Behavior habit recognition method and device, storage medium, and electronic device

Abstract

The application discloses a behavior habit identification method and device, a storage medium and an electronic device, and relates to the technical field of smart homes. The method comprises the following steps: acquiring behavior data stored in a server, the behavior data being used to indicate a target object controlling a plurality of home appliances in a target area, the behavior data comprising: a first operation action of the plurality of home appliances; removing irrelevant actions existing in the behavior data to obtain a first association result information set comprising a plurality of second operation actions; determining action content corresponding to each second operation action in the first association result information set, confirming the action content by using a preset rule, and obtaining a second association result information set; and according to a preset grouping, counting a plurality of third operation actions existing in the second association result information set, so as to identify a behavior habit corresponding to the target object according to a statistical result, the behavior habit being a set corresponding to a behavior preference of the target object controlling the plurality of home appliances in the target area.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and more specifically, to a method and apparatus for identifying behavioral habits, a storage medium, and an electronic device. Background Technology

[0002] In recent years, the continuous upgrading and iteration of IoT technology has enabled the smart home industry to develop rapidly. Smart home products and services are gradually bringing users richer, higher-quality, and more effective recommendation services. To accurately identify user behavior habits and provide more personalized recommendation services, smart home manufacturers and service providers are constantly exploring and researching message recommendation applications to meet the precise needs of various users. Among related technologies, user habit recognition solutions have the following shortcomings: insufficient differentiation of user behavior, failure to filter invalid user operation-related behavior information; and a lack of consideration for the support information of user behavior correlations in the acquired user behavior information, resulting in insufficient accuracy of the ultimately mined user habit information.

[0003] Therefore, no effective solution has yet been proposed for the problems in related technologies, such as insufficient differentiation of behaviors and inability to identify and statistically analyze the associated behaviors of target objects when mining the behavioral habits of target objects. Summary of the Invention

[0004] This application provides a method and apparatus for identifying behavioral habits, a storage medium, and an electronic device to at least solve the problems in related technologies, such as insufficient differentiation of behaviors and inability to identify and statistically analyze associated behaviors of target objects when mining behavioral habits corresponding to target objects.

[0005] According to one embodiment of this application, a method for identifying behavioral habits is provided, comprising: acquiring behavioral data stored in a server for instructing a target object to control multiple home appliances within a target area, wherein the behavioral data includes: first operation actions on the multiple home appliances; removing unrelated actions from the behavioral data to obtain a first association result information set containing multiple second operation actions, wherein the unrelated actions are any two consecutive first operation actions in the behavioral data with an interval greater than a first preset interval; determining the action content corresponding to each second operation action in the first association result information set, confirming the action content using preset rules to obtain a second association result information set; and statistically analyzing multiple third operation actions present in the second association result information set according to preset groupings to identify the behavioral habits corresponding to the target object based on the statistical results, wherein the behavioral habits are a set corresponding to the target object's behavioral preferences for controlling multiple home appliances within a target area.

[0006] In an exemplary embodiment, confirming the action content using preset rules includes: if there are any two consecutive second operation actions with the same action content in the first association result information set, determining the target home appliance corresponding to the two consecutive second operation actions; if there are action content of natural pairing behavior in the first association result information set, identifying the second operation action corresponding to the action content that occurs first in the natural pairing behavior as a valid action, and identifying other second operation actions in the natural pairing behavior other than the second operation action corresponding to the action content that occurs first as invalid actions.

[0007] In an exemplary embodiment, when there are any two consecutive second operation actions with the same action content in the first set of associated result information, after determining the target home appliance corresponding to the two consecutive second operation actions, the method further includes: when the target home appliance corresponding to the two consecutive second operation actions is the same home appliance, marking the second operation action with the earlier time point as a valid action and the second operation action with the later time point as an invalid action; when the target home appliance corresponding to the two consecutive second operation actions is not the same home appliance, marking both of the two consecutive second operation actions as valid actions.

[0008] In an exemplary embodiment, the multiple third operation actions existing in the second associated result information set are statistically analyzed according to a preset group, including: obtaining first group information and second group information corresponding to the preset group, wherein the first group information includes: target object, total time taken by the target object to operate the home appliance, location of the operation action, and operation result of the home appliance corresponding to the operation action; the second group information includes: target object, location of the operation action, operation result of the home appliance corresponding to the operation action, and associated behavior related to the operation action; and the multiple third operation actions existing in the second associated result information set are statistically analyzed based on the first group information and the second group information.

[0009] In an exemplary embodiment, the statistical analysis of multiple third operation actions existing in the second associated result information set based on the first grouping information and the second grouping information includes: statistically analyzing the occurrence frequency of each operation action among the multiple third operation actions based on the first grouping information to obtain first statistical information; determining the associated action corresponding to each operation action among the multiple third operation actions based on the second grouping information, and determining the occurrence probability of the associated action to obtain second statistical information.

[0010] In an exemplary embodiment, identifying the behavioral habits corresponding to the target object based on statistical results includes: using the target object as a data alignment identifier to summarize the first statistical information and the second statistical information to obtain third statistical information; determining the target third operation action that occurs most frequently and has the highest probability of occurrence in the third statistical information; obtaining the target home appliance corresponding to the current target third operation action; determining the target object's behavioral preferences based on the behavioral data of the target object using the target third operation action to operate the target home appliance; and determining the behavioral habits corresponding to the target object through the behavioral preferences.

[0011] In an exemplary embodiment, after statistically analyzing multiple third operation actions existing in the second associated result information set according to a preset group to identify the behavioral habits corresponding to the target object based on the statistical results, the method further includes: determining the number of types of behavioral preferences included in the behavioral habits; generating a home appliance operation scenario corresponding to the behavioral habits when the number of types is greater than a preset number; and sending a scenario update message carrying the home appliance operation scenario to the target object.

[0012] According to another embodiment of this application, a behavior habit identification device is also provided, comprising: an acquisition module, configured to acquire behavior data stored in a server for instructing a target object to control multiple home appliances within a target area, wherein the behavior data includes: first operation actions on the multiple home appliances; a removal module, configured to remove unrelated actions from the behavior data to obtain a first association result information set containing multiple second operation actions, wherein the unrelated actions are any two consecutive first operation actions in the behavior data with an interval greater than a first preset interval; a determination module, configured to determine the action content corresponding to each second operation action in the first association result information set, confirm the action content using preset rules, and obtain a second association result information set; and a statistics module, configured to perform statistics on multiple third operation actions present in the second association result information set according to preset grouping, so as to identify the behavior habit corresponding to the target object based on the statistics results, wherein the behavior habit is a set corresponding to the target object's behavior preferences for controlling multiple home appliances within a target area.

[0013] In an exemplary embodiment, the determining module is further configured to: determine the target home appliance corresponding to any two consecutive second operation actions with the same action content in the first association result information set; and, in the case where there is action content of natural pairing behavior in the first association result information set, identify the second operation action corresponding to the action content that occurs first in the natural pairing behavior as a valid action, and identify other second operation actions in the natural pairing behavior other than the second operation action corresponding to the action content that occurs first as invalid actions.

[0014] In an exemplary embodiment, the determining module further includes: an identification unit, configured to, when the target home appliances corresponding to any two consecutive second operation actions are the same home appliance, identify the second operation action with the earlier time point as a valid action and the second operation action with the later time point as an invalid action; and to identify both of the two consecutive second operation actions as valid actions when the target home appliances corresponding to any two consecutive second operation actions are not the same home appliance.

[0015] In an exemplary embodiment, the above-mentioned statistics module is further configured to obtain first group information and second group information corresponding to the preset group, wherein the first group information includes: target object, total time taken by the target object to operate the home appliance, location of the operation action, and operation result of the home appliance corresponding to the operation action; the second group information includes: target object, location of the operation action, operation result of the home appliance corresponding to the operation action, and associated behavior related to the operation action; and to perform statistics on multiple third operation actions existing in the second associated result information set based on the first group information and the second group information.

[0016] In an exemplary embodiment, the above-mentioned statistics module further includes: a first statistics unit, configured to count the number of occurrences of each of the plurality of third operation actions based on the first grouping information to obtain first statistics; and a second statistics unit, configured to determine the associated action corresponding to each of the plurality of third operation actions based on the second grouping information, and determine the probability of occurrence of the associated action to obtain second statistics.

[0017] In an exemplary embodiment, the aforementioned statistics module is further configured to: aggregate the first and second statistical information using the target object as a data alignment identifier to obtain third statistical information; identify the target third operation action that occurs most frequently and has the highest probability of occurrence in the third statistical information; acquire the target home appliance corresponding to the current target third operation action; determine the target object's behavioral preferences based on the behavioral data of the target object using the target third operation action to operate the target home appliance; and determine the behavioral habits corresponding to the target object through the behavioral preferences.

[0018] In one exemplary embodiment, the above-described apparatus further includes: a scenario module, configured to determine the number of types of behavioral preferences included in the behavioral habit; if the number of types is greater than a preset number, generate a home appliance operation scenario corresponding to the behavioral habit; and send a scenario update message carrying the home appliance operation scenario to the target object.

[0019] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, and the computer program is configured to execute the above-mentioned method for recognizing behavioral habits when running.

[0020] According to another aspect of the embodiments of this application, 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 method for recognizing behavioral habits through the computer program.

[0021] In this embodiment, behavioral data stored in a server, used to instruct a target object to control multiple home appliances within a target area, is obtained. The behavioral data includes: first operational actions on the multiple home appliances; removing unrelated actions from the behavioral data to obtain a first associated result information set containing multiple second operational actions, wherein unrelated actions are any two consecutive first operational actions in the behavioral data with an interval greater than a first preset interval; determining the action content corresponding to each second operational action in the first associated result information set, confirming the action content using preset rules, and obtaining a second associated result information set; and statistically analyzing the multiple third operational actions present in the second associated result information set according to preset groupings to identify the behavior corresponding to the target object based on the statistical results. Habits, wherein the behavioral habits are a set of behavioral preferences of a target object controlling multiple home appliances within a target area; the above technical solution solves the problems in related technologies, such as insufficient differentiation of behaviors and inability to identify and statistically analyze associated behaviors of the target object when mining behavioral habits corresponding to the target object. By using an association information model that includes time-series rules and matching rules, the association validity and support of operation actions in the behavioral data are determined. By using hierarchical classification to narrow down the behavioral data, the accuracy of the behavioral habits determined from the behavioral data is improved. Furthermore, hierarchical filtering greatly improves the processing of large amounts of behavioral data, enabling the rapid and effective extraction of multiple behavioral habits from the behavioral data. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the hardware environment for a method of recognizing behavioral habits according to an embodiment of this application;

[0025] Figure 2 This is a flowchart of a method for recognizing behavioral habits according to an embodiment of this application;

[0026] Figure 3 A flowchart of a user habit recognition technology solution according to an optional embodiment of the present invention;

[0027] Figure 4This is a schematic diagram of the structure of a system for recognizing user habits based on user home appliance operation behavior, according to an optional embodiment of the present invention.

[0028] Figure 5 This is a schematic diagram of the data flow corresponding to a system for recognizing user habits based on user home appliance operation behavior, which is an optional embodiment of the present invention.

[0029] Figure 6 This is a flowchart illustrating a user habit recognition algorithm for a behavior association algorithm according to an optional embodiment of the present invention.

[0030] Figure 7 This is a structural block diagram of a behavior habit recognition device according to an embodiment of this application;

[0031] Figure 8 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] According to one aspect of the embodiments of this application, a method for recognizing behavioral habits is provided. This method for recognizing behavioral habits is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligencehouse ecosystems. Optionally, in this embodiment, the above-mentioned method for recognizing behavioral habits can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. For example... Figure 1 As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0035] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0036] This embodiment provides a method for recognizing behavioral habits, applied to the aforementioned computer terminal. Figure 2 This is a flowchart of a method for recognizing behavioral habits according to an embodiment of this application. The process includes the following steps:

[0037] Step S202: Obtain behavioral data stored in the server for instructing the target object to control multiple home appliances within the target area, wherein the behavioral data includes: first operation actions on the multiple home appliances;

[0038] It should be noted that the aforementioned home appliances are devices that are associated with and bound to the target object. The corresponding behavioral data can be identified through the user information corresponding to the target object. The aforementioned user information can identify a unique user. Then, when the user operates the home appliance on the device, the device's base plate collects the operation record information and sends it to the cloud server in real time via the network. The data is then transmitted to the corresponding server of the data platform through the distributed publish-subscribe messaging system Kafka, and the data platform performs association processing on the user's home appliance operation record information (equivalent to the aforementioned behavioral data).

[0039] Step S204: Remove the unrelated actions in the behavior data to obtain a first set of associated result information containing multiple second operation actions, wherein the unrelated actions are any two consecutive first operation actions in the behavior data with an interval time greater than a first preset interval time.

[0040] Optionally, the first preset interval time is used to compare with the current interval time corresponding to the occurrence time of two consecutive first operation actions, so as to quickly remove two consecutive first operation actions in the behavior data whose interval time is greater than the first preset interval time. The first preset interval time can be 5 minutes, 10 minutes or 30 seconds, which can be flexibly set according to the processing requirements of the behavior data.

[0041] Step S206: Determine the action content corresponding to each second operation action in the first associated result information set, and confirm the action content using preset rules to obtain the second associated result information set;

[0042] Step S208: Statistically analyze multiple third operation actions existing in the second associated result information set according to a preset grouping, so as to identify the behavioral habits corresponding to the target object based on the statistical results, wherein the behavioral habits are a set of behavioral preferences of the target object in controlling multiple home appliances in the target area.

[0043] Through the above steps, behavioral data stored on the server, used to instruct the target object to control multiple home appliances within the target area, is obtained. This behavioral data includes: first operational actions on the multiple home appliances; removing unrelated actions from the behavioral data to obtain a first set of associated result information containing multiple second operational actions, wherein unrelated actions are any two consecutive first operational actions in the behavioral data with an interval greater than a first preset interval; determining the action content corresponding to each second operational action in the first set of associated result information, confirming the action content using preset rules, and obtaining a second set of associated result information; and statistically analyzing the multiple third operational actions present in the second set of associated result information according to preset groupings to identify the behavioral habits corresponding to the target object based on the statistical results. The behavioral habits, in this context, refer to the set of behavioral preferences of a target object in controlling multiple home appliances within a target area. This technical solution addresses issues in related technologies, such as insufficient differentiation of behaviors and the inability to identify and statistically analyze associated behaviors when mining behavioral habits of a target object. By using an association information model incorporating temporal and matching rules, the effectiveness of associations and the support levels of corresponding actions in behavioral data are determined. Hierarchical classification narrows down the behavioral data, improving the accuracy of the behavioral habits ultimately identified. Furthermore, hierarchical filtering significantly enhances the processing capabilities for large volumes of behavioral data, enabling the rapid and effective extraction of multiple behavioral habits.

[0044] In an exemplary embodiment, confirming the action content using preset rules includes: if there are any two consecutive second operation actions with the same action content in the first association result information set, determining the target home appliance corresponding to the two consecutive second operation actions; if there are action content of natural pairing behavior in the first association result information set, identifying the second operation action corresponding to the action content that occurs first in the natural pairing behavior as a valid action, and identifying other second operation actions in the natural pairing behavior other than the second operation action corresponding to the action content that occurs first as invalid actions.

[0045] In an exemplary embodiment, when there are any two consecutive second operation actions with the same action content in the first set of associated result information, after determining the target home appliance corresponding to the two consecutive second operation actions, the method further includes: when the target home appliance corresponding to the two consecutive second operation actions is the same home appliance, marking the second operation action with the earlier time point as a valid action and the second operation action with the later time point as an invalid action; when the target home appliance corresponding to the two consecutive second operation actions is not the same home appliance, marking both of the two consecutive second operation actions as valid actions.

[0046] Understandably, in appliance operation logs, if the same device performs the same action twice consecutively within a certain time interval, or if two consecutive actions are a natural match, then the second action record is considered invalid relative to the first. Optionally, in practical applications, data like that shown in Table 1 might be generated, where record 3, 'Opening the refrigerator door,' is the same action as record 2, 'Opening the refrigerator door'; in this case, record 3 is an invalid associated action record relative to record 2. Similarly, record 4, 'Closing the refrigerator door,' is a natural match with record 3, 'Opening the refrigerator door,' meaning the two actions have a causal relationship; therefore, record 4 is an invalid associated action record relative to record 3.

[0047] Table 1

[0048]

[0049] In an exemplary embodiment, the multiple third operation actions existing in the second associated result information set are statistically analyzed according to a preset group, including: obtaining first group information and second group information corresponding to the preset group, wherein the first group information includes: target object, total time taken by the target object to operate the home appliance, location of the operation action, and operation result of the home appliance corresponding to the operation action; the second group information includes: target object, location of the operation action, operation result of the home appliance corresponding to the operation action, and associated behavior related to the operation action; and the multiple third operation actions existing in the second associated result information set are statistically analyzed based on the first group information and the second group information.

[0050] In an exemplary embodiment, the statistical analysis of multiple third operation actions existing in the second associated result information set based on the first grouping information and the second grouping information includes: statistically analyzing the occurrence frequency of each operation action among the multiple third operation actions based on the first grouping information to obtain first statistical information; determining the associated action corresponding to each operation action among the multiple third operation actions based on the second grouping information, and determining the occurrence probability of the associated action to obtain second statistical information.

[0051] In simple terms, after removing irrelevant actions from the behavioral data and confirming the action content through preset rules, a second set of associated result information corresponding to effective and relatively accurate behavioral data is obtained. Then, in order to make the determined behavioral habits more consistent with the current target object, the operation actions in the second set of associated result information are statistically analyzed from different dimensions through preset grouping to obtain the frequency statistics of each behavioral action and the support information of the associated behavioral actions corresponding to each behavioral action (equivalent to the above-mentioned probability of occurrence).

[0052] In an exemplary embodiment, the behavioral habits corresponding to the target object are identified based on statistical results. The behavioral habits are a set of behavioral preferences corresponding to the target object's control of multiple home appliances within a target area. This includes: using the target object as a data alignment identifier to summarize the first and second statistical information to obtain third statistical information; identifying the target third operation action that occurs most frequently and has the highest probability of occurrence in the third statistical information; obtaining the target home appliance corresponding to the current target third operation action; determining the target object's behavioral preferences based on the target object's behavioral data of operating the target home appliance using the target third operation action; and determining the behavioral habits corresponding to the target object through the behavioral preferences.

[0053] As an optional example, the above statistical information can be presented in a table or in a graph. This application does not impose too many restrictions on the presentation. Taking a table as an example, the first statistical information is shown in Table 2 below; the second statistical information is shown in Table 3 below.

[0054] Table 2

[0055] U01 17 living room Turn on the air conditioner 4 U01 18 living room Turn on the air conditioner 5 U01 19 living room Turn on the air conditioner 6

[0056] Table 3

[0057] U01 living room Turn on the air conditioner Turn on the TV 20％ U01 living room Turn on the air conditioner Turn on the lights 30％ U01 living room Turn on the air conditioner Turn on the water heater 40％

[0058] By combining Tables 2 and 3 above, we obtain Table 4, which corresponds to the third statistical information; Table 4 is as follows:

[0059] Table 4

[0060]

[0061] At this point, the information that occurs most frequently and has the highest support in Table 4 is taken as the user habit record information (equivalent to the above-mentioned behavioral preferences). The corresponding behavioral habit data in Table 4 has a support of 40% and a frequency of 6.

[0062] In an exemplary embodiment, multiple third operation actions existing in the second associated result information set are statistically analyzed according to a preset grouping to identify the behavioral habits corresponding to the target object based on the statistical results. Wherein, the behavioral habits are a set of behavioral preferences corresponding to multiple home appliances controlled by the target object within the target area. The method further includes: determining the number of types of behavioral preferences included in the behavioral habits; generating a home appliance operation scenario corresponding to the behavioral habits when the number of types is greater than a preset number; and sending a scenario update message carrying the home appliance operation scenario to the target object.

[0063] It is understandable that when the target's behavioral habits include a preference for operating multiple home appliances, it means that while operating the first home appliance, the target may have performed associated operations on the second or third home appliance. Therefore, based on this behavioral habit, corresponding home appliance operation scenarios can be generated to control the current first, second, and third home appliances according to the association order. It should be noted that the home appliance operation scenarios are flexibly changed according to the content of the behavioral habits.

[0064] To better understand the process of the above-mentioned method for identifying behavioral habits, the implementation flow of the above-mentioned method for identifying behavioral habits will be described below in conjunction with optional embodiments, but this is not intended to limit the technical solution of the embodiments of this application.

[0065] In recent years, the continuous upgrading and iteration of IoT technology has enabled the smart home industry to develop rapidly. Smart home products and services are gradually bringing users richer, higher-quality, and more effective recommendation services. In order to accurately identify user behavior habits and provide more personalized recommendation services, smart home manufacturers and service providers are constantly exploring and researching message recommendation applications to meet the precise needs of various users.

[0066] As an optional implementation method, Figure 3 The flowchart of the user habit recognition technology solution of an optional embodiment of the present invention shows that after completing the binding between the user and the home appliance, the user's home appliance operation data is collected, then the user's behavior is statistically analyzed, and finally the user's habits are marked based on the statistical results. However, the above user habit recognition technology solution has the following disadvantages:

[0067] 1. Insufficient differentiation of user behavior; no filtering of invalid user operation-related behavior information.

[0068] 2. The obtained user behavior information does not take into account the support information related to user behavior.

[0069] Therefore, to address the shortcomings of the aforementioned technologies, an optional embodiment of the present invention also provides a method for identifying user habits based on user appliance operation behavior. Before a user uses a home appliance, user information needs to be bound to the appliance. When the user operates the appliance, the data collection device collects real-time records of user operation behavior, which can identify user information and operation behavior information. User habit information is then calculated and labeled using a user behavior association algorithm model. In essence, the core is based on the binding relationship between the user and the data collection device; based on the recorded information of the user's home appliance operation behavior, invalid associated behavior records are eliminated, and user habit information is mined using a behavior association algorithm.

[0070] Optional, Figure 4 This is a schematic diagram of the structure of a system for recognizing user habits based on user home appliance operation behavior, which is an optional embodiment of the present invention. It includes: user-bound home appliances, cloud servers, and data computing servers. The system completes the determination and collection of user binding information and the collection of user home appliance operation data through information interaction between the user-bound home appliances and the cloud servers. After the cloud servers complete the data collection, the data is sent to the data computing servers, and the final user habit tag is calculated by the behavior association model in the data computing servers.

[0071] Specifically, this can be achieved through the following steps:

[0072] Step 1: The user binds to the information collection device.

[0073] The second step involves uploading user appliance operation records to a cloud server, where they are then loaded into a Hadoop server for data storage and processing. Based on these records and according to business rules, user behavior is categorized, and invalid or irrelevant behavior records are filtered out.

[0074] Optional, Figure 5This is a schematic diagram of the data flow corresponding to a system for recognizing user habits based on user home appliance operation behavior, as shown in an optional embodiment of the present invention. When a user is bound to multiple home appliances, a cloud server is placed in the target area corresponding to the multiple home appliances. The user's home appliance operation records of the multiple home appliances are collected to the cloud server using Bluetooth technology. The cloud server uploads the corresponding user home appliance operation records to the Hadoop big data platform corresponding to the Hadoop server through the distributed message subscription system Kafka. The user home appliance operation records are then filtered by the user habit recognition model set in the Hadoop big data platform.

[0075] Step 3: Perform correlation analysis on valid user behaviors to obtain user-related behaviors, and calculate the corresponding calculation results using a behavior correlation model.

[0076] Step 4: Based on the calculation results of user-related behaviors, mark user habit information.

[0077] Optional, Figure 6 This is a flowchart of a user habit recognition algorithm for a behavior association algorithm according to an optional embodiment of the present invention; it includes the following steps:

[0078] Step 1: User binding information processing. Standardize the existing bound user information to identify unique users.

[0079] Step 2: User appliance operation record information association processing, including data collection and rule processing. Data collection involves the device floor collecting operation record information after the user operates the appliance, and sending it to the cloud server in real time via the network. The data is then transmitted to the data platform via Kafka for data computation. Rule processing includes time-series rule processing and matching rule processing.

[0080] Optionally, the process can be handled according to time sequence rules: Based on the user's home appliance operation record information a(k), the user's home appliance operation information can be processed according to time sequence rules to obtain the user's associated behavior result information set B1. Optionally, if the time interval between two consecutive actions exceeds 5 minutes, it can be defined as invalid behavior association information.

[0081] For example, the user's home appliance operation record information a(k) is shown in Table 5 below:

[0082] Table 5

[0083]

[0084] The time interval between record 5, 'Turn on the water heater', and record 4, 'Close the refrigerator door', exceeds 5 minutes; therefore, record 5 is an invalid associated behavior record relative to record 4. This yields user associated behavior result information set B1, as shown in Table 6 below.

[0085] Table 6

[0086]

[0087] Optionally, processing can be performed according to matching rules: Based on the user-associated behavior result information set B1, the user's home appliance operation information is processed according to the matching rules to obtain the user-associated behavior result information set B2. The matching rules are as follows: if the same device performs the same behavior twice consecutively within a certain time interval in the home appliance operation records, or if two consecutive behavior actions are a natural matching pair, then the second behavior action record is considered invalid relative to the first behavior record.

[0088] For example, in Table 6 corresponding to the user-related behavior result information set B1 above, record 3, 'Opening the refrigerator door,' has the same action as record 2, 'Opening the refrigerator door'; therefore, record 3 is an invalid related behavior record relative to record 2. Record 4, 'Closing the refrigerator door,' has a natural match with record 3, 'Opening the refrigerator door,' meaning the two actions have a causal relationship; therefore, record 4 is also an invalid related behavior record relative to record 3. After processing with matching rules, user-related behavior result information set B2 is obtained, corresponding to Table 7 below.

[0089] Table 7

[0090]

[0091] Step 3: Calculate the behavior association model. Optional, there are two methods: Method 1: Calculate the number of user behaviors: Based on the user's valid appliance operation record information set B2, group the data by user, time, location, and behavior, and calculate the statistical information on the number of occurrences of each behavior. Method 2: Calculate the support for user behaviors: Based on the user's valid appliance operation record information set B2, group the data by user, location, behavior, and associated behaviors, and calculate the support information for the associated behaviors corresponding to each behavior.

[0092] Step 4: User habit tagging. Based on the results of the behavior association model, the information that marks the behavior with the highest frequency and the highest support is the user habit record information.

[0093] This embodiment establishes a user habit model: based on user appliance operation behavior information, invalid related behavior information is distinguished and filtered out to narrow down the range of valid related behavior data; a behavior association algorithm model is used to mine user habit information. Then, by classifying user appliance operation behavior information, the range of valid related behavior data is narrowed down, improving data accuracy and computational efficiency; association analysis is performed on users, and based on support and confidence parameters, valid user related behaviors are calculated and user habit information is labeled.

[0094] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0095] Figure 7 This is a structural block diagram of a behavioral habit recognition device according to an embodiment of this application. Figure 7 As shown, it includes:

[0096] The acquisition module 52 is used to acquire behavioral data stored in the server for instructing a target object to control multiple home appliances in a target area, wherein the behavioral data includes: a first operation action on the multiple home appliances;

[0097] The removal module 54 is used to remove unrelated actions from the behavior data to obtain a first set of associated result information containing multiple second operation actions, wherein the unrelated actions are any two consecutive first operation actions in the behavior data with an interval time greater than a first preset interval time.

[0098] The determining module 56 is used to determine the action content corresponding to each second operation action in the first associated result information set, and to confirm the action content using preset rules to obtain the second associated result information set;

[0099] The statistics module 58 is used to perform statistics on multiple third operation actions existing in the second association result information set according to a preset group, so as to identify the behavioral habits corresponding to the target object based on the statistical results, wherein the behavioral habits are a set of behavioral preferences of the target object in controlling multiple home appliances in the target area.

[0100] Using the aforementioned device, behavioral data stored in the server, used to instruct a target object to control multiple home appliances within a target area, is acquired. This behavioral data includes: first operational actions on the multiple home appliances; removing unrelated actions from the behavioral data to obtain a first set of associated result information containing multiple second operational actions, wherein unrelated actions are any two consecutive first operational actions in the behavioral data with an interval greater than a first preset interval; determining the action content corresponding to each second operational action in the first set of associated result information, confirming the action content using preset rules, and obtaining a second set of associated result information; and statistically analyzing the multiple third operational actions present in the second set of associated result information according to preset groupings to identify the behavioral habits corresponding to the target object based on the statistical results. The behavioral habits, in this context, refer to the set of behavioral preferences of a target object in controlling multiple home appliances within a target area. This technical solution addresses issues in related technologies, such as insufficient differentiation of behaviors and the inability to identify and statistically analyze associated behaviors when mining behavioral habits of a target object. By using an association information model incorporating temporal and matching rules, the effectiveness of associations and the support levels of corresponding actions in behavioral data are determined. Hierarchical classification narrows down the behavioral data, improving the accuracy of the behavioral habits ultimately identified. Furthermore, hierarchical filtering significantly enhances the processing capabilities for large volumes of behavioral data, enabling the rapid and effective extraction of multiple behavioral habits.

[0101] In an exemplary embodiment, the determining module is further configured to: determine the target home appliance corresponding to any two consecutive second operation actions with the same action content in the first association result information set; and, in the case where there is action content of natural pairing behavior in the first association result information set, identify the second operation action corresponding to the action content that occurs first in the natural pairing behavior as a valid action, and identify other second operation actions in the natural pairing behavior other than the second operation action corresponding to the action content that occurs first as invalid actions.

[0102] In an exemplary embodiment, the determining module further includes: an identification unit, configured to, when the target home appliances corresponding to any two consecutive second operation actions are the same home appliance, identify the second operation action with the earlier time point as a valid action and the second operation action with the later time point as an invalid action; and to identify both of the two consecutive second operation actions as valid actions when the target home appliances corresponding to any two consecutive second operation actions are not the same home appliance.

[0103] In an exemplary embodiment, the above-mentioned statistics module is further configured to obtain first group information and second group information corresponding to the preset group, wherein the first group information includes: target object, total time taken by the target object to operate the home appliance, location of the operation action, and operation result of the home appliance corresponding to the operation action; the second group information includes: target object, location of the operation action, operation result of the home appliance corresponding to the operation action, and associated behavior related to the operation action; and to perform statistics on multiple third operation actions existing in the second associated result information set based on the first group information and the second group information.

[0104] In an exemplary embodiment, the above-mentioned statistics module further includes: a first statistics unit, configured to count the number of occurrences of each of the plurality of third operation actions based on the first grouping information to obtain first statistics; and a second statistics unit, configured to determine the associated action corresponding to each of the plurality of third operation actions based on the second grouping information, and determine the probability of occurrence of the associated action to obtain second statistics.

[0105] In an exemplary embodiment, the above-mentioned statistics module is further configured to use the target object as a data alignment identifier to summarize the first and second statistical information to obtain third statistical information; determine the target third operation action that occurs most frequently and has the highest probability of occurrence in the third statistical information; obtain the target home appliance corresponding to the current target third operation action; determine the target object's behavioral preference based on the behavioral data of the target object using the target third operation action to operate the target home appliance; and determine the behavioral habit corresponding to the target object through the behavioral preference.

[0106] In one exemplary embodiment, the above-described apparatus further includes: a scenario module, configured to determine the number of types of behavioral preferences included in the behavioral habit; if the number of types is greater than a preset number, generate a home appliance operation scenario corresponding to the behavioral habit; and send a scenario update message carrying the home appliance operation scenario to the target object.

[0107] Embodiments of this application also provide a storage medium including a stored program, wherein the program executes any of the methods described above when it is run.

[0108] Optionally, in this embodiment, the storage medium may be configured to store program code for performing the following steps:

[0109] S1, acquire behavioral data stored in the server for instructing a target object to control multiple home appliances within a target area, wherein the behavioral data includes: first operation actions on the multiple home appliances; S2, remove unrelated actions from the behavioral data to obtain a first set of associated result information containing multiple second operation actions, wherein the unrelated actions are any two consecutive first operation actions in the behavioral data with an interval time greater than a first preset interval time;

[0110] S3, determine the action content corresponding to each second operation action in the first associated result information set, confirm the action content using preset rules, and obtain the second associated result information set;

[0111] S4, the multiple third operation actions existing in the second association result information set are statistically analyzed according to a preset group, so as to identify the behavioral habits corresponding to the target object based on the statistical results, wherein the behavioral habits are a set of behavioral preferences of the target object in controlling multiple home appliances in the target area.

[0112] Embodiments of this application also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0113] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0114] Optional, such as Figure 8 As shown, the electronic device includes a memory 702 and a processor 704. The memory 702 stores a computer program, and the processor 704 is configured to execute the steps of any of the above method embodiments via the computer program.

[0115] Optionally, in this embodiment, the electronic device may be located in at least one of a plurality of network devices in a computer network.

[0116] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0117] S1, Obtain behavioral data stored in the server for instructing the target object to control multiple home appliances within the target area, wherein the behavioral data includes: a first operation action on the multiple home appliances;

[0118] S2, remove the unrelated actions in the behavior data to obtain a first set of associated result information containing multiple second operation actions, wherein the unrelated actions are any two consecutive first operation actions in the behavior data with an interval time greater than a first preset interval time.

[0119] S3, determine the action content corresponding to each second operation action in the first associated result information set, confirm the action content using preset rules, and obtain the second associated result information set;

[0120] S4, the multiple third operation actions existing in the second association result information set are statistically analyzed according to a preset group, so as to identify the behavioral habits corresponding to the target object based on the statistical results, wherein the behavioral habits are a set of behavioral preferences of the target object in controlling multiple home appliances in the target area.

[0121] Alternatively, as those skilled in the art will understand, Figure 8 The structure shown is for illustrative purposes only. The electronic device can also be a smartphone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile internet device (MID), a PAD, and other terminal devices. Figure 8 This does not limit the structure of the aforementioned electronic device. For example, the electronic device may also include components that are more... Figure 8 The more or fewer components shown (such as network interfaces, etc.), or having the same Figure 8 The different configurations shown.

[0122] The memory 702 can be used to store software programs and modules, such as the program instructions / modules corresponding to the communication connection method and apparatus in this embodiment. The processor 704 executes various functional applications and data processing by running the software programs and modules stored in the memory 702, thereby realizing the aforementioned communication connection method. The memory 702 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 instances, the memory 702 may further include memory remotely located relative to the processor 704, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. As an example, such as... Figure 8 As shown, the memory 702 may include, but is not limited to, the acquisition module 52, removal module 54, determination module 56, and statistics module 58 from the communication connection device. Furthermore, it may include, but is not limited to, other module units from the communication connection device, which will not be elaborated upon in this example.

[0123] Optionally, the transmission device 706 described above is used to receive or send data via a network. Specific examples of the network described above may include wired networks and wireless networks. In one example, the transmission device 706 includes a Network Interface Controller (NIC), which can be connected to other network devices and a router via a network cable to communicate with the Internet or a local area network. In one example, the transmission device 1106 is a Radio Frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0124] In addition, the aforementioned electronic device also includes: a display 708 for displaying the aforementioned behavioral data and behavioral habits; and a connection bus 710 for connecting the various module components in the aforementioned electronic device.

[0125] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0126] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0127] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0128] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for identifying behavioral habits, characterized in that, include: Obtain behavioral data stored in the server that is used to instruct a target object to control multiple home appliances within a target area, wherein the behavioral data includes: a first operation action on the multiple home appliances; Remove the unrelated actions in the behavior data to obtain a first set of associated result information containing multiple second operation actions, wherein the unrelated actions are any two consecutive first operation actions in the behavior data with an interval time greater than a first preset interval time. Determine the action content corresponding to each second operation action in the first set of associated result information, and confirm the action content using preset rules to obtain the second set of associated result information; The third operation actions existing in the second set of associated result information are statistically analyzed according to a preset group, so as to identify the behavioral habits corresponding to the target object based on the statistical results. The behavioral habits are a set of behavioral preferences of the target object in controlling multiple home appliances in the target area. The step of using preset rules to confirm the action content and obtain a second set of associated result information includes: if there are any two consecutive second operation actions with the same action content in the first set of associated result information, determining the target home appliance corresponding to the two consecutive second operation actions; if there are action content of natural pairing behavior in the first set of associated result information, marking the second operation action corresponding to the action content that occurs first in the natural pairing behavior as a valid action, and marking other second operation actions in the natural pairing behavior other than the second operation action corresponding to the action content that occurs first as invalid actions, thereby obtaining a second set of associated result information containing the second operation actions marked as valid actions.

2. The method for identifying behavioral habits according to claim 1, characterized in that, If, in the first set of associated result information, there are any two consecutive second operation actions with the same action content, after determining the target home appliance corresponding to the two consecutive second operation actions, the method further includes: If the target home appliance corresponding to any two consecutive second operation actions is the same home appliance, the second operation action with the earlier time point among the two consecutive second operation actions is marked as a valid action, and the second operation action with the later time point is marked as an invalid action. If the target home appliances corresponding to any two consecutive second operation actions are not the same home appliance, then both of the consecutive second operation actions will be marked as valid actions.

3. The method for identifying behavioral habits according to claim 1, characterized in that, The third operation actions existing in the second set of associated result information are statistically analyzed according to preset groups, including: Obtain the first group information and the second group information corresponding to the preset group, wherein the first group information includes: target object, total time taken by the target object to operate the home appliance, location where the operation action occurs, and operation result of the home appliance corresponding to the operation action; the second group information includes: target object, location where the operation action occurs, operation result of the home appliance corresponding to the operation action, and associated behavior related to the operation action; Based on the first grouping information and the second grouping information, statistics are performed on multiple third operation actions existing in the second associated result information set.

4. The method for identifying behavioral habits according to claim 3, characterized in that, Based on the first grouping information and the second grouping information, statistics are performed on multiple third operation actions existing in the second association result information set, including: Based on the first grouping information, the number of occurrences of each of the multiple third operation actions is counted to obtain the first statistical information; Based on the second grouping information, determine the associated action corresponding to each of the plurality of third operation actions, and determine the probability of occurrence of the associated action to obtain the second statistical information.

5. The method for identifying behavioral habits according to claim 4, characterized in that, Based on the statistical results, the behavioral habits corresponding to the target object are identified, including: The first and second statistical information are summarized using the target object as a data alignment identifier to obtain the third statistical information; The target third operation action that occurs most frequently and has the highest probability of occurrence in relation to the third statistical information is identified. Obtain the target home appliance corresponding to the current target third operation action, and determine the target object's behavior preference based on the target object's behavior data of operating the target home appliance using the target third operation action; The behavioral habits of the target object are determined by the behavioral preferences.

6. The method for identifying behavioral habits according to claim 1, characterized in that, After statistically analyzing multiple third operation actions present in the second set of associated result information according to preset groups, and identifying the behavioral habits corresponding to the target object based on the statistical results, the method further includes: Determine the number of types of behavioral preferences included in the stated behavioral habits; If the number of the types is greater than the preset number, generate the home appliance operation scenario corresponding to the behavioral habit; Send a scene update message carrying the operation scene of the home appliance to the target object.

7. A device for recognizing behavioral habits, characterized in that, include: The acquisition module is used to acquire behavioral data stored in the server that instructs a target object to control multiple home appliances within a target area, wherein the behavioral data includes: a first operation action on the multiple home appliances; The removal module is used to remove unrelated actions from the behavior data to obtain a first set of associated result information containing multiple second operation actions, wherein the unrelated actions are any two consecutive first operation actions in the behavior data with an interval time greater than a first preset interval time. The determination module is used to determine the action content corresponding to each second operation action in the first set of associated result information, and to confirm the action content using preset rules to obtain the second set of associated result information. The statistics module is used to perform statistics on multiple third operation actions existing in the second set of associated result information according to a preset group, so as to identify the behavioral habits corresponding to the target object based on the statistical results, wherein the behavioral habits are a set of behavioral preferences of the target object in controlling multiple home appliances in the target area; The determining module is further configured to: determine the target home appliance corresponding to any two consecutive second operation actions with the same action content in the first association result information set; and, if there is action content of natural pairing behavior in the first association result information set, mark the second operation action corresponding to the action content that occurs first in the natural pairing behavior as a valid action, and mark other second operation actions in the natural pairing behavior other than the second operation action corresponding to the action content that occurs first as invalid actions, thereby obtaining a second association result information set containing the second operation actions marked as valid actions.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the behavioral habit recognition method described in any one of claims 1 to 6.

9. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the behavioral habit recognition method according to any one of claims 1 to 6 through the computer program.

Images