JP4923876B2 - Information providing robot and information providing method using robot - Google Patents

Description

  The present invention relates to an information providing robot for providing information to a customer who has visited a store or the like, and an information providing method using the robot.

  Traditionally, robots that can be run independently, such as in shopping centers, have a fixed menu and explain to the customer according to the menu, sometimes run by themselves, or point to it with an arm. Was displayed and uttered.

Further, the current position information of the robot is detected, and guidance display is performed based on the position information (Patent Document 1).
JP 2005-172879 A

  As described above, since the store has been fixed or changed to the customer based on the current location information and the store information and the product guide, the contents corresponding to adults, children, infants, etc. There is a problem that the service cannot be improved by providing information to the customer efficiently and flexibly according to the situation such as the congestion of the store and the quiet.

  In order to solve these problems, the present invention detects an adult, a dwarf, an infant, and the like based on the height and face height of a customer who visits a store at a robot, etc., and detects the degree of congestion. The most suitable information is selected (or created) from the table and displayed, the voice is uttered, expressed in a gesture, and moved further for efficient explanation and guidance.

  The present invention detects adults, dwarfs, infants, etc. from the height and face height of customers who visit the store, etc., and detects the degree of congestion, and selects the optimal information for the customer from the table based on these (Or create) and display, speak voice, express in gesture, and move and explain and guide efficiently, according to the degree of congestion for customers (adults, children, infants) who visited the store etc. It is possible to provide information efficiently and to improve customer service.

  The present invention detects adults, dwarfs, infants, etc. from the height and face height of customers who visit the store, etc., and detects the degree of congestion, and selects the optimal information for the customer from the table based on these (Or create) and display, voice is spoken, expressed in gestures, moved further to explain and guide efficiently, depending on the degree of congestion for customers (adults, children, infants) who visited the store Realize information and improve customer service.

FIG. 1 shows a block diagram of an embodiment of the present invention.
FIG. 1A shows a configuration example in which the height (head height) of a customer is detected by a plurality of sensors 21 mounted on the robot 1, and FIG. A configuration example for detecting the height of the head or the height of the face is shown.

  1 (a) and 1 (b), a robot 1 is a self-propelled robot that is arranged in a store or the like and provides services such as explanation and guidance when a customer visits the store. 2. A mode switching table 9, a product introduction content table 10, an introduction content DB 11, a display 12, a speaker 13, a sensor 21, a camera 22, and the like.

  The processing device 2 performs various processes provided by the known self-running robot 1 according to the present invention, and includes a preprocessing unit 3, a user detection unit 4, a congestion level detection unit 5, a mode setting unit 6, The processing execution means 7 and the post-processing means 8 are configured.

  The pre-processing means 3 performs various initial settings, or greets customers when they visit the store (displays greetings such as “I welcome you”, greets you with your voice and lowering your head and hands) Etc.

  The user detecting means 4 detects the height of the customer's head and face with the sensor 21 or the camera 22 when the customer comes to the store and approaches the robot 1 (from FIG. 2). (See FIG. 7).

  The congestion degree detection means 5 detects the degree of congestion (high, low, etc.) based on the number of customers who have visited the store or the like photographed with the camera 22 attached to the robot 1, or the store visited with the in-store camera 31. The notification of the degree of congestion (high, low, etc.) determined by the congestion degree detection device 32 based on the number of customers that have been received is received wirelessly (see FIGS. 2 to 7).

  The mode setting means 6 determines and sets whether the mode is adult, dwarf or infant based on the height of the customer who came to the store detected by the user detection means 4 and approached the robot 1. Furthermore, a mode (submode) corresponding to the congestion level near the robot 1 notified from the congestion level detection means 5 and the congestion level in the store is set (see FIGS. 2 to 7). ).

  The processing execution means 7 executes processing on the robot 1 in accordance with the set mode (for example, processing such as displaying the introduction content of the adult mode, uttering with voice, moving and guiding and explaining while pointing with the hand) Execute).

  The post-processing means 8 performs various post-processing and greets customers when they approach the exit (for example, displays greetings such as “Thank you so much”, utters and greets with the head and hands lowered) Etc.

  The mode switching table 9 stores modes (adult, dwarf, and infant modes) in advance in association with customer heights (head height detected by the sensor 21, head height detected by the camera 22, and face height). This is a registered table (see FIGS. 2 and 5).

  The product introduction contents table 10 is a table in which introduction contents (such as robot movement amount, gesture, utterance, introduction contents (display), etc.) are registered in advance in association with modes (see FIGS. 2 to 7).

  The introduction content table 11 is a DB in which detailed contents such as product introduction set in the product introduction content table 10 are registered in advance (see FIGS. 2 to 7).

  The display 12 is a display device that is attached to the robot 1 to display introduction contents and inform a customer (see FIGS. 2 to 7).

  The speaker 13 is a speaker attached to the robot 1 and is used to utter a voice.

  The sensor 21 is a sensor that detects the height (head height) of a customer approaching after being attached to the robot 1.

  The camera 22 is a camera attached to the robot 1 and detects the height of the customer (head height or face height) approaching the robot 1 (see FIGS. 2 to 7). ). When the height of the customer's face (or head) is detected by the camera 22, the feature of the face (or head) is recognized from the image of the customer approaching the robot 1, and the face (or head) is included in the image. For example, the height of the customer's face (head) is detected from the angle by changing the swinging (upward) angle of the camera 22 so as to be approximately at the center.

  The in-store camera 31 is a camera arranged in the store, and is for detecting the degree of customer congestion.

  The degree-of-mixing detection device 32 recognizes the number of customers who have visited the store based on the images taken by the in-store camera 31, detects the degree of congestion (the degree of congestion is high, low, etc.), and the degree of congestion detection means 5 or the like.

Next, the operation of the configuration of FIG. 1 will be described in detail according to the order of the flowchart of FIG.
FIG. 2 shows a flowchart for explaining the operation of the present invention.

  In FIG. 2, S1 determines whether a person is approaching. This is detected by a sensor 21 (or a proximity sensor (not shown) (for example, an infrared sensor that detects that a person has approached)) whether a person (customer) who has visited the store or the like in FIG. 1 has approached the robot 1. If YES, the process proceeds to S2. If NO, repeat S1 and wait.

  In S2, preprocessing is performed. This is because the pre-processing means 3 of the robot 1 in FIG. 1 greets the customer (for example, “speak” is uttered by voice from the speaker 13, “is welcome” is displayed on the display 12, and the robot 1 Greet the customer with their heads and hands down with their faces facing the customer).

  In S3, it is determined whether or not it is very crowded. This is the degree of congestion of the customer determined by the congestion degree detection device 32 based on the image of the customer in the store taken by the in-store camera 31 by the congestion degree detecting means 5 constituting the robot 1 and the image taken by the camera 22. Based on the degree of congestion determined based on the number of customers in the vicinity of the robot 1, it is determined whether the number of customers who have visited the store is currently large and very crowded. In the case of YES, since it is found that it is very crowded, it is set to “very crowded mode” that is very crowded in S4, and the process proceeds to S15. On the other hand, in the case of NO, it has been found that it is not very crowded, so the process proceeds to S5.

  In S5, it is determined whether it is congested. This is determined to be very crowded with NO in S4, so it is further determined whether or not it is crowded. In the case of YES, since it is found that the traffic is congested, the “congested mode” is set in S6 and the process proceeds to S7 or S8. If NO, the process proceeds to S7 or S8.

  Through the above S1 to S6, the robot 1 greets customers who have visited the store, and “very crowded mode” when the shop or around the robot 1 is very crowded. When the “congestion mode” is set, and it is not crowded, it can be set without setting the congestion mode.

  In S7, the height is detected by the sensor. For this, the height (head height) of the customer approaching the robot 1 is detected by the plurality of sensors 21 attached to the robot 1 of FIG. 1A, and the process proceeds to S10.

In S8, the face is detected by the camera.
In step S9, the detected face height is calculated. In S8 and S9, the feature of the face of the person (customer) approaching the robot 1 is detected by the camera 22 shown in FIG. 1B, and the angle of the camera 22 is set so that the detected face is substantially at the center of the image. The height of the customer's face corresponding to the adjusted angle is calculated. Instead of the customer's face, the camera 22 may recognize the head and detect the height of the head. Then, the process proceeds to S10.

  In S10, it is determined whether the height of the infant. This is based on the height of the customer's head detected at SS7 or the height of the customer's face (or head) detected at S8 and S9, with reference to the mode switching table 9 in FIG. Determine whether. In the case of YES, the person (customer) who has approached the robot 1 in S12 is set to the “infant mode”, and the process proceeds to S15. If NO, the process proceeds to S11.

  In S11, it is determined whether the height of the dwarf. Since this is not the height of the infant in S10, it is further determined whether it is the height of the dwarf (child) with reference to the mode switching table 9 of FIG. In the case of YES, the person (customer) who has approached the robot 1 is set to “dwarf mode” in S13, and the process proceeds to S15. In the case of NO, the “adult mode” is set in S14, and the process proceeds to S15.

  Through S7 to S15 described above, it is possible to set one of the “infant mode”, “dwarf mode”, and “adult mode” based on the height of the person approaching the robot 1.

  In step S15, processing corresponding to the mode is performed. This is because the optimal information corresponding to any of the congestion mode set in S1 to S6 and the adult / dwarf / infant mode set in S7 to S14 is shown in the product introduction table in FIG. 10 read, display, voice utterance, express in gesture, further move and explain and guide efficiently, customers who come to the store (adults, children, infants), the degree of congestion (very crowded, It is possible to improve customer service by efficiently providing information according to congestion, normal). This will be described in more detail below.

  FIG. 3 shows a flowchart (part 2) for explaining the operation of the present invention. This shows a detailed flowchart of S15 of FIG.

In FIG. 3, S21 reads the processing content corresponding to the mode from the table.
In S22, the process is executed. These S21 and S22 are the details of S15 of FIG. 2 described above, and the set modes (“infant mode”, “dwarf mode”, “adult mode”, “very crowded mode”, “ The processing contents for “congestion mode” and “normal mode”) are read from the product introduction table 10 in FIG.

  For example, in the case of “very crowded mode”, the lowest mode of the product introduction table 10 in FIG. 4A regardless of “infant mode”, “dwarf mode”, or “adult mode” And the contents of the entries that are set to “very crowded (mode)” for both the sub-mode (movement amount (none), gesture (slightly), utterance (normal), introduction contents (repeating one guide (operation) (Repeat the same content))) (specific content is read from the highly congested DB constituting the introduction content DB 11 of FIG. 4B), and the processing is executed. Therefore, when the inside of the store is very crowded, the robot 1 is crowded with many customers, so there is no movement, the gesture by the arm is slightly suppressed, and the voice is not disturbed. Ordinary In introduces contents is executed to repeat the one guide (see FIG. 7 (d)).

  ・ In cases other than “very congested mode”, the contents corresponding to the mode of any mode of infant / dwarf / adult and the combination of the congested mode and no congested mode setting (normal mode) are shown in FIG. Read from the product introduction table 10 in (a) (read from any of the DB 111 for infants, the DB 112 for children, and the DB 113 for adults constituting the introduction content DB 11), and cause the robot 1 to execute (FIGS. 6 and 7). reference).

FIG. 4 shows a table / DB example of the present invention.
FIG. 4A shows an example of a product introduction table. The illustrated product introduction table 10 is registered in advance in association with the following product introduction information shown in association with modes and sub-modes.

·mode:
・ Sub mode:
·Amount of movement:
·gesture:
・ Voice:
・ Introduction contents:
・ Example:
Here, the mode is a column for setting any one of the infant mode, the dwarf mode, and the adult mode set in S10 to S14 of FIG. 2 described above, and is a mode classified based on the height of the customer who visited the store. It is. The sub-mode is a column for setting any one of the very congested mode, congested mode, and no congested mode setting (normal mode) set in S3 to S6 of FIG. This is a column for setting. The amount of movement, gestures, utterances, and introduction contents are preset with the amount of movement of the robot, the degree of gesture by the hand and the whole body, utterances, and introduction contents in association with the mode and submode. 4 (b) is registered in the introduction content DB 11. For example,
・ When the mode is `` infant mode '' and the sub mode is `` normal '',
・ Movement amount: None ・ Gestures: None ・ Voice: Speak in easy words ・ Introduction content: Content for infants (may not be related to the store). Example: A few frames (picture-story show) of a fairy tale are displayed and voiced (see FIG. 6A).

・ When the mode is `` Dwarf mode '' and the sub mode is `` Normal ''
・ Movement: Move to some extent ・ Gestures: Normal ・ Voice: Normal ・ Introduction: Introduction of products for children. Example: A toy advertisement is displayed, gestured, voiced, and moved (moved in the direction of the introduced product and guided to the toy store), and the product is introduced (see (b) of FIG. 6).

・ When the mode is `` Adult mode '' and the sub mode is `` Normal ''
・ Movement amount: Normal ・ Gestures: Normal ・ Voice: Normal ・ Introduction: Introduction of store products. Example: Introducing wine contents by display, gesture, movement, and voice (see (a) of FIG. 7).

  FIG. 4B shows an introduction content DB example. The introduction content DB 11 is a DB in which the introduction content of the product introduction table 10 in FIG. 4A is specifically registered in advance. Here, as shown in the figure, for each mode, a DB 111 for children, The DB 113, the adult DB 113, and the extremely crowded DB 114 are provided separately.

  FIG. 5 shows an example table of the present invention. The mode switching table 9 shown in the figure is a table for switching (setting) the mode based on the height of the customer who visits the store, and here, the following information shown in the figure is associated and registered in advance. .

·mode:
・ Height 1:
・ Height 2:
・ Other:
Here, the mode is any one of three modes, an infant mode, a dwarf mode, and an adult mode. Height 1 sets a value indicating whether the mode is set to “infant mode”, “dwarf mode”, or “adult mode” depending on the highest height (height 1) of the head of the customer who visited the store ( The set value is set by obtaining an optimum value by experiment. For example, sensor positions 3, 2, and 1 are sensors 21 at positions of 150 cm, 80 cm, and 40 cm, respectively). The height 2 is set to a value indicating whether the mode is set to “infant mode”, “dwarf mode”, or “adult mode” depending on the height of the customer's face (height 2). The set value is set by obtaining an optimum value by experiment. For example, when the face of the camera 22 comes to the center on the screen, the face heights 3, 2, 1 are sensors 21 at positions of 135 cm, 65 cm, and 35 cm, respectively. Is).

6 and 7 are explanatory diagrams of the present invention. This is an easy-to-understand explanation of typical examples of modes and sub-modes registered in the product introduction table 10 in FIG.

FIG. 6A shows an example of an infant (mode “infant mode”, sub-mode “normal”), and an example when the sub-mode is further set to “congestion mode” is shown in parentheses at the bottom. For example, in the product introduction table 10 of FIG. 4 (a): • Mode: Infant • Submode: Normal • Movement amount: None • Gesture: None • Speaking: Talking with easy words • Introduction content: Content for infants (What is a store? It doesn't matter)
Example: A few frames of fairy tales (picture-story show) are displayed and voiced.
6 is displayed on the display 12 and uttered from the speaker 13 as shown in FIG.

When the sub mode is set to “congested”, as described in parentheses at the bottom of FIG.
・ Reduced content: Reads the information that the content of 10 frames is reduced to 5 frames, is displayed on the display 12 as shown in FIG. 6A, utters from the speaker 13, and is about half of the normal time when crowded At this time, a series of introductions (explanations) to the infant is completed, the infant is encouraged to move to another place, and processing can be performed so that the next infant can be explained.

FIG. 6B shows an example of a dwarf (mode “dwarf mode”, sub-mode “normal”), and the parentheses at the bottom indicate an example when the sub-mode is further set to “congestion mode”. . For example, in the product introduction table 10 in FIG. 4A: • Mode: Dwarf • Submode: Normal • Movement amount: Move to some extent • Gesture: Normal • Speaking: Normal • Introduction content: Introduction of products for dwarfs Example: Displaying toy advertisements, gesturing, voice, moving (moving in the direction of the location of the introduced product and guiding to the toy store)
6 is displayed and displayed on the display 12 as shown in FIG. 6 (b), uttered from the speaker 13, and the robot 1 is self-propelled to move to the “toy store”.

When the sub mode is set to “congested”, as described in parentheses at the bottom of FIG. 6B,
・ Reduced contents: (1) Double speed display and playback
(2) Like a TV commercial, a 30-second full and a 10-second shortened version are prepared, and the information that the shortened version is flown is read out, displayed on the display 12 as shown in FIG. The robot 1 automatically moves and moves to the “toy counter”, completing a series of introductions (explanations) for the dwarf in about 1/3 of the normal time, and explaining to the next dwarf etc. It becomes possible to process like this.

FIG. 7C shows an example of an adult (mode “adult mode”, sub mode “normal”), and the parenthesis in the lower row shows an example when the sub mode further becomes “congestion mode”. For example, in the product introduction table 10 in FIG. 4 (a): • Mode: Adult • Submode: Normal • Movement amount: Normal • Gesture: Normal • Speaking: Normal • Introduction content: Introduction of store products Example: The introduction information of wine contents is displayed, gestures, movements, and voice introductions are read and displayed on the display 12 as shown in FIG. 7 (c). While pointing to the “event venue”, the speaker 13 speaks by voice and guides to the “event venue”.

When the sub mode is set to “congested”, as described in parentheses at the bottom of FIG.
・ Reduced contents: (1) Double speed display and playback
(2) Like a TV commercial, a 30-second full and a 10-second shortened version are prepared, and the information that the shortened version is sent is read, and displayed on the display 12 as shown in FIG. The robot 1 is self-propelled, moves and points at the arm, and at the “event venue”, a series of introductions (explanations) for adults is completed in about 1/3 of the normal time, and the next adult, etc. On the other hand, it is possible to process as explained.

(D) of FIG. 7 shows an example of very crowded (mode “arbitrary mode”, sub mode “very crowded”). For example, in the product introduction table 10 in FIG. 4 (a): • Mode: Very crowded • Submode: Very crowded • Amount of movement: None • Gesture: Slightly • Speaking: Normal • Introduction content: One guide Repeat (Suppress the action and repeat the same contents)
Example: Display a store event guide, introduce by voice, and point to the location with a gesture.
7 is displayed on the display 12 as shown in FIG. 7D. The robot 1 moves the arm slightly to point to the “event venue”, and speaks with voice from the speaker 13 to introduce the information. .

  The present invention detects adults, dwarfs, infants, etc. from the height and face height of customers who visit the store, etc., and detects the degree of congestion, and selects the optimal information for the customer from the table based on these (Or create) and display, voice is spoken, expressed in gestures, moved further to explain and guide efficiently, depending on the degree of congestion for customers (adults, children, infants) who visited the store The present invention relates to an information providing robot that provides information in an improved manner to improve customer service, and an information providing method using the robot.

1 is a configuration diagram of one embodiment of the present invention. It is an operation | movement explanatory flowchart of this invention. It is operation | movement description flowchart (the 2) of this invention. It is a table / DB example of this invention. It is an example table of this invention. It is explanatory drawing (the 1) of this invention. It is explanatory drawing (the 2) of this invention.

Explanation of symbols

1: Robot 2: Processing device 3: Preprocessing means 4: User detection means 5: Congestion degree detection means 6: Mode setting means 7: Process execution means 8: Post-processing means 9: Mode switching table 10: Product introduction contents table 11: Introduction DB
12: Display 13: Speaker 21: Sensor 22: Camera 31: In-store camera 32: Congestion degree detection device

Claims (4)

In an information providing robot that provides information to customers who visit the store,
A means of detecting the height of the customer who visited the store,
Means for determining one of a plurality of modes corresponding to an adult, a dwarf, and an infant based on the detected height of the customer;
Means for detecting the number of customers who have visited the store and gathered around the robot or the number of customers who have visited the store and determining a sub-mode according to the degree of congestion;
Corresponding to the mode and sub-mode , a table that pre-registers the robot introduction content, utterance, gesture, and movement,
Means for referring to the table based on the determined mode and sub-mode , and for reading information on the introduction contents of the robot, utterance, gesture, and movement;
An information providing robot comprising means for causing the robot to execute based on the read information. The customer of the height, according to claim 1, wherein the information providing robot, characterized in that to recognize the face of the detection or customer the highest head height of the customer to detect the height of the face. 3. The information providing robot according to claim 1, wherein when the degree of congestion is high in the sub mode, the content of introduction is reduced and the process ends in a short time. In the information provision method to provide information to customers who visited the store,
Corresponding to the mode and sub-mode , a table to register in advance the robot introduction content, utterance, gesture, and movement,
Detecting the height of the customer who came to the store;
Determining one of a plurality of modes corresponding to an adult, a dwarf, and an infant based on the detected height of the customer;
Detecting the number of customers who visit the store and gather around the robot or the number of customers who visit the store and determine a sub-mode according to the degree of congestion;
Referring to the table based on the determined mode and sub-mode , and reading information on the introduction contents of the robot, utterances, gestures, and movements;
And a step of causing the robot to execute based on the read information.

Images