WO2023165051A1 - Identity determination method, storage medium and electronic apparatus - Google Patents

Abstract

The present disclosure relates to the technical field of smart homes. Provided are an identity determination method, a storage medium and an electronic apparatus. The identity determination method comprises: acquiring target data of a target object, wherein the target data is data that is generated when the target object operates a first terminal, and is uploaded to a server; determining a target feature of the target object on the basis of the target data; analyzing the target feature on the basis of a pre-established target data model, so as to obtain an analysis result, wherein the target data model is established on the basis of data generated when a first object operates the first terminal within a past predetermined time period, and the first object comprises the target object; and when the analysis result indicates that there is a matching feature in the target data model that matches the target feature, determining an identity of the target object on the basis of the matching feature.

Description

Identity determination method, storage medium and electronic device

This disclosure claims the priority of the Chinese patent application with the application number 202210212279.4 and the title of the invention "identity determination method, storage medium and electronic device" filed with the China Patent Office on March 4, 2022, the entire contents of which are incorporated herein by reference. In public.

technical field

The present disclosure relates to the technical field of smart home, in particular, to an identity determination method, a storage medium and an electronic device.

Background technique

In recent years, the smart home industry has developed rapidly. People can use smart home products in different scenarios and applications, enabling smart products to interact with users anytime and anywhere, improving and improving the user's life experience. However, in the process of using smart devices at home, users often fail to register the user identity on the device side due to various reasons such as cumbersome user registration process or worry about user information leakage, resulting in the device being unable to identify the user identity information and unable to Make relevant information recommendations. There is also a situation where only one person in a multi-person family registers as a user, but the situation that multiple people in the family use the device will also lead to the problem that the identity of the real user cannot be accurately identified, and it will also cause inaccurate information push. That is, the accuracy rate of user identification in related technologies is relatively low.

Therefore, no effective solution has been proposed for the problem of how to improve the accuracy of user identification in related technologies.

Contents of the invention

Embodiments of the present disclosure provide an identity determination method and device, a storage medium, and an electronic device, so as to at least solve the problem of how to improve the accuracy of user identity recognition in the related art.

According to an embodiment of the present disclosure, an identity determination method is provided, including: acquiring target data of a target object, wherein the target data is generated by the target object when operating the first terminal and uploaded to data at the server end; 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 an analysis result, wherein the target data model is based on the first object established from data generated while operating the first terminal within a predetermined period of time in the past, the first object includes the target object; the analysis result indicates that there is a feature match with the target in the target data model In the case of the matching feature of the target object, the identity of the target object is determined based on the matching feature.

According to another embodiment of the embodiments of the present disclosure, there is also provided an identity determining device, including: a first acquisition module configured to acquire target data of a target object, wherein the target data is obtained by the target object in the second operation The data generated by a terminal and uploaded to the server; the first determination module is configured to determine the target characteristics of the target object based on the target data; the analysis module is configured to analyze the target based on a pre-established target data model features are analyzed to obtain an analysis result, wherein the target data model is established based on the data generated when the first object operates the first terminal in the past predetermined period, and the first object includes the target Object; a second determining module, configured to determine the identity of the target object based on the matching feature when the analysis result indicates that there is a matching feature matching the target feature in the target data model.

According to yet another embodiment of the embodiments of the present disclosure, there is also provided a computer-readable storage medium, the computer-readable storage medium includes a stored program, wherein, when the program is running, any one of the above-mentioned methods is implemented. steps in the example.

According to yet another embodiment of the embodiments of the present disclosure, there is also provided an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute any one of the above-mentioned The steps in the method embodiment.

Through the present disclosure, by acquiring the target data generated when the target object operates the first terminal the last time and determining the target features of the target object based on the target data, and then analyzing the target features based on the pre-established target data model, the target data model is based on It is established based on the data generated when the first object including the target object operates the first terminal in the past predetermined period, that is, the target data model is established based on the historical data of the first object. When the analysis result indicates that there are differences in the target data model In the case of matching features where the target features match, the identity of the target object can be determined based on the matching features. It achieves the purpose of identifying the identity of the target object based on the pre-established target data model when the target object is not registered, and can also realize the identification of each object based on the target data model when only one object is registered and multiple objects are used. The purpose of identifying the identity of each object, so as to further realize the purpose of pushing messages to each object. The problem of being unable to identify the user's identity or having a low identification accuracy rate existing in related technologies is solved, and the effect of improving the identification accuracy rate is achieved.

Description of drawings

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

In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, In other words, other drawings can also be obtained from these drawings without paying creative labor.

FIG. 1 is a schematic diagram of a hardware environment of an identity determination method according to an embodiment of the present disclosure;

Fig. 2 is the flow chart of the user identification method in the related art;

Fig. 3 is a flowchart of an identity determination method according to an embodiment of the present disclosure;

FIG. 4 is a flow chart of a method for identifying a user according to an embodiment of the present disclosure;

Fig. 5 is an example diagram 1 of data analysis of a body fat scale according to a specific embodiment of the present disclosure;

Fig. 6 is an example diagram 2 of body fat scale data analysis according to a specific embodiment of the present disclosure;

Fig. 7 is an example diagram 1 of water heater data analysis according to a specific embodiment of the present disclosure;

Fig. 8 is an example diagram 2 of water heater data analysis according to a specific embodiment of the present disclosure;

Fig. 9 is a third example of water heater data analysis according to a specific embodiment of the present disclosure;

Fig. 10 is an example diagram 4 of water heater data analysis according to a specific embodiment of the present disclosure;

Fig. 11 is an example diagram 1 of air-conditioning data analysis according to a specific embodiment of the present disclosure;

Fig. 12 is an example diagram 2 of air-conditioning data analysis according to a specific embodiment of the present disclosure;

Fig. 13 is a third example of air-conditioning data analysis according to a specific embodiment of the present disclosure;

Fig. 14 is an example diagram 4 of air-conditioning data analysis according to a specific embodiment of the present disclosure;

Fig. 15 is a schematic flowchart of a method for identifying a user identity according to an embodiment of the present disclosure;

Fig. 16 is a structural block diagram of an identity determination device according to an embodiment of the present disclosure;

Fig. 17 is a structural block diagram of an electronic device for implementing an identity determination method according to an embodiment of the present disclosure.

Detailed ways

In order to enable those skilled in the art to better understand the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only It is an embodiment of a part of the present disclosure, but not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present disclosure.

It should be noted that the terms "first" and "second" in the specification and claims of the present disclosure and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", as well as any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device comprising a sequence of steps or elements is not necessarily limited to the expressly listed instead, may include other steps or elements not explicitly listed or inherent to the process, method, product or apparatus.

According to an aspect of an embodiment of the present disclosure, a method for interacting with smart home devices is provided. The interaction method of the smart home device is widely used in smart home (Smart Home), smart home, smart home device ecology, smart house (Intelligence House) ecology and other intelligent digital control application scenarios of the whole house. Optionally, in this embodiment, the above-mentioned interaction method for smart home devices may be applied in a hardware environment composed of a terminal device 102 and a server 104 as shown in FIG. 1 . As shown in Figure 1, the server 104 is connected to the terminal device 102 through the network, and can be set to provide services (such as application services, etc.) for the terminal or the client installed on the terminal. To provide data storage services for the server 104, cloud computing and/or edge computing services can be configured on the server or independently of the server, and set to provide data computing services for the server 104.

The foregoing network may include but not limited to at least one of the following: a wired network and a wireless network. The above-mentioned wired network may include but not limited to at least one of the following: wide area network, metropolitan area network, and local area network, and the above-mentioned wireless network may include but not limited to at least one of the following: WIFI (Wireless Fidelity, Wireless Fidelity), Bluetooth. The terminal device 102 is not limited to PC, mobile phone, tablet computer, smart air conditioner, smart hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing device, smart dishwasher, smart projection device , smart TV, smart drying rack, smart curtain, smart video, smart socket, smart audio, smart speaker, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart sweeping robot, smart window cleaning robot, smart mopping robot, Smart air purification equipment, smart steamer, smart microwave oven, smart kitchen treasure, smart purifier, smart water dispenser, smart door lock, etc.

In the related technology, the user identification method needs to rely on the user being a registered user, as shown in Figure 2, which is a flow chart of the user identification method in the related technology, which requires the user to register the user identity on the device side in advance , the system generates and stores the user ID, and at the same time retains obvious user characteristic information on the device side; then, when the user subsequently uses the device, the device side automatically collects user behavior-related information, and needs to analyze and match the user characteristic information to identify the user. The user identification method in the related art has the following disadvantages: 1) if the user is not registered or the user characteristics are missing, the user identity cannot be identified; 2) if the user has registered on the device side, but during the use of the device, if multiple people , will generate different forms of use results, and will also cause difficulties in user identification.

An identity determination method is provided in this embodiment. FIG. 3 is a flowchart of an identity determination method according to an embodiment of the present disclosure. As shown in FIG. 3 , the process includes the following steps:

Step S302, acquiring target data of the target object, wherein the target data is generated by the target object when operating the first terminal and uploaded to the server;

Step S304, determining the target feature of the target object based on the target data;

Step S306, analyzing the characteristics of the target based on a pre-established target data model to obtain an analysis result, wherein the target data model is generated based on the operation of the first terminal by the first subject in the past predetermined period of time data, the first object includes the target object;

Step S308, if the analysis result indicates that there is a matching feature matching the target feature in the target data model, determine the identity of the target object based on the matching feature.

Through the above steps, by obtaining the target data generated when the target object operates the first terminal the last time and determining the target features of the target object based on the target data, and then analyzing the target features based on the pre-established target data model, the target data model is based on It is established based on the data generated when the first object including the target object operates the first terminal in the past predetermined period, that is, the target data model is established based on the historical data of the first object. When the analysis result indicates that there are differences in the target data model In the case of matching features where the target features match, the identity of the target object can be determined based on the matching features. It achieves the purpose of identifying the identity of the target object based on the pre-established target data model when the target object is not registered, and can also realize the identification of each object based on the target data model when only one object is registered and multiple objects are used. The purpose of identifying the identity of each object, so as to further realize the purpose of pushing messages to each object. The problem of being unable to identify the user's identity or having a low identification accuracy rate existing in related technologies is solved, and the effect of improving the identification accuracy rate is achieved.

Wherein, the executor of the above steps may be a server, or a server, or a cloud, for example, a data computing server, or a processor configured on a storage device with human-computer interaction capabilities, or a processing device with similar processing capabilities or processing units, etc., but not limited thereto. The following takes the data calculation server to perform the above operations as an example (it is only an exemplary description, and other devices or modules can also be used to perform the above operations in actual operation):

In the above embodiment, the data calculation server acquires the 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, in The first terminal is an air conditioner as an example. The target data can include data such as the time when the target object turns on the air conditioner, the temperature of the air conditioner, the mode of the air conditioner, and the location of the air conditioner. Of course, if the target object is a registered user, the target data includes It 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; and then determine the target feature of the target object based on the target data, and the target feature It can be the behavior characteristic of the target object operating the first terminal, such as turning on the air conditioner, setting the parameters of the air conditioner, etc. The target characteristic can also be the time characteristic of the target object operating the first terminal, for example, every night at 8 o'clock or in the morning at 6 o'clock Zhong et al. Of course, the target feature can also be other features. In addition, the target feature can include one feature or multiple features; then analyze the target feature based on the pre-established target data model to obtain the analysis result. The target data model It is established on the data generated when the first object including the above-mentioned target object operates the first terminal in the past predetermined period (such as one month, or 7 days, or 10 days, or other periods), that is, the target data The model is established based on the historical data of multiple objects. Among the multiple objects, only one object may be a registered user, or multiple objects may be unregistered users. In practical applications, the historical data of multiple objects can be Data analysis, for example, analyze the distribution characteristics of historical data to obtain the characteristics of one or more objects; when the analysis results indicate that there are matching characteristics in the target data model that match the target characteristics, it can be determined based on the matching characteristics The identity of the target audience. It achieves the purpose of identifying the identity of the target object based on the pre-established target data model when the target object is not registered, and can also realize the identification of each object based on the target data model when only one object is registered and multiple objects are used. The purpose of identifying the identity of each object, so as to further realize the purpose of pushing messages to each object. The problem of being unable to identify the user's identity or having a low identification accuracy rate existing in related technologies is solved, and the effect of improving the identification accuracy rate is achieved.

In an optional embodiment, before analyzing the target feature based on a pre-established target data model to obtain an analysis result, the method includes: acquiring a first data set, wherein the first data set Including the first data generated by the first object when operating the first terminal within the predetermined period and uploaded to the server; according to the data attribute, each of the The first data is classified 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 the same type; building the target data model based on the tuple data. In this embodiment, before analyzing the target characteristics of the target object, the target data model is first established, for example, the first object (that is, a plurality of objects) including the target object is first obtained within a predetermined period of time in the past (such as a month, or 7 days, or 10 days, or other time periods), the data generated when operating the first terminal, that is, the first data group is the historical data of multiple objects, and these historical data are uploaded to the server. The first data group includes a plurality of first data, for example, the first data is a piece of data generated by a certain user operating a certain device or terminal (such as an air conditioner, or a water heater) at a certain time in the past, and the first data includes a variety of different types The data of the data attribute, for example, the first data includes the data of the time attribute, or the data of the location attribute, or the data of the behavior attribute, etc. Of course, if the user is a registered user, the first data may also include the user attribute data, and classify each first data included in the first data group according to the data attribute to obtain multi-group data, and each tuple data included in the multi-group data represents data of one of the data attributes, and then, Build a target data model based on multigroup data. For example, in practical applications, tuple data may include part or all of user tuple data, time tuple data, location tuple data, context tuple data, intent tuple data, etc., wherein context tuple data is used It is used to represent continuous behavior information such as the current behavior of the object, the previous behavior, and the next behavior. Through this embodiment, the purpose of establishing the target data model based on the historical data of the object is realized.

In an optional embodiment, analyzing the target features based on a pre-established target data model to obtain an analysis result includes: analyzing the distribution characteristics of each of the tuple data included in the tuple data ; determining a first feature of each of the tuple data based on the distribution feature of each of the tuple data; analyzing the target feature based on the first feature to obtain the analysis result. In this embodiment, by analyzing the distribution characteristics of each tuple data included in the tuple data, for example, each tuple data includes one or more objects generated by operating the first terminal multiple times in the past predetermined period of time Analyze the distribution characteristics of these data, that is, analyze the distribution characteristics of each tuple data, and then determine the first feature of each tuple data based on the distribution characteristics of each tuple data. Take the data reported by water heaters as an example For example, there are two users in a family who use the water heater at different times. One of them is used to setting the temperature to about 45°C every time he turns on the water heater, while the other is used to adjusting the temperature to about 40°C every time he turns on the water heater. In this way, 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. For example, the behavior of turning on the water heater and the set temperature parameters are used as the first feature of the corresponding tuple data, so that when the two users operate the device next time, the generated data can also identify each user's Identity, it should be noted that here we only take the behavior of turning on the water heater and setting temperature parameters as an example. In practical applications, data of multiple behavior attributes can be included, for example, the previous behavior and the next behavior related to the current behavior. Behavior, etc. The tuple data can include multiple first features, and can also include first features of other tuple data, such as time tuple data, location tuple data, etc., and optionally, user-to-multiple The first feature of each tuple data in the tuple data generated by the continuous operation behavior of a terminal, and then analyze based on the first feature and the target feature to obtain the analysis result. Through this embodiment, it is realized that the first feature of each tuple data is determined by analyzing the distribution characteristics of each tuple data included in the tuple data, and the target feature is analyzed based on the first feature to obtain the analysis The purpose of the result.

In an optional embodiment, determining the first feature of each of the tuple data based on the distribution feature of each of the tuple data includes: dividing each of the tuple data based on the distribution feature of each of the The tuple data is divided into one or more subgroup data; determining the feature value of each of the subgroup data included in one or more of the subgroup data; combining the data attributes of each of the subgroup data with The feature value is determined as a second feature of each of the subgroup data; and the first feature of each of the tuple data is determined based on the second feature of each of the subgroup data. In this embodiment, each tuple data is grouped according to the distribution characteristics of each tuple data, and the behavior attribute tuple data (or called context tuple data) is taken as an example, combined with the aforementioned turning on the water heater as an example for illustration , the tuple data includes the data generated by two unregistered users when they operated the water heater for many times in the past. One of them is used to setting the temperature to about 45°C every time he turns on the water heater, while the other is used to setting the temperature to about 45°C every time he turns on the water heater. Adjust it to about 40°C. In this way, according to the distribution characteristics of all the data included in the tuple data, the tuple data can be divided into two subgroup data, where each subgroup data corresponds to a user, and the user's behavior status value Corresponding to the above 45°C and 40°C respectively, each user’s comfort state value can be used as the feature value corresponding to each subgroup data, and then the feature value and the data attribute of the subgroup data are determined as the second feature, for example, The second feature can be the behavior of turning on the water heater, and the feature value is 45°C. Optionally, in practical applications, because there may be a little difference in each operation of each user, it can be based on multiple histories The average value and variance of the data are obtained. When the eigenvalue of the target feature of the data generated when an object operates the water heater next time and the eigenvalue of the second feature are within a certain range of error, it can be confirmed that the object is the above-mentioned first. The user corresponding to the subgroup data where the two features are located; after determining the second feature of each subgroup data, the first feature of each tuple data can be determined, and the first feature can include one or more second features, In the same way, the first features of other tuple data in the tuple data can also be obtained. Through this embodiment, the purpose of determining the first feature of each tuple data based on the distribution feature of each tuple data is achieved.

In an optional embodiment, analyzing the target features based on a pre-established target data model to obtain an analysis result includes: combining each feature included in the first feature of each of the tuple data with the The target features are matched to obtain a matching result; the analysis result is determined based on the matching result. In this embodiment, each feature included in the first feature of each tuple data is matched with the target feature to obtain a matching result. The first feature may include one or more second features, that is, each of the first features The two features are respectively matched with the target feature. For example, when the eigenvalue of the second feature and the eigenvalue of the target feature meet the preset conditions, such as the error is within the preset range, the second feature can be considered to match the target feature. If the preset condition is not satisfied between the eigenvalue of the second feature and the eigenvalue of the target feature, it is considered that the second feature does not match the target feature. Through this embodiment, the purpose of analyzing each feature included in the first feature to the target feature to obtain an analysis result is achieved.

In an optional embodiment, determining the identity of the target object based on the matching feature includes: determining a target feature value of the target feature; If the feature value of the second feature and the target feature value meet a preset condition, the target second feature is determined as the matching feature; and the identity of the target object is determined based on the matching feature. In this embodiment, the target feature value of the target feature is determined based on the data generated by the target object's current operation of the first terminal, for example, the behavior state value of turning on the air conditioner is 26°C. Optionally, in practical applications, The matching feature may comprise a plurality of second features of tuple data, for example, a plurality of second features comprising two tuple data of the tuple data, such as time tuple data and context tuple data (or behavior attribute tuple data), or multiple second features including three tuple data in tuple data, such as time tuple data, location tuple data and context tuple data (or behavior attribute tuple data ), can also include multiple second features of more tuple data, and the target feature value can 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 It can also include the feature value of the position attribute of the target object's operation behavior, such as the living room, or the study room, etc., when the above analysis results indicate that there is a preset condition between the feature value of the target second feature and the target feature value in the first feature Next, the target second feature can be determined as the matching feature, and 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. Through this embodiment, the purpose of determining the identity of the target object by determining the matching features is achieved.

In an optional embodiment, the feature value of the second feature includes: an average value used to represent the subgroup data corresponding to the second feature, used to represent the subgroup corresponding to the second feature The variance of the data; 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 eigenvalue of the second feature may include the mean and/or variance of the subgroup data corresponding to the second feature. In practical applications, each subgroup of data may include a plurality of data, which can be analyzed to obtain The data distribution feature information such as the maximum value, minimum value, average value, and variance of these data, after determining the target feature based on the target data of the current secondary target object, if the difference between the target feature value and the above average value is less than or equal to the variance , it is considered that the eigenvalue of the target second feature and the target eigenvalue meet the preset condition. Through this embodiment, the purpose of the preset condition that needs to be satisfied when determining the matching feature is achieved.

In an optional embodiment, determining the identity of the target object based on the matching feature includes: determining matching data corresponding to the matching feature; an object that will generate the matching data by operating the first terminal The identity of is determined 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 generating the matching data is determined as the identity of the target object. data, the matching data may include the data generated by the object in the past multiple operations. In practical applications, the matching feature may include a second feature (that is, the second feature corresponding to the aforementioned subgroup data), and the matching feature may also include A plurality of second features, such as the second features corresponding to the subgroup data included in the multiple tuple data, for example, the time tuple data may include multiple subgroup data, and each subgroup data has a corresponding second feature , meanwhile, multiple subgroup data may also be included in the context attribute tuple data (or behavior attribute tuple data), and each subgroup data has a corresponding second feature, so that the matching feature can include data from different data attributes (or Multiple second features for matching from different angles), that is, based on the target data model, it is determined that there is a data set (multiple pieces of data generated by multiple operations) in the historical data. The feature of one of the tuple data matches the target feature, or When the features of multiple tuple data match the features of the target, the data set can be determined as matching data, and then the identity of the object corresponding to the matching data can be determined as the identity of the target object. Through this embodiment, the purpose of determining the identity of the target object is achieved.

In an optional embodiment, after determining the identity of the target object based on the matching feature, the method further includes: pushing a message to the target object. In this embodiment, after the identity of the target object is determined, a message can be pushed to the target object. In practical applications, when multiple objects are not registered or only one object is registered, the identity of each object can be identified After that, push personalized messages to different objects in a targeted manner. Through this embodiment, the purpose of pushing personalized messages to users is achieved.

In an optional embodiment, obtaining the 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 A 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, an air conditioner and a TV, or other multiple terminals, and the target data may include the target object in the preset The data generated by operating the first terminal within the duration, for example, the data generated by the target object continuously operating the air conditioner and TV within 1 minute (or 2 minutes, or other duration), and if the target data model also includes a certain object The identity of the target object can be determined based on the characteristics of the data generated by the continuous operation of multiple terminals within a preset period of time. Through this embodiment, the purpose of determining the identity of the target object is achieved based on the continuous behavior of operating multiple terminals of the target object.

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 of the target object; second metadata, Wherein, the second metadata is used to indicate data of the time attribute of the target object operating the first terminal; the third metadata is used to indicate that the target object operates the The data of the location attribute of the first terminal; the fourth metadata, wherein the fourth metadata is used to indicate the behavior data that satisfies the association relationship generated by the target object by operating the first terminal; the fifth metadata , wherein the fifth metadata is used as data indicating an attribute of the target object's intention to operate the first terminal. In this embodiment, the target data includes unary or multivariate data, and each metadata is used to represent different attributes of the target object. Similarly, the first object including the target object stored on the server has operated the first The data generated by the terminal also includes unary or multivariate data. Through this embodiment, the purpose of more accurately determining the identity of the target object by acquiring diversified target data is achieved.

In order to better understand the process of the above-mentioned identity determination method, the flow of the above-mentioned identity determination method will be described below in combination with optional embodiments, but it is not used to limit the technical solutions of the embodiments of the present disclosure.

In this embodiment, a user identity recognition method is provided. FIG. 4 is a flowchart of a user identity recognition method according to an embodiment of the present disclosure, as shown in FIG. 4 , specifically as follows:

S402, acquiring user behavior information: based on each device terminal (corresponding to the aforementioned first terminal), collect related information such as user information, family information, location information, environment information, device information, and user behavior. Related information includes not only basic user information such as user age, birthday, and body fat, but also continuous or historical behavior information such as current behavior, previous behavior, and next behavior; it also includes information such as family information, environmental information, and device status information;

S404, constructing a multi-tuple data model, optionally, the multi-tuple data model can be a two-tuple data model, or a three-tuple data model, or a four-tuple data model, or a five-tuple data model; Taking the data model as an example, all the element information obtained in the above step S402 is divided into five tuples to construct a user five-tuple data model. User quintuples are user tuples, time tuples, location tuples, context tuples, and intent tuples; in practical applications, a unified data model can be designed, including unified storage formats, unified codes, unified units, etc., for example , the units of data obtained from different devices may be inconsistent, and some are 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. To unify, for example, the user may turn on the air conditioner through remote control or APP or voice, and the behavior coding of the same operation behavior (that is, turning on the air conditioner) generated by different methods may be inconsistent, and unified coding can also be carried out for this;

S406, analyze and organize each tuple information of the user quintuple, and obtain the distribution feature information of the relevant tuple data, for example, the analysis of the context tuple in Figure 4 may also include other tuple data in the quintuple to analyze;

S408, according to the user quintuple analysis results, correlate and match existing user characteristics and behavior characteristics, the user characteristics in this step are user characteristics determined based on historical data, if the user has registered user information, the user characteristics can be determined Information, if the user is not registered, the behavior characteristics of different users can be determined based on historical data, and then the target characteristics of the data generated based on the current user operation behavior can be associated and matched with existing user characteristics and behavior characteristics to identify the current user identity information;

S410, further, push relevant recommendation messages according to the identity of the user.

The relevant terms in this embodiment are explained below:

U: user attribute information set (corresponding to the aforementioned first metadata); u(x) represents a certain user attribute, and u(u_1,u_2,...,u_k ₁ ) represents the 1st to k _1th attributes of the user. For example, a user contains attributes such as age, gender, and occupation information;

T: time attribute information set (corresponding to the aforementioned second metadata); t(x) represents the time attribute of a certain user behavior, and t(t_1,t_2,...,t_k ₂ ) represents the 1st to k ₂ attributes of time . For example, the year, month, day, hour and other attributes of the user behavior;

A: location attribute information set (corresponding to the aforementioned third metadata); a(x) represents the location attribute of a certain user behavior, a(a_1,a_2,...,a_k ₃ ) represents the 1st to k ₃ attributes of the location . For example, attributes such as provinces, cities, districts and counties, and rooms to which user behaviors belong;

L: context attribute information set (corresponding to the aforementioned fourth metadata); l(x) represents the context attribute of a certain user behavior, l(l_1,l_2,...,l_k ₄ ) represents the 1st to k ₄ features of the context . For example, the user's previous behavior, current behavior, current weather, current device power-on status and other attributes;

I: intent attribute information set (corresponding to the aforementioned fifth metadata); i(x) represents a certain user intent attribute, and i(i_1,i_2,...,i_k ₅ ) represents the 1st to k _5th attributes of user intent. For example, open the curtains, turn on the lights, increase the wind speed and other attributes;

F: five-tuple attribute information set; f_x(u_1,t_1,a_1,l_1,i_1,…) indicates that user u_1 and the corresponding user behavior time attribute 1 is t_1, address location attribute 1 is a_1, and context attribute 1 is l_1 ; Get the fifth tuple i_1 according to the first four tuples. For example, f_1(u_1, t_1, a_1, l_1, i_1) indicates that the user: 'Zhang San', the corresponding user time attribute is "2021-10-20", the location attribute is "living room", and the context attribute is "too cold" , to predict the user behavior intention as "turn on the air conditioner".

Each step in the above-mentioned embodiment is described in detail below:

1. Information collection (corresponding to the above step S402)

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

1.2 The collected information includes but is not limited to user information, family information, location information, environmental information, device information, user behavior and other related information;

2. Generating the five-tuple data model (corresponding to the above step S404)

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

2.1 User: user ID information, user characteristic information, etc.;

2.2 Time: Behavior time series; including user behavior time stamp, year, month, day, hour and other information of behavior time;

2.3 Location: behavior location address information; including the space to which the user behavior belongs, such as 'living room'; also includes information such as the province, city, district, county, and community to which the behavior belongs;

2.4 Context: Information such as pre- and post-sequential behavior, pre-sequence behavior status, user or network device portrait, weather and air quality;

2.5 Intent: Data predicts follow-up behavior information.

3. Multiple group data analysis (corresponding to the above step S406)

3.1 Non-user tuple data analysis

For the case that the user is not registered, that is, the user tuple data is not included, the time tuple information, location tuple information, and context information are counted and analyzed.

A) Context tuple analysis: For example, analyze the "behavior state value" attribute in the "context" tuple: for the same behavior of different users, the "behavior state value" attribute will present different characteristic state distributions. According to the data distribution form, the data is grouped; the data statistics such as maximum value, minimum value, average value and variance are performed on the grouped data.

For example, two people in a family are weighed using a body fat scale. The body fat scale reports two weight record information every day. Table 1 is the data record information reported by the body fat scale, as shown in Table 1.

Table 1

serial number	time (day)	Behavior	Behavior status value (unit: catties)
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

Fig. 5 is an example of data analysis of a body fat scale according to a specific embodiment of the present disclosure Fig. 1. Through data analysis, it can be known that the recorded data are clearly divided into two groups of data;

1. Group 1: Data with serial numbers 1, 3, 5, 7 and weight data of 98, 100, 99, 98 are divided into one group;

2. Group 2: Data with serial numbers 2, 4, 6, 8 and body weight data of 135, 134, 133, 134 are divided into one group;

The body fat scale data is equivalent to one of the tuple data included in the aforementioned tuple data, and the data in group 1 and group 2 is equivalent to one or more subgroup data included in the aforementioned tuple data, that is, group 1 corresponds to a Subgroup data, group 2 corresponds to another subgroup data;

After grouping, the data distribution characteristics are analyzed, as shown in Figure 6, Figure 6 is an example of body fat scale data analysis Figure 2 according to a specific embodiment of the present disclosure, and can be obtained by grouping data analysis:

1. Data analysis of group 1: the data distribution characteristic information such as the maximum value, minimum value, average value and variance of the group data can be obtained;

2. Group 2 data analysis: the data distribution characteristic information such as the maximum value, minimum value, average value and variance of the group data can be obtained;

It should be noted that after the distribution characteristics of each grouped data are determined, the behavioral characteristics (ie, weighing behavior) and the characteristic values of the behavioral characteristics (including the above-mentioned average value and variance) of the user corresponding to each grouped 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 identification; therefore, in the current time a certain user ( Equivalent to the aforementioned target object) when the weighing behavior occurs and the generated state value of the behavior matches the behavior characteristics and characteristic values corresponding to the above-mentioned group data, the user corresponding to the group data can be determined as the current target object identity, thus achieving the purpose of determining the identity of the target object.

B) Time and context tuple analysis: For example, analyze the "time stamp" attribute in the "time" tuple and the "behavior state value" attribute in the "context" tuple: for the same behavior of different users, the "time stamp" attribute and The Behavioral State Value attribute presents different characteristic state distributions. According to the data distribution form, the data is grouped; the grouped data is counted on the maximum value, minimum value, average value, variance and other data.

For example, there are two people in the family who use the water heater to take a bath at different time periods. The water heater reports the operation record information every day. Table 2 is the data record information reported by the water heater, as shown in Table 2.

Table 2

serial number	Boot time (minutes)	Behavior	Behavior status value (unit: ℃)
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

Fig. 7 is a water heater data analysis example Fig. 1 according to a specific embodiment of the present disclosure. Through data analysis, it can be known that the recorded data are clearly divided into two groups of data;

1. Group 1: The data with serial numbers 1, 3, 5, 7 and outlet water temperature values of 46, 47, 46, 48 are divided into one group;

2. Group 2: The data with serial numbers 2, 4, 6, 8 and outlet water temperature values of 40, 39, 40, 38 are divided into one group;

After grouping, analyze the distribution characteristics of water heater outlet temperature data, as shown in Figure 8, Figure 8 is an example of water heater data analysis Figure 2 according to a specific embodiment of the present disclosure; similarly, after grouping, analyze the data distribution characteristics of the water heater start-up time point , as shown in FIG. 9, FIG. 9 is an example of water heater data analysis according to a specific embodiment of the present disclosure; FIG. Figure 4 is an example of water heater data analysis; through group data analysis, you can get:

1. Data analysis of group 1: the data distribution characteristic information such as the maximum value, minimum value, average value and variance of the group data can be obtained;

2. Group 2 data analysis: the data distribution characteristic information such as the maximum value, minimum value, average value and variance of the group data can be obtained;

It should be noted that, in combination with FIG. 10, it can be known that group 1 and group 2 in this embodiment (water heater) include multiple tuple data, such as time tuple data and context tuple data. The same method as above determines the distribution characteristics of each grouped data, thereby determining the behavior characteristics of the user corresponding to each grouped data, the time attribute characteristics of the behavior, etc., which is equivalent to determining a plurality of second characteristics, and then can be based on A plurality of second features determines whether there is a matching feature that matches the target feature of the current target object, and the identity of the target object can be determined when it is determined to exist. Through this embodiment, the distribution characteristics of the multi-group data are combined to improve the determination of the target. The accuracy of the object's identity.

C) Location and context tuple analysis: For example, analyze the "room" attribute in the "location" tuple and the "behavior state value" attribute in the "context" tuple: for the same behavior of different users, the "room" attribute and the "behavior State value" attribute will present different characteristic state distributions. According to the data distribution form, the data is grouped; the data statistics such as maximum value, minimum value, average value and variance are performed on the grouped data.

D) Time, location, and context tuple analysis: For example, analyze the "time stamp" attribute in the "time" tuple, the "room" attribute in the "location" tuple, and the "behavior state value" attribute in the "context" tuple : For the same behavior of different users, the "time stamp" attribute, "room" attribute and "behavior state value" attribute will present different feature state distributions. According to the data distribution form, the data is grouped; the data statistics such as maximum value, minimum value, average value and variance are performed on the grouped data.

For example, two people in a family use the air conditioner at different times and in different spaces. The air conditioner reports the operation record information every day. Table 3 is the data record information reported by the air conditioner, as shown in Table 3.

table 3

serial number	time (hours)	Location	Behavior	Behavior status value (unit: ℃)
1	2021-10-01 18:00:00	living room		target temperature	26
2	2021-10-01 20:04:00	study	target temperature	twenty two
3	2021-10-02 18:05:00	living room		target temperature	27
4	2021-10-02 20:03:00	study	target temperature	twenty one
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	twenty one

Fig. 11 is an example of air-conditioning data analysis Fig. 1 according to a specific embodiment of the present disclosure. Through data analysis, it can be known that the recorded data are clearly divided into two groups of data;

1. Group 1: Data with sequence numbers 1, 3, 5, 7 and target temperature values of 26, 27, 26, 28 are divided into one group;

2. Group 2: The data with serial numbers 2, 4, 6, 8 and target temperature values of 20, 22, 21, 21 are divided into one group;

After grouping, analyze the distribution characteristics of air conditioner target temperature data, as shown in Figure 12, Figure 12 is an example of air conditioner data analysis Figure 2 according to a specific embodiment of the present disclosure; similarly, after grouping, analyze the data distribution characteristics of the air conditioner start-up time point , as shown in Figure 13, Figure 13 is an example of air-conditioning data analysis Figure 3 according to a specific embodiment of the present disclosure; and then the distribution characteristics of the air-conditioning operation data are synthesized, as shown in Figure 14, Figure 14 is according to a specific embodiment of the present disclosure An example of air-conditioning data analysis is shown in Figure 4; through grouped data analysis, it can be obtained:

1. Data analysis of group 1: the data distribution characteristic information such as the maximum value, minimum value, average value and variance of the group data can be obtained;

2. Group 2 data analysis: the data distribution characteristic information such as the maximum value, minimum value, average value and variance of the group data can be obtained;

It should be noted that, in combination with FIG. 14, it can be known that group 1 and group 2 in this embodiment (air conditioner) include a plurality of tuple data, such as time tuple data, location tuple data, context tuple data, for each The tuple data uses the same method as above to determine the distribution characteristics of each group data, so as to determine the user's behavior characteristics corresponding to each group data, the time attribute characteristics of the behavior, the location attribute characteristics of the behavior, etc., that is It is equivalent to determining a plurality of second features, and then it can be determined based on the plurality of second features whether there is a matching feature that matches the target feature of the current target object, and the identity of the target object can be determined if it exists. For example, combining the distribution characteristics of multi-group data to improve the accuracy of determining the identity of the target object.

3.2 Five-tuple data analysis

Horizontally pull related information such as time tuple information, location tuple information, context information, and user information, and associate behavior data value distribution characteristics and related tuple attribute characteristics with user tuple information to form user behavior value distribution feature (corresponding to the aforementioned second feature).

4. User identification (corresponding to the above step S408)

According to the analysis of the new features of the five-tuple (corresponding to the target features of the aforementioned target object), it is associated and matched with the known user features and behavioral features to identify the user identity. If the user uses the device for the first time, uploads the first usage record information, and has no historical user identification information, then newly establishes user characteristics and user behavior characteristic information, so that it can be associated and matched with it in subsequent user identification.

4.1 Recognition based on context tuples: According to the analyzed context tuple information characteristics, and the user's behavior state value attribute distribution characteristics, it is associated and matched with known user characteristics and user behavior characteristics to identify user identity information;

4.2 Recognition based on time and context tuples: According to the analyzed time and context tuple information characteristics, as well as the user's behavior state value attribute distribution characteristics, correlate and match with known user characteristics and user behavior characteristics, and identify user identity information;

4.3 Identification based on location and context tuples: According to the analyzed location and context tuple information characteristics, as well as the distribution characteristics of the user's behavior state value attribute, it is associated and matched with known user characteristics and user behavior characteristics to identify user identity information;

4.4 Recognition based on time, location, and context tuples: According to the analyzed time, location, and context tuple information characteristics, as well as user behavior state value attribute distribution characteristics, correlate and match with known user characteristics and user behavior characteristics, and identify user identity information;

The above-mentioned known user characteristics and behavior characteristics refer to those determined based on historical data. Among them, if the user has registered user information, the user characteristic information can be determined, and the user’s behavior characteristics can also be determined. If the user has not registered, it can be determined based on historical data. Identify behavioral characteristics of different users;

5. User message push (corresponding to the above step S410)

According to the information push rules, the personalized recommendation message that matches the user's identity is pushed to the user.

Fig. 15 is a schematic flow diagram of a method for identifying a user identity according to an embodiment of the present disclosure. As shown in Fig. 15 , the flow includes the following steps:

S1502, user behavior information is uploaded to the cloud server (corresponding to the aforementioned server), including the operation behavior information of the current secondary user uploaded to the cloud server, and the historical data of the current secondary user and other users are also uploaded to the cloud server, and the user behavior information includes multidimensional data (i.e. multivariate data);

S1504, the data landing, the data calculation server obtains the data from the cloud server;

S1506, constructing a user quintuple model;

S1508, analyzing the quintuple data;

S1510, identifying the identity of the user based on the quintuple data analysis;

S1512, transmitting the data to the cloud server, and transmitting the identification result to the cloud server;

S1514. The cloud server sends a recommendation message to the user client.

Through the above embodiments, during the process of using the smart device by the user, information of each element can be collected from multiple user terminals to generate a user quintuple data model. Based on the user quintuple, the statistics of the "behavior status value" information in the "context" tuple can be analyzed, and the user identity can be identified according to the value distribution characteristics matching the user's related value characteristics. It can avoid the problem of not being able to identify the user's identity caused by the user not registering the device, or missing user attributes, or one person registering for the whole family to use. In this embodiment, by combing and analyzing various collected information, a quintuple data model is constructed, and based on the user quintuple model, the association relationship of each tuple and the matching with the user are analyzed to identify the user identity information, thereby having Push messages in a targeted manner.

Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the technical solution of the present disclosure can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as ROM/RAM, disk, CD) contains several instructions to make a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) execute the method of each embodiment of the present disclosure.

Fig. 16 is a structural block diagram of an identity determination device according to an embodiment of the present disclosure, as shown in Fig. 16 , including:

The first obtaining module 1602 is configured to obtain the target data of the target object, wherein the target data is generated by the target object when operating the first terminal and uploaded to the data of the server;

The first determining module 1604 is configured to determine the target feature of the target object based on the target data;

The analysis module 1606 is configured to analyze the characteristics of the target based on a pre-established target data model to obtain an analysis result, wherein the target data model is based on when the first subject operates the first terminal in the past predetermined period created from the generated data, the first object includes the target object;

The second determining module 1608 is configured to determine the identity of the target object based on the matching feature if the analysis result indicates that there is a matching feature matching the target feature in the target data model.

In an optional embodiment, the above-mentioned device further includes: a second acquisition module, configured to acquire the first data group before analyzing the target features based on a pre-established target data model to obtain the analysis result, wherein , the first data group includes the first data generated when the first object operates the first terminal within the predetermined period of time and uploaded to the server; the classification module is configured to classify the data according to data attributes Each of the first data included in the first data group is classified to obtain multi-group data, wherein the first data includes data of a plurality of different types of data attributes, and the multi-group data included The data attributes of each tuple data are of the same type; the building module is configured to build the target data model based on the tuple data.

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

In an optional embodiment, the above-mentioned first determination unit includes: a dividing subunit, configured to divide each of the tuple data into one or more subgroup data based on the distribution characteristics of each of the tuple data; The first determination subunit is configured to determine the feature value of each of the subgroup data included in one or more of the subgroup data; the second determination subunit is configured to determine the feature value of each of the subgroup data The data attribute and the feature value are determined as the second feature of each of the subgroup data; the third determining subunit is configured to determine each of the elements based on the second feature of each of the subgroup data The first feature of the group data.

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; A determination unit configured to determine the analysis result based on the matching result.

In an optional embodiment, the above-mentioned second determination module 1608 includes: a third determination unit configured to determine the target feature value of the target feature; a fourth determination unit configured to determine the target feature value when the analysis result indicates the first When the feature value of the target second feature included in a feature and the target feature value meet a preset condition, determine the target second feature as the matching feature; the fifth determining unit is configured to The matching feature determines the identity of the target object.

In an optional embodiment, the feature value of the above-mentioned second feature includes: an average value used to represent the subgroup data corresponding to the second feature, used to represent the subgroup data corresponding to the second feature variance; the preset condition includes: the difference between the target feature value and the average value is less than or equal to the variance.

In an optional embodiment, the above-mentioned second determination module 1608 includes: a sixth determination unit configured to determine the matching data corresponding to the matching feature; a seventh determination unit configured to operate the first terminal And the identity of the object generating the matching data is determined as the identity of the target object.

In an optional embodiment, the above apparatus further includes: a push module configured to push a message to the target object after the identity of the target object is determined based on the matching feature.

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.

In an optional embodiment, the above target data includes at least one of the following: first metadata, wherein the first metadata is used to indicate the identity attribute of the target object; second metadata, wherein , the second metadata is used to indicate data of the time attribute of the target object operating the first terminal; third metadata, wherein the third metadata is used to indicate that the target object operates the first terminal The data of the location attribute of a terminal; the fourth metadata, wherein the fourth metadata is used to indicate the behavior data that satisfies the association relationship generated by the target object by operating the first terminal; the fifth metadata, Wherein, the fifth metadata is used as data indicating an attribute of the target object's intention to operate the first terminal.

It should be noted that the above-mentioned modules can be realized by software or hardware. For the latter, it can be realized by the following methods, but not limited to this: the above-mentioned modules are all located in the same processor; or, the above-mentioned modules can be combined in any combination The forms of are located in different processors.

Embodiments of the present disclosure also provide a computer-readable storage medium, where the computer-readable storage medium includes a stored program, wherein, when the program is run, the steps in any one of the above method embodiments are executed.

In an exemplary embodiment, the above-mentioned computer-readable storage medium may include but not limited to: U disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM) ), mobile hard disk, magnetic disk or optical disk and other media that can store computer programs.

According to yet another aspect of the embodiments of the present disclosure, there is also provided an electronic device for implementing the above identity determination method. As shown in FIG. 17, the electronic device includes a memory 1702 and a processor 1704, and the memory 1702 stores computer program, the processor 1704 is configured to execute the steps in any one of the above method embodiments through a computer program.

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

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

S1. Obtain target data of the target object, wherein the target data is generated by the target object when operating the first terminal and uploaded to the server;

S2. Determine target features of the target object based on the target data;

S3. Analyze the target feature based on a pre-established target data model to obtain an analysis result, wherein the target data model is based on data generated by the first object when operating the first terminal within a predetermined period of time in the past established, the first object includes the target object;

S4. If the analysis result indicates that there is a matching feature that matches the target feature in the target data model, determine the identity of the target object based on the matching feature.

Optionally, those of ordinary skill in the art can understand that the structure shown in FIG. Internet Devices, MID), PAD and other terminal equipment. FIG. 17 does not limit the structure of the above-mentioned electronic device. For example, the electronic device may also include more or less components than those shown in FIG. 17 (such as a network interface, etc.), or have a different configuration from that shown in FIG. 17 .

Wherein, the memory 1702 can be used to store software programs and modules, such as the program instructions/modules corresponding to the semantic transformation method and device in the embodiments of the present disclosure, and the processor 1704 runs the software programs and modules stored in the memory 1702 to execute various A functional application and data processing, that is, to realize the above-mentioned semantic conversion method. The memory 1702 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 1702 may further include a memory that is remotely located relative to the processor 1704, and these remote memories may be connected to the terminal through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof. As an example, as shown in FIG. 17 , the memory 1702 may include, but is not limited to, the first acquisition module 1602 , the first determination module 1604 , the analysis module 1606 and the second determination module 1608 in the semantic conversion device. In addition, it may also include but not limited to other module units in the above-mentioned identity determination device, which will not be described in detail in this example.

Optionally, the above-mentioned transmission device 1706 is configured to receive or send data via a network. The specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 1706 includes a network adapter (Network Interface Controller, NIC), which can be connected with other network devices and a router through a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 1706 is a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet in a wireless manner.

In addition, the above-mentioned electronic device further includes: a display 1708 for displaying the above-mentioned second control instruction; and a connecting bus 1710 for connecting various module components in the above-mentioned electronic device.

For specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiments and exemplary implementation manners, and details are not repeated in this embodiment.

Obviously, those skilled in the art should understand that each module or each step of the above-mentioned disclosure can be realized by a general-purpose computing device, and they can be concentrated on a single computing device, or distributed in a network composed of multiple computing devices Alternatively, they may be implemented in program code executable by a computing device so that they may be stored in a storage device to be executed by a computing device, and in some cases in an order different from that shown here The steps shown or described are carried out, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps among them are fabricated into a single integrated circuit module for implementation. As such, the present disclosure is not limited to any specific combination of hardware and software.

The above descriptions are only preferred implementations of the present disclosure. It should be pointed out that those skilled in the art can make some improvements and modifications without departing from the principles of the present disclosure. These improvements and modifications are also It should be regarded as the protection scope of the present disclosure.

Claims (20)

1. A method of identification comprising:

   Acquiring target data of the target object, wherein the target data is generated by the target object when operating the first terminal and uploaded to the server;

   determining target characteristics of the target object based on the target data;

   Analyzing the target features based on a pre-established target data model to obtain an analysis result, wherein the target data model is established based on data generated by the first object when operating the first terminal within a predetermined period of time in the past Yes, the first object includes the target object;

   If the analysis result indicates 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.
2. The method according to claim 1, wherein, before analyzing the target features based on a pre-established target data model to obtain analysis results, the method comprises:

   Acquiring a first data group, wherein the first data group includes first data generated by the first object when operating the first terminal within the predetermined period of time and uploaded to the server;

   Classify each of the first data included in the first data group according to data attributes to obtain multi-group data, wherein the first data includes multiple data of different types of data attributes, and the multi-group The data attributes of each tuple data included in the group data are of the same type;

   The target data model is established based on the tuple data.
3. The method according to claim 2, wherein analyzing the target features based on a pre-established target data model to obtain analysis results includes:

   analyzing distribution characteristics of each of the tuple data included in the tuple data;

   determining a first feature of each of the tuple data based on a distribution feature of each of the tuple data;

   Analyzing the target feature based on the first feature to obtain the analysis result.
4. The method according to claim 3, wherein determining the first feature of each of the tuple data based on the distribution characteristics of each of the tuple data comprises:

   dividing each of the tuple data into one or more subgroup data based on the distribution characteristics of each of the tuple data;

   determining a characteristic value for each of said subsets of data included in one or more of said subsets of data;

   determining the data attribute and the feature value of each of the subgroups of data as a second feature of each of the subgroups of data;

   The first characteristic of each of said tuple data is determined based on said second characteristic of each of said subgroup of data.
5. The method according to claim 4, wherein analyzing the target features based on a pre-established target data model to obtain analysis results includes:

   Match each feature included in the first feature of each tuple data with the target feature to obtain a matching result;

   The analysis result is determined based on the matching result.
6. The method of claim 5, wherein determining the identity of the target object based on the matching features comprises:

   determining a target feature value for said target feature;

   When the analysis result indicates that the feature value of the target second feature included in the first feature and the target feature value meet a preset condition, determining the target second feature as the matching feature;

   The identity of the target object is determined based on the matching features.
7. The method of claim 6, wherein,

   The feature value of the second feature includes: used to represent the average value of the subgroup data corresponding to the second feature, and used to represent the variance of the subgroup data corresponding to the second feature;

   The preset condition includes: a difference between the target feature value and the average value is less than or equal to the variance.
8. The method of claim 1, wherein determining the identity of the target object based on the matching features comprises:

   determining matching data corresponding to the matching feature;

   The identity of the object generating the matching data by operating the first terminal is determined as the identity of the target object.
9. The method according to claim 1, wherein after determining the identity of the target object based on the matching characteristics, the method further comprises:

   Push a message to the target object.
10. The method according to claim 1, wherein obtaining the target data of the target object comprises:

    acquiring 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.
11. The method according to any one of claims 1-10, wherein the target data includes at least one of the following:

    first metadata, wherein the first metadata is used to indicate data of identity attributes of the target object;

    second metadata, wherein the second metadata is used to indicate data of a time attribute when the target object operates the first terminal;

    third metadata, wherein the third metadata is used to indicate data of a location attribute of the target object operating the first terminal;

    Fourth metadata, wherein the fourth metadata is used to indicate behavior data that satisfies the association relationship generated by the target object by operating the first terminal;

    The fifth metadata, wherein the fifth metadata is used to indicate data of the target object's intention attribute of operating the first terminal.
12. An identity determination device comprising:

    The first acquiring module is configured to acquire the target data of the target object, wherein the target data is generated by the target object when operating the first terminal and uploaded to the server;

    A first determining module, configured to determine target features of the target object based on the target data;

    The analysis module is configured to analyze the characteristics of the target based on a pre-established target data model to obtain an analysis result, wherein the target data model is based on the first object operating the first terminal within a predetermined period of time in the past generated data, the first object includes the target object;

    The second determining module is configured to determine the identity of the target object based on the matching feature when the analysis result indicates that there is a matching feature matching the target feature in the target data model.
13. The apparatus according to claim 12, wherein said apparatus further comprises:

    The second acquisition module is configured to acquire a first data set before analyzing the target features based on a pre-established target data model to obtain an analysis result, wherein the first data set includes the first object in First data generated when operating the first terminal within the predetermined period of time and uploaded to the server;

    A classification module, configured to classify each of the first data included in the first data group according to data attributes to obtain multi-group data, wherein the first data includes a plurality of different types of data attributes data, the data attributes of each tuple data included in the tuple data are of the same type;

    A building module configured to build the target data model based on the tuple data.
14. The apparatus according to claim 13, wherein the analysis module comprises:

    a first analysis unit configured to analyze distribution characteristics of each of the tuple data included in the tuple data;

    A first determining unit configured to determine a first feature of each of the tuple data based on a distribution feature of each of the tuple data;

    The second analysis unit is configured to analyze the target feature based on the first feature to obtain the analysis result.
15. The device according to claim 14, wherein the first determining unit comprises:

    dividing subunits, configured to divide each of the tuple data into one or more subgroup data based on the distribution characteristics of each of the tuple data;

    A first determination subunit configured to determine a feature value of each of the subset data included in one or more of the subset data;

    The second determination subunit is configured to determine the data attribute and the feature value of each of the subgroup data as the second feature of each of the subgroup data;

    The third determining subunit is configured to determine the first feature of each of the tuple data based on the second feature of each of the subgroup data.
16. The apparatus according to claim 15, wherein the analysis module comprises:

    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;

    The second determination unit is configured to determine the analysis result based on the matching result.
17. The apparatus according to claim 16, wherein the second determining module comprises:

    a third determination unit configured to determine a target feature value of the target feature;

    The fourth determination unit is configured to: when the analysis result indicates that the feature value of the target second feature included in the first feature and the target feature value meet a preset condition, the target second feature determined as the matching feature;

    The fifth determining unit is configured to determine the identity of the target object based on the matching feature.
18. The apparatus of claim 17, wherein,

    The feature value of the second feature includes: used to represent the average value of the subgroup data corresponding to the second feature, and used to represent the variance of the subgroup data corresponding to the second feature;

    The preset condition includes: a difference between the target feature value and the average value is less than or equal to the variance.
19. A computer-readable storage medium, the computer-readable storage medium comprising a stored program, wherein, when the program is run, the method according to any one of claims 1 to 11 is executed.
20. An electronic device, comprising a memory and a processor, the memory stores a computer program, and the processor is configured to execute the method according to any one of claims 1 to 11 through the computer program.

Images