Methods for identity verification, storage media and electronic devices

Abstract

This application discloses an identity determination method, storage medium, and electronic device, relating to the field of smart home technology. The identity determination method includes: acquiring target data of a target object, wherein the target data is data generated by the target object when operating a first terminal and uploaded to a server; determining target features of the target object based on the target data; analyzing the target features based on a pre-established target data model to obtain analysis results, wherein the target data model is established based on data generated by a first object when operating a first terminal within a predetermined time period, and the first object includes the target object; and determining the identity of the target object based on the matching features when the analysis results indicate the existence of matching features in the target data model. This method can solve the problem of how to improve the accuracy of user identity recognition in related technologies.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and more specifically, to an identity verification method, storage medium, and electronic device. Background Technology

[0002] In recent years, the smart home industry has developed rapidly, enabling people to use smart home products in various scenarios and applications. This allows smart products to interact with users anytime, anywhere, improving their quality of life. However, currently, users often fail to register their identities on the devices themselves due to cumbersome registration processes or concerns about information leaks. This results in the devices being unable to identify user information and thus unable to recommend relevant information. Furthermore, situations exist where only one person in a multi-person household registers their identity, but multiple family members use the devices, leading to inaccurate identification of the real user and inaccurate information delivery. In short, the accuracy of user identification in related technologies is relatively low.

[0003] Therefore, no effective solution has yet been proposed for the problem of how to improve the accuracy of user identification in related technologies. Summary of the Invention

[0004] This application provides an identity verification method and apparatus, a storage medium, and an electronic device to at least address the problem of how to improve the accuracy of user identity recognition in related technologies.

[0005] According to one embodiment of this application, an identity determination method is provided, comprising: acquiring target data of a target object, wherein the target data is data generated by the target object when operating a first terminal and uploaded to a server; determining target features of the target object based on the target data; analyzing the target features based on a pre-established target data model to obtain analysis results, wherein the target data model is established based on data generated by a first object when operating the first terminal within a predetermined time period in the past, and the first object includes the target object; and determining the identity of the target object based on the matching features when the analysis results indicate that there are matching features in the target data model that match the target features.

[0006] In an exemplary embodiment, before analyzing the target features based on a pre-established target data model to obtain analysis results, the method includes: acquiring a first data set, wherein the first data set includes first data generated and uploaded to the server by the first object when operating the first terminal within the predetermined time period; classifying each piece of first data included in the first data set according to data attributes to obtain tuple data, wherein the first data includes data of multiple different types of data attributes, and the data attributes of each tuple data included in the tuple data are of the same type; and establishing the target data model based on the tuple data.

[0007] In an exemplary embodiment, analyzing the target features based on a pre-established target data model to obtain analysis results includes: analyzing the distribution characteristics of each tuple data included in the tuple data; determining a first feature of each tuple data based on the distribution characteristics of each tuple data; and analyzing the target features based on the first feature to obtain the analysis results.

[0008] In an exemplary embodiment, determining a first feature of each tuple data based on the distribution characteristics of each tuple data includes: dividing each tuple data into one or more subgroup data based on the distribution characteristics of each tuple data; determining a feature value for each subgroup data included in the one or more subgroup data; determining a second feature of each subgroup data by combining the data attributes and the feature values ​​of each subgroup data; and determining the first feature of each tuple data based on the second feature of each subgroup data.

[0009] In an exemplary embodiment, analyzing the target features based on a pre-established target data model to obtain analysis results includes: matching each feature included in the first feature of each tuple data with the target feature to obtain a matching result; and determining the analysis result based on the matching result.

[0010] In an exemplary embodiment, determining the identity of the target object based on the matching feature includes: determining the target feature value of the target feature; if the analysis result indicates that the feature value of the target second feature included in the first feature meets the target feature value under a preset condition, determining the target second feature as the matching feature; and determining the identity of the target object based on the matching feature.

[0011] In an exemplary embodiment, the feature value of the second feature includes: the average value of the subgroup data corresponding to the second feature, and the variance of the subgroup data corresponding to the second feature; the preset condition includes: the difference between the target feature value and the average value is less than or equal to the variance.

[0012] In an exemplary embodiment, determining the identity of the target object based on the matching feature includes: determining the matching data corresponding to the matching feature; and determining the identity of the object that generates the matching data by operating the first terminal as the identity of the target object.

[0013] In one exemplary embodiment, after determining the identity of the target object based on the matching features, the method further includes: pushing a message to the target object.

[0014] In an exemplary embodiment, obtaining target data of a target object includes: obtaining data generated by the target object operating the first terminal within a preset time period and uploaded to the server, wherein the first terminal includes one or more terminals.

[0015] In one exemplary embodiment, the target data includes at least one of the following: first metadata, wherein the first metadata is used to indicate data representing the identity attribute of the target object; second metadata, wherein the second metadata is used to indicate data representing the time attribute of the target object operating the first terminal; third metadata, wherein the third metadata is used to indicate data representing the location attribute of the target object operating the first terminal; fourth metadata, wherein the fourth metadata is used to indicate behavioral data that satisfies an association relationship generated by the target object operating the first terminal; and fifth metadata, wherein the fifth metadata is used to indicate data representing the intent attribute of the target object operating the first terminal.

[0016] According to another embodiment of the present application, an identity determination device is also provided, comprising: a first acquisition module, configured to acquire target data of a target object, wherein the target data is data generated by the target object when operating a first terminal and uploaded to a server; a first determination module, configured to determine target features of the target object based on the target data; an analysis module, configured to analyze the target features based on a pre-established target data model to obtain analysis results, wherein the target data model is established based on data generated by a first object when operating the first terminal within a predetermined time period in the past, and the first object includes the target object; and a second determination module, configured to determine the identity of the target object based on the matching features when the analysis results indicate that there are matching features in the target data model that match the target features.

[0017] According to yet another embodiment of the present application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program, when executed, performs the steps in any of the above method embodiments.

[0018] According to yet another embodiment of the present application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to perform the steps of any of the above method embodiments through the computer program.

[0019] This invention acquires target data generated during the target object's current operation of a first terminal and determines the target object's target features based on this data. Then, it analyzes these target features using a pre-established target data model. This target data model is built upon data generated during past operations of the first object, including the target object, on the first terminal within a predetermined time period—that is, based on the target object's historical data. When the analysis results indicate the existence of matching features in the target data model that correspond to the target features, the target object's identity can be determined based on these matching features. This achieves the goal of identifying the target object's identity based on a pre-established target data model even when the target object is not registered, and also enables the identification of each object's identity based on the target data model when only one object is registered but multiple objects are using the device. This further facilitates message push notifications to each object. This invention solves the problems of inability to identify user identities or low accuracy in related technologies, thus improving the accuracy of identity recognition. Attached Figure Description

[0020] 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.

[0021] 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.

[0022] Figure 1 This is a schematic diagram of the hardware environment for an identity determination method according to an embodiment of this application;

[0023] Figure 2 This is a flowchart of a user identification method in related technologies;

[0024] Figure 3This is a flowchart of an identity determination method according to an embodiment of this application;

[0025] Figure 4 This is a flowchart of a user identification method according to an embodiment of this application;

[0026] Figure 5 This is an example of body fat scale data analysis according to a specific embodiment of this application. Figure 1 ;

[0027] Figure 6 This is an example of body fat scale data analysis according to a specific embodiment of this application. Figure 2 ;

[0028] Figure 7 This is an example of water heater data analysis according to a specific embodiment of this application. Figure 1 ;

[0029] Figure 8 This is an example of water heater data analysis according to a specific embodiment of this application. Figure 2 ;

[0030] Figure 9 This is an example of water heater data analysis according to a specific embodiment of this application. Figure 3 ;

[0031] Figure 10 This is an example of water heater data analysis according to a specific embodiment of this application. Figure 4 ;

[0032] Figure 11 This is an example of air conditioning data analysis according to a specific embodiment of this application. Figure 1 ;

[0033] Figure 12 This is an example of air conditioning data analysis according to a specific embodiment of this application. Figure 2 ;

[0034] Figure 13 This is an example of air conditioning data analysis according to a specific embodiment of this application. Figure 3 ;

[0035] Figure 14 This is an example of air conditioning data analysis according to a specific embodiment of this application. Figure 4 ;

[0036] Figure 15 This is a flowchart illustrating a user identification method according to an embodiment of this application;

[0037] Figure 16 This is a structural block diagram of an identity verification device according to an embodiment of this application. Detailed Implementation

[0038] 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.

[0039] 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.

[0040] According to one aspect of the embodiments of this application, an interaction method for smart home devices is provided. This interaction method for smart home devices is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligence house ecosystems. Optionally, in this embodiment, the above-mentioned interaction method for smart home devices 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.

[0041] 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.

[0042] In related technologies, user identification methods rely on the user being a registered user, such as... Figure 2 As shown, Figure 2 This is a flowchart of a user identification method in related technologies. This method requires users to register their identity on the device beforehand, the system generates and stores a user ID, and retains clear user characteristic information on the device. Then, when the user subsequently uses the device, the device automatically collects user behavior-related information, analyzes and matches the user characteristic information, and performs user identification. The user identification method in related technologies has the following drawbacks: 1) If the user is not registered or their characteristics are missing, the user's identity cannot be identified; 2) Even if the user has registered on the device, multiple users may generate different usage results during device use, which can also cause difficulties in user identification.

[0043] This embodiment provides an identity verification method. Figure 3 This is a flowchart of an identity determination method according to an embodiment of this application, such as... Figure 3 As shown, the process includes the following steps:

[0044] Step S302: Obtain target data of the target object, wherein the target data is data generated by the target object when operating the first terminal and uploaded to the server;

[0045] Step S304: Determine the target features of the target object based on the target data;

[0046] Step S306: Analyze the target features based on the pre-established target data model to obtain analysis results, wherein the target data model is established based on the data generated when the first object operates the first terminal within a predetermined time period in the past, and the first object includes the target object;

[0047] Step S308: If the analysis result indicates that there is a matching feature in the target data model that matches the target feature, determine the identity of the target object based on the matching feature.

[0048] Through the above steps, target data generated during the target object's current operation of the first terminal is obtained, and target characteristics of the target object are determined based on this data. Then, the target characteristics are analyzed based on a pre-established target data model. This target data model is built upon data generated during past operations of the first object, including the target object, on the first terminal within a predetermined time period—that is, a target data model built based on the historical data of the first object. When the analysis results indicate the existence of matching features in the target data model that match the target characteristics, the identity of the target object can be determined based on these matching features. This achieves the goal of identifying the target object's identity based on the pre-established target data model even when the target object is not registered, and also achieves the goal of identifying the identity of each object based on the target data model when only one object is registered but multiple objects are using it, thereby further enabling message push notifications to each object. This solves the problems of inability to identify user identity or low accuracy in related technologies, achieving the effect of improving the accuracy of identity recognition.

[0049] The entity performing the above steps can be a server, a server-side application, or a cloud-based application. For example, it could be a data computing server, a processor with human-computer interaction capabilities configured on a storage device, or a processing device or unit with similar processing capabilities, but it is not limited to these. The following explanation uses a data computing server performing the above operations as an example (this is merely an illustrative example; in actual operation, other devices or modules could also perform the above operations):

[0050] In the above embodiments, the data computing server obtains target data of the target object. The target data is generated by the target object when operating the first terminal and uploaded to the server. The target data may include one-dimensional or multi-dimensional data. For example, taking an air conditioner as the first terminal, the target data may include the time when the target object turns on the air conditioner, the temperature set, the air conditioner mode set, the location of the air conditioner, etc. Of course, if the target object is a registered user, the target data may also include the user data of the target object, that is, the user's personal information. Optionally, in practical applications, the first terminal may also include multiple terminals or devices. Then, based on the target data, the target characteristics of the target object are determined. The target characteristics may be the behavioral characteristics of the target object operating the first terminal, such as turning on the air conditioner, setting the air conditioner parameters, etc. The target characteristics may also be the time characteristics of the target object operating the first terminal, such as 8 pm or 6 am every day. Of course, the target feature can also be other features. Furthermore, the target feature can include one feature or multiple features. Then, based on a pre-established target data model, the target features are analyzed to obtain the analysis results. The target data model is established based on data generated when the first object, including the aforementioned target object, operates the first terminal within a predetermined time period (such as one month, 7 days, 10 days, or other time periods). That is, the target data model is established based on the historical data of multiple objects. Among these multiple objects, there may be only one registered user, or all objects may be unregistered users. In practical applications, the historical data of multiple objects can be analyzed, for example, by analyzing the distribution characteristics of the historical data, to obtain the features of one or more objects. When the analysis results indicate that there is a matching feature in the target data model that matches the target feature, the identity of the target object can be determined based on the matching feature. This achieves the goal of identifying the identity of the target object based on a pre-established target data model even when the target object is not registered, and also achieves the goal of identifying the identity of each object based on the target data model when only one object is registered but multiple objects are using it, thereby further achieving the goal of pushing messages to each object. This solves the problem of inability to identify user identity or low accuracy in related technologies, and achieves the effect of improving the accuracy of identity recognition.

[0051] In an optional embodiment, before analyzing the target features based on a pre-established target data model to obtain analysis results, the method includes: acquiring a first data set, wherein the first data set includes first data generated and uploaded to the server by the first object when operating the first terminal within the predetermined time period; classifying each piece of first data included in the first data set according to data attributes to obtain tuple data, wherein the first data includes data of multiple different types of data attributes, and the data attributes of each tuple data included in the tuple data are of the same type; and establishing the target data model based on the tuple data. In this embodiment, before analyzing the target features of the target object, a target data model is first established. For example, data generated by a first object (i.e., multiple objects) including the target object when operating a first terminal within a predetermined time period (such as one month, 7 days, 10 days, or other time periods) is first obtained. That is, the first data group is the historical data of multiple objects. This historical data is uploaded to the server. The first data group includes multiple first data. For example, the first data is a piece of data generated by a user operating a device or terminal (such as an air conditioner or a water heater) at a certain time in the past. The first data includes data of various different types of data attributes. For example, the first data includes data of time attributes, or data of location attributes, or data of behavioral attributes, etc. Of course, if the user is a registered user, the first data may also include user attribute data. Then, each first data included in the first data group is classified according to the data attributes to obtain tuple data. Each tuple data included in the tuple data represents data of one type of data attribute. Then, a target data model is established based on the tuple data. For example, in practical applications, tuple data may include some or all of user tuple data, time tuple data, location tuple data, context tuple data, intent tuple data, etc., where context tuple data is used to represent continuous behavioral information such as the object's current behavior, previous behavior, and next behavior. This embodiment achieves the goal of building a target data model based on the object's historical data.

[0052] In an optional embodiment, analyzing the target features based on a pre-established target data model to obtain the analysis results includes: analyzing the distribution characteristics of each tuple data included in the tuple data; determining a first feature of each tuple data based on the distribution characteristics of each tuple data; and analyzing the target features based on the first feature to obtain the analysis results. In this embodiment, by analyzing the distribution characteristics of each tuple data included in the tuple data, for example, each tuple data includes data generated by one or more objects operating a first terminal multiple times in the past predetermined time period, analyzing the distribution characteristics of this data, that is, analyzing the distribution characteristics of each tuple data, and then determining the first feature of each tuple data based on the distribution characteristics of each tuple data, taking the data reported by the water heater as an example, for example, two users in a family use the water heater at different times. One person habitually sets the temperature to about 45°C each time they turn on the water heater, while the other person habitually sets the temperature to about 40°C each time they turn on the water heater. Thus, according to the distribution characteristics of the data reported by the water heater, it can be concluded that the data is generated by the operations of two users, even if both users are unregistered users. At this time, the data can be determined based on the user's operation of the water heater device. The generated behavioral attribute data, such as the action of turning on the water heater and the set temperature parameters, serves as the first feature of the corresponding tuple data. This allows for identification of each user based on the generated data when the two users operate the device again. It should be noted that this example only uses the action of turning on the water heater and setting temperature parameters; in practical applications, it can include data with multiple behavioral attributes, such as previous and next actions related to the current action. The tuple data can include multiple first features, and can also include first features of other tuple data, such as time tuple data and location tuple data. Optionally, it can also include the first feature of each tuple data generated from continuous user operations on multiple terminals. Then, analysis is performed based on the first features and target features to obtain the analysis results. This embodiment achieves the goal of determining the first feature of each tuple data by analyzing the distribution characteristics of each tuple data included in the tuple data, and then analyzing the target feature based on the first feature to obtain the analysis results.

[0053] In an optional embodiment, determining a first feature of each tuple data based on the distribution characteristics of each tuple data includes: dividing each tuple data into one or more subgroup data based on the distribution characteristics of each tuple data; determining a feature value for each subgroup data included in the one or more subgroup data; determining a second feature of each subgroup data by combining the data attributes of each subgroup data with the feature value; and determining the first feature of each tuple data based on the second feature of each subgroup data. In this embodiment, each tuple is grouped according to its distribution characteristics. Taking behavioral attribute tuple data (or context tuple data) as an example, and using the aforementioned example of turning on the water heater, this tuple includes data generated from multiple past operations of the water heater by two unregistered users. One user habitually sets the temperature to around 45℃ each time they turn on the water heater, while the other habitually sets it to around 40℃. Based on the distribution characteristics of all the data included in this tuple, it can be divided into two subgroups, each corresponding to a user. The user's behavioral state values ​​correspond to the aforementioned 45℃ and 40℃, respectively. The user's satisfaction state value can be used as the feature value corresponding to each subgroup. The feature value and the data attribute of the subgroup data are determined as the second feature. For example, the second feature could be the behavior of turning on the water heater, with a feature value of 45℃. Optionally, in practical applications, since there may be slight differences in each user's operation, the average and variance can be derived based on multiple historical data. When the feature value of the target feature of the data generated when a certain object operates the water heater next time is within a certain error range of the feature value in the second feature, the object can be confirmed as the user corresponding to the subgroup data containing the second feature. After determining the second feature of each subgroup data, the first feature of each tuple data can be determined. The first feature may include one or more second features. The same method can be used to obtain the first features of other tuple data in the tuple data. Through this embodiment, the purpose of determining the first feature of each tuple data based on the distribution characteristics of each tuple data is achieved.

[0054] In an optional embodiment, analyzing the target features based on a pre-established target data model to obtain analysis results includes: matching each feature included in the first feature of each tuple data with the target feature to obtain a matching result; and determining the analysis result based on the matching result. In this embodiment, matching each feature included in the first feature of each tuple data with the target feature to obtain a matching result, the first feature may include one or more second features, i.e., each second feature is matched with the target feature separately. For example, if the feature value of the second feature and the feature value of the target feature meet a preset condition, such as an error within a preset range, then the second feature is considered to be a match with the target feature; if the feature value of the second feature and the feature value of the target feature do not meet the preset condition, then the second feature is considered to be a mismatch with the target feature. Through this embodiment, the purpose of analyzing the target feature with each feature included in the first feature to obtain analysis results is achieved.

[0055] In an optional embodiment, determining the identity of the target object based on the matching feature includes: determining the target feature value of the target feature; if the analysis result indicates that the feature value of the target second feature included in the first feature meets the target feature value under a preset condition, determining the target second feature as the matching feature; and determining the identity of the target object based on the matching feature. In this embodiment, based on the data generated by the first terminal during the current operation of the target object, the target feature value is determined. For example, the behavior state value of turning on the air conditioner is 26°C. Optionally, in practical applications, the matching feature may include the second feature of multiple tuple data. For example, it may include multiple second features of two tuple data in the tuple data, such as multiple second features of time tuple data and context tuple data (or behavior attribute tuple data), or multiple second features of three tuple data in the tuple data, such as multiple second features of time tuple data, location tuple data and context tuple data (or behavior attribute tuple data). It may also include multiple second features of more tuple data. The target feature value may also include the feature value of the time attribute of the target object's operation behavior, such as 20:00, or the target feature value may also include the feature value of the location attribute of the target object's operation behavior, such as living room or study. When the above analysis results indicate that there exists a feature value of the target second feature in the first feature that meets the preset conditions with the target feature value, the target second feature can be determined as the matching feature. Accordingly, the operator or user of the subgroup data corresponding to the target second feature can be determined as the identity of the target object. This embodiment achieves the goal of determining the identity of the target object by identifying matching features.

[0056] In an optional embodiment, the feature value of the second feature includes: the average value representing the subgroup data corresponding to the second feature, and the variance representing the subgroup data corresponding to the second feature; the preset condition includes: the difference between the target feature value and the average value is less than or equal to the variance. In this embodiment, the feature value of the second feature may include the average value and / or variance of the subgroup data corresponding to the second feature. In practical applications, each subgroup data may include multiple data points, and the maximum, minimum, average, and variance of these data points can be analyzed to obtain data distribution feature information. After determining the target feature based on the target data of the current target object, if the difference between the target feature value and the above average value is less than or equal to the variance, then the feature value of the target second feature is considered to satisfy the preset condition. Through this embodiment, the purpose of satisfying the preset condition required when determining the matching feature is achieved.

[0057] In an optional embodiment, determining the identity of the target object based on the matching feature includes: determining the matching data corresponding to the matching feature; and determining the identity of the object that generates the matching data by operating the first terminal as the identity of the target object. In this embodiment, by determining the matching data corresponding to the matching feature, the identity of the object that generates the matching data is determined as the identity of the target object. The matching data refers to the data generated by the object when operating the first terminal within a predetermined time period in the past. The matching data may include data generated by the object through multiple operations in the past. In practical applications, the matching feature may include a second feature (i.e., the second feature corresponding to the aforementioned subgroup data), and the matching feature may also include multiple second features, such as the second features corresponding to the subgroup data included in multiple tuple data. For example, time tuple data may include multiple subgroup data, and each subgroup data has a corresponding second feature. Secondly, the context attribute tuple data (or behavioral attribute tuple data) may also include multiple sub-tuple data, each with its own corresponding second feature. Thus, the matching features can include multiple second features matched from different data attributes (or different perspectives). Specifically, based on the target data model, if a dataset (multiple data points generated from multiple operations) in the historical data is found to have a feature that matches the target feature, or if the features of multiple tuple data match the target feature, then that dataset can be identified as the matching data. Furthermore, the identity of the object corresponding to that matching data can be determined as the identity of the target object. This embodiment achieves the purpose of determining the identity of the target object.

[0058] In an optional embodiment, after determining the identity of the target object based on the matching features, the method further includes: pushing a message to the target object. In this embodiment, after determining the identity of the target object, a message can be pushed to the target object. In practical applications, when multiple objects are unregistered or only one object is registered, personalized messages can be pushed to different objects in a targeted manner after identifying the identity of each object. Through this embodiment, the purpose of pushing personalized messages to users is achieved.

[0059] In an optional embodiment, obtaining target data of the target object includes: obtaining data generated by the target object operating the first terminal within a preset time period and uploaded to the server, wherein the first terminal includes one or more terminals. In this embodiment, the first terminal may include one or more terminals, for example, the first terminal may be an air conditioner, or it may be an air conditioner and a television, or other multiple terminals, and the target data may include data generated by the target object operating the first terminal within the preset time period, for example, data generated by the target object continuously operating the air conditioner and the television within 1 minute (or 2 minutes, or other time periods). If the target data model also includes data generated by an object repeatedly operating multiple terminals within a preset time period, then the identity of the target object can be determined based on the characteristics of the data generated by such continuous behavior. Through this embodiment, the purpose of determining the identity of the target object based on the continuous behavior of the target object operating multiple terminals is achieved.

[0060] In an optional embodiment, the target data includes at least one of the following: first metadata, wherein the first metadata is used to indicate the identity attribute data of the target object; second metadata, wherein the second metadata is used to indicate the time attribute data of the target object operating the first terminal; third metadata, wherein the third metadata is used to indicate the location attribute data of the target object operating the first terminal; fourth metadata, wherein the fourth metadata is used to indicate the behavioral data that satisfies the association relationship generated by the target object through operating the first terminal; and fifth metadata, wherein the fifth metadata is used to indicate the intent attribute data of the target object operating the first terminal. In this embodiment, the target data includes unary or multi-dimensional data, where each metadata is used to represent a different attribute of the target object. Similarly, the data stored on the server, including the target object and the data generated by the first object operating the first terminal within a predetermined time period, also includes unary or multi-dimensional data. Through this embodiment, the purpose of more accurately determining the identity of the target object is achieved by acquiring diversified target data.

[0061] To better understand the process of the above identity verification method, the flow of the above identity verification method 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.

[0062] This embodiment provides a user identification method. Figure 4 This is a flowchart of a user identification method according to an embodiment of this application, such as... Figure 4 As shown, the details are as follows:

[0063] S402, User behavior information acquisition; Based on various device terminals (corresponding to the aforementioned first terminal), collect user information, family information, location information, environmental information, device information, and related information such as user behavior. Related information includes not only basic user information such as age, birthday, and body fat percentage, as well as continuous or historical behavior information such as current behavior, previous behavior, and next behavior; it also includes family information, environmental information, and device status information.

[0064] S404, Construct a tuple data model. Optionally, the tuple data model can be a binary, triple, quadruple, or quintuple data model. Taking the quintuple data model as an example, all element information obtained in step S402 is divided into five tuples to construct a user quintuple data model. The user quintuple consists of a user tuple, a time tuple, a location tuple, a context tuple, and an intent tuple. In practical applications, a unified data model can be designed, including a unified storage format, unified encoding, and unified units. For example, the units of data obtained from different devices may be inconsistent, some accurate to seconds or milliseconds; the units need to be unified. For example, the format of dates obtained from different devices may include 20200101 or 2020-01-01; this also needs to be unified. For example, a user may turn on the air conditioner via remote control, APP, or voice; the encoding of the same operation (i.e., turning on the air conditioner) produced by different methods may be inconsistent; this can also be unified in encoding, etc.

[0065] S406 analyzes and organizes the information of each tuple in the user's 5-tuple to obtain the distribution characteristics of the relevant tuple data, for example... Figure 4 The analysis of contextual tuples can also include the analysis of other tuple data in the quintuple;

[0066] S408. Based on the user quintuple analysis results, the user features are associated and matched with existing user features and behavioral features. The user features in this step are user features determined based on historical data. If the user has registered user information, the user feature information can be determined. If the user has not registered, the behavioral features of different users can be determined based on historical data. Then, the target features of the data generated based on the current user's operation behavior are associated and matched with existing user features and behavioral features to identify the current user's identity information.

[0067] Furthermore, the S410 can also push relevant recommendation messages based on the user's identity.

[0068] The following explains the relevant terms in this embodiment:

[0069] U: A set of user attribute information (corresponding to the aforementioned first metadata); u(x) represents a certain user attribute, and u(u_1,u_2,…,u_k1) represents the first to k1th attributes of the user. For example, a user may have attributes such as age, gender, and occupation.

[0070] T: A set of time attribute information (corresponding to the aforementioned second metadata); t(x) represents the time attribute of a user action, and t(t_1,t_2,…,t_k2) represents the first to k2th attributes of the time. For example, attributes such as year, month, day, and hour to which the user action belongs;

[0071] A: Location attribute information set (corresponding to the aforementioned third metadata); a(x) represents the location attribute of a user's behavior, and a(a_1,a_2,…,a_k3) represents the first to k3 attributes of the location. For example, attributes such as the province, city, district / county, and room to which the user's behavior belongs;

[0072] L: A set of context attribute information (corresponding to the aforementioned fourth metadata); l(x) represents the context attribute of a user behavior, and l(l_1,l_2,…,l_k4) represents the first to k4th features of the context. Examples include attributes such as the user's previous behavior, current behavior, current weather, and current device power-on status.

[0073] I: Set of intent attribute information (corresponding to the aforementioned fifth metadata); i(x) represents a user intent attribute, and i(i_1,i_2,…,i_k5) represents the first to k5th attributes of the user intent. Examples include attributes such as opening curtains, turning on lights, and increasing wind speed.

[0074] F: A set of five-tuple attribute information; f_x(u_1,t_1,a_1,l_1,i_1,…) represents user u_1 and its corresponding user behavior time attribute 1 is t_1, address location attribute 1 is a_1, and context attribute 1 is l_1; the fifth tuple i_1 is obtained based on the first four tuples. For example, f_1(u_1,t_1,a_1,l_1,i_1) represents user: 'Zhang San', corresponding user time attribute is "2021-10-20", location attribute is "living room", context attribute is "too cold", and the predicted user behavior intent is "turn on the air conditioner".

[0075] The steps in the above embodiments are described in detail below:

[0076] 1. Information collection (corresponding to step S402 above)

[0077] 1.1 Collect user behavior-related information through different user terminals, such as APP, AI, multi-screen, etc., and related systems, such as user center, IoT domain model, family model, etc.;

[0078] 1.2 The information collected includes, but is not limited to, user information, family information, location information, environmental information, device information, and related information such as user behavior;

[0079] 2. Generation of the quintuple data model (corresponding to step S404 above)

[0080] Based on the analysis and classification of the collected information, a user quintuple data model is generated, specifically including:

[0081] 2.1 Users: User ID information, user characteristic information, etc.;

[0082] 2.2 Time: Behavioral time series; includes user behavior timestamps, the year, month, day, and hour of the behavior time;

[0083] 2.3 Location: Location information of the behavior; including the space where the user's behavior belongs, such as 'living room'; also including information such as the province, city, district, and community where the behavior belongs;

[0084] 2.4 Context: Information such as preceding and following behaviors, preceding and following behavior states, user or device profiles, weather and air quality;

[0085] 2.5 Intent: Data predicts subsequent behavioral information.

[0086] 3. Multivariate data analysis (corresponding to step S406 above)

[0087] 3.1 Analysis of Non-User Tuple Data

[0088] For users who are not registered, i.e., those without user tuple data, statistics and analysis are performed on time tuple information, location tuple information, and context information.

[0089] A) Context tuple analysis: For example, analyzing the "behavioral state value" attribute in the "context" tuple: For the same behavior by different users, the "behavioral state value" attribute will show different characteristic state distributions. Based on the data distribution pattern, group the data; perform data statistics such as maximum value, minimum value, average value, and variance on the grouped data.

[0090] For example, two people in a household use a body fat scale to weigh themselves. The body fat scale reports two weight records per day. Table 1 shows the data records reported by the body fat scale.

[0091] Table 1

[0092] Serial Number Time (Day) Behavior Behavioral status value (unit: kilograms) 1 2021-10-01 Weighing 98 2 2021-10-01 Weighing 135 3 2021-10-02 Weighing 100 4 2021-10-02 Weighing 134 5 2021-10-03 Weighing 99 6 2021-10-03 Weighing 133 7 2021-10-04 Weighing 98 8 2021-10-04 Weighing 134

[0093] Figure 5 This is an example of body fat scale data analysis according to a specific embodiment of this application. Figure 1 Data analysis reveals that the recorded data is clearly divided into two groups.

[0094] 1. Group 1: Data with serial numbers 1, 3, 5, and 7, and weight data of 98, 100, 99, and 98 respectively, are grouped together;

[0095] 2. Group 2: Data with serial numbers 2, 4, 6, and 8, and weight data of 135, 134, 133, and 134 respectively, are grouped together;

[0096] The body fat scale data is equivalent to one of the tuples in the aforementioned tuple data, while the data in group 1 and group 2 are equivalent to one or more subgroups in the aforementioned tuple data. That is, group 1 corresponds to one subgroup data and group 2 corresponds to another subgroup data.

[0097] After grouping, analyze the data distribution characteristics, such as... Figure 6 As shown, Figure 6 This is an example of body fat scale data analysis according to a specific embodiment of this application. Figure 2 Through grouped data analysis, we can obtain the following:

[0098] 1. Group 1 data analysis: This can obtain data distribution characteristics information such as the maximum value, minimum value, average value, and variance of the data in this group;

[0099] 2. Group 2 data analysis: This can yield data distribution characteristics such as the maximum, minimum, average, and variance of the data in this group;

[0100] It should be noted that after determining the distribution characteristics of each group of data, the behavioral characteristics (i.e., weighing behavior) and feature values ​​(including the average and variance mentioned above) of the user corresponding to each group of data can be determined, which is equivalent to determining the aforementioned second feature. In addition, the above only takes the operation behavior of two people as an example. For the operation behavior of more people, a similar method can be used for identity recognition. Therefore, when a certain user (equivalent to the aforementioned target object) performs a weighing behavior and the generated behavior status value matches the behavioral characteristics and feature values ​​corresponding to a certain group of data, the user corresponding to that group of data can be identified as the current target object, thereby achieving the purpose of determining the identity of the target object.

[0101] B) Time and Context Tuple Analysis: For example, analyzing the "timestamp" attribute in the "time" tuple and the "behavioral state value" attribute in the "context" tuple: for the same behavior by different users, the "timestamp" and "behavioral state value" attributes will exhibit different characteristic state distributions. Based on the data distribution pattern, group the data; perform statistical analysis on the grouped data, including maximum, minimum, average, and variance.

[0102] For example, two people in a household use the water heater to shower at different times. The water heater reports its daily operation records. Table 2 shows the data records reported by the water heater.

[0103] Table 2

[0104] Serial Number Power-on time (minutes) Behavior Behavioral status value (unit: °C) 1 2021-10-01 18:00:00 Outflow temperature 46 2 2021-10-01 21:04:00 Outflow temperature 40 3 2021-10-02 18:05:00 Outflow temperature 47 4 2021-10-02 21:03:00 Outflow temperature 39 5 2021-10-03 18:02:00 Outflow temperature 46 6 2021-10-03 21:03:00 Outflow temperature 40 7 2021-10-04 18:03:00 Outflow temperature 48 8 2021-10-04 21:05:00 Outflow temperature 38

[0105] Figure 7 This is an example of water heater data analysis according to a specific embodiment of this application. Figure 1 Data analysis reveals that the recorded data is clearly divided into two groups.

[0106] 1. Group 1: Data with serial numbers 1, 3, 5, and 7, and outlet water temperatures of 46, 47, 46, and 48 respectively, are grouped together;

[0107] 2. Group 2: Data with serial numbers 2, 4, 6, and 8, and outlet water temperatures of 40, 39, 40, and 38 respectively, are grouped together;

[0108] After grouping, the distribution characteristics of the water heater outlet temperature data were analyzed, such as... Figure 8 As shown, Figure 8 This is an example of water heater data analysis according to a specific embodiment of this application. Figure 2 Similarly, after grouping, the distribution characteristics of the water heater start-up and operation time data were analyzed, such as... Figure 9 As shown, Figure 9 This is an example of water heater data analysis according to a specific embodiment of this application. Figure 3 Then, the distribution characteristics of the water heater's operating data are comprehensively analyzed, such as... Figure 10 As shown, Figure 10 This is an example of water heater data analysis according to a specific embodiment of this application. Figure 4 Through grouped data analysis, we can obtain the following:

[0109] 1. Group 1 data analysis: This can obtain data distribution characteristics information such as the maximum value, minimum value, average value, and variance of the data in this group;

[0110] 2. Group 2 data analysis: This can yield data distribution characteristics such as the maximum, minimum, average, and variance of the data in this group;

[0111] It should be noted that, in combination Figure 10 As can be seen, in this embodiment (water heater), group 1 and group 2 include multiple tuple data, such as time tuple data and context tuple data. The distribution characteristics of each group data are determined using the same method as described above, thereby determining the user's behavioral characteristics and the time attribute characteristics of the behavior corresponding to each group data. That is, it is equivalent to determining multiple second features. Then, based on multiple second features, it can be determined whether there are matching features that match the target features of the current target object. If it is determined that there are, the identity of the target object can be determined. Through this embodiment, the distribution characteristics of tuple data are combined to improve the accuracy of determining the identity of the target object.

[0112] C) Location and Context Tuple Analysis: For example, analyzing the "room" attribute in the "location" tuple and the "behavioral state value" attribute in the "context" tuple: for the same behavior by different users, the "room" attribute and the "behavioral state value" attribute will exhibit different characteristic state distributions. Based on the data distribution pattern, group the data; perform statistical analysis on the grouped data, including maximum value, minimum value, average value, and variance.

[0113] D) Time, Location, and Context Tuple Analysis: For example, analyzing the "timestamp" attribute in the "time" tuple, the "room" attribute in the "location" tuple, and the "behavioral state value" attribute in the "context" tuple: For the same behavior by different users, the "timestamp" attribute, "room" attribute, and "behavioral state value" attribute will exhibit different characteristic state distributions. Based on the data distribution pattern, group the data; perform statistical analysis on the grouped data, including maximum, minimum, average, and variance data.

[0114] For example, two people in a household use the air conditioner at different times and in different spaces. The air conditioner reports its daily operation records. Table 3 shows the data records reported by the air conditioner.

[0115] Table 3

[0116] Serial Number Time (hours) Location Behavior Behavioral status value (unit: °C) 1 2021-10-01 18:00:00 living room Target temperature 26 2 2021-10-01 20:04:00 study Target temperature 22 3 2021-10-02 18:05:00 living room Target temperature 27 4 2021-10-02 20:03:00 study Target temperature 21 5 2021-10-03 18:02:00 living room Target temperature 26 6 2021-10-03 20:03:00 study Target temperature 20 7 2021-10-04 18:03:00 living room Target temperature 28 8 2021-10-05 20:05:00 study Target temperature 21

[0117] Figure 11 This is an example of air conditioning data analysis according to a specific embodiment of this application. Figure 1 Data analysis reveals that the recorded data is clearly divided into two groups.

[0118] 1. Group 1: Data with serial numbers 1, 3, 5, and 7, and target temperature values ​​of 26, 27, 26, and 28 respectively, are grouped together;

[0119] 2. Group 2: Data with serial numbers 2, 4, 6, and 8, and target temperature values ​​of 20, 22, 21, and 21 respectively, are grouped together;

[0120] After grouping, the distribution characteristics of the air conditioning target temperature data are analyzed, such as... Figure 12 As shown, Figure 12 This is an example of air conditioning data analysis according to a specific embodiment of this application. Figure 2 Similarly, after grouping, the distribution characteristics of the air conditioner start-up and operation time data were analyzed, such as... Figure 13 As shown, Figure 13 This is an example of air conditioning data analysis according to a specific embodiment of this application. Figure 3 Then, the distribution characteristics of air conditioning operation data are comprehensively analyzed, such as... Figure 14 As shown, Figure 14 This is an example of air conditioning data analysis according to a specific embodiment of this application. Figure 4 Through grouped data analysis, we can obtain the following:

[0121] 1. Group 1 data analysis: This can obtain data distribution characteristics information such as the maximum value, minimum value, average value, and variance of the data in this group;

[0122] 2. Group 2 data analysis: This can yield data distribution characteristics such as the maximum, minimum, average, and variance of the data in this group;

[0123] It should be noted that, in combination Figure 14 As can be seen, in this embodiment (air conditioner), group 1 and group 2 include multiple tuple data, such as time tuple data, location tuple data, and context tuple data. For each tuple data, the distribution characteristics of each group data are determined using the same method as described above, thereby determining the user's behavioral characteristics, the time attribute characteristics of the behavior, the location attribute characteristics of the behavior, etc., corresponding to each group data. That is, multiple second features are determined. Then, based on multiple second features, it can be determined whether there are matching features that match the target features of the current target object. If it is determined that there are, the identity of the target object can be determined. Through this embodiment, the distribution characteristics of tuple data are combined to improve the accuracy of determining the identity of the target object.

[0124] 3.2 Five-tuple data analysis

[0125] By horizontally integrating time tuple information, location tuple information, context information, and user information, and associating behavioral data value distribution characteristics and related tuple attribute characteristics with user tuple information, a user's behavioral value distribution characteristics (corresponding to the aforementioned second characteristic) are formed.

[0126] 4. User identification (corresponding to step S408 above)

[0127] Based on the analysis of the new features of the five-tuple (corresponding to the target features of the aforementioned target object), the user's identity is identified by associating and matching them with known user features and behavioral features. If the user is using the device for the first time and uploads the first usage record information, and there is no historical user identification information, then new user feature and user behavioral feature information is created so that it can be associated and matched with in subsequent user identification.

[0128] 4.1 Identification based on context tuples: Based on the features of the analyzed context tuple information and the distribution features of the user's behavioral state value attributes, the user identity information is identified by associating and matching with known user features and user behavioral features.

[0129] 4.2 Identification based on time and context tuples: Based on the analyzed time and context tuple information features, as well as the distribution features of user behavior state value attributes, the user identity information is identified by associating and matching with known user features and user behavior features.

[0130] 4.3 Identification based on location and context tuples: Based on the analyzed location and context tuple information features, as well as the distribution features of user behavior state value attributes, the user identity information is identified by associating and matching with known user features and user behavior features.

[0131] 4.4 Identification based on time, location, and context tuples: Based on the analyzed time, location, and context tuple information features, as well as the distribution features of user behavior state value attributes, the user identity information is identified by associating and matching with known user features and user behavior features.

[0132] The aforementioned known user characteristics and behavioral characteristics refer to those determined based on historical data. If a user has registered user information, user characteristic information and user behavioral characteristics can be determined. If a user has not registered, the behavioral characteristics of different users can be determined based on historical data.

[0133] 5. User message push (corresponding to step S410 above)

[0134] According to the information push rules, personalized recommendation messages that match the user's identity will be pushed to the user.

[0135] Figure 15 This is a flowchart illustrating a user identification method according to an embodiment of this application, as shown below. Figure 15 As shown, the process includes the following steps:

[0136] S1502, User behavior information is uploaded to the cloud server (corresponding to the aforementioned server), including the current user's operation behavior information being uploaded to the cloud server, and the historical data of the current user and other users being uploaded to the cloud server. The user behavior information includes multi-dimensional data (i.e., multi-dimensional data).

[0137] S1504, Data localization, the data computing server obtains data from the cloud server;

[0138] S1506, Construct the user quintuple model;

[0139] S1508, Analysis of quintuple data;

[0140] S1510 identifies user identities based on quintuple data analysis;

[0141] S1512 transmits data to the cloud server and transmits the recognition results to the cloud server;

[0142] S1514, the cloud server sends a recommendation message to the user client.

[0143] Through the above embodiments, during the user's use of smart devices, information on various elements can be collected from multiple user terminals to generate a user quintuple data model. Based on the user quintuple, the statistical situation of the "behavioral state value" information in the "context" tuple can be analyzed. By matching the distribution characteristics of this value with the user's relevant value features, the user's identity can be identified. This avoids the problem of being unable to identify users due to situations such as the user not registering the device, missing user attribute characteristics, or one person registering and the whole family using the device. In this embodiment, by sorting and analyzing the collected information, a quintuple data model is constructed. Based on the user quintuple model, the relationship between each tuple and its matching with the user are analyzed to identify user identity information, thereby enabling targeted message pushes.

[0144] 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.

[0145] Figure 16 This is a structural block diagram of an identity verification device according to an embodiment of this application, such as... Figure 16 As shown, it includes:

[0146] The first acquisition module 1602 is used to acquire target data of the target object, wherein the target data is data generated by the target object when operating the first terminal and uploaded to the server.

[0147] The first determining module 1604 is used to determine the target features of the target object based on the target data;

[0148] Analysis module 1606 is used to analyze the target features based on a pre-established target data model to obtain analysis results, wherein the target data model is established based on data generated by a first object operating the first terminal within a predetermined time period in the past, and the first object includes the target object;

[0149] The second determining module 1608 is used to determine the identity of the target object based on the matching feature when the analysis result indicates that there is a matching feature in the target data model that matches the target feature.

[0150] In an optional embodiment, the above apparatus further includes: a second acquisition module, configured to acquire a first data set before analyzing the target features based on a pre-established target data model to obtain analysis results, wherein the first data set includes first data generated and uploaded to the server by the first object when operating the first terminal within the predetermined time period; a classification module, configured to classify each of the first data sets included in the first data set according to data attributes to obtain tuple data, wherein the first data sets include data with multiple different types of data attributes, and the data attributes of each tuple data set included in the tuple data set are of the same type; and a building module, configured to build the target data model based on the tuple data set.

[0151] In an optional embodiment, the analysis module 1606 includes: a first analysis unit, configured to analyze the distribution characteristics of each tuple data included in the tuple data; a first determination unit, configured to determine a first feature of each tuple data based on the distribution characteristics of each tuple data; and a second analysis unit, configured to analyze the target feature based on the first feature to obtain the analysis result.

[0152] In an optional embodiment, the first determining unit includes: a partitioning subunit, configured to partition each tuple data into one or more subgroup data based on the distribution characteristics of each tuple data; a first determining subunit, configured to determine a feature value for each of the one or more subgroup data; a second determining subunit, configured to determine the data attribute and the feature value of each subgroup data as a second feature of each subgroup data; and a third determining subunit, configured to determine a first feature of each tuple data based on the second feature of each subgroup data.

[0153] In an optional embodiment, the analysis module 1606 includes: a matching unit, configured to match each feature included in the first feature of each tuple data with the target feature to obtain a matching result; and a second determining unit, configured to determine the analysis result based on the matching result.

[0154] In an optional embodiment, the second determining module 1608 includes: a third determining unit, configured to determine the target feature value of the target feature; a fourth determining unit, configured to determine the target second feature as the matching feature when the analysis result indicates that the feature value of the target second feature included in the first feature meets the target feature value under a preset condition; and a fifth determining unit, configured to determine the identity of the target object based on the matching feature.

[0155] In an optional embodiment, the feature value of the second feature includes: the average value of the subgroup data corresponding to the second feature, and the variance of the subgroup data corresponding to the second feature; the preset condition includes: the difference between the target feature value and the average value is less than or equal to the variance.

[0156] In an optional embodiment, the second determining module 1608 includes: a sixth determining unit, configured to determine the matching data corresponding to the matching feature; and a seventh determining unit, configured to determine the identity of the object that generates the matching data by operating the first terminal as the identity of the target object.

[0157] In an optional embodiment, the above apparatus further includes: a push module, configured to push a message to the target object after determining the identity of the target object based on the matching features.

[0158] In an optional embodiment, the first acquisition module 1602 includes: an acquisition unit, configured to acquire data generated by the target object operating the first terminal within a preset time period and uploaded to the server, wherein the first terminal includes one or more terminals.

[0159] In an optional embodiment, the target data includes at least one of the following: first metadata, wherein the first metadata is used to indicate the identity attribute data of the target object; second metadata, wherein the second metadata is used to indicate the time attribute data of the target object operating the first terminal; third metadata, wherein the third metadata is used to indicate the location attribute data of the target object operating the first terminal; fourth metadata, wherein the fourth metadata is used to indicate the behavioral data that satisfies the association relationship generated by the target object operating the first terminal; and fifth metadata, wherein the fifth metadata is used to indicate the intent attribute data of the target object operating the first terminal.

[0160] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0161] Embodiments of this application also provide a computer-readable storage medium comprising a stored program, wherein the program, when executed, performs the steps of any of the method embodiments described above.

[0162] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0163] Embodiments of this application also provide an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0164] In one exemplary embodiment, 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.

[0165] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0166] 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.

[0167] 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 identity verification, characterized in that, include: Obtain target data of the target object, wherein the target data is data generated by the target object when operating the first terminal and uploaded to the server; Based on the target data, determine the target features of the target object; The target features are analyzed based on a pre-established target data model to obtain analysis results. The target data model is established based on data generated by the first object when it operates the first terminal within a predetermined time period in the past. The first object includes the target object. If the analysis results indicate that there is a matching feature in the target data model that matches the target feature, the identity of the target object is determined based on the matching feature; Before analyzing the target features based on a pre-established target data model to obtain the analysis results, the process includes: acquiring a first data group, wherein the first data group includes first data generated and uploaded to the server by a first object, including the target object, when operating the first terminal within a predetermined time period; classifying each piece of first data included in the first data group according to data attributes to obtain tuple data, wherein the first data includes data of multiple different types of data attributes, and the data attributes of each tuple data included in the tuple data are of the same type; and establishing the target data model based on the tuple data. The step of analyzing the target features based on a pre-established target data model to obtain analysis results includes: analyzing the distribution characteristics of each tuple data included in the tuple data; dividing each tuple data into one or more subgroup data based on the distribution characteristics of each tuple data; determining the feature value of each subgroup data included in one or more subgroup data; determining the data attribute and the feature value of each subgroup data as a second feature of each subgroup data; determining a first feature of each tuple data based on the second feature of each subgroup data; and analyzing the target features based on the first feature to obtain the analysis results.

2. The method according to claim 1, characterized in that, The target features are analyzed based on a pre-established target data model to obtain the following analysis results: Each feature included in the first feature of each tuple data is matched with the target feature to obtain a matching result; The analysis results are determined based on the matching results.

3. The method according to claim 2, characterized in that, Determining the identity of the target object based on the matching features includes: Determine the target feature value of the target feature; If the analysis results indicate that the feature value of the target second feature included in the first feature meets the preset condition with the target feature value, the target second feature is determined as the matching feature; The identity of the target object is determined based on the matching features.

4. The method according to claim 3, characterized in that, The eigenvalues ​​of the second feature include: the mean value representing the subgroup data corresponding to the second feature, and the variance representing the subgroup data corresponding to the second feature; The preset conditions include: the difference between the target feature value and the average value is less than or equal to the variance.

5. The method according to claim 1, characterized in that, Determining the identity of the target object based on the matching features includes: Determine the matching data corresponding to the matching feature; The identity of the object that generates the matching data by operating the first terminal is determined as the identity of the target object.

6. The method according to claim 1, characterized in that, After determining the identity of the target object based on the matching features, the method further includes: Push messages to the target object.

7. The method according to claim 1, characterized in that, The target data for obtaining the target object includes: The data generated by the target object operating the first terminal within a preset time period and uploaded to the server is obtained, wherein the first terminal includes one or more terminals.

8. The method according to any one of claims 1-7, characterized in that, The target data includes at least one of the following: First metadata, wherein the first metadata is used to indicate the identity attributes of the target object; The second metadata, wherein the second metadata is used to indicate the time attribute data of the target object operating the first terminal; Third metadata, wherein the third metadata is used to indicate the location attribute data of the target object operating the first terminal; The fourth metadata, wherein the fourth metadata is used to indicate the behavioral data that satisfies the association relationship generated by the target object through operating the first terminal; The fifth metadata, wherein the fifth metadata is used to indicate the intent attribute of the target object to operate the first terminal.

9. An identity verification device, characterized in that, include: The first acquisition module is used to acquire target data of the target object, wherein the target data is data generated by the target object when operating the first terminal and uploaded to the server. The first determining module is used to determine the target features of the target object based on the target data; An analysis module is used to analyze the target features based on a pre-established target data model to obtain analysis results, wherein the target data model is established based on data generated when a first object operates the first terminal within a predetermined time period in the past, and the first object includes the target object; The second determining module is used to determine the identity of the target object based on the matching feature when the analysis result indicates that there is a matching feature in the target data model that matches the target feature; The second acquisition module is used to acquire a first data group, wherein the first data group includes first data generated and uploaded to the server by a first object, including the target object, when operating the first terminal within a predetermined time period; classify each piece of first data included in the first data group according to data attributes to obtain tuple data, wherein the first data includes data of multiple different types of data attributes, and the data attributes of each tuple data included in the tuple data are of the same type; and establish the target data model based on the tuple data. The analysis module is further configured to analyze the distribution characteristics of each tuple data included in the tuple data; divide each tuple data into one or more subgroup data based on the distribution characteristics of each tuple data; determine the feature value of each subgroup data included in one or more subgroup data; determine the data attribute and the feature value of each subgroup data as a second feature of each subgroup data; determine the first feature of each tuple data based on the second feature of each subgroup data; and analyze the target feature based on the first feature to obtain the analysis result.

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

11. 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 method of any one of claims 1 to 8 through the computer program.

Images