determines whether the employee is in the “waiting”, “outside of the sales floor”, “approach from the customer”, “approach from the employee”, “business negotiation” based on the relationship between the employee and the customer such as position, distance, speed, and direction. "Checkout" or "Move out of sales area". The pattern determination unit 42 calculates the determined time for each employee, every month, every day of the week, every day, and every time zone. “Waiting” means a state where the customer is in the sales area. “Outside the sales floor” means a state where “approach from the customer”, “approach from the employee”, “business negotiation”, and “settlement” are excluded from the state where the sales area is in charge. “Approach from customer” refers to a state in which a customer approaches a predetermined approach distance such as within 60 cm for an employee who is “waiting” or “out of sales” and the distance continues for a predetermined time. “Approach from employee” refers to a state in which an employee who is “waiting” or “out of the sales area” approaches a predetermined approach distance such as within 60 cm from the customer, and the approach distance continues for a predetermined time. The pattern determination unit 42 may determine which of the customer and the employee is approaching by comparing the calculated values based on both motion vectors. For example, let V _a be the employee vector and V _{b the} customer vector. Assuming a straight line connecting the position and customer location employees, the straight line and the vector V _a is a contact angle of theta _a, straight line and the vector V _b is the angle formed with the theta _b. If V _a cosθ _a is larger than V _b cosθ _b , it is determined that the employee has approached the customer. If V _a cosθ _a and V _b cosθ _b are equal, it is determined that the employee has approached the customer, and V _a cosθ _a is If it is smaller than V _b cos θ _b, it is determined that the customer has approached the employee. _{Incidentally,} V a cos [theta] _a and _V b cos [theta] _b is the value of approaching each other direction and positive values. The pattern determination unit 42 determines that the state has shifted to the “business negotiation” state when the approach between the employee and the customer continues even after a predetermined time has elapsed, and the state of “waiting” or “out of sales” otherwise. It is determined that it has moved to. After the transition to the “negotiation” state, if at least one of the employee or customer moves to the settlement area and it is recognized from the POS data that the settlement has been made at that time, the “negotiation” at that time Is finished, and it is determined that the state is “settlement”. The pattern determination unit 42 determines that the “negotiation” has ended when the employee and the customer who are in the “negotiation” state are separated by a predetermined distance or more and the state has elapsed for a predetermined time, and “wait” or “ It is determined that the state has shifted to the “out of sales” state. Therefore, the employee in the “business negotiation” state can only shift to the “settlement”, “waiting”, and “out of sales” states. The pattern determination unit 42 determines that “settlement” is completed when the distance between the customer and the employee is more than a predetermined distance after the “settlement” state and the state continues for a predetermined time.

  For each employee, the pattern determination unit 42 determines the number of times, the shortest time, the longest time, and the average for the employee's behavioral states such as “wait”, “approach from customer”, “approach from employee”, “business negotiation”, and “settlement”. Calculate the time ratio of each state in hours and all working hours. The pattern determination unit 42 calculates the contract probability for the number of negotiations for each employee. The number of negotiations is recognized from the route information of the employee and the relationship between position, distance, speed, direction, etc. between the employee and the customer. recognize. The pattern determination unit 42 determines the stay time in each sales floor area for each customer (1) when no employees are present, (2) when all employees are in service, (3) one employee is not in service When the above exists, the calculation is performed separately for each of the three patterns. Each of (1) to (3) is totaled by the active or frozen customers who have passed through the sales area. For each sales floor area, the pattern determination unit 42 allows the employee to respond to the number of customers whose stay time in the sales area corresponds to (1) or (2) and the total value of the stay time in the sales floor area. Calculated as missing number and time. This value is used as one index that represents sales opportunity loss. As a result, it is possible to grasp a situation in which the employee is absent or in the customer service indefinitely in the sales area.

  The customer behavior analysis system 10 can be applied to the management of the entire store. For example, the pattern determination unit 42 includes the number of visitors, the average stay time from entry to exit, sales, average speed excluding average speed or freeze, average traffic distance, average number of stops, passing ratio, active ratio, freeze Ratio, customer density in checkout area, maximum wait time in checkout area, average wait time in checkout area, active purchase probability and average purchase price, purchase probability and average purchase price in passing, purchase probability and average purchase in freeze Parameters such as the amount of money can be calculated for each store. Parameters such as a minimum value, an average value, and a maximum value of the ratio of the number of customers and the number of employees per unit area may be calculated for each store.

  FIG. 18 shows an example of a screen that displays a list of the length of time for each employee behavior state. The screen 400 corresponds to each state of employee behavior such as “waiting”, “outside of the sales floor”, “approach from the customer”, “approach from the employee”, “business negotiations”, “settlement”, and “moving outside the sales floor area”. The length of time spent is indicated by the length of the bar graph. The output processing unit 48 can also display the time lengths of these states for each employee, for example.

  In addition to the display contents of this figure, the output processing unit 48 displays on the display unit 56 the time that the employee stayed in each sales floor area on a monthly, weekly, day-of-week, day-by-day, and time-zone basis. . Based on the operation of the manager, the output processing unit 48 displays, for example, a table with the stay time for each sales area on the horizontal axis and the type of the sales area on the vertical axis on the display unit 56.

  In the above, this invention was demonstrated based on the Example. This embodiment is an exemplification, and it will be understood by those skilled in the art that various modifications can be made to each component and combination of processing processes, and such modifications are within the scope of the present invention. Hereinafter, modifications will be described.

  In the embodiment, a shopping cart used by a customer as a “moving body” is mainly exemplified. The “mobile body” in the modification may be a shopping basket used by a customer, a communication device such as a mobile phone or a mobile terminal possessed by a customer or an employee, an IC card or an IC chip. It may be a medium with a communication function such as a ticket. In the case of an IC tag such as an IC card or an IC chip, it may be an active IC tag with a built-in power supply or a passive IC tag supplied with power from the outside.

  In the embodiment, the system for calculating the position and speed in order to analyze the behaviors of customers and employees who are moving bodies in the space in the store is exemplified. In a modified example, it may be configured as a system for analyzing the behavior of a visitor moving in a recreational facility such as a shopping street, amusement park, theme park, or zoo. Furthermore, you may comprise as a system which analyzes a player's motion in exercise facilities, such as a baseball field, a soccer field, and a rugby field.

  In the third embodiment, an IC tag is embedded in a shopping cart, a shopping cart, a membership card, a mobile phone, a mobile terminal, etc. possessed by a customer, and a number of reader / writers are installed in the store, and these communicate with each other. explained. In the modified example, a reader / writer is built in a shopping cart, a shopping cart, a mobile phone, etc. possessed by a customer, a large number of IC tags are installed in the store, and these communicate with each other to detect the position of the customer. It may be a configuration.

  The imaging by the camera described in the fourth embodiment may be special imaging using sensors such as ultrasonic waves, microwaves, infrared rays, and electromagnetic waves, in addition to imaging using a CCD sensor or a CMOS sensor. In the fifth embodiment, the method of detecting the position by the angle of the radio wave in the communication between the ultrasonic transmitter and the receiver has been described. However, according to the time required for transmitting and receiving the ultrasonic wave between the mobile body and the receiver. The structure which detects the position of a moving body may be sufficient.

  ADVANTAGE OF THE INVENTION According to this invention, useful information can be provided by analyzing the action of the moving body in space.

Claims (8)

A position acquisition unit for acquiring position information indicating the position of a moving body that changes with time in a real space in a predetermined store and time information indicating the positioning timing;
A space acquisition unit that acquires, as spatial information, respective coordinates for specifying the arrangement of a plurality of sales floors included in the store on a virtual space;
Based on the position information, the time information, and the space information, the moving body indicates the route information indicating the movement path of the moving body in the real space in the store by the position in the virtual space. A route acquisition unit that generates information along with information about which one of
Based on the position information and the time information, a speed acquisition unit that generates, as speed information, information indicating an average speed of the moving body in each of the plurality of sales floors;
As a type of purchasing behavior based on the relationship between the movement path and movement speed of a customer, who is a mobile object, the first pattern showing the case of passing through the sales floor area, purchasing goods or considering purchasing after stopping in the sales floor area for a relatively short time The second pattern indicating the case of performing, and the third pattern indicating the case of staying for a long time in one sales area, the standard regarding the stay time for each sales area of each behavior pattern is the customer's stay time in the past and the customer's A pattern storage unit for storing a plurality of behavior pattern data defined in advance in relation to statistics of purchase contents;
Based on the route information, the position of the checkout area where the mobile customer stayed for product purchase and the date and time of the product purchase which is the stay date and time are determined, and the position of the checkout area and the product purchase By acquiring POS data indicating purchase contents corresponding to the date and time, the POS data and the route information are associated with each other and stored in the pattern storage unit as the reference of the action pattern, and the customer as the mobile object Based on the route information including information on which one of a plurality of sales floors is passed, the speed information, and the plurality of behavior pattern data, the behavior of the customer as the mobile body is in any of the types of the behavior patterns. A pattern determination unit for determining whether they match, and
An output processing unit for outputting the result of the determination ,
The pattern determination unit
Each time the mobile body enters each of a plurality of sales floor areas, the stay time from the entry to the exit is calculated,
Based on the route information and the data indicating the purchase content, the mobile unit that has purchased the product and the sales area of the purchased product are specified, and the stay time of the mobile unit in the sales area is defined as the stay time at the time of product purchase. Identified as
For each of a plurality of sales floor areas, identify the actual shortest time and longest time for each day or time period out of the stay time at the time of purchasing the product,
A first shortest time for distinguishing the first pattern from the second pattern is calculated by calculating an average shortest time obtained by averaging the substantial shortest time over a plurality of days or a plurality of time periods for each sales area. Stored in the pattern storage unit as a threshold value corresponding to the sales area,
An average longest time obtained by averaging the substantial longest time over a plurality of days or a plurality of time zones is calculated for each sales floor area, and this is used as a second process for distinguishing the second pattern from the third pattern. Stored in the pattern storage unit as a threshold value,
When the staying time in a certain sales floor area of a mobile object that is subject to action pattern determination is less than the first threshold value associated with the sales floor area, the behavior pattern of the mobile body for the sales floor area is the first. Judge that it matches the pattern,
If the staying time in a certain sales area of a mobile object that is subject to action pattern determination is greater than or equal to the first threshold value associated with the sales area and falls below the second threshold value, the sales area Determining that the behavior pattern of the moving object matches the second pattern with respect to the region;
If the staying time in a certain sales floor area for a mobile object that is the target of behavior pattern determination is greater than or equal to the second threshold value associated with the sales floor area, the behavior pattern of the mobile body for the sales floor area is the first A behavior analysis apparatus characterized by determining that three patterns are matched . A position acquisition unit for acquiring position information indicating the position of a moving body that changes with time in a real space in a predetermined store and time information indicating the positioning timing;
A space acquisition unit that acquires, as spatial information, respective coordinates for specifying the arrangement of a plurality of sales floors included in the store on a virtual space;
Based on the position information, the time information, and the space information, the moving body indicates the route information indicating the movement path of the moving body in the real space in the store by the position in the virtual space. A route acquisition unit that generates information along with information about which one of
Based on the position information and the time information, a speed acquisition unit that generates, as speed information, information indicating an average speed of the moving body in each of the plurality of sales floors;
As a type of purchasing behavior based on the relationship between the movement path and movement speed of a customer, who is a mobile object, the first pattern showing the case of passing through the sales floor area, purchasing goods or considering purchasing after stopping in the sales floor area for a relatively short time The second pattern indicating the case of performing, and the third pattern indicating the case of staying for a long time in one sales area, the standard regarding the stay time for each sales area of each behavior pattern is the customer's stay time in the past and the customer's A pattern storage unit for storing a plurality of behavior pattern data defined in advance in relation to statistics of purchase contents;
Based on the route information, the position of the checkout area where the mobile customer stayed for product purchase and the date and time of the product purchase which is the stay date and time are determined, and the position of the checkout area and the product purchase By acquiring POS data indicating purchase contents corresponding to the date and time, the POS data and the route information are associated with each other and stored in the pattern storage unit as the reference of the action pattern, and the customer as the mobile object Based on the route information including information on which one of a plurality of sales floors is passed, the speed information, and the plurality of behavior pattern data, the behavior of the customer as the mobile body is in any of the types of the behavior patterns. A pattern determination unit for determining whether they match, and
An output processing unit for outputting the result of the determination,
The pattern determination unit
When the relationship between the staying time in the area and the number of customers staying for each sales floor area is represented, among the customers whose staying time is shorter than the first time value, the sum of the customers who have purchased products in the sales floor area and the sales floor A time value such that the ratio to the total of customers who did not purchase products in the area becomes a predetermined ratio is specified as the first time value for each day or every time zone, and a plurality of days or An average value of the first time values over a plurality of time zones is calculated and stored in the pattern storage unit as a first threshold value for distinguishing the first pattern from the second pattern,
When the relationship between the staying time in the sales area and the number of customers staying for each sales floor area is represented, among the customers whose staying time is longer than the second time value, the sum of the customers who have purchased products in the sales floor area and the sales floor A time value such that the ratio to the total of customers who did not purchase products in the area becomes a predetermined ratio is specified as the second time value for each day or every time zone, and a plurality of days or An average value of the second time values over a plurality of time zones is calculated and stored in the pattern storage unit as a second threshold value for distinguishing between the second pattern and the third pattern,
When the staying time in a certain sales floor area of a mobile object that is subject to action pattern determination is less than the first threshold value associated with the sales floor area, the behavior pattern of the mobile body for the sales floor area is the first. Judge that it matches the pattern,
If the staying time in a certain sales area of a mobile object that is subject to action pattern determination is greater than or equal to the first threshold value associated with the sales area and falls below the second threshold value, the sales area Determining that the behavior pattern of the moving object matches the second pattern with respect to the region;
If the staying time in a certain sales floor area for a mobile object that is the target of behavior pattern determination is greater than or equal to the second threshold value associated with the sales floor area, the behavior pattern of the mobile body for the sales floor area is the first 3 behavior analyzer shall be the determining means determines that match the pattern. The pattern determination unit
Depending on at least one of the flow line distance from the store entry to the store exit in the entire space in the store, the entrance time, the stay time, the average speed, and the total number of stops Classifying into segments, calculating the first threshold value and the second threshold value for each segment and storing them in the pattern storage unit;
For mobile objects that are subject to behavior pattern determination, which of the plurality of segments corresponds to the flow line distance from entry to exit, entry time, stay time, average speed in the entire space in the store , after determining based on at least one aspect of the stop total, appropriate corresponding to the segment of the first threshold and the first pattern on the basis of the second threshold value, the second path turn, and behavioral analysis apparatus according to claim 1 or 2, wherein the determining whether to match any of the third pattern. A position acquisition unit for acquiring position information indicating the position of a moving body that changes with time in a real space in a predetermined store and time information indicating the positioning timing;
A space acquisition unit that acquires, as spatial information, respective coordinates for specifying the arrangement of a plurality of sales floors included in the store on a virtual space;
Based on the position information, the time information, and the space information, the moving body indicates the route information indicating the movement path of the moving body in the real space in the store by the position in the virtual space. A route acquisition unit that generates information along with information about which one of
Based on the position information and the time information, a speed acquisition unit that generates, as speed information, information indicating an average speed of the moving body in each of the plurality of sales floors;
As a type of purchasing behavior based on the relationship between the movement path and movement speed of a customer, who is a mobile object, the first pattern showing the case of passing through the sales floor area, purchasing goods or considering purchasing after stopping in the sales floor area for a relatively short time The second pattern indicating the case of performing, and the third pattern indicating the case of staying for a long time in one sales area, the standard regarding the stay time for each sales area of each behavior pattern is the customer's stay time in the past and the customer's A pattern storage unit for storing a plurality of behavior pattern data defined in advance in relation to statistics of purchase contents;
Based on the route information, the position of the checkout area where the mobile customer stayed for product purchase and the date and time of the product purchase which is the stay date and time are determined, and the position of the checkout area and the product purchase By acquiring POS data indicating purchase contents corresponding to the date and time, the POS data and the route information are associated with each other and stored in the pattern storage unit as the reference of the action pattern, and the customer as the mobile object Based on the route information including information on which one of a plurality of sales floors is passed, the speed information, and the plurality of behavior pattern data, the behavior of the customer as the mobile body is in any of the types of the behavior patterns. A pattern determination unit for determining whether they match, and
An output processing unit for outputting the result of the determination,
The plurality of behavior pattern data stored in the pattern storage unit includes at least one of a position, a distance from the customer, a relative speed with the customer, and a duration of the state regarding the behavior type of the employee who is the moving body. Standards are predetermined,
The pattern determination unit matches any of the plurality of behavior pattern data according to the position, the distance to the customer, the relative speed with the customer, and the duration of the state. Action analyzer you and judging whether the to. In the plurality of behavior pattern data stored in the pattern storage unit, as a type of behavior of the employee who is the moving body, a state of waiting for a customer, a state of being outside a sales floor, a state of approaching a customer, The standard is defined for at least one of the following types: a state of approaching a customer, a state of business negotiations, a state of payment, and a state of moving out of the sales area,
The pattern determination unit is a state in which the behavior of the employee as the moving body is waiting for a customer, a state outside the sales floor, a state where the customer is approaching, a state where the customer is approaching, a state where a negotiation is performed The behavior analysis apparatus according to claim 4 , wherein the behavior analysis apparatus determines which type is matched among a state in which payment is being made and a state in which the payment is out of the sales area. The pattern determination unit is a state in which the behavior of the employee as the moving body is waiting for a customer, a state outside the sales floor, a state where the customer is approaching, a state where the customer is approaching, a state where a negotiation is performed 6. The method according to claim 5 , wherein, for at least one type of the state of payment and the state of moving out of the sales area, the total time corresponding to the type is calculated for each employee. The behavior analysis device described. The pattern determination unit displays the stay time of customers corresponding to the second pattern and the third pattern in each sales floor area, and when no employees are present in the sales floor area, all employees in the sales floor area are in service. If there are one or more employees who are not in service in the sales area, it is divided in each case, and the total time in each case and the ratio in each case are calculated. Item 7. The behavior analysis device according to any one of Items 4 to 6 . The pattern determination unit displays the stay time of customers corresponding to the second pattern and the third pattern in each sales floor area, and when no employees are present in the sales floor area, all employees in the sales floor area are in service. If there are one or more employees who are not serving customers in the sales area, it is divided in each case, and for each sales area, all the staying time in the sales area is absent. The total number of customers and the total staying time when the employee is in attendance with the employee, or the total number of hours, is calculated as the number and time that the employee missed a sales opportunity without being available in the sales area. behavior analysis apparatus according to claim 4, wherein 6.

Images