Family relationship recognition method, device, equipment, medium and product

Abstract

The present application discloses a method, apparatus, device, medium and product for identifying family relationships. The method includes: when obtaining the index data of multiple users, determining multiple user pairs with family relationships among the multiple users according to the index data and the family relationship recognition model; performing community division on the multiple user pairs according to the community division model to obtain multiple first family groups; obtaining the resident base station data of the first user corresponding to each first family group; splitting each first family group according to the resident base station data of the first user to obtain at least one second family group corresponding to each first family group, and the residential community information corresponding to all second users in the same second family group is the same; obtaining the target data of the second user corresponding to each second family group; and identifying the family relationships of all second users in each second family group according to the target data of the second user corresponding to each second family group.

Description

Technical Field

[0001] This application belongs to the field of communication technologies, and particularly relates to a method, apparatus, device, medium, and product for identifying family relationships. Background Art

[0002] With the development of mobile communication, major telecom operators have successively started to explore the home user market. In addition to services such as mobile phone communication cards and home short number networks, the home user market also includes home broadband and home intelligent devices for home broadband. Therefore, the home user market has broad growth potential.

[0003] In related technologies, due to the need to explore the home user market, the identification of the relationships between home users and family members is the key. Therefore, how to accurately identify home users from a large number of user groups and the family relationships between family members is an urgent problem to be solved currently. Summary of the Invention

[0004] Embodiments of this application provide a method, apparatus, device, medium, and product for identifying family relationships, which can solve the problem of how to accurately identify home users from a large number of user groups and the family relationships between family members.

[0005] In a first aspect, embodiments of this application provide a method for identifying family relationships. The method includes: when obtaining the metric data of multiple users, determining multiple user pairs with family relationships among the multiple users according to the metric data and a family relationship recognition model, where each user pair corresponds to two users; performing community division on the multiple user pairs according to a community division model to obtain multiple first family groups, where each first family group includes at least one user pair, and the users corresponding to the first family group are first users; obtaining the resident base station data of the first users corresponding to each first family group; splitting each first family group according to the resident base station data of the first users to obtain at least one second family group corresponding to each first family group, where the users corresponding to the second family group are second users, and the residential community information corresponding to all second users in the same second family group is the same; obtaining the target data of the second users corresponding to each second family group, where the target data includes at least one of individual metrics and service behavior data; and identifying the family relationships of all second users in each second family group according to the target data of the second users corresponding to each second family group.

[0006] In a second aspect, an embodiment of the present application provides a family relationship recognition device, which includes: a determination module, configured to determine, when obtaining the metric data of multiple users, multiple user pairs with family relationships among the multiple users according to the metric data and a family relationship recognition model, where each user pair corresponds to two users; a division module, configured to divide the multiple user pairs according to a community division model to obtain multiple first family groups, where each first family group includes at least one user pair, and the users corresponding to the first family group are first users; an acquisition module, configured to acquire the resident base station data of the first users corresponding to each first family group; a splitting module, configured to split each first family group according to the resident base station data of the first users to obtain at least one second family group corresponding to each first family group, where the users corresponding to the second family group are second users, and the residential community information corresponding to all the second users in the same second family group is the same; the acquisition module is further configured to acquire the target data of the second users corresponding to each second family group, and the target data includes at least one of individual metrics and business behavior data; an identification module, configured to identify the family relationships of all the second users in each second family group according to the target data of the second users corresponding to each second family group.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, which includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the steps of the family relationship recognition method shown in any one of the embodiments of the first aspect are implemented.

[0008] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the steps of the family relationship recognition method shown in any one of the embodiments of the first aspect are implemented.

[0009] In a fifth aspect, an embodiment of the present application provides a computer program product, which is stored in a non-volatile storage medium, and the program product is executed by at least one processor to implement the steps of the family relationship recognition method shown in any one of the embodiments of the first aspect.

[0010] The family relationship recognition method, device, equipment, medium and product according to the embodiments of the present application, in the case of obtaining the index data of multiple users, can initially determine multiple pairs of users with family relationships among the multiple users according to the index data and the family relationship recognition model, and perform community division on the multiple pairs of users according to the community division model to obtain multiple first family groups. Based on this, in order to improve the accuracy of family user recognition, obtain the resident base station data of the first user corresponding to each first family group, and split each first family group according to the resident base station data of the first user, and divide the first users with the same residential community information in each first family group into the same family group to obtain the second family group. Since the second family group is divided on the basis of the first family group according to whether the residential communities where the users are located are the same, it can be further optimized on the basis of the first family group, ensuring that the family members in the second family group can have an actual family relationship and effectively improving the recognition accuracy of family users. In this way, by obtaining at least one of the individual indicators and business behavior data of the second user corresponding to each second family group, the family relationships of all the second users in each second family group can be accurately recognized according to the individual indicators and / or business behavior data of each second user, improving the recognition accuracy of family users and family relationships. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0012] Figure 1 is one of the flow diagrams of the family relationship recognition method provided by the embodiments of the present application;

[0013] Figure 2 is the second flow diagram of the family relationship recognition method provided by the embodiments of the present application;

[0014] Figure 3 is the third flow diagram of the family relationship recognition method provided by the embodiments of the present application;

[0015] Figure 4 is the fourth flow diagram of the family relationship recognition method provided by the embodiments of the present application;

[0016] Figure 5 is the fifth flow diagram of the family relationship recognition method provided by the embodiments of the present application;

[0017] Figure 6 is the sixth flow diagram of the family relationship recognition method provided by the embodiments of the present application;

[0018] Figure 7 It is a schematic structural diagram of a family relationship recognition device provided by an embodiment of the present application;

[0019] Figure 8 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0020] The features and exemplary embodiments of various aspects of the present application will be described in detail below. To make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than limiting the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only intended to provide a better understanding of the present application by showing examples of the present application.

[0021] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, elements defined by the statement "comprising..." do not exclude the presence of additional identical elements in the process, method, article or device comprising the said elements.

[0022] As described in the background art, due to the need to explore the home user market, the recognition of the relationship between home users and family members is the focus. Therefore, how to accurately identify home users from a large number of user groups and the family relationships between family members is an urgent problem to be solved currently.

[0023] In view of the problems in the related art, the embodiments of the present application provide a family relationship recognition method. When obtaining the index data of multiple users, it is possible to initially determine multiple pairs of users with family relationships among the multiple users according to the index data and the family relationship recognition model, and perform community division on the multiple pairs of users according to the community division model to obtain multiple first family groups. Based on this, in order to improve the accuracy of family user recognition, obtain the resident base station data of the first user corresponding to each first family group, and split each first family group according to the resident base station data of the first user. Divide the first users with the same residential community information in each first family group into the same family group to obtain the second family group. Since the second family group is divided on the basis of the first family group according to whether the residential communities where the users are located are the same, it can be further optimized on the basis of the first family group, ensuring that the family members in the second family group can have an actual family relationship, and effectively improving the recognition accuracy of family users. In this way, by obtaining at least one of the individual indicators and business behavior data of the second user corresponding to each second family group, it is possible to accurately recognize the family relationships of all the second users in each second family group according to the individual indicators and / or business behavior data of each second user, improving the recognition accuracy of family users and family relationships, and solving the problems in the related art of how to accurately identify family users from a large number of user groups and the family relationships between family members.

[0024] The following will combine the accompanying drawings to detail the family relationship recognition method provided by the embodiments of the present application through specific embodiments and their application scenarios.

[0025] It should be noted that the acquisition, storage, use, processing, etc. of data in the embodiments of the present application all comply with the relevant regulations of national laws and regulations.

[0026] Figure 1 It is a schematic flowchart of a family relationship recognition method provided by the embodiments of the present application. The execution subject of this family relationship recognition method can be an electronic device. It should be noted that the above execution subject does not constitute a limitation to the present application.

[0027] Here, the electronic device can be a device with communication functions such as a mobile phone, a tablet computer, an all-in-one computer, etc., or a device simulated by a virtual machine or an emulator. Of course, it can also be a device with storage and computing functions such as a cloud server or a server cluster.

[0028] As Figure 1 shown, the family relationship recognition method provided by the embodiments of the present application may include step 110-step 160.

[0029] Step 110, in the case of obtaining the metric data of multiple users, determine multiple user pairs with family relationships among the multiple users according to the metric data and the family relationship recognition model.

[0030] Specifically, the multiple users can be divided into multiple groups, with each group including two users. The electronic device can input the metric data of each group of users into the family relationship recognition model. The family relationship recognition model can identify whether the users in each group have a family relationship based on the metric data of each group of users and output a positive / negative label corresponding to each group of users. When a group of users corresponds to a positive label, it is determined that the group of users is a user pair with a family relationship. It can be understood that each group includes two users, so each user pair corresponds to two users.

[0031] Step 120, perform community division on the multiple user pairs according to the community division model to obtain multiple first family groups.

[0032] Among them, each first family group includes at least one user pair, and the users corresponding to the first family group are first users. The first family group can be used to represent a physical family group.

[0033] Exemplarily, the multiple user pairs can include {User A, User B}, {User C, User D}, {User C, User E}, {User A, User P}. After performing community division on the 4 user pairs according to the community division model, two first family groups {User A, User B, User P} and {User C, User D, User E} can be obtained.

[0034] Step 130, obtain the resident base station data of the first users corresponding to each first family group.

[0035] Step 140, split each first family group according to the resident base station data of the first users to obtain at least one second family group corresponding to each first family group.

[0036] Among them, the users corresponding to the second family group are second users. The residential community information of all second users in the same second family group is the same. The second family group can be used to represent a "natural family group".

[0037] Exemplarily, the first family group can be {User A, User B, User P}. Since the residential community information of User A and User B is the same, and the residential community information of User P is different from that of User A and B, {User A, User B, User P} is split into two second family groups {User A, User B} and {User P}.

[0038] In the embodiments of the present application, due to possible errors in the recognition model during the recognition process caused by family relationships, the identified user pairs may not necessarily be those with real family relationships. For example, user A and user P with a colleague relationship often make calls. Based on the call data of the two users, the family relationship recognition model can determine this group of users as the user pair {user A, user P}. Therefore, when performing community division, user P may be grouped together with the user pair {user A, user B} with a real family relationship, resulting in the first family group {user A, user B, user P}. Therefore, in order to group together users with real family relationships, the electronic device can split the first family group based on the residential community information, and divide the second users with the same residential community information into the same second family group, ensuring that all second users in the second family group have real family relationships and improving the recognition accuracy of family users. At the same time, although all first users in the first family group may have real family relationships, family services such as the operator's home broadband are usually carried out for family users in the same residence. Therefore, for a "big family" (i.e., the first family group) with family relationships but different residences, the electronic device can split it based on the residential community information, splitting the "big family" into "small families" corresponding to the same residence, identifying the "family users" in the same residence in the true sense, and facilitating the subsequent development of family services for family users by the operator.

[0039] Step 150, obtain the target data of the second users corresponding to each second family group.

[0040] Wherein, the target data includes at least one of individual indicators and business behavior data.

[0041] Step 160, identify the family relationships of all second users in each second family group according to the target data of the second users corresponding to each second family group.

[0042] The family relationship recognition method provided by the embodiments of the present application, when obtaining the index data of multiple users, can, according to the index data and the family relationship recognition model, initially determine multiple pairs of users with family relationships among the multiple users, and perform community division on the multiple pairs of users according to the community division model to obtain multiple first family groups. Based on this, in order to improve the accuracy of family user recognition, obtain the resident base station data of the first user corresponding to each first family group, and split each first family group according to the resident base station data of the first user. Divide the first users with the same residential community information in each first family group into the same family group to obtain a second family group. Since the second family group is divided on the basis of the first family group according to whether the residential communities where the users are located are the same, it can be further optimized on the basis of the first family group, ensuring that the family members in the second family group can have an actual family relationship and effectively improving the recognition accuracy of family users. In this way, by obtaining at least one of the individual indicators and business behavior data of the second user corresponding to each second family group, it is possible to accurately recognize the family relationships of all second users in each second family group based on the individual indicators and / or business behavior data of each second user, improving the recognition accuracy of family users and family relationships.

[0043] The following combines specific embodiments to detail the specific implementation manners of the above step 110-step 130.

[0044] Regarding step 110, when obtaining the index data of multiple users, according to the index data and the family relationship recognition model, determine multiple pairs of users with family relationships among the multiple users.

[0045] In some embodiments of the present application, the index data may include at least one of the following: call duration, call frequency, call days, call weeks, call duration ratio, call frequency ratio, call week ratio, interaction index, influence, and intimacy.

[0046] In some embodiments of the present application, Figure 2 is a flowchart of another family relationship recognition method provided by the embodiments of the present application. Before step 110, the method may further include Figure 2 the steps 210-250 shown.

[0047] Step 210, when obtaining the service handling information and address information of the first sample user, determine the second sample user with a family relationship with the first sample user according to the service handling information and address information to obtain the first sample user pair.

[0048] Among them, the first sample user may be the service handling user, and the second sample user may be the user associated with the service handled by the first sample user.

[0049] Specifically, the electronic device can determine a set of users associated with the business handled by the first sample user based on the business handling information of the first sample user, and the electronic device can determine a second sample user in the user set who has the same address as the first sample user based on the address information of the first sample user, thereby accurately determining the second sample user who has a family relationship with the first sample user.

[0050] Exemplarily, the first sample user may be a user who has subscribed to a shared voice service (eg, a family number), a family group service (eg, home broadband), or other related services.

[0051] In one embodiment, the second sample user may be a user identified by the intelligent gateway associated with the first sample user.

[0052] Step 220: When the call data of the third sample user is obtained, the call behavior characteristics are determined according to the call data.

[0053] Among them, the third sample user may be a non-business processing user.

[0054] Specifically, the electronic device can construct features based on the voice details of the third sample user, use statistical methods to expand the feature vector, and mine the user's call behavior characteristics, which may include but are not limited to: call duration, number of calls, number of call days, number of call weeks, call duration ratio, number of calls ratio, call week ratio, interaction index, influence, and intimacy.

[0055] In one embodiment, when calculating the intimacy index by using the interaction index and influence, a standardized transformation process may be performed according to formula (1).

[0056]

[0057] Among them, X normal represents the standardized data, x represents the original data, represents the mean of the data, and sd(x) represents the standard deviation of the data.

[0058] In the embodiment of the present application, by performing standardization transformation processing on the original data, the influence of the measurement unit of the indicator can be removed (de-dimensionalization), thereby improving the accuracy of intimacy calculation.

[0059] In one embodiment, the electronic device may identify the family group of the third sample user through a data mining algorithm to determine the fourth sample user who has a family relationship with the third sample user.

[0060] Step 230: Determine a fourth sample user having a family relationship with a third sample user based on call behavior characteristics, and obtain a second sample user pair.

[0061] Step 240: Obtain the index data of the first sample user pair and the second sample user pair to obtain a training data set.

[0062] Step 250: Train a logistic regression model based on the training data set to obtain a family relationship pair recognition model.

[0063] Specifically, the electronic device can use the index data of the first sample user pair and the second sample user pair as model input data, and use the positive label as model output data to perform model training on the logistic regression model to obtain a trained logistic regression model, that is, a family relationship pair recognition model.

[0064] In the embodiment of the present application, considering that the scale of the model analysis object in this time is large (all customers) and the index calculation amount is complex, a logistic regression algorithm with advantages such as small calculation amount, fast speed, low storage resources, and easy interpretation is selected to build the model, so as to improve the training efficiency and performance of the family relationship pair recognition model.

[0065] Regarding step 120: Perform community division on multiple user pairs according to the community division model to obtain multiple first family groups.

[0066] In one embodiment, the community division model can use the community discovery Louvain algorithm to perform community division on multiple user pairs. The Louvain algorithm is an algorithm based on multi-level optimization of Modularity and is considered to be one of the best-performing community discovery algorithms. Its optimization goal is to maximize the modularity of the entire graph attribute structure (community network). The Modularity function was initially used to measure the quality of the results of community discovery algorithms.

[0067] In one embodiment, the steps of the Louvain community discovery algorithm may include: Step 1, continuously traverse the nodes in the network, and try to add a single node to the community that can maximize the increase in Modularity until all nodes no longer change; Step 2, process the results of Step 1, merge a small community into a supernode to reconstruct the network. At this time, the edge weight is the sum of the edge weights of all original nodes within the two nodes; Step 3, iterate Step 1 and Step 2 until the algorithm is stable.

[0068] In the embodiments of the present application, the community division model can greatly improve the running speed of group division and can depict the tightness of the discovered communities by adopting the Louvain algorithm in which the connections between nodes within a community are relatively tight and the connections between communities are relatively sparse, identify the family groups at the physical family level, and quickly and accurately achieve the community division of multiple user pairs.

[0069] It involves step 130 of obtaining the resident base station data of the first user corresponding to each first family group.

[0070] In one embodiment, the electronic device can locate the resident base stations of all users at different times through data conversion and accumulation, obtain the resident base station data of all users, and the electronic device can obtain the resident base station data of the first user from the resident base station data of all users.

[0071] It involves step 140 of splitting each first family group according to the resident base station data of the first user to obtain at least one second family group corresponding to each first family group.

[0072] In some embodiments of the present application, Figure 3 is a schematic flowchart of another method for identifying family relationships provided by the embodiments of the present application, and step 140 may include Figure 3 steps 310 and 320 shown.

[0073] Step 310 of determining the residential community information of each first user according to the resident base station data of each first user.

[0074] In some embodiments of the present application, in order to determine the residential community information of each first user, Figure 4 is a schematic flowchart of another method for identifying family relationships provided by the embodiments of the present application, and step 310 may include Figure 4 steps 411-step 421 shown.

[0075] Step 411 of determining the fifth user among all first users.

[0076] Among them, the fifth user may be a user who has handled a broadband service.

[0077] Step 412 of determining the night resident base station of the fifth user according to the resident base station data of the fifth user.

[0078] Step 413 of obtaining the residential community information corresponding to the night resident base station as the residential community information of the fifth user.

[0079] Specifically, the mapping relationship between base station data and residential community information can be stored in a preset database. The electronic device can obtain the residential community information mapped to the base station data from the preset database based on the base station data of the night-time resident base station of each fifth user as the residential community information of the fifth user.

[0080] Among them, the base station data can include the base station location area code, base station cell positioning information, and base station longitude and latitude, and the residential community information can include the community name, community six-level address, and community longitude and latitude.

[0081] In one embodiment, when the electronic device fails to obtain the residential community information corresponding to the night-time resident base station, it can obtain the location information of the preset covered residential communities, and determine the information of the residential community closest to the night-time resident base station in the preset covered residential communities as the residential community information of the fifth user according to the night-time resident base station and the location information of the preset covered residential communities.

[0082] In the above embodiment, if there are at least two residential communities closest to the night-time resident base station, the information of the residential community with the largest number of community broadband coverage people can be selected as the residential community information of the fifth user.

[0083] Step 414, determine the sixth user among all the first users.

[0084] Among them, the sixth user is the user among all the first users other than the fifth user, that is, the user who has not subscribed to the broadband service.

[0085] Step 415, determine the first target user among the sixth users who has established a connection relationship with the first resident base station according to the resident base station data of the sixth user.

[0086] Among them, the first resident base station can be any night-time resident base station corresponding to the fifth user.

[0087] Step 416, obtain the residential community information corresponding to the first resident base station as the residential community information of the first target user.

[0088] Specifically, for a user (i.e., the first target user) who has not subscribed to the broadband service but has appeared at the night-time resident base station (i.e., the first resident base station) of a user who has subscribed to the broadband service (i.e., the fifth user), the first target user can be located in the community six-level address corresponding to the first resident base station to obtain the residential community information of the first target user.

[0089] In one embodiment, the electronic device may match the sixth-level cell address of the fifth user and the night resident base station data to obtain the corresponding relationship between the sixth-level cell address and the night resident base station data. The electronic device may obtain the sixth-level cell address corresponding to the first resident base station from this corresponding relationship to obtain the residential cell information of the first target user.

[0090] Step 417, determine the second target user among the sixth users.

[0091] Wherein, the second target user may be a user among the sixth users other than the first target user.

[0092] Step 418, obtain the location information of the second resident base station corresponding to the second target user from the resident base station data of the second target user.

[0093] Step 419, obtain the location information of the preset covered residential cells.

[0094] Wherein, the preset covered residential cells may be cells covered by broadband.

[0095] Step 420, determine the target residential cell in the preset covered residential cells that is closest to the second resident base station according to the location information of the second resident base station and the preset covered residential cells.

[0096] In one embodiment, the electronic device may obtain a set of residential cells (the actual distance is about 1 kilometer) from the preset covered residential cells whose decimal parts of longitude and latitude differ from those of the second resident base station by 0.01, and then calculate the distances between the longitude and latitude of the second resident base station and each residential cell in the set of residential cells, and screen out the residential cell with the closest distance as the target residential cell.

[0097] In the embodiment of the present application, the electronic device first filters out a set of residential cells that are relatively close to the second resident base station among all the covered residential cells based on longitude and latitude, which can narrow the range. Based on this, calculating the longitude and latitude distances between the second resident base station and the residential cells in the set of residential cells can significantly reduce the calculation amount and improve the recognition and matching efficiency.

[0098] Step 421, obtain the residential cell information of the target residential cell as the residential cell information of the second target user.

[0099] In one embodiment, a user cell falling model may be constructed before step 411, and the electronic device executes the above steps 411 - 421 through this user cell falling model.

[0100] Step 320, divide the first users with the same residential cell information in each first family group into the same second family group to obtain at least one second family group corresponding to each first family group.

[0101] Exemplarily, the first family group may be {User D, User E, User Q}. Since the residential community information of User D and User E is the same, and the residential community information of User Q is different from that of User D and E, {User D, User E, User Q} is split into two second family groups {User D, User E} and {User Q}.

[0102] In some embodiments of the present application, there are multiple second users in the first family group living in the same community. However, since the resident base station of a certain second user falls into the neighboring community, multiple second users are divided into different second family groups due to different residential community information obtained by the electronic device. At this time, there is an error in the residential community information of the second user obtained by the electronic device. Therefore, when dividing the first family group based on the residential community information, there will be a problem of inaccurate division.

[0103] Based on this, Figure 5 is a schematic flowchart of another family relationship recognition method provided by an embodiment of the present application. As Figure 5 shown, after step 320, the method may include steps 510 - 530.

[0104] Step 510, determine a third family group and a fourth family group in at least one second family group.

[0105] Among them, the number of second users in the third family group is less than a preset quantity threshold, and the number of second users in the fourth family group is greater than or equal to the preset quantity threshold. The preset quantity threshold can be set according to specific requirements, and the present application does not make specific limitations here.

[0106] Exemplarily, if the preset quantity threshold is 2, after the first family group {User D, User E, User Q} is split into two second family groups {User D, User E} and {User Q}, since the number of second users in {User Q} is less than 2, the electronic device determines that the third family group is {User Q}, and the fourth family group is {User D, User E}.

[0107] Step 520, calculate the distance between the residential communities corresponding to the third family group and the fourth family group according to the residential community information corresponding to the third family group and the fourth family group respectively.

[0108] Specifically, the electronic device may calculate the distance between two residential communities based on the longitude and latitude of the residential communities corresponding to the third family group and the fourth family group respectively. Among them, the residential community corresponding to the third family group is the residential community corresponding to the second user in the third family group, and the residential community corresponding to the fourth family group is the residential community corresponding to the second user in the fourth family group.

[0109] In one embodiment, the electronic device can specifically calculate the distance Distance between the third family group and the corresponding residential community of the fourth family group through formula (2) and formula (3).

[0110] C = sin(LatA) * sin(LatB) * cos(LonA - LonB) + cos(LatA) * cos(LatB) (2)

[0111] Distance = R * Arccos(C) * Pi / 180 (3)

[0112] Wherein, the longitude and latitude of the residential community corresponding to the third family group are (LonA, LatA), the longitude and latitude of the residential community corresponding to the fourth family group are (LonB, LatB), R is the average radius of the earth, and C is the intermediate value.

[0113] Step 530, when the distance is less than the preset distance threshold, merge the third family group and the fourth family group.

[0114] Wherein, the preset distance threshold can be set according to actual needs, and the present application does not make specific limitations here.

[0115] For example, the preset distance threshold can be 3m, 5m or 8m, etc.

[0116] In the embodiment of the present application, when the number of the third family user group is less than the preset number threshold, for example, it is 1, it means that a certain second user is divided into a single-person group. Therefore, the electronic device can calculate the distance between the residential community corresponding to the second user and the residential community of the second user in other second family groups (i.e., the fourth family group), and re-determine the natural family group to which the second user belongs through the distance. When the distance is less than the preset distance threshold, it means that the residential communities of the second users in the two second family groups (the third family group and the fourth family group) are very close. At this time, the two second family groups can be merged into the same natural family group to improve the accuracy of natural family group division.

[0117] Regarding step 150, obtain the target data of the second users corresponding to each second family group.

[0118] Wherein, the target data can include at least one of individual indicators and business behavior data.

[0119] Regarding step 160, identify the family relationships of all second users in each second family group according to the target data of the second users corresponding to each second family group.

[0120] In some embodiments of the present application, the individual indicators include age data and gender data, and the business behavior data may include application usage data. Figure 6 FIG. Figure 6 is a schematic flowchart of another method for identifying family relationships provided by an embodiment of the present application. Step 160 may include Figure 6 the steps 610 and 620 shown in FIG. Figure 6 .

[0121] Step 610, draw a dimension cross matrix based on the target data corresponding to each second family group.

[0122] Step 620, determine the family relationships of all second users in each second family group based on the dimension cross matrix, and obtain the role information of each second user.

[0123] In one embodiment, the electronic device may draw a dimension cross matrix based on age data and gender data, that is, the electronic device subtracts the age and gender identifiers of any two second users in each second family group respectively. Among them, different age differences and different gender identifier differences correspond to different family relationship types.

[0124] Optionally, the male identifier is 1 and the female identifier is 0.

[0125] Exemplarily, the male identifier is 1 and the female identifier is 0. The second users in the second family group include user D and user E. The ages of user D and user E are 32 and 6 respectively, and the gender identifiers are both 1. Then, based on the age difference of 26 and the gender identifier difference of 0, it can be determined that the family relationship type between user D and user E is father-son, the family role of user D is father, and the family role of user E is son.

[0126] In another embodiment, the electronic device may draw a dimension cross matrix based on application usage data. Based on the application usage data of the second user, the application category used by the second user can be determined, so as to judge the family role of the second user and obtain the family relationship between any two second users.

[0127] Exemplarily, the application usage data of user D includes usage data of office APPs, and the application usage data of user E includes usage data of homework tutoring APPs. Then, it can be judged that the family role of user D is parent and the family role of user E is child, so as to obtain the family relationship between any user D and user E.

[0128] In the embodiments of the present application, the electronic device may obtain the age data, gender data, or APP usage data of the second users corresponding to each second family group, draw a dimension cross matrix through the personal basic information or network behavior information of the above users, and can accurately determine the family relationships among family members in the same natural family group according to the dimension cross matrix, so as to facilitate the operator to make targeted family service recommendations subsequently.

[0129] In some embodiments of the present application, after step 160, the method may further include the following steps: obtaining the traffic usage data and voice usage data of each second user in the second family group; determining the family service saturation corresponding to the second family group according to the traffic usage data and the voice usage data; and determining a family portrait based on the family service saturation and the family relationships of all second users in the second family group.

[0130] Specifically, by comprehensively evaluating the in-package traffic and voice usage volumes of products of family members, the family service saturation can be output, thereby further improving the whole-network family portrait ability and realizing feature extraction and application based on the family unit.

[0131] It should be noted that for the family relationship recognition method provided in the embodiments of the present application, the execution subject may be a family relationship recognition device, or a control module in the family relationship recognition device for executing the family relationship recognition method. In the embodiments of the present application, the case where the family relationship recognition device executes the family relationship recognition method is taken as an example to illustrate the family relationship recognition device provided in the embodiments of the present application. The family relationship recognition device will be introduced in detail below.

[0132] Figure 7 It is a schematic structural diagram of a family relationship recognition device provided in the embodiments of the present application. As Figure 7 shown, the family relationship recognition device 700 may include: a determination module 710, a division module 720, an acquisition module 730, a splitting module 740, and an identification module 750.

[0133] Among them, a determination module 710 is configured to, when obtaining the metric data of multiple users, determine multiple user pairs with family relationships among the multiple users according to the metric data and a family relationship pair recognition model, where each user pair corresponds to two users; a division module 720 is configured to divide the multiple user pairs according to a community division model to obtain multiple first family groups, where each first family group includes at least one user pair, and the users corresponding to the first family group are first users; an acquisition module 730 is configured to acquire the resident base station data of the first users corresponding to each first family group; a splitting module 740 is configured to split each first family group according to the resident base station data of the first users to obtain at least one second family group corresponding to each first family group, where the users corresponding to the second family group are second users, and the residential community information corresponding to all the second users in the same second family group is the same; the acquisition module 730 is further configured to acquire the target data of the second users corresponding to each second family group, where the target data includes at least one of individual metrics and service behavior data; an identification module 750 is configured to identify the family relationships of all the second users in each second family group according to the target data of the second users corresponding to each second family group.

[0134] In the family relationship identification device according to the embodiment of the present application, when obtaining the metric data of multiple users, it can initially determine multiple user pairs with family relationships among the multiple users according to the metric data and a family relationship pair recognition model, and divide the multiple user pairs according to the community division model to obtain multiple first family groups. Based on this, in order to improve the accuracy of family user identification, the resident base station data of the first users corresponding to each first family group is acquired, and each first family group is split according to the resident base station data of the first users, and the first users with the same residential community information in each first family group are divided into the same family group to obtain a second family group. Since the second family group is divided on the basis of the first family group according to whether the residential communities where the users are located are the same, it can be further optimized on the basis of the first family group, ensuring that the family members in the second family group can have an actual family relationship and effectively improving the accuracy of family user identification. In this way, by obtaining at least one of the individual metrics and service behavior data of the second users corresponding to each second family group, the family relationships of all the second users in each second family group can be accurately identified according to the individual metrics and / or service behavior data of each second user, improving the identification accuracy of family users and family relationships.

[0135] In some embodiments of the present application, the splitting module 740 is specifically configured to: determine the residential community information of each first user according to the resident base station data of each first user; divide the first users with the same residential community information in each first family group into the same second family group, so as to obtain at least one second family group corresponding to each first family group.

[0136] In some embodiments of the present application, the apparatus further includes: a determining module 710, configured to determine a third family group and a fourth family group in at least one second family group after dividing the first users with the same residential community information in each first family group into the same second family group, so as to obtain at least one second family group corresponding to each first family group, where the number of second users in the third family group is less than a preset number threshold, and the number of second users in the fourth family group is greater than or equal to the preset number threshold; a calculating module, configured to calculate the distance between the residential communities corresponding to the third family group and the fourth family group according to the residential community information corresponding to the third family group and the fourth family group respectively; a merging module, configured to merge the third family group and the fourth family group when the distance is less than a preset distance threshold.

[0137] In some embodiments of the present application, the determining module 710 is specifically configured to: determine a fifth user among all first users, where the fifth user is a user who has subscribed to a broadband service; determine the night resident base station of the fifth user according to the resident base station data of the fifth user; obtain the residential community information corresponding to the night resident base station as the residential community information of the fifth user.

[0138] In some embodiments of the present application, the determining module 710 is specifically configured to: determine a sixth user among all first users, where the sixth user is a user other than the fifth user among all first users; according to the resident base station data of the sixth user, determine a first target user among the sixth users who has established a connection relationship with a first resident base station, where the first resident base station is any night resident base station corresponding to the fifth user; obtain the residential community information corresponding to the first resident base station as the residential community information of the first target user.

[0139] In some embodiments of the present application, the determining module 710 is specifically configured to: determine a second target user among the sixth users, where the second target user is a user other than the first target user among the sixth users; obtain the location information of the second resident base station corresponding to the second target user from the resident base station data of the second target user; obtain the location information of a preset covered residential community; determine the target residential community in the preset covered residential community that is closest to the second resident base station according to the location information of the second resident base station and the preset covered residential community; obtain the residential community information of the target residential community as the residential community information of the second target user.

[0140] In some embodiments of the present application, the individual indicators include age data and gender data, the business behavior data includes application usage data, and the recognition module 750 includes: a drawing unit for drawing a dimension cross matrix based on the target data corresponding to each second family group; a determination unit for determining the family relationships of all second users in each second family group based on the dimension cross matrix to obtain the role information of each second user.

[0141] In some embodiments of the present application, the indicator data includes at least one of the following: call duration, number of calls, number of call days, number of call weeks, call duration ratio, number of calls ratio, number of call weeks ratio, interaction index, influence, and intimacy.

[0142] In some embodiments of the present application, the device further includes: a determination module 710, further configured to, before determining multiple user pairs with family relationships for the recognition model according to the indicator data and family relationships, when obtaining the service handling information and address information of the first sample user, determine a second sample user having a family relationship with the first sample user according to the service handling information and address information to obtain a first sample user pair; the determination module 710, further configured to determine call behavior characteristics according to the call data when obtaining the call data of the third sample user; the determination module 710, further configured to determine a fourth sample user having a family relationship with the third sample user according to the call behavior characteristics to obtain a second sample user pair; an acquisition module 730, further configured to acquire the indicator data of the first sample user pair and the second sample user pair to obtain a training data set; a training module for training a logistic regression model based on the training data set to obtain a family relationship pair recognition model.

[0143] In some embodiments of the present application, the first sample user is a service handling user, the second sample user is a user associated with the service handled by the first sample user, and the third sample user is a non-service handling user.

[0144] In some embodiments of the present application, the device further includes: an acquisition module 730, further configured to acquire the traffic usage data and voice usage data of each second user in the second family group after recognizing the family relationships of all second users in each second family group according to the target data of the second users corresponding to each second family group; a determination module 710, further configured to determine the family service saturation corresponding to the second family group according to the traffic usage data and voice usage data; the determination module 710, further configured to determine a family portrait based on the family service saturation and the family relationships of all second users in the second family group.

[0145] The family relationship recognition device in the embodiments of the present application may be a device, or a component, an integrated circuit, or a chip in a terminal. The device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a palmtop computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0146] The family relationship recognition device in the embodiments of the present application may be a device with an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems. The embodiments of the present application do not make specific limitations.

[0147] Figure 8 It is a schematic hardware structure diagram of an electronic device provided by the embodiments of the present application.

[0148] As Figure 8 shown, the electronic device 800 in this embodiment may include a processor 801 and a memory 802 storing computer program instructions.

[0149] Specifically, the above-mentioned processor 801 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0150] The memory 802 may include a mass storage for data or instructions. By way of example and not limitation, the memory 802 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc, a magneto-optical disc, magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 802 may include removable or non-removable (or fixed) media. Where appropriate, the memory 802 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, the memory 802 is a non-volatile solid-state memory. The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to embodiments of the present application.

[0151] The processor 801 reads and executes the computer program instructions stored in the memory 802 to implement any one of the family relationship recognition methods in the above embodiments.

[0152] In one example, the electronic device 800 may further include a communication interface 803 and a bus 810. Among them, as Figure 8 shown, the processor 801, the memory 802, and the communication interface 803 are connected through the bus 810 and complete communication with each other.

[0153] The communication interface 803 is mainly used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present application.

[0154] The bus 810 includes hardware, software, or both, and couples the components of the online data flow metering device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, the bus 810 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0155] The electronic device provided by the embodiments of the present application can implement Figures 1-6 each process implemented by the electronic device in the method embodiment, and can achieve the same technical effects. To avoid repetition, it will not be described in detail here.

[0156] Combined with the family relationship recognition method in the above embodiments, the embodiments of the present application can provide a family relationship recognition system, which includes the electronic device in the above embodiments. The specific content of the electronic device can be seen in the relevant descriptions in the above embodiments, and will not be described in detail here.

[0157] In addition, combined with the family relationship recognition method in the above embodiments, the embodiments of the present application can be implemented by providing a computer-readable storage medium. Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by a processor, the steps of any one of the family relationship recognition methods in the above embodiments are implemented.

[0158] Combined with the family relationship recognition method in the above embodiments, the embodiments of the present application can be implemented by providing a computer program product. The (computer) program product is stored in a non-volatile storage medium, and when the program product is executed by at least one processor, the steps of any one of the family relationship recognition methods in the above embodiments are implemented.

[0159] It should be clear that the present application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, the detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0160] The functional blocks shown in the above-described structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments for performing the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via a data signal carried in a carrier wave. A "machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0161] It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or can be different from the order in the embodiments, or several steps can be executed simultaneously.

[0162] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block in the flowcharts and / or block diagrams, and the combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and the combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0163] As described above, this is only the specific implementation manner of the present application. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application.

Claims

1. A method for identifying family relationships, characterized in that, it includes: When obtaining the index data of multiple users, according to the index data and the family relationship pair recognition model, determine multiple user pairs with family relationships among the multiple users, where each user pair corresponds to two users, and the family relationship pair recognition model is trained based on the logistic regression algorithm; Perform community division on the multiple user pairs according to the community division model to obtain multiple first family groups, where each first family group includes at least one user pair, the users corresponding to the first family group are first users, and the community division model includes the Louvain algorithm; Obtain the resident base station data of the first users corresponding to each first family group; Split each first family group according to the resident base station data of the first users to obtain at least one second family group corresponding to each first family group, where the users corresponding to the second family group are second users, and the residential community information corresponding to all second users in the same second family group is the same; Obtain the target data of the second users corresponding to each second family group, where the target data includes at least one of individual indicators and business behavior data; Identify the family relationships of all second users in each second family group according to the target data of the second users corresponding to each second family group; Among them, the step of splitting each first family group according to the resident base station data of the first users to obtain at least one second family group corresponding to each first family group includes: Determine the second target users among the sixth users, where the sixth users are the first users who have not subscribed to the broadband service, and the second target users are the users who have not established a connection relationship with the first resident base station. The first resident base station is the night resident base station corresponding to the first users who have subscribed to the broadband service; Obtain the location information of the second resident base station corresponding to the second target users from the resident base station data of the second target users; Based on the longitude and latitude, screen the location information of the preset covered residential communities to obtain a set of preset covered residential communities, and the preset covered residential communities are broadband-covered communities; According to the location information of the second resident base station and the location information of the preset covered residential communities in the set of preset covered residential communities, determine the target residential community closest to the second resident base station in the preset covered residential communities; Obtain the residential community information of the target residential community as the residential community information of the second target users; Divide the first users with the same residential community information in each first family group into the same family group to obtain at least one second family group corresponding to each first family group.

2. The method according to claim 1, characterized in that, the step of splitting each first family group according to the resident base station data of the first users to obtain at least one second family group corresponding to each first family group includes: Determine the residential community information of each first user according to the resident base station data of each first user; Divide the first users with the same residential community information in each first family group into the same second family group, so as to obtain at least one second family group corresponding to each first family group.

3. The method according to claim 2, wherein, after dividing the first users with the same residential community information in each first family group into the same second family group to obtain at least one second family group corresponding to each first family group, the method further includes: Determine a third family group and a fourth family group in the at least one second family group, wherein the number of second users in the third family group is less than a preset quantity threshold, and the number of second users in the fourth family group is greater than or equal to the preset quantity threshold; Calculate the distance between the residential communities corresponding to the third family group and the fourth family group according to the residential community information corresponding to the third family group and the fourth family group respectively; Merge the third family group and the fourth family group when the distance is less than a preset distance threshold.

4. The method according to claim 2, wherein, the determining the residential community information of each first user according to the resident base station data of each first user includes: Determine a fifth user among all the first users, where the fifth user is a user who has handled a broadband service; Determine the night resident base station of the fifth user according to the resident base station data of the fifth user; Obtain the residential community information corresponding to the night resident base station as the residential community information of the fifth user.

5. The method according to claim 4, wherein, the determining the residential community information of each first user according to the resident base station data of each first user includes: Determine a sixth user among all the first users, where the sixth user is a user among the first users who has not handled a broadband service; According to the resident base station data of the sixth user, determine a first target user among the sixth users who has established a connection relationship with a first resident base station, where the first resident base station is any night resident base station corresponding to the fifth user; Obtain the residential community information corresponding to the first resident base station as the residential community information of the first target user.

6. The method according to claim 1, wherein, the individual indicators include age data and gender data, the service behavior data includes application program usage data, and the identifying the family relationships of all second users in each second family group according to the target data of the second users corresponding to each second family group includes: Draw a dimension cross matrix based on the target data corresponding to each second family group; Determine the family relationships of all second users in each second family group based on the dimension cross matrix to obtain the role information of each second user.

7. The method according to claim 1, wherein, The indicator data includes at least one of the following: call duration, number of calls, number of call days, number of call weeks, proportion of call duration, proportion of number of calls, proportion of number of call weeks, interaction index, influence, and intimacy.

8. The method according to claim 1, wherein, before determining, according to the indicator data and family relationship, a plurality of user pairs with family relationships in the recognition model, the method further includes: when obtaining the service handling information and address information of a first sample user, determining a second sample user having a family relationship with the first sample user according to the service handling information and address information, to obtain a first sample user pair; when obtaining the call data of a third sample user, determining call behavior characteristics according to the call data; determining a fourth sample user having a family relationship with the third sample user according to the call behavior characteristics, to obtain a second sample user pair; obtaining the indicator data of the first sample user pair and the second sample user pair, to obtain a training data set; training a logistic regression model based on the training data set to obtain the family relationship pair recognition model.

9. The method according to claim 8, wherein, the first sample user is a service handling user, the second sample user is a user associated with the service handled by the first sample user, and the third sample user is a non-service handling user.

10. The method according to claim 9, wherein, after recognizing, according to the target data of the second users corresponding to each second family group, the family relationships of all the second users in each second family group, the method further includes: obtaining the traffic usage data and voice usage data of each second user in the second family group; determining the family service saturation corresponding to the second family group according to the traffic usage data and voice usage data; determining a family portrait based on the family service saturation and the family relationships of all the second users in the second family group.

11. A family relationship recognition device, wherein, it includes: a determination module, configured to, when obtaining the indicator data of a plurality of users, determine, according to the indicator data and a family relationship pair recognition model, a plurality of user pairs having family relationships among the plurality of users, wherein each user pair corresponds to two users, and the family relationship pair recognition model is trained based on a logistic regression algorithm; a division module, configured to divide the plurality of user pairs into communities according to a community division model to obtain a plurality of first family groups, wherein each first family group includes at least one user pair, the users corresponding to the first family group are first users, and the community division model includes the Louvain algorithm; an acquisition module, configured to acquire the resident base station data of the first users corresponding to each first family group. A splitting module, which splits each first family group according to the resident base station data of the first user to obtain at least one second family group corresponding to each first family group, where the users corresponding to the second family group are second users, and the residential community information corresponding to all second users in the same second family group is the same; The obtaining module is further configured to obtain target data of second users corresponding to each second family group, where the target data includes at least one of individual indicators and service behavior data; An identifying module, configured to identify the family relationships of all second users in each second family group according to the target data of the second users corresponding to each second family group; Wherein, splitting each first family group according to the resident base station data of the first user to obtain at least one second family group corresponding to each first family group includes: Determining a second target user among the sixth users, where the sixth users are the first users who have not subscribed to the broadband service, and the second target user is a user who has not established a connection relationship with the first resident base station, and the first resident base station is the night resident base station corresponding to the first user who has subscribed to the broadband service; Obtaining the location information of the second resident base station corresponding to the second target user from the resident base station data of the second target user; Based on the longitude and latitude, screening the location information of the preset covered residential communities to obtain a set of preset covered residential communities, where the preset covered residential communities are broadband-covered communities; Determining the target residential community closest to the second resident base station among the preset covered residential communities according to the location information of the second resident base station and the location information of the preset covered residential communities in the set of preset covered residential communities; Obtaining the residential community information of the target residential community as the residential community information of the second target user; Dividing the first users with the same residential community information in each first family group into the same family group to obtain at least one second family group corresponding to each first family group.

12. An electronic device, Characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the family relationship recognition method according to any one of claims 1-10.

13. A computer-readable storage medium, Characterized in that, Computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a processor, the steps of the family relationship recognition method according to any one of claims 1-10 are implemented.

14. A computer program product, Characterized in that, The program product is stored in a non-volatile storage medium, and the program product is executed by at least one processor to implement the steps of the family relationship recognition method according to any one of claims 1-10.

Images