WO2024045501A1

WO2024045501A1 - Recommendation information determination method and apparatus, and storage medium and electronic apparatus

Info

Publication number: WO2024045501A1
Application number: PCT/CN2023/075734
Authority: WO
Inventors: 胡百春
Original assignee: 海尔优家智能科技（北京）有限公司; 青岛海尔科技有限公司; 海尔智家股份有限公司
Priority date: 2022-08-30
Filing date: 2023-02-13
Publication date: 2024-03-07
Also published as: CN115481315A; CN115481315B

Abstract

The present disclosure relates to the technical field of smart homes. Provided are a recommendation information determination method and apparatus, and a storage medium and an electronic apparatus. The recommendation information determination method comprises: acquiring historical operation information of a target object controlling a water heater set; generating a quintuple data model on the basis of the historical operation information; and determining recommendation information according to the quintuple data model so that the target object controls, according to the recommendation information, a first water heater in a second region to heat a target volume of water to a second temperature, wherein the water heater set comprises a second water heater.

Description

Recommended information determination method and device, storage medium and electronic device

This disclosure claims priority to the Chinese patent application filed with the China Patent Office on August 30, 2022, with application number 202211049934.5 and the invention title "Method and device for determining recommended information, storage medium and electronic device", the entire content of which is incorporated by reference. incorporated in this disclosure.

Technical field

The present disclosure relates to the field of communications, and specifically, to a method and device for determining recommended information, a storage medium, and an electronic device.

Background technique

In recent years, the smart home industry has developed rapidly. People can use smart home products in different scenarios and applications, allowing smart home products to interact with users anytime and anywhere, improving the user's life experience.

In the current process of users using smart devices at home, in order to save timed startup and preheat in advance, some water heater manufacturers provide users with a timing template function to set the water heater startup time and startup temperature in advance or regularly. The method of starting up the water heater in the prior art is as shown in Figure 3. However, due to different factors such as seasonal changes, different bathroom locations, and bathroom area, the amount of hot water required each time is very different; if comprehensive consideration cannot be taken, there will be insufficient hot water or wasted hot water.

In related technologies, the influence of different factors such as seasonal changes, different bathroom locations, and bathroom area are not taken into account. Fixed startup time, startup temperature, water consumption and other information are set for the user each time. Insufficient hot water volume or hot water consumption may occur. Effective solutions have not yet been proposed for problems such as waste situations.

Contents of the invention

Embodiments of the present disclosure provide a method and device, a storage medium and an electronic device for determining recommended information, to at least solve the problem in related technologies that does not consider the influence of different factors such as seasonal changes, different bathroom locations, bathroom area sizes, etc., each time for the user Setting fixed startup time, startup temperature, water consumption and other information may cause problems such as insufficient hot water or wasted hot water.

According to an embodiment of the present disclosure, a method for determining recommended information is provided, including: obtaining historical operation information of a target object's control water heater collection, wherein the historical operation information includes: the first user of the target object information, the first windowed information and the first area information of the first area where each water heater in the water heater set is located, the first operation of the target object to control each water heater to heat water to a first temperature, the The target object controls the first time information when each water heater performs the first operation, and the first water consumption of each water heater used by the target object; generates a five-tuple data model based on the historical operation information, and generates a five-tuple data model based on the historical operation information. The five-tuple data model determines recommendation information, so that the target object controls the first water heater in the second area to heat the water of the target capacity to the second temperature according to the recommendation information, wherein the water heater set includes: the First water heater.

According to another embodiment of the present disclosure, a device for determining recommended information is also provided, including: an acquisition module configured to acquire historical operation information of the target object's control water heater collection, wherein the historical operation information includes: The first user information of the target object, the first windowed information and the first area information of the first area where each water heater in the water heater set is located, and the target object controls each water heater to heat water to a first temperature. the first operation, the first time information when the target object controls each water heater to perform the first operation, and the first water consumption of each water heater used by the target object; the determination module is configured to operate according to the historical operation The information generates a five-tuple data model, and determines recommendation information according to the five-tuple data model, so that the target object controls the first water heater in the second area to heat the water of the target capacity to the second area according to the recommendation information. temperature, wherein the set of water heaters includes: the first water heater.

According to yet another aspect of the embodiments of the present disclosure, a computer-readable storage medium is also provided. The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the above recommendation information when running. Determine the method.

According to another aspect of the embodiment of the present disclosure, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned steps through the computer program. How to determine recommended information.

In this embodiment of the present disclosure, the historical operation information of the water heater set controlled by the target object is obtained, where the historical operation information includes: the first user information of the target object, the first user information of each water heater. The first windowed information and the first area information of the area, the target object controls the first operation of each water heater to heat water to a first temperature, and the target object controls the first time when each water heater performs the first operation. information, the first water consumption of each water heater used by the target object; a five-tuple data model is generated according to the historical operation information, and recommendation information is determined according to the five-tuple data model, so that the target object The first water heater in the second area is controlled according to the recommendation information to heat the water of the target capacity to the second temperature, wherein the water heater set includes: the first water heater; using the above technical solution, the problem of not considering seasonal changes is solved Affected by different factors such as the location of the bathroom and the size of the bathroom, if fixed startup time, startup temperature, water consumption and other information are set for the user each time, problems such as insufficient hot water or wastage of hot water may occur, and further this disclosure The embodiment is based on the five-tuple data model of user behavior, by analyzing the first user information of the target object, the first windowed information and the first area information of the first area where each water heater is located, the target object The first operation of controlling each water heater to heat water to a first temperature, the first time information when the target object controls each water heater to perform the first operation, and the first water consumption of each water heater used by the target object. The mutual correlation between them can identify the water heater startup behavior information and push accurate personalized recommendation information to users.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.

In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those of ordinary skill in the art, It is said that other drawings can be obtained based on these drawings without exerting creative labor.

Figure 1 is a schematic diagram of the hardware environment of a method for determining recommended information according to an embodiment of the present disclosure;

Figure 2 is a flow chart of a method for determining recommended information according to an embodiment of the present disclosure;

Figure 3 is a schematic diagram of a method for determining recommended information according to the prior art;

Figure 4 is a sequence diagram of a method for determining recommended information according to an embodiment of the present disclosure;

Figure 5 is a flow chart of a method for determining recommended information according to an embodiment of the present disclosure;

Figure 6 is a line graph of target temperature analysis according to an embodiment of the present disclosure;

Figure 7 is a line chart of winter water consumption analysis according to an embodiment of the present disclosure;

Figure 8 is a line chart of summer water consumption analysis according to an embodiment of the present disclosure;

Figure 9 is a line chart of water consumption analysis of different bathrooms according to an embodiment of the present disclosure;

Figure 10 is a line chart of comprehensive water consumption analysis according to an embodiment of the present disclosure;

Figure 11 is a structural block diagram of a device for determining recommended information according to an embodiment of the present disclosure;

Figure 12 is a structural block diagram of an optional electronic device according to an embodiment of the present disclosure.

Detailed ways

In order to enable those skilled in the art to better understand the present disclosure, the following will clearly and completely describe the technical solutions in the present disclosure embodiments in conjunction with the accompanying drawings. Obviously, the described embodiments are only These are part of the embodiments of this disclosure, not all of them. Based on the embodiments in this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts should fall within the scope of protection of this disclosure.

It should be noted that the terms "first", "second", etc. in the description and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances so that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or apparatus that encompasses a series of steps or units and need not be limited to those explicitly listed. Those steps or elements may instead include other steps or elements not expressly listed or inherent to the process, method, product or apparatus.

According to one aspect of an embodiment of the present disclosure, a method for determining recommended information is provided. This method of determining recommended information is widely used in whole-house intelligent digital control application scenarios such as Smart Home, smart home, smart home device ecology, and smart residence (Intelligence House) ecology. optionally, In this embodiment, the above method for determining recommended information can be applied to a hardware environment composed of a terminal device 102 and a server 104 as shown in FIG. 1 . As shown in Figure 1, the server 104 is connected to the terminal device 102 through the network and can be used to provide services (such as application services, etc.) for the terminal or the client installed on the terminal. A database can be set up on the server or independently from the server. To provide data storage services for the server 104, cloud computing and/or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

The above-mentioned network may include but is not limited to at least one of the following: wired network, wireless network. The above-mentioned wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, and local area network. The above-mentioned wireless network may include at least one of the following: WIFI (Wireless Fidelity, Wireless Fidelity), Bluetooth. The terminal device 102 may be, but is not limited to, a PC, a mobile phone, a tablet, a smart air conditioner, a smart hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing equipment, a smart dishwasher, or a smart projection device. , smart TV, smart clothes drying rack, smart curtains, smart audio and video, smart sockets, smart audio, smart speakers, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart sweeping robot, smart window cleaning robot, smart mopping robot, Smart air purification equipment, smart steamers, smart microwave ovens, smart kitchen appliances, smart purifiers, smart water dispensers, smart door locks, etc.

This embodiment provides a method for determining recommended information, which is applied to a computer terminal. Figure 2 is a flow chart of a method for determining recommended information according to an embodiment of the present disclosure. The process includes the following steps:

Step S202: Obtain the historical operation information of the water heater set controlled by the target object, where the historical operation information includes: the first user information of the target object, the first user information of the first area where each water heater in the water heater set is located. Window information and first area information, the first operation of the target object controlling each water heater to heat water to a first temperature, the first time information when the target object controls each water heater to perform the first operation, the The first water consumption of each water heater used by the target object;

It should be noted that the above windowed information is used to indicate whether the first area has a window.

Step S204: Generate a five-tuple data model based on the historical operation information, and determine recommendation information based on the five-tuple data model, so that the target object controls the first water heater in the second area according to the recommendation information. A target volume of water is heated to a second temperature, wherein the set of water heaters includes: the first water heater.

Through the above steps, the historical operation information of the set of water heaters controlled by the target object is obtained, wherein the historical operation information includes: the first user information of the target object, the first windowed information of the first area where each water heater is located and the first area information, the first operation of the target object controlling each water heater to heat water to a first temperature, the first time information when the target object controls each water heater to perform the first operation, the use of the target object The first water consumption of each water heater; generate a five-tuple data model based on the historical operation information, and determine recommendation information based on the five-tuple data model, so that the target object controls the first water consumption based on the recommendation information. The first water heater in the second area heats the target capacity of water to the second temperature, wherein the water heater set includes: the first water heater; it solves the problem in related technologies that seasonal changes, different bathroom locations, and bathroom area sizes are not considered Affected by different factors, such as setting a fixed power-on time, power-on temperature, water consumption and other information for the user each time, problems such as insufficient hot water or waste of hot water may occur. Furthermore, the embodiment of the present disclosure is based on the five-yuan system based on user behavior. A set of data models, by analyzing the first user information of the target object, the first windowed information and the first area information of the first area where each water heater is located, the target object controls each water heater to heat water to Identify the correlation between the first operation at the first temperature, the first time information when the target object controls each water heater to perform the first operation, and the first water consumption of each water heater used by the target object. Information on water heater startup behavior habits can be used to push accurate personalized recommendation information to users.

In an exemplary embodiment, generating a five-tuple data model based on the historical operation information includes: classifying the first user information of the target object into a user attribute information set, and classifying the first user information where each water heater is located. The first windowed information of the area is classified into a location information set, the first area information of the first area where each water heater is located is classified into a context information set, and the target object controls each water heater when performing the first operation. The first time information is classified into a time information set, and the first operation of the target object controlling each water heater to heat water to a first temperature, and the first water consumption of each water heater used by the target object are classified into intentions. Attribute information set; generate a five-tuple data model according to the user attribute information set, the location information set, the context information set, the time information set, and the intention attribute information set.

That is to say, the user attribute information set u(x) is used to represent a certain user attribute, and u(u_1,u_2,...,u_k) represents the 1st to kth attributes of the user. For example, users contain attributes such as age and gender information; the time attribute information set t(x) is used to represent the time attributes of a user's behavior, t(t_1,t_2,...,t_k) represents the first time attribute to k attributes. For example, attributes such as year, season, month, day, hour, etc. to which user behavior belongs; location attribute information set a(x) is used to represent the location attribute of a certain user behavior, and a(a_1,a_2,...,a_k) represents the location. Attributes 1 to k. For example, attributes such as province, city, district, room, etc. to which the user's behavior belongs; the context attribute information set l(x) is used to represent the context attributes of a certain user behavior, and l(l_1, l_2,...,l_k) represents the context attribute. 1 to k features. For example, the user’s previous behavior, current behavior, current weather, current device power-on status and other attributes; the intent attribute information set i(x) is used to represent a certain user intent attribute, i(i_1,i_2,…,i_k) represents the user’s intent The 1st to k attributes of . For example, turn on the water heater, set the target temperature, increase the heating speed and other properties. The five-tuple data model f_x(u_1,t_1,a_1,l_1,i_1,...) is used to represent user l_1 and the corresponding user behavior time attribute 1 is t_1, the address location attribute 1 is a_1, and the context attribute 1 is l_1; according to The first four tuples get the fifth tuple i_1. For example, f_1(u_1,t_1,a_1,l_1,i_1) means: User: 'Zhang San', the corresponding user behavior time attribute is ['2021-01-20', 'Winter'], and the location attribute is 'With Window Bathroom', the contextual attributes are ['I want to take a shower', 'Bathroom area is 2 square meters'], and the predicted user behavior intention is ['Turn on the water heater', 'Target temperature: 60 degrees Celsius', 'Water consumption: 30 liters'] .

Through the above embodiments, a five-tuple data model is accurately established. Based on the five-tuple data model of user behavior, the user's behavioral habits for turning on the water heater are determined, and accurate personalized recommendation information is pushed to the user, thereby solving the problem in related technologies. Users may encounter problems such as insufficient hot water or waste of hot water when using the water heater.

In an exemplary embodiment, the recommendation information is determined according to the five-tuple data model, wherein the five-tuple data model includes: a user attribute information set, a location information set, a context information set, a time information set, and an intent attribute. The information set includes: dividing multiple first temperatures in the intention attribute information set into multiple temperature sets, wherein the temperatures in each temperature set are the same; for each of the temperature sets, at the location The information set, the context information set, the time information set, and the intention attribute information set determine the second windowed information and the second area information of the third area where the second water heater corresponding to each temperature set is located, The target object controls the second time information when the second water heater heats water to a third temperature, and the second water consumption of the second water heater when the target object uses the second water heater, wherein the water heater set also includes: a second water heater ; Determine recommended information based on the second windowed information, the second area information, the second time information, and the second water consumption.

Specifically, the third window information and the third area information of the fourth area where the fourth water heater is located corresponding to each temperature in each temperature set are determined, and the target object controls the fourth water heater to heat water to the fourth temperature. The third time information, the third water consumption of the fourth water heater used by the target object, until the information corresponding to each temperature in all temperature sets is determined, and then the recommended information is determined based on the determined information.

Through the above embodiment, multiple sets of data are used to determine the recommended information based on the second windowed information, the second area information, the second time information, and the second water consumption corresponding to each temperature, and then Recommended information can be determined more accurately.

In an exemplary embodiment, determining recommended information according to the second windowed information, the second area information, the second time information, and the second water consumption includes: according to each temperature set The corresponding second time information determines the first season information corresponding to each temperature set to obtain a plurality of first season information; determine based on the second windowed information, the second area information, and the second water consumption The corresponding relationship between the third area and the second water consumption; determining third season information consistent with the second season information corresponding to the current time among the plurality of first season information, and determining the third season A target temperature set corresponding to the information; use the temperature corresponding to the target temperature set as the second temperature, and determine the recommended information according to the second temperature and the corresponding relationship.

It should be noted that the seasonal information can be: spring, summer, autumn and winter, or it can be: early spring, mid-spring, late spring, early summer, mid-summer, late summer, early autumn, mid-autumn, late autumn, early winter, mid-winter, late winter; according to the seasonal information and the second The window information, the second area information, and the second water consumption determine the recommended information.

Through the above embodiment, the recommended information is determined based on the seasonal information, the second windowed information, the second area information, and the second water consumption. When determining the recommended information, not only the second windowed information, The second area information and the second water consumption also consider seasonal information, and the recommended information is determined by four factors, which can improve the accuracy of the recommended information.

In an exemplary embodiment, determining the recommended information according to the second temperature and the corresponding relationship includes: calculating the average, variance and standard deviation of the second water consumption, and determining whether the variance is greater than A preset threshold; if the variance is greater than the preset threshold, determine the area without a window and with the smallest area in the third area as the second area; determine the third area based on the average and the standard deviation. water consumption, and generating the recommendation letter based on the second temperature, the third water consumption, and the second area interest.

That is to say, calculate the average value, variance and standard deviation of the second water consumption. According to the variance value, it can be determined whether the difference in water consumption between the bathroom with a window and the bathroom without a window is too large; considering the water consumption, so in the bathroom with a window If the water consumption gap between the bathroom and the windowless bathroom is too large, it can be suggested that the target object: the water heater startup information in winter is: target temperature: second temperature, location: windowless bathroom, estimated water consumption: third water consumption, through the above implementation For example, the water consumption of the water heater can be reduced, thereby achieving the effect of saving water.

It should be noted that when the area corresponding to the target object only includes a bathroom with a window, the water heater startup information in winter is: target temperature: second temperature, location: bathroom with a window, estimated water consumption: third water consumption.

In an exemplary embodiment, after determining whether the variance is greater than a preset threshold, the method further includes: if the variance is greater than the preset threshold, determining a windowed area with the largest area in the third region area as the second area; determine a fourth water consumption based on the average value and the variance, and generate the recommendation information based on the second temperature, the fourth water consumption, and the second area.

That is to say, calculate the average value, variance and standard deviation of the second water consumption. According to the variance value, it can be determined whether the difference in water consumption between the bathroom with a window and the bathroom without a window is too large; considering the water consumption, so in the bathroom with a window When the difference in water consumption between the bathroom and the windowless bathroom is not too large, based on comfort and ventilation considerations, it is recommended that the water heater startup information is: target temperature: second temperature, location: windowed bathroom, estimated water consumption: fourth Water consumption, through the above embodiments, can not only reduce the water consumption of the water heater, but also ensure the user's comfort during the bathing process.

In an exemplary embodiment, after determining the recommendation information according to the five-tuple data model, the method further includes: determining a target time required for the first water heater to heat water of a target capacity to a second temperature; according to The five-tuple data model determines the first time point when the target object uses the first water heater; determines the second time point based on the first time point and the target duration, and sends the message to the target object at the second time point. The first water heater sends a control command, wherein the control command is used to instruct the first water heater to heat the target capacity of water to a second temperature.

That is to say, according to the user's usage habits, the water heater is turned on in advance, so that when the target object uses the water heater, the temperature of the water in the water heater reaches the second temperature. Through the above embodiment, the water heater is intelligently turned on according to the user's usage. Get used to it and turn on the water heater in advance to avoid the problem of the water heater not being turned on when using the water heater, thus achieving the effect of improving the user experience.

In order to better understand the process of the method for determining the above recommended information, the process of the method for determining the above recommended information will be described below with reference to optional embodiments, but this is not intended to limit the technical solutions of the embodiments of the present disclosure.

This embodiment provides a method for determining recommended information. Figure 4 is a sequence diagram of a method for determining recommended information according to an embodiment of the present disclosure. As shown in Figure 4, the specific steps are as follows:

Step S401: Based on each device, collect user information, seasonal information, water heater location information, bathroom area and other environmental information, as well as user behavior and other related information. Among them, the related information not only includes basic information such as the user's age and gender, as well as continuous or historical behavior information such as current behavior, previous behavior, and next behavior; it also includes seasonal information, water heater location information, environmental information and other information;

Step S402: Send all related information to the data calculation server to implement the data;

Step S403: Divide all related information into five tuples and build a user five-tuple data model. The user five-tuples are user tuples, time tuples, location tuples, context tuples, and intent tuples. Design a unified data model, including unified storage format, unified encoding, unified units, etc.;

Step S404: Analyze and organize each tuple information of the user's five-tuple to obtain the distribution characteristic information of the relevant tuple data;

Step S405: Identify the water heater starting behavior habit information based on the user's quintuple analysis results;

Step S406: push relevant recommendation messages based on the user's water heater startup behavior information;

Step S407: Data sending rule verification;

Step S408: If the verification passes, send the recommendation message to the device.

Among them, U: user attribute information set u(x), which represents a certain user attribute, and u(u_1,u_2,…,u_k) represents the 1st to kth attributes of the user. For example, users contain attributes such as age and gender information.

T: Time attribute information set t(x), which represents the time attribute of a certain user behavior. t(t_1,t_2,…,t_k) represents the 1st to kth attributes of time. For example, attributes such as year, season, month, day, hour, etc. to which user behavior belongs.

A: The location attribute information set a(x) represents the location attributes of a certain user behavior, and a(a_1,a_2,…,a_k) represents the 1st to kth attributes of the location. For example, attributes such as province, city, district, room, etc. to which the user's behavior belongs.

L: Context attribute information set l(x), representing the context attributes of a certain user behavior, l(l_1, l_2,...,l_k) represents the 1st to k features of the context. For example, attributes such as the user's previous behavior, current behavior, current weather, current device power-on status, etc.

I: Intention attribute information set i(x), which represents a certain user intention attribute, i(i_1,i_2,…,i_k) represents the 1st to kth attributes of user intention. For example, turn on the water heater, set the target temperature, increase the heating speed and other properties.

F: Five-tuple attribute information set f_x(u_1,t_1,a_1,l_1,i_1,...), indicating that user l_1 and the corresponding user behavior time attribute 1 are t_1, the address location attribute 1 is a_1, and the context attribute 1 is l_1 ; Get the fifth tuple i_1 based on the first four tuples. For example, f_1(u_1,t_1,a_1,l_1,i_1) indicates that user: 'Zhang San', the corresponding user behavior time attribute is ['2021-01-20', 'winter'], and the location attribute is 'bathroom with window' , the contextual attributes are ['I want to take a shower', 'Bathroom area is 2 square meters'], and the predicted user behavior intention is ['Turn on the water heater', 'Target temperature: 60 degrees Celsius', 'Water consumption: 30 liters'].

Optionally, this embodiment also provides a method for determining recommended information. Figure 5 is a flow chart of a method for determining recommended information according to an embodiment of the present disclosure. As shown in Figure 5, the specific steps are as follows:

Step S501: Start;

Step S502: Obtain user behavior information;

Specifically, information related to user behavior is collected through different user terminals, such as APP, AI, multi-screen, etc., and related systems, such as user center, IOT domain model, family model, etc. The user behavior information includes but is not limited to user information, family information, location information, environmental information, device information, user behavior and other related information.

Step S503: Generate a user five-tuple data model based on analysis and classification of the collected information.

specific:

The user attribute information set includes: user ID information, user feature information, etc.

The time attribute information collection includes: behavior time series; including user behavior timestamp, behavior time year, month, day, hour and other information.

The location attribute information set includes: behavior location address information; including the space to which the user's behavior belongs, such as 'living room'; and also includes information such as the province, city, district, county, community, etc. to which the behavior belongs.

The contextual attribute information set includes: pre- and post-order behaviors, pre- and post-order behavior status, room area, user or network device portrait, weather and air quality and other information.

The set of intent attribute information includes: data predicting subsequent behavior information.

Step S504: Analyze quintuple data;

Specifically, 3.1: Analyze non-user tuple data;

Perform statistics and analysis on time tuple information, location tuple information, and context information.

A) Time and context tuple analysis: For example, analyze the 'timestamp' attribute in the 'time' tuple and the 'behavior status value' attribute (for example, room area) in the 'context' tuple: for the same behavior of different users, The 'timestamp' attribute and the 'behavior status value' attribute will present different characteristic status distributions. Group the data according to the data distribution shape; perform statistics on the maximum value, minimum value, average value, variance and other data of the grouped data.

For example, users use water heaters to take baths in different bathrooms in different seasons. The water heater reports operation record information every day, as shown in Table 1.

Table 1

Target temperature analysis of water heater startup record data is shown in Figure 6 . Figure 6 is a line graph of target temperature analysis according to an embodiment of the present disclosure.

Through data analysis, it can be known that the recorded data is clearly divided into two groups of data

1. Group 1: Data with serial numbers 1-8 and target temperature values of 60 degrees Celsius are divided into one group and marked as winter boot behavior.

2. Group 2: Data with serial numbers 9-16 and target temperature values of 50 degrees Celsius are divided into one group and marked as summer startup behavior.

After grouping, analyze the water heater start-up data and water consumption in different seasons:

Winter startup analysis is shown in Figure 7. Figure 7 is a line chart of winter water consumption analysis according to an embodiment of the present disclosure.

Summer startup analysis is shown in Figure 7. Figure 8 is a line chart of summer water consumption analysis according to an embodiment of the present disclosure.

After grouping, the water heater start-up data in different seasons and the corresponding water consumption analysis of different bathrooms are analyzed, as shown in Figure 9. Figure 9 is a line chart of the water consumption analysis of different bathrooms according to an embodiment of the present disclosure.

Analyze the distribution characteristics of the water heater operating data comprehensively, as shown in Figure 10. Figure 10 is a line chart of comprehensive water consumption analysis according to an embodiment of the present disclosure.

Through group data analysis, we can get:

1. Group 1 data analysis: It can be calculated that the maximum value, minimum value, average value, variance and other data distribution characteristic information of this group of data are 27, 22, 24.375, 4.734375 respectively.

2. Group 2 data analysis: It can be calculated that the maximum value, minimum value, average value, variance and other data distribution characteristic information of this group of data are 21, 18, 19.5, 0.75 respectively.

3.2: Five-tuple data analysis

Horizontally connect related information such as time tuple information, location tuple information, context information, and user information, and associate behavioral data value distribution characteristics and related tuple attribute characteristics with user tuple information to form the user's behavior value distribution feature.

Step S505: Identify the user's water heater startup behavior habits;

Identification based on time, location, and context tuples: Based on the analyzed time, location, and context tuple information characteristics, as well as the user's behavior status value attribute distribution characteristics, and associated matching with known user characteristics and user behavior characteristics, identify the user Water heater start-up behavior information.

According to winter-related data and graphics, it can be known that the linear deflection angle is higher in winter; according to the variance, it can be known that the water consumption gap between bathrooms with windows and bathrooms without windows is large; based on water conservation considerations, Therefore, it can be recommended that the water heater startup information in winter is: target temperature: 60 degrees Celsius, location: windowless bathroom, estimated water consumption: 26.5 liters.

According to summer-related data and graphics, it can be known that the linear deflection angle is lower and higher in summer; according to the variance, it can be known that there is not much difference in water consumption between bathrooms with windows and bathrooms without windows; based on comfort and ventilation considerations, it can be The recommended information for starting up the water heater in summer is: target temperature: 50 degrees Celsius, location: bathroom with window, estimated water consumption: 20.25 liters.

Step S506: User message push;

According to the information push rules, personalized recommendation messages that conform to the user's water heater startup behavior are pushed to the user.

In this disclosure, when a user uses a smart device, each element information can be collected from multiple user terminals to generate a user five-tuple data model. Based on the user quintuple, the statistics of the 'timestamp' attribute in the 'time' tuple and the 'behavior status value' information and location information in the 'context' tuple can be analyzed to identify the water heater startup behavior habits. It can avoid insufficient hot water or waste of hot water due to the user not considering seasonal changes, different bathroom locations, bathroom area and other factors, and setting fixed startup time, startup temperature, water consumption and other information for the user each time. Case.

Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is Better implementation. Based on this understanding, the technical solution of the present disclosure can be embodied in the form of a software product in essence or that contributes to the existing technology. The computer software product is stored in a storage medium (such as ROM/RAM, disk, CD), including several instructions to cause a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present disclosure.

Figure 11 is a structural block diagram of a device for determining recommended information according to an embodiment of the present disclosure; as shown in Figure 4, it includes:

The acquisition module 1102 is configured to acquire the historical operation information of the target object's control water heater collection, where the historical operation information includes: the first user information of the target object, each user in the water heater collection The first windowed information and the first area information of the first area where each water heater is located, the target object controls each water heater to perform a first operation of heating water to a first temperature, and the target object controls each water heater to perform a first operation. The first time information during operation and the first water consumption of each water heater used by the target object;

The determination module 1104 is configured to generate a five-tuple data model based on the historical operation information, and determine recommendation information based on the five-tuple data model, so that the target object controls the third object in the second area based on the recommendation information. A water heater heats a target volume of water to a second temperature, wherein the set of water heaters includes: the first water heater.

Through the above device, the historical operation information of the set of water heaters controlled by the target object is obtained, wherein the historical operation information includes: the first user information of the target object, the first window information of the first area where each water heater is located, and the first window information of the first area where each water heater is located. An area information, the first operation of the target object controlling each water heater to heat water to a first temperature, the first time information when the target object controls each water heater to perform the first operation, the use of the target object The first water consumption of each water heater; generate a five-tuple data model based on the historical operation information, and determine recommendation information based on the five-tuple data model, so that the target object controls the second area based on the recommendation information The first water heater in the system heats the water of the target capacity to the second temperature, wherein the water heater set includes: the first water heater; it solves the problem that in the related technology, seasonal changes, different bathroom locations, different bathroom area sizes, etc. are not considered. Affected by factors, each time a fixed boot time, boot temperature, water consumption and other information are set for the user, problems such as insufficient hot water or wasted hot water may occur. Furthermore, the embodiment of the present disclosure is based on the five-tuple data of user behavior. model, by analyzing the first user information of the target object, the first windowed information and the first area information of the first area where each water heater is located, the target object controls each water heater to heat water to the first The correlation between the first operation of temperature, the first time information when the target object controls each water heater to perform the first operation, and the first water consumption of each water heater used by the target object identifies the start-up of the water heater. Behavioral habits information, push accurate personalized recommendation information to users.

In an exemplary embodiment, the determination module 1104 is configured to classify the first user information of the target object into a user attribute information set, and classify the first windowed information of the first area where each water heater is located into The location information set classifies the first area information of the first area where each water heater is located into the context information set, and controls the first time when the target object controls each water heater to perform the first operation. The information is classified into a time information set, and the target object controls a first operation of each water heater to heat water to a first temperature, and the first water consumption of each water heater used by the target object is classified into an intention attribute information set. ; Generate a five-tuple data model according to the user attribute information set, the location information set, the context information set, the time information set, and the intention attribute information set.

In an exemplary embodiment, the determination module 1104 is configured as a user attribute information set, a location information set, a context information set, a time information set, and an intention attribute information set, including: combining a plurality of the intention attribute information sets in the intention attribute information set. A temperature is divided into multiple temperature sets, where the temperatures in each temperature set are the same; for each temperature set, the location information set, the context information set, the time information set, the The second windowed information and the second area information of the third area where the second water heater is located corresponding to each temperature set are determined in the intention attribute information set, and the target object controls the second water heater to heat the water to the third temperature. The second time information and the second water consumption of the second water heater used by the target object, wherein the water heater set further includes: a second water heater; according to the second windowed information and the second area information, The second time information and the second water consumption determination recommendation information.

In an exemplary embodiment, the determination module 1104 is configured to determine the first season information corresponding to each temperature set according to the second time information corresponding to each temperature set, so as to obtain a plurality of first season information; according to the The second windowed information, the second area information, and the second water consumption determine the corresponding relationship between the third area and the second water consumption; in the plurality of first season information, the corresponding relationship with the current water consumption is determined. The third season information that is consistent with the second season information corresponding to the time, and determine the target temperature set corresponding to the third season information; use the temperature corresponding to the target temperature set as the second temperature, according to the second temperature and the corresponding relationship to determine the recommended information.

In an exemplary embodiment, the determination module 1104 is configured to calculate the mean, variance and standard deviation of the second water consumption, and determine whether the variance is greater than a preset threshold; when the variance is greater than the preset threshold, In this case, determine the area without windows and with the smallest area in the third area as the second area; determine the third water consumption according to the average value and the standard deviation, and determine the third water consumption according to the second temperature, the The third water consumption and the second area generate the recommendation information.

In an exemplary embodiment, the determination module 1104 is configured to detect when the variance is greater than a preset threshold. In this case, determine the area with the window and the largest area in the third area as the second area; determine the fourth water consumption according to the average value and the variance, and determine the fourth water consumption according to the second temperature, the fourth The recommended information is generated using water consumption and the second area.

In an exemplary embodiment, the determination module 1104 is configured to determine the target duration required for the first water heater to heat the water of the target capacity to the second temperature; determine the target object usage according to the five-tuple data model. The first time point of the first water heater; determine a second time point according to the first time point and the target duration, and send a control command to the first water heater at the second time point, wherein, the The control command is used to instruct the first water heater to heat the target capacity of water to the second temperature.

An embodiment of the present disclosure also provides a storage medium that includes a stored program, wherein the method of any of the above items is executed when the program is run.

Optionally, in this embodiment, the above-mentioned storage medium may be configured to store program codes configured to perform the following steps:

S1. Obtain the historical operation information of the water heater set controlled by the target object, where the historical operation information includes: the first user information of the target object, the first window information of the first area where each water heater is located, and the first window information of the first area where each water heater is located. An area information, the first operation of the target object controlling each water heater to heat water to a first temperature, the first time information when the target object controls each water heater to perform the first operation, the use of the target object The first water consumption of each water heater;

S2, generate a five-tuple data model based on the historical operation information, and determine recommendation information based on the five-tuple data model, so that the target object controls the first water heater in the second area to the target based on the recommendation information. A volume of water is heated to a second temperature, wherein the set of water heaters includes: the first water heater.

According to yet another aspect of the embodiment of the present disclosure, an electronic device for implementing the above method for determining recommended information is also provided. As shown in Figure 12, the electronic device includes a memory 1202 and a processor 1204. The memory 1202 stores There is a computer program, and the processor 1204 is configured to execute the steps in any of the above method embodiments through the computer program.

Optionally, in this embodiment, the above-mentioned electronic device may be located in multiple network devices of the computer network. at least one network device in .

Optionally, in this embodiment, the above-mentioned processor may be configured to perform the following steps through a computer program:

Optionally, those of ordinary skill in the art can understand that the structure shown in Figure 12 is only illustrative, and the electronic device can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, and a mobile Internet device (Mobile Internet Devices, MID), PAD and other terminal equipment. FIG. 12 does not limit the structure of the above-mentioned electronic device. For example, the electronic device may also include more or fewer components (such as network interfaces, etc.) than shown in FIG. 12 , or have a different configuration than shown in FIG. 12 .

The memory 1202 can be used to store software programs and modules, such as program instructions/modules corresponding to the method and device for determining recommended information in the embodiment of the present disclosure. The processor 1204 runs the software programs and modules stored in the memory 1202, thereby Execute various functional applications and data processing, that is, implement the above-mentioned determination method of recommended information. Memory 1202 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 1202 may further include memory located remotely relative to the processor 1204, and these remote memories may be connected to the terminal through a network. Examples of the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof. As an example, as shown in FIG. 12 , the memory 1202 may include, but is not limited to, the acquisition module 1102 and the determination module 1104 in the determination device for the recommendation information. In addition, it may also include, but is not limited to, the above recommended information. Other modular units in the specified device will not be described in this example.

Optionally, the above-mentioned transmission device 1206 is used to receive or send data via a network. Specific examples of the above-mentioned network may include wired networks and wireless networks. In one example, the transmission device 1206 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers through network cables to communicate with the Internet or a local area network. In one example, the transmission device 1206 is a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

In addition, the above-mentioned electronic device also includes: a display 1208 for displaying the above-mentioned historical operation information; and a connection bus 1210 for connecting various module components in the above-mentioned electronic device.

Optionally, in this embodiment, the above storage medium may include but is not limited to: U disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), Various media that can store program code, such as mobile hard drives, magnetic disks, or optical disks.

Optionally, for specific examples in this embodiment, reference can be made to the examples described in the above-mentioned embodiments and optional implementations, and details will not be described again in this embodiment.

Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present disclosure can be implemented using general-purpose computing devices, and they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices. , optionally, they may be implemented in program code executable by a computing device, such that they may be stored in a storage device for execution by the computing device, and in some cases, may be in a sequence different from that herein. The steps shown or described are performed either individually as individual integrated circuit modules, or as multiple modules or steps among them as a single integrated circuit module. As such, the present disclosure is not limited to any specific combination of hardware and software.

The above are only preferred embodiments of the present disclosure. It should be pointed out that for those of ordinary skill in the art, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications can also be made. should be regarded as the scope of protection of this disclosure.

Claims

A method for determining recommended information, including:

Obtain the historical operation information of the water heater set controlled by the target object, where the historical operation information includes: the first user information of the target object, the first windowed information of the first area where each water heater in the water heater set is located and the first area information, the first operation of the target object controlling each water heater to heat water to a first temperature, the first time information when the target object controls each water heater to perform the first operation, the use of the target object The first water consumption of each water heater;

Generate a five-tuple data model based on the historical operation information, and determine recommendation information based on the five-tuple data model, so that the target object controls the first water heater in the second area to increase the target capacity based on the recommendation information. The water is heated to a second temperature, wherein the set of water heaters includes the target water heater.
The method for determining recommended information according to claim 1, wherein generating a five-tuple data model based on the historical operation information includes:

The first user information of the target object is classified into a user attribute information set, the first windowed information of the first area where each water heater is located is classified into a location information set, and the first window information of the first area where each water heater is located is classified into a location information set. The first area information of the region is classified into a context information set, the first time information when the target object controls each water heater to perform a first operation is classified into a time information set, and the target object controls each water heater to heat water. The first operation to the first temperature, the first water consumption of each water heater used by the target object is classified into the intended attribute information set;

A five-tuple data model is generated according to the user attribute information set, the location information set, the context information set, the time information set, and the intention attribute information set.
The method for determining recommended information according to claim 1, wherein the recommended information is determined according to the five-tuple data model, wherein the five-tuple data model includes: a user attribute information set, a location information set, and a context information set. , time information collection, intent attribute information collection, including:

Divide multiple first temperatures in the intended attribute information set into multiple temperature sets, wherein, The temperatures in each temperature set are the same;

For each temperature set, determine the third area where the second water heater corresponding to each temperature set is located in the location information set, the context information set, the time information set, and the intention attribute information set. The second window information and the second area information, the second time information when the target object controls the second water heater to heat the water to the third temperature, the second water consumption of the second water heater when the target object uses the second water heater, Wherein, the water heater set also includes: a second water heater;

Recommended information is determined based on the second windowed information, the second area information, the second time information, and the second water consumption.
The method for determining recommended information according to claim 3, wherein determining the recommended information based on the second windowed information, the second area information, the second time information, and the second water consumption includes:

Determine the first season information corresponding to each temperature set according to the second time information corresponding to each temperature set, so as to obtain a plurality of first season information;

Determine the corresponding relationship between the third area and the second water consumption according to the second windowed information, the second area information, and the second water consumption;

Determine third season information that is consistent with the second season information corresponding to the current time among the plurality of first season information, and determine a target temperature set corresponding to the third season information;

The temperature corresponding to the target temperature set is used as the second temperature, and the recommendation information is determined based on the second temperature and the corresponding relationship.
The method for determining recommended information according to claim 4, wherein determining the recommended information according to the second temperature and the corresponding relationship includes:

Calculate the mean, variance and standard deviation of the second water consumption, and determine whether the variance is greater than a preset threshold;

If the variance is greater than the preset threshold, determine the area without a window and with the smallest area in the third area as the second area;

A third water consumption is determined based on the average value and the standard deviation, and based on the second temperature, The third water consumption and the second area generate the recommendation information.
The method for determining recommended information according to claim 5, wherein after determining whether the variance is greater than a preset threshold, the method further includes:

If the variance is greater than the preset threshold, determine the area with the window and the largest area in the third area as the second area;

A fourth water consumption is determined based on the average value and the variance, and the recommendation information is generated based on the second temperature, the fourth water consumption, and the second area.
The method for determining recommended information according to claim 1, wherein after determining the recommended information according to the five-tuple data model, the method further includes:

Determining a target length of time required for the first water heater to heat a target volume of water to a second temperature;

Determine the first time point when the target object uses the first water heater according to the five-tuple data model;

A second time point is determined according to the first time point and the target duration, and a control command is sent to the first water heater at the second time point, where the control command is used to instruct the first water heater Heat the target volume of water to a second temperature.
A device for determining recommended information, including:

The acquisition module is configured to acquire the historical operation information of the water heater set controlled by the target object, wherein the historical operation information includes: the first user information of the target object, and the first area where each water heater in the water heater set is located. first windowed information and first area information, the first operation of the target object controlling each water heater to heat water to a first temperature, the first time information when the target object controls each water heater to perform the first operation, The target object uses the first water consumption of each water heater;

A determination module configured to generate a five-tuple data model based on the historical operation information, and determine recommendation information based on the five-tuple data model, so that the target object controls the first object in the second area based on the recommendation information. The water heater heats a target volume of water to a second temperature, wherein the water heater collects The combination includes: the first water heater.
The device for determining recommended information according to claim 8, wherein:

The determination module is further configured to classify the first user information of the target object into a user attribute information set, classify the first window information of the first area where each water heater is located into a location information set, and classify the first user information of the target object into a location information set. The first area information of the first area where each water heater is located is classified into a context information set, the first time information when the target object controls each water heater to perform a first operation is classified into a time information set, and the target The object controls the first operation of each water heater to heat water to a first temperature, and the target object uses the first water consumption of each water heater to classify it into an intention attribute information set; according to the user attribute information set, the location The information set, the context information set, the time information set, and the intent attribute information set generate a five-tuple data model.
The device for determining recommended information according to claim 8, wherein:

The determination module is also configured as a user attribute information set, a location information set, a context information set, a time information set, and an intention attribute information set, including: dividing multiple first temperatures in the intention attribute information set into multiple Temperature set, where the temperatures in each temperature set are the same; for each temperature set, it is determined among the location information set, the context information set, the time information set, and the intention attribute information set. The second windowed information and the second area information of the third area where the second water heater is located corresponding to each temperature set, the second time information when the target object controls the second water heater to heat the water to the third temperature, the The target object uses the second water consumption of the second water heater, wherein the water heater set also includes: a second water heater; according to the second window information, the second area information, and the second time information , the second water consumption determination recommendation information.
The device for determining recommended information according to claim 10, wherein:

The determination module is further configured to determine the first season information corresponding to each temperature set according to the second time information corresponding to each temperature set, so as to obtain a plurality of first season information; according to the second windowed information , the second area information and the second water consumption determine the corresponding relationship between the third area and the second water consumption; determine the first season information corresponding to the current time in the plurality of first season information. Third season information that is consistent with the two seasonal information, and determining a target temperature set corresponding to the third season information; using the temperature corresponding to the target temperature set as the second temperature, according to the second temperature and the corresponding The relationship determines the recommended information.
The device for determining recommended information according to claim 11, wherein:

The determination module is also configured to calculate the average, variance and standard deviation of the second water consumption, and determine whether the variance is greater than a preset threshold; in the case where the variance is greater than the preset threshold, the The area without windows and with the smallest area in the third area is determined as the second area; the third water consumption is determined based on the average value and the standard deviation, and the third water consumption is determined based on the second temperature, the third water consumption and the The second area generates the recommendation information.
The device for determining recommended information according to claim 12, wherein:

The determination module is further configured to determine, in the third region, the windowed region with the largest area as the second region when the variance is greater than a preset threshold; determine based on the average value and the variance a fourth water consumption, and generating the recommendation information according to the second temperature, the fourth water consumption and the second area.
The device for determining recommended information according to claim 8, wherein:

The determination module is also configured to determine the target duration required for the first water heater to heat the water of the target capacity to the second temperature; determine the target object's use of the first water heater according to the five-tuple data model. A time point; determine a second time point according to the first time point and the target duration, and send a control command to the first water heater at the second time point, wherein the control command is used to indicate the The first water heater heats a target volume of water to a second temperature.
A computer-readable storage medium includes a stored program, wherein when the program is run, the method described in any one of claims 1 to 7 is executed.
An electronic device includes a memory and a processor, a computer program is stored in the memory, and the processor is configured to execute the method described in any one of claims 1 to 7 through the computer program.