CN110543586B - Multi-user identity fusion method, device, equipment and storage medium - Google Patents

Abstract

The application discloses a multi-user identity fusion method, device, equipment and storage medium, and relates to the technical field of big data. The specific implementation plan is: obtain user identity data, the user identity data has at least two identity characteristics; according to the at least two identity characteristics of the user identity data, construct a graph network, the graph network includes: nodes representing identity characteristics and representing identity The connection edge of the associated relationship of the feature; according to the connection relationship between the nodes in the graph network, and the connection relationship between the node and the connection edge, the identity group of the same user is determined, and the identity group includes: multiple identity features. This technical solution associates the identity features of user identity data in the form of graph network, not only can accurately determine the identity group corresponding to multiple identity features of the same user, but also can be applied to any scene, avoiding the scope of use limited problem.

Description

Multi-user identity fusion method, device, equipment and storage medium

technical field

The present application relates to the field of computer technology, and in particular to a method, device, device and storage medium for the fusion of multiple user identities in big data technology.

Background technique

In the general environment of Internet popularity, associate virtual user identities (such as device IDs, network IDs, etc.) , can restore the complete human behavior from different expression carriers, thus creating huge product commercial value.

In the prior art, the solution for the fusion of multiple identities can be mainly based on preset rules, determine multiple different user identities that meet the same rule as belonging to the same user, and fuse the multiple user identities of the user to make them related to each other .

However, although this fusion method has a high accuracy rate of attribution judgment, it cannot be applied to complex scenarios because the rules used are artificially set, and the scope of use is limited.

Contents of the invention

Embodiments of the present application provide a method, device, device, and storage medium for merging multiple user identities, which are used to solve the problem that the existing merging methods cannot be applied to complex scenarios and the scope of use is limited.

In the first aspect, the present application provides a method for merging multiple user identities, including:

Obtaining user identity data, the user identity data having at least two identity characteristics;

Constructing a graph network according to at least two identity features of the user identity data, the graph network including: nodes representing identity features and connection edges representing association relationships of identity features;

According to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges, an identity group of the same user is determined, and the identity group includes: a plurality of identity features.

In this embodiment, by associating the identity features of user identity data in the form of a graph network, not only can the identity group corresponding to multiple identity features of the same user be accurately determined, but also it can be applied to any scene, avoiding problem of limited scope of use.

In a possible design of the first aspect, the acquiring user identity data includes:

Obtain preset configuration information, the configuration information including: data source type, data source path, extraction method and extraction cycle;

Extract the user identity data from the data source corresponding to the data source type according to the data source path, the extraction method and the extraction cycle.

In this embodiment, user data extraction is implemented based on information dependencies in preset configuration information, which can ensure that the data extraction task can be executed in a stable and orderly manner.

Optionally, the configuration information further includes: a field mapping relationship;

The method also includes:

According to the field mapping relationship, sequentially analyze the acquired user identity data, and extract at least two identity features of the user identity data;

In another possible design of the first aspect, the constructing a graph network according to at least two identity features of the user identity data includes:

Each identity feature in the user identity data is used as a node of the graph network, and the association relationship between every two identity features in the user identity data is used as a connection edge of the graph network to construct the graph network, the graph Each node and each connection edge in the network has attribute information respectively.

Through the above scheme, it can be seen that for the problem that different data may come from different systems, the extraction of user identity data, the identification and extraction of identity features in user identity data are realized through preset configuration information, and based on the extracted identity features Realized The construction of the graph network has a high degree of automation and low cost.

In yet another possible design of the first aspect, the determining the identity group of the same user according to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges includes:

determining the number of connections between adjacent nodes in the graph network according to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges;

Based on the number of connections between adjacent nodes in the graph network and a preset number of thresholds, a first connection relationship and a second connection relationship are determined, and the first connection relationship is that the number of connections between adjacent nodes is greater than the number of times A threshold connection relationship, the second connection relationship is a connection relationship in which the number of connections between adjacent nodes is less than or equal to the number of times threshold;

According to the first connection relationship and the second connection relationship, starting from the target node, traversing the nodes of the graph network outward in sequence, and determining the identity group of the user corresponding to the target node.

In this embodiment, by determining the identity group of the user corresponding to the target node based on the determined connection relationship, the accuracy of the obtained result is high.

In yet another possible design of the first aspect, the determining the identity group of the same user according to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges includes:

Determine the association relationship between nodes according to the connection relationship between nodes in the graph network, the connection relationship between nodes and connection edges, and the attribute information of each node;

Based on the association relationship between the nodes, the nodes in the graph network are aggregated to determine the identity group of the same user.

In this embodiment, the identity group of the same user is obtained based on the association relationship between nodes and through an aggregation method, which can ensure a high fusion rate.

In yet another possible design of the first aspect, the method further includes:

According to the identity group of the same user, determine a plurality of user identity features associated with the target identity feature in the identity group, and the target identity feature is any one of the user identity features included in the identity group;

Pushing a message to at least one identity feature among the plurality of user identity features.

In this embodiment, the commercial value of the product is improved by determining multiple user identity features in the identity group that are associated with the target identity feature, and then pushing messages to the users in a targeted manner.

Optionally, the determining multiple user identity features associated with the target identity feature in the identity group according to the identity group of the same user includes:

Retrieve, traverse and filter nodes in the identity group of the same user, and determine multiple user identity features associated with the target identity feature in the identity group.

In this embodiment, through the above-mentioned processes of node identity retrieval, node identity breadth traversal, and node identity feature screening, vertices that are connected to vertices corresponding to target identity features can be quickly derived.

In yet another possible design of the first aspect, the method further includes:

In the form of a graph database, storing the corresponding relationship between nodes and connection edges in the graph network;

The graph database includes: point storage, connection edge storage and attribute storage;

The point storage includes: node primary key, attribute information owned by the node and connection edges connected by the node;

The storage of the connection edge includes: the primary key of the connection edge, the starting point and the termination point connected by the connection edge, and the attribute information carried by the connection edge;

The attribute storage includes: the attribute primary key, the meaning represented by the attribute, and the specific content represented by the attribute.

In this embodiment, the vertices and connection edges of the graph database are described based on the association relationship between the identity features of the user identity data and the co-occurrence records of the identity features, so that the user identity data can solve the data fusion problem through the graph theory algorithm.

Optionally, the node primary key, the connection edge primary key, and the attribute primary key are all stored in an index manner.

In this embodiment, the convenience of retrieval and data management can be improved by constructing indexes on node primary keys, connection edge primary keys and attribute primary keys.

In the second aspect, the present application provides a device for merging multiple user identities, including:

An acquisition module, configured to acquire user identity data, where the user identity data has at least two identity characteristics;

A processing module, configured to construct a graph network according to at least two identity features of the user identity data, the graph network including: nodes representing identity features and connection edges representing association relationships of identity features;

The determination module is configured to determine the identity group of the same user according to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges, and the identity group includes: a plurality of identity characteristics.

In a possible design of the second aspect, the acquiring module is specifically configured to acquire preset configuration information, the configuration information including: data source type, data source path, extraction method, and extraction cycle; according to the data The source path, the extraction method, and the extraction period extract the user identity data from the data source corresponding to the data source type.

Optionally, the configuration information further includes: a field mapping relationship;

Correspondingly, the processing module is further configured to sequentially analyze the acquired user identity data according to the field mapping relationship, and extract at least two identity features of the user identity data.

In another possible design of the second aspect, the processing module is specifically configured to use each identity feature in the user identity data as a node of the graph network, and use every two identities in the user identity data The association relationship of features is used as the connection edge of the graph network to construct the graph network, and each node and each connection edge in the graph network has attribute information respectively.

In yet another possible design of the second aspect, the determining module is specifically configured to determine the relative The number of connections between adjacent nodes, based on the number of connections between adjacent nodes in the graph network and the preset number of thresholds, determine the first connection relationship and the second connection relationship, the first connection relationship is between adjacent nodes The number of connection times is greater than the number of times threshold, and the second connection relationship is a connection relationship whose connection times between adjacent nodes is less than or equal to the number of times threshold; according to the first connection relationship, the second connection relationship, starting from the target node, traversing the nodes of the graph network outward in sequence, and determining the identity group of the user corresponding to the target node.

In yet another possible design of the second aspect, the determination module is specifically configured to, according to the connection relationship between nodes in the graph network, the connection relationship between nodes and connection edges, and the attribute information of each node, Determine the association relationship between the nodes; based on the association relationship between the nodes, aggregate the nodes in the graph network to determine the identity group of the same user.

In yet another possible design of the second aspect, the determination module is further configured to determine, according to the identity group of the same user, a plurality of user identity features associated with the target identity feature in the identity group, so The target identity feature is any one of the user identity features included in the identity group;

The device also includes: a push module;

The push module is configured to push a message to at least one identity feature among the plurality of user identity features.

Optionally, the determination module is further specifically configured to perform retrieval, traversal and screening on nodes in the identity group of the same user, and determine multiple user identities in the identity group that have an association relationship with the target identity feature feature.

In yet another possible design of the second aspect, the processing module is further configured to store the correspondence between nodes and connection edges in the graph network in the form of a graph database;

The graph database includes: point storage, connection edge storage and attribute storage;

The point storage includes: node primary key, attribute information owned by the node and connection edges connected by the node;

The storage of the connection edge includes: the primary key of the connection edge, the starting point and the termination point connected by the connection edge, and the attribute information carried by the connection edge;

The attribute storage includes: the attribute primary key, the meaning represented by the attribute, and the specific content represented by the attribute.

Optionally, the node primary key, the connection edge primary key, and the attribute primary key are all stored in an index manner.

The device provided in the second aspect of the present application can be used to execute the method provided in the first aspect, and its implementation principle and technical effect are similar, and will not be repeated here.

In a third aspect, the present application provides an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the first aspect and all possible designs of the first aspect. described method.

In a fourth aspect, the present application provides a non-transitory computer-readable storage medium storing computer instructions, the computer instructions are used to enable the computer to execute the method described in the first aspect and possible designs of the first aspect.

In the fifth aspect, the present application provides a method for merging multiple user identities, including:

According to at least two identity characteristics of the user identity data, determine the association relationship of the at least two identity characteristics;

According to the association relationship of the at least two identity features, the identity group of the same user is determined.

An embodiment in the above application has the following advantages or beneficial effects: the identity group corresponding to multiple identity features of the same user can be accurately determined, and it can be applied to any scene and has a wide range of applications. Because of the technical means of associating the identity characteristics of user identity data in the form of a graph network, it overcomes the technical problems that the existing fusion methods cannot be applied to complex scenarios and the scope of use is limited, and can be applied to any scenario. , using a wide range of technical effects.

Other effects of the above optional manner will be described below in conjunction with specific embodiments.

Description of drawings

The accompanying drawings are used to better understand the solution, and do not constitute a limitation to the application. in:

FIG. 1 is a schematic flowchart of a method for merging multiple user identities according to a first embodiment of the present application;

Fig. 2 is a schematic diagram of the K-V form corresponding to point storage in the embodiment of the present application;

Fig. 3 is a schematic diagram of the K-V format corresponding to the connection edge storage in the embodiment of the present application;

Fig. 4 is a schematic diagram of the K-V format corresponding to attribute storage in the embodiment of the present application;

Fig. 5 is a schematic diagram of association of identity groups of the same person;

FIG. 6 is a schematic flowchart of a method for merging multiple user identities according to a second embodiment of the present application;

FIG. 7 is a schematic flowchart of a method for merging multiple user identities according to a third embodiment of the present application;

FIG. 8 is a schematic flowchart of a method for merging multiple user identities according to a fourth embodiment of the present application;

FIG. 9 is a schematic flowchart of a method for merging multiple user identities according to a fifth embodiment of the present application;

FIG. 10 is a schematic structural diagram of a multiple identity fusion device provided by an embodiment of the present application;

Fig. 11 is a block diagram of an electronic device used to implement the method for merging multiple user identities according to the embodiment of the present application.

Detailed ways

Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the general environment of Internet popularization, a large amount of user online information is generated every day. Usually, the user's online information includes the information of the user's identity, and the user's identity can be represented by a virtual user's identity or a real identity. Exemplary, the virtual user identity includes: various types of identification numbers (identity document, ID) on the Internet (including device ID, such as international mobile equipment identity (international mobile equipment identity, IMEI), advertising identifier (identifier for advertising, IDFA) etc.; network ID, such as Internet protocol (internet protocol, IP) address, access point (access point, AP), service set identifier (service setidentifier, SSID) etc.); real user identity includes: identity information (such as ID number , mobile phone number) and various asset information of users (such as cars and houses).

In practical applications, by associating the user's virtual identity with the user's real identity, the complete human behavior can be restored from different manifestation carriers (cars, houses, mobile device codes, etc.), thereby creating huge product commercial value. For example, based on various connected IDs, it is possible to portray a complete user portrait; to make accurate recommendations for users on different devices; to reach out to the environment and place precise advertisements for different user behaviors in stores; at the same time, it can also carry out inter-enterprise advantages Complementary, such as opening up the identities of a search website and an e-commerce website, recommending products that users have searched on the search website on the e-commerce website, so as to recommend products that the user may be interested in to the user in a targeted manner.

However, with the continuous accumulation of users' online information, the data that needs to be opened up is expanding rapidly, so the following challenging problems need to be solved:

From the perspective of computing storage: it is necessary to solve the problem of data processing at the PB level, where PB refers to petabyte, which is a higher-level storage unit, and 1PB=1024TB.

In terms of user scale: for tens of billions of user IDs, it is necessary to determine whether two pairs are the same person, which is approximately equivalent to 10 to the 20th power similarity calculation, which cannot be handled by the current computing resource capabilities of large Internet companies , needs to be optimized.

From the perspective of the market scenario: more and more companies hope to integrate the ID of Internet devices with their own data to enhance the vitality of their products. Therefore, it is necessary to consider how to privatize the fusion of virtual and real data and migrate it to the enterprise when the enterprise has limited resources.

From the perspective of technology: With the development of artificial intelligence (AI), new types of user IDs will inevitably emerge, such as face IDs, voiceprint IDs, and fingerprint IDs. Therefore, it is necessary to consider the fusion of existing virtual and real data. How to adaptively adapt to various new types of user IDs.

It can be seen from the introduction of the background technology that the multiple identity fusion scheme in the prior art is realized based on preset rules, which cannot be applied to complex scenarios, and the scope of use is limited. To solve this problem, the embodiment of the present application provides a multi-user The identity fusion method mainly uses graph theory technology to fuse the user's virtual and real identities, regards each identity feature of the user as a node in a large-scale graph, and uses graph theory algorithms to determine whether there is a strong correlation between two nodes The connection edge of , if it exists, is regarded as belonging to the same user, so as to achieve the purpose of identity fusion. The technical solution involves data extraction, data storage, data fusion computing, and associated retrieval. It supports privatization deployment and facilitates data fusion for small businesses.

It can be understood that, the execution subject of the embodiment of the present application may be an electronic device, for example, a terminal device such as a computer or a tablet computer, or a server, for example, a background processing platform and the like. Therefore, in this embodiment, a terminal device and a server are collectively referred to as an electronic device for explanation, and whether the electronic device is specifically a terminal device or a server can be determined according to actual conditions.

Below, the technical solution of the present application will be described in detail through specific embodiments. It should be noted that the following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

Fig. 1 is a schematic flowchart of a method for merging multiple user identities according to the first embodiment of the present application. As shown in Figure 1, the method may include the following steps:

S101. Acquire user identity data, where the user identity data has at least two identity characteristics.

In practical applications, data generally used for fusion is mainly divided into two categories, including Internet virtual data (virtual network data, VND) and real data (real data, RD). Internet virtual data involves users' online browsing data, search data, map positioning data, consumption data (for example, online shopping data), bayonet camera data, etc.; real data involves social data, government affairs data, enterprise data, consumption data (such as , offline shopping data), enterprise internal data (for example, bank data), etc.

The identity features of user identity data may include: virtual identity features and real identity features, among which virtual identity (virtual identity, VI) features specifically refer to the identity features of a series of activities of the user on the Internet, including various types of equipment information of the user , account information, etc. From the perspective of data types, real identity (RI) features include address information registered by the public security, domicile, address, household registration, etc., and can also include government or functional department information and data such as real estate, car properties, debts, and bank accounts; The actual identity feature can also be defined as the internal identity ID of the enterprise according to the specific enterprise usage scenarios.

It can be understood that the embodiment of the present application does not limit the identity features of user identity data, nor does it limit the specific manifestations of virtual identity features and real identity features, which can be determined according to actual conditions, and will not be repeated here.

In the embodiment of the present application, the purpose of this step is to obtain user identity data for fusion of multiple user identities. The user identity data needs to have at least two identity characteristics. extracted from.

S102. Construct a graph network according to at least two identity features of the above-mentioned user identity data.

Wherein, the graph network includes: nodes representing identity features and connection edges representing association relationships of identity features.

In practical applications, the usual data is relational form data, and the graph structure is described by an adjacency list. Therefore, it is generally necessary to create a point table and an edge table. However, due to the complex structure of the graph, especially when the node scale exceeds 100 million, it is necessary to use distributed storage to ensure the scalability of the system. Due to the selection of a general relational database, after the data is distributed and stored, the communication problem between the data will become more complicated, which will increase the design cost. Therefore, in the embodiment of the present application, the graph database is used to store the nodes representing the identity features and the connection edges representing the association relationship of the identity features. Since the graph database is a non-relational database, it uses graph theory to store the relationship information between entities , which reduces the organization cost of point edges.

In this embodiment, the vertices and connection edges of the graph database are described based on the association relationship between the identity features of the user identity data and the co-occurrence records of the identity features, so that the user identity data can solve the data fusion problem through the graph theory algorithm.

Exemplarily, in the embodiment of the present application, the method of the present application may further include the following steps:

In the form of a graph database, the corresponding relationship between nodes and connection edges in the graph network is stored.

Among them, the graph database includes: point storage, connection edge storage and attribute storage.

The point storage includes: the primary key of the node, the attribute information owned by the node and the connection edge of the node connection.

The connection edge storage includes: the primary key of the connection edge, the start point and the end point connected by the connection edge, and the attribute information carried by the connection edge.

The attribute storage includes: the attribute primary key, the meaning represented by the attribute, and the specific content represented by the attribute.

Further, in the embodiment of the present application, the node primary key, the connection edge primary key, and the attribute primary key are all stored in an index manner.

Specifically, in the embodiment of the present application, the graph database mainly involves storage of points, edges, and attributes. Optionally, the vertex-edge-attributes are organized, indexed and stored in the form of key-value (Key-Value, K-V) pairs within the storage medium.

For example, FIG. 2 is a schematic diagram of the K-V format corresponding to the point storage in the embodiment of the present application. Fig. 3 is a schematic diagram of the K-V format corresponding to the connection edge storage in the embodiment of the present application. FIG. 4 is a schematic diagram of the K-V format corresponding to attribute storage in the embodiment of the present application. As shown in Figure 2, when the point storage is represented by the K-V form (key)-value (value), the point primary key is mainly composed of the node primary key (vertex_id), the attribute information owned by the node, and the edges connected to the node. Wherein, both the attribute information and the connection edge store the corresponding primary key, that is, the attribute primary key (property_id) shown in FIG. 3 and the edge primary key (edge_id) shown in FIG. 4 .

It is worth noting that in practical applications, the primary key of a node is actually the identifier of a vertex, the primary key of an attribute is actually the identifier of an attribute, and the primary key of an edge is actually the identifier of a connecting edge.

Referring to Figure 2, for example, for two nodes containing identity feature information, the primary keys of the nodes are 12345 and 67894 respectively, which specifically represent a certain ID card and a certain mobile phone number, then, point 12345 has two attributes P-123 and P-124, meanwhile, point 12345 has two edges E-12323 and E-86743; point 67894 has two attributes P-376 and P-377, meanwhile, point 67894 has two edges E-12323 and E-86743.

Referring to FIG. 3 , the connection edge storage is composed of the primary key (edge_id) of the edge, the start point and the end point connected by the connection edge, and the attributes carried on the connection edge. Among them, the start and end points are the primary key (vertex_id) of the corresponding point, and the attribute is the attribute in the point storage, and the value corresponds to the attribute primary key (property_id).

For example, the edge whose primary key is E-12323 has a starting point of 12345 and an ending point of 67894, and the connecting edge primary key E-12323 has two edge attributes P-73625 and P-5325. The edge whose primary key is E-86743 has a starting point of 12345 and an ending point of 87251, and the connecting edge primary key E-86743 has two edge attributes P-56342 and P-672.

Referring to FIG. 4 , the property storage is composed of the property primary key (property_id), the meaning represented by the current property (property meaning: property_key), and the specific content represented by the property (property content: property_value).

For example, for the two attributes P-123 and P-124 that point 12345 has, wherein, P-123 indicates that the characteristic type is a mobile phone, that is, ID-TYPE=phone, and P-124 indicates that the characteristic information is a specific mobile phone number, namely , ID-INFO=138****1232. For the two attributes P-376 and P-377 that point 67894 has, P-376 indicates that the characteristic type is an ID card, that is, ID-TYPE=idcard, and P-124 indicates that the characteristic information is a specific ID number, namely , ID-INFO=3401**********1273.

It is worth noting that in the embodiment of this application, in order to facilitate retrieval and data management, each node, connection edge, and attribute's primary key are indexed, and support for a specific type of attribute is indexed, so that it is convenient to pass the attribute Retrieve nodes and/or connected edges.

Exemplarily, in this embodiment, based on the above-mentioned analysis of each data structure in the graph database, various identity IDs can construct a graph relationship, wherein the attributes on the connecting edge include the identities represented by the two connected nodes The specific connection information of features, such as connection time, connection frequency, etc., can provide feature representation for subsequent calculations.

In this embodiment, the user identity data is stored in the form of a K-V-based graph database. Specifically, distributed K-V storage can be used for trillion-scale data, and memory or stand-alone K-V storage can be used for data within tens of millions. storage.

S103. Determine an identity group of the same user according to the connection relationship between nodes and the connection relationship between nodes and connection edges in the graph network, where the identity group includes: multiple identity features.

In the embodiment of the present application, after the graph network is constructed based on at least two identity features of the user identity data, the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges can be determined. Therefore, the identity group of the same user can be determined based on the connection relationship between nodes and the connection relationship between nodes and connection edges.

Specifically, in the embodiment of the present application, the step of determining the identity group of the same user based on the created graph network can be understood as a process of data fusion, that is, performing fusion calculation on each identity feature in the graph network, specifically Yes, according to the topological properties of the identity feature itself and the node attributes it mounts, other identity features that have an implicit connection relationship with the identity feature are mined, and finally an identity group (ID-group) in the dimension of natural persons is formed.

In practical applications, the methods of identity fusion calculation can be divided into rule mode and model mode. For specific implementation principles of the rule mode and the model mode, reference may be made to the descriptions in the embodiments shown in FIG. 7 and FIG. 8 in the following embodiments, and details are not repeated here.

It is worth noting that, in the embodiment of the present application, no matter it is a rule mode or a model mode, it involves a large number of computational problems of repeatedly traversing the graph network. For scenarios with small data scale, data clipping can be performed by narrowing down the target group of demand (such as clipping by city or by each type of feature) to obtain a data set with a small amount of data, and then perform stand-alone operations to determine the identity of the same user group. For scenarios with large data scale, distributed graph computing, such as computing frameworks such as GraphX, GraphLab, and Giraph, can be used to determine the identity group of the same user.

Exemplarily, in the embodiment of the present application, the identity group ID-group of the same user determined above may be expressed as a set of identity identifiers of a natural person. For example, FIG. 5 is a schematic diagram of association of identity groups of the same person. Referring to Figure 5, the identity of a natural person is expanded separately (two-by-two to build a connection relationship), and each identity feature pair is poured into the graph network created above, which can connect the relationship between identity features. Get a strongly connected graph of identity features.

Exemplarily, in the schematic diagram shown in FIG. 5 , the representation forms of identity features may include: IMEI, AP, IP address, IDFA, mobile phone number, ID number, house, car, and others.

The method of multiple user identity fusion provided by the embodiment of the present application obtains user identity data and constructs a map network according to at least two identity features of the user identity data. The map network includes: nodes representing identity features and identity features According to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges, the identity group of the same user is determined, and the identity group includes: multiple identity features. In this technical solution, the identity features of user identity data are associated in the form of graph network, not only can accurately determine the identity group corresponding to multiple identity features of the same user, but also it can be applied to any scene, avoiding the Issues of limited use.

Exemplarily, on the basis of the above-mentioned embodiments, FIG. 6 is a schematic flowchart of a method for fusing multiple user identities according to the second embodiment of the present application. As shown in Figure 6, in this embodiment, the above S101 can be implemented through the following steps:

S601. Obtain preset configuration information, where the configuration information includes: data source type, data source path, extraction mode, and extraction cycle.

In the embodiment of this application, since the user identity data to be fused can be Internet virtual data and real data, and different user identity data can be stored in different types of storage systems after being generated, for example, HDFS, HIVE, MYSQL, NoSQL etc. Because, in order to obtain the user identity data from different storage systems, it is necessary to obtain preset configuration information, so as to obtain the user identity data from different storage systems according to the preset configuration information.

Correspondingly, in this embodiment, the above preset configuration information may include data source type (HDFS, HIVE, MYSQL, NoSQL...), data source path (host: port (host: port), hdfspath...), extraction method , Extraction cycle. Among them, the data source type is used to represent the type of system that stores user identity data, the data source path is used to represent the route passed when extracting user identity data, the extraction method is used to represent the method used for data extraction, and the extraction cycle is used to represent How often to automate data extraction. The extraction period can also be regarded as a scheduling frequency (execution period), which is used to indicate that the user data extraction task is executed on a daily level, an hourly level, or a single time.

In this embodiment, a piece of user identity data must contain at least two identity features, each identity feature is represented by a point, and there is a weak link between these two points. For example, if the identity feature can be equipment code, mobile phone number, identity number, account number, etc., then a piece of user identity data includes at least two of the equipment code, mobile phone number, identity number, and account number.

S602. Extract user identity data from the data source corresponding to the data source type according to the data source path, extraction method, and extraction period.

In this embodiment, based on the preset configuration information, first determine the data source type, data source path, extraction method and extraction cycle, and then select hadoop/spark/stand-alone according to the extraction method, based on the length of each interval extraction cycle of the data source path from Extract user identity data from the data source corresponding to the data source type.

It can be understood that the user data extraction is implemented based on the information dependencies in the preset configuration information, which can ensure the stable and orderly execution of the data extraction task.

Optionally, in the embodiment of the present application, if the above configuration information further includes: field mapping relationship; then, the method may also include the following steps:

S603. According to the field mapping relationship, sequentially analyze the acquired user identity data, and extract at least two identity features of the user identity data.

Among them, the field mapping relationship is used to indicate which fields (identity features in time) are extracted from the obtained user identity data as nodes and connection edges of the graph network, and which attributes are marked as point attributes (for example, point attributes include: mobile phone No., device identification), which attributes are used as edge attributes (edge attributes can refer to information such as login time).

Therefore, in this embodiment, each line of data in the obtained user identity data can be analyzed according to the field mapping relationship, and at least two identity features of each line of data can be determined, which provides an implementation for subsequent graph network construction possible.

Correspondingly, on the basis of the foregoing embodiments, for example, as shown in FIG. 6 , the foregoing step 102 may be implemented through the following steps:

S604. Construct a graph network by using each identity feature in the user identity data as a node of the graph network, and using an association relationship between every two identity features in the user identity data as a connection edge of the graph network.

Wherein, each node and each connection edge in the graph network has attribute information respectively.

In this embodiment, when at least two identity features of the user identity data are determined according to the field mapping relationship, the association relationship between each two identity features and the attribute information of each node and each connection edge are determined. Therefore, By using each identity feature of the user identity data as the vertex of the graph network, and using the association relationship between each two identity features as the connection edge of the graph network, the graph network constructed can be obtained.

From the above analysis, it can be seen that user identity data can be organized into structural data with start point, start point attribute, end point, end point attribute, connection edge, and connection edge attribute. The structural data is actually a directed graph, the relationship between nodes can be configured, and the output format of the structural data can be json, proto, csv. The embodiment of the present application does not limit the specific output form, which can be selected according to the actual situation.

Further, operations such as node deduplication and attribute merging are performed on the structural data formed based on user identity data to ensure that the nodes corresponding to the identity characteristics of the newly added data can be inserted into the graph network, and the identity characteristics of the original data correspond to Nodes can perform corresponding update operations.

In the same way, it is also possible to deduplicate connection edges and merge attributes for structural data formed based on user identity data, that is, to merge edges with the same connection relationship in multiple pieces of data, and to remove duplicate connection edges and attributes. The merged form reconstructs the information in the user identity data. Finally, based on the reconstructed structural data, the extracted attribute information such as vertices and connection edges can be updated to the graph network.

The method for merging multiple user identities provided in the embodiment of the present application obtains preset configuration information, which includes: data source type, data source path, extraction method, and extraction cycle, according to the data source path, extraction method, and extraction cycle , extract user identity data from the data source corresponding to the data source type, and when the configuration information also includes: field mapping relationship, the obtained user identity data can be analyzed in turn according to the field mapping relationship, and the user identity data extracted has At least two identity features of user identity data, and each identity feature in the user identity data is used as a node of the graph network, and the association relationship between each two identity features is used as a connection edge of the graph network to construct a graph network. In this technical solution, aiming at the problem that different data may come from different systems, the extraction of user identity data, the identification and extraction of identity features in user identity data are realized through preset configuration information, and the map is realized based on the extracted identity features. The construction of the network has a high degree of automation and low cost.

Exemplarily, on the basis of the above-mentioned embodiments, FIG. 7 is a schematic flowchart of a method for fusing multiple user identities according to the third embodiment of the present application. As shown in Figure 7, in this embodiment, the above S103 can be implemented through the following steps:

S701. Determine the number of connections between adjacent nodes in the graph network according to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges.

In the graph network, which nodes have a connected relationship can be determined according to the connection relationship between nodes, and the basic information of the connection between nodes can be determined according to the connection relationship between nodes and connection edges, such as connection time, connection times, etc. , thus, the number of connections between adjacent nodes in the graph network can be determined according to the connection relationship between nodes and the basic information of connectivity between nodes.

In this embodiment, since the connection relationship between nodes and the connection relationship between nodes and connection edges are also node connection information, the number of connections between adjacent nodes in the graph network can also be interpreted as according to multiple presets The node connection information in the time period determines the number of connections between adjacent nodes.

S702. Determine a first connection relationship and a second connection relationship based on the number of connections between adjacent nodes in the graph network and a preset number of times threshold.

Wherein, the first connection relationship is a connection relationship in which the number of connections between adjacent nodes is greater than a threshold, and the second connection relationship is a connection relationship in which the number of connections between adjacent nodes is less than or equal to the threshold.

The embodiment of the present application mainly performs the calculation of identity fusion based on the rule mode. Specifically, in this implementation mode, the number of connections between adjacent nodes in the graph network, the node connection information in different time periods, and the definition The preset number of thresholds, and then according to the node connection information in different time periods and the number of connections between adjacent nodes, determine the relationship between the number of connections between adjacent nodes and the number of times threshold, so as to determine the Which connection relationship does it belong to.

In practical applications, the first connection relationship may also be called a strong connection relationship, and the second connection relationship may also be called a weak connection relationship.

S703. According to the first connection relationship and the second connection relationship, starting from the target node, traverse the nodes of the graph network outward in sequence, and determine the identity group of the user corresponding to the target node.

In this embodiment, after the connection relationship between adjacent nodes is determined, each node in the graph network can be used as a starting point to traverse to the surrounding area, and the first connection relationship, For the determination of the second connection relationship, the identity features corresponding to all the node sets satisfying the first connection relationship are taken as an identity group. Similarly, for the target node, by traversing all the identity groups, according to a certain strategy (for example, finding the smallest connected subgraph), the identity group of the user corresponding to the target node can be determined.

It can be understood that, in the embodiment of the present application, the depth (out-degree) of node traversal can be determined according to actual conditions, which is not limited in this embodiment. Typically, the depth of traversal is generally 3 degrees.

It can be seen from the above analysis that in this embodiment, based on the number of connections between adjacent nodes in the graph network and the preset number of thresholds, the first connection relationship and the second connection relationship are determined. The first connection relationship is the connection between adjacent nodes. The number of connections between nodes is greater than the number of times threshold, and the second connection relationship is the connection between adjacent nodes whose number of connections is less than or equal to the number of times threshold. According to the first connection relationship and the second connection relationship, starting from the target node, the The nodes of the graph network are traversed externally to determine the identity group of the user corresponding to the target node, that is, the solution is based on the fusion method of the rule pattern, and the obtained result has a high accuracy rate.

Exemplarily, on the basis of the above-mentioned embodiments, FIG. 8 is a schematic flowchart of a method for fusing multiple user identities according to the fourth embodiment of the present application. The difference between this embodiment and the embodiment shown in FIG. 7 lies in the way that the two embodiments determine the identity group of the same user. Specifically, as shown in FIG. 8, in this embodiment, the above S103 may be implemented through the following steps:

S801. Determine the association relationship between nodes according to the connection relationship between nodes in the graph network, the connection relationship between nodes and connection edges, and the attribute information of each node.

In this embodiment, the calculation of identity fusion is mainly based on the model mode. Specifically, the nodes are characterized according to the connection relationship between nodes, the connection relationship between nodes and connection edges, and the attribute information of each node. For example, ID-Embedding is performed. The purpose of ID-Embedding is to extract a set of features (a set of vectors) for each node in the graph network to achieve the purpose of mathematical operations between nodes.

It is understandable that there are many methods for node characterization, for example, node2vec, graph-embedding, etc. The method actually adopted can be determined according to actual needs, and will not be repeated here.

In the embodiment of this application, in order to meet more demand scenarios, a characterization scheme based on attribute data types can be used, which is a general feature representation method. Specifically, it can be based on different types of attribute features: string , int, double, enum, for related encoding. For example, the string type can perform numerical normalization encoding according to onehot character encoding and int.

S802. Based on the association relationship between the nodes, aggregate the nodes in the graph network to determine the identity group of the same user.

In this embodiment, the nodes are clustered based on the association relationship between the nodes, that is, the nodes with high similarity (association) are aggregated using a similarity algorithm to form a strongly related group. Wherein, the similarity algorithm may be selected according to the difference of the feature attributes extracted in S801. For example, the Jaccard similarity algorithm can be used for discrete features, the cosine similarity can be used for continuous feature vectors, and the Euclidean similarity can be used for numerical features.

From the above analysis, it can be known that after determining the association relationship between nodes, the corresponding degree of association between nodes can be obtained. Therefore, different algorithms can be selected to cluster nodes. For example, the classic Louvain community discovery algorithm can also be used. The k-means algorithm for clustering. The final output is a high-confidence identity group for the same user.

The method for merging multiple user identities provided by the embodiment of the present application determines the association relationship between nodes according to the connection relationship between nodes in the graph network, the connection relationship between nodes and connection edges, and the attribute information of each node. Based on the association relationship between nodes, the nodes in the graph network are aggregated to determine the identity group of the same user. In this technical solution, a fusion method based on a model mode can ensure a high fusion rate.

It is worth noting that in practical applications, the fusion methods based on the rule mode and the model mode can be used in combination, that is, the two complement each other to form a complete fusion system. In the embodiment of the present application, distributed and non-distributed computing can be selected according to the data scale, thus facilitating independent deployment from an engineering point of view.

Exemplarily, on the basis of any of the foregoing embodiments, FIG. 9 is a schematic flowchart of a method for fusing multiple user identities according to the fifth embodiment of the present application. Referring to Figure 9, the method may also include the following steps:

S901. According to the identity group of the same user, determine a plurality of user identity features associated with a target identity feature in the identity group, where the target identity feature is any one of the user identity features included in the identity group.

In this embodiment, the scheme of determining multiple associated user identity features of the target identity feature according to the identity group is actually a process of associated retrieval. Specifically, the association retrieval is mainly a process of graph traversal retrieval based on the strongly connected graph formed by S103 in the embodiment shown in FIG. 1 and the association relationship shown in FIG. 5 .

Specifically, based on the given source node type, identity characteristics of the source node, and target node type, etc., the connected node identifier and corresponding score can be output, which represents the degree of association between the connected node and the source node and the target node. . Since the connection relationship between nodes has formed a connected graph, as shown in Figure 5, the identity of the target identity feature can be intuitively deduced according to the target identity feature, and then all users who have an association relationship with the target identity feature can be obtained identity traits.

Exemplarily, in this embodiment, this step can be implemented in the following manner:

The nodes in the identity group of the same user are retrieved, traversed and screened to determine multiple user identity features associated with the target identity feature in the identity group.

In the embodiment of the present application, the process of deriving identity feature connectivity can be divided into: node identity retrieval, node identity breadth traversal, and node identity feature screening.

Specifically, node identity retrieval: From the introduction in the embodiment shown in FIG. 1 above, it can be seen that the point storage mainly includes the node primary key (KEY), the attribute information owned by the node and the connection edges of the node connection. By building an index on the attribute primary key (for example, building an index on ID-TYPE and ID-INFO), it can provide improved retrieval performance. For example, if it is necessary to retrieve the node whose mobile phone number is 139xxxxxxxx, the process of retrieving the node is to query the data with ID-TYPE=phone and ID-INFO=139xxxxxxxx.

Breadth traversal of node identity: node traversal of graph-based breadth first search (BFS). Starting from the target node corresponding to the target identity feature, from the inside to the outside, sequentially traverse the nodes connected to it with 1 layer, 2 layers...n layers (can be controlled by parameters).

Exemplarily, in the schematic diagram shown in Figure 5, for the mobile phone number in Figure 5, the first layer obtains IMEI, IDFA, AP, IP address, etc., and the second layer obtains the car, house, etc. From the point storage shown in Figure 2 above, it can be seen that the process of BFS is the process of traversing the connection edges stored in the value of the node. One-degree traversal of a node only requires one K-V search, which greatly improves the traversal efficiency.

Screening of node identity characteristics: By traversing the nodes in the graph network, all the identity groups connected to the nodes corresponding to the target identity characteristics can be obtained. Since the attribute primary key of the node has an index, it can support retrieval based on the index of the attribute primary key The results are filtered. For example, to obtain the idfa connected to the mobile phone, one round of traversal can get the result, and the nodes with non-ID-TYPE=idfa will be filtered out.

Therefore, through the above processes of node identity retrieval, node identity breadth traversal, and node identity feature screening, vertices that are connected to the corresponding vertex of the target identity feature can be quickly derived.

In this embodiment, the online identity feature derivation based on graph traversal, by using the storage and indexing scheme of the graph network, compared with the existing scheme of storing the mapping relationship of identity features through the positive direction table, the average response effect is significantly improved, especially when When the connected path step length (degree) is greater than 2 steps, the average response performance is increased by 10 times.

S902. Push a message to at least one identity feature among the plurality of user identity features.

In this embodiment, for the identity group of the same user, after determining multiple user identity features in the identity group that are associated with the target identity feature, a message may be pushed to at least one of the multiple user identity features.

For example, when the identities of a search website and an e-commerce website are connected, after the user searches for a product on the search website, the product that the user has searched for can be recommended on the e-commerce website when the user logs in to the e-commerce website, thereby having The products that the user may be interested in are recommended to the user in a targeted manner.

It can be seen from the above analysis that in this embodiment, according to the identity group of the same user, multiple user identity features that have an association relationship with the target identity feature in the identity group are determined, and the target identity feature is the identity group included. Any one of the user identity features, pushing a message to at least one of the plurality of user identity features. The technical solution realizes targeted pushing of messages to users and improves the commercial value of products.

To sum up, in the technical implementation of the embodiment of the present application, each identity feature in the user identity data is regarded as a node in the graph network, and the connection relationship between several weakly related identity feature pairs is strengthened through the graph theory algorithm. Form a strong relationship pair to achieve the purpose of identity fusion, which involves a complete set of solutions for data extraction, data storage, fusion computing, and associated retrieval, supports privatization deployment, and facilitates data fusion for small enterprises.

The above describes the specific implementation of the multiple identity fusion method mentioned in the embodiment of the present application. The following is the embodiment of the device of the present application, which can be used to implement the method embodiment of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

FIG. 10 is a schematic structural diagram of an apparatus for fusion of multiple identities provided by an embodiment of the present application. The apparatus can be integrated in or implemented by electronic equipment, and the electronic equipment can be a terminal equipment or a server. As shown in Figure 10, in this embodiment, the device 100 for the fusion of multiple identities may include:

An acquisition module 1001, configured to acquire user identity data, the user identity data having at least two identity characteristics;

The processing module 1002 is configured to construct a graph network according to at least two identity features of the user identity data, and the graph network includes: nodes representing identity features and connection edges representing association relationships of identity features;

The determination module 1003 is configured to determine the identity group of the same user according to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges, and the identity group includes: multiple identity features.

In a possible design of the embodiment of the present application, the acquisition module 1001 is specifically configured to acquire preset configuration information, the configuration information including: data source type, data source path, extraction mode, and extraction cycle; according to the The data source path, the extraction method and the extraction period extract the user identity data from the data source corresponding to the data source type.

Exemplarily, the configuration information further includes: field mapping relationship;

Correspondingly, the processing module 1002 is further configured to sequentially analyze the acquired user identity data according to the field mapping relationship, and extract at least two identity features of the user identity data.

In another possible design of the present application, the processing module 1002 is specifically configured to use each identity feature in the user identity data as a node of the graph network, and use every two identities in the user identity data The association relationship of features is used as the connection edge of the graph network to construct the graph network, and each node and each connection edge in the graph network has attribute information respectively.

In yet another possible design of the embodiment of the present application, the determining module 1003 is specifically configured to determine the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges in the graph network. The number of connections between adjacent nodes, based on the number of connections between adjacent nodes in the graph network and the preset number of thresholds, determine the first connection relationship and the second connection relationship, the first connection relationship is the adjacent node The number of connections between adjacent nodes is greater than the number of times threshold, and the second connection relationship is a connection relationship with the number of connections between adjacent nodes less than or equal to the number of times threshold; according to the first connection relationship, the second The connection relationship starts from the target node, traverses the nodes of the graph network outwards in sequence, and determines the identity group of the user corresponding to the target node.

In yet another possible design of the embodiment of the present application, the determination module 1003 is specifically configured to, according to the connection relationship between nodes in the graph network, the connection relationship between nodes and connection edges, and the attribute information of each node , determine the association relationship between the nodes; based on the association relationship between the nodes, aggregate the nodes in the graph network to determine the identity group of the same user.

In any of the above-mentioned possible designs of the embodiment of the present application, the determination module 1003 is further configured to determine, according to the identity group of the same user, a plurality of user identity features associated with the target identity feature in the identity group , the target identity feature is any one of the user identity features included in the identity group;

Correspondingly, the device also includes: a push module;

The push module is configured to push a message to at least one identity feature among the plurality of user identity features.

In the embodiment of the present application, the determination module 1003 is also specifically configured to perform retrieval, traversal and screening on the nodes in the identity group of the same user, and determine the node in the identity group that has an association relationship with the target identity feature. Multiple user identity characteristics.

In any of the above-mentioned possible designs of this embodiment, the above-mentioned processing module 1002 is further configured to store the corresponding relationship between nodes and connection edges in the graph network in the form of a graph database;

Wherein, the graph database includes: point storage, connection edge storage and attribute storage;

The point storage includes: node primary key, attribute information owned by the node and connection edges connected by the node;

The storage of the connection edge includes: the primary key of the connection edge, the starting point and the termination point connected by the connection edge, and the attribute information carried by the connection edge;

The attribute storage includes: the attribute primary key, the meaning represented by the attribute, and the specific content represented by the attribute.

Optionally, the node primary key, the connection edge primary key, and the attribute primary key are all stored in an index manner.

The device provided in the embodiment of the present application can be used to execute the method in the embodiment shown in FIG. 1 to FIG. 9 , and its implementation principle and technical effect are similar, and details are not repeated here.

It should be noted that it should be understood that the division of each module of the above device is only a division of logical functions, and may be fully or partially integrated into one physical entity or physically separated during actual implementation. And these modules can all be implemented in the form of calling software through processing elements; they can also be implemented in the form of hardware; some modules can also be implemented in the form of calling software through processing elements, and some modules can be implemented in the form of hardware. For example, the determining module may be a separate processing element, or may be integrated in a chip of the above-mentioned device. In addition, it may be stored in the memory of the above-mentioned device in the form of program code, and a certain processing element of the above-mentioned device may Call and execute the functions of the modules identified above. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, and can also be implemented independently. The processing element mentioned here may be an integrated circuit with signal processing capability. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or an instruction in the form of software.

For example, the above modules may be one or more integrated circuits configured to implement the above method, for example: one or more specific integrated circuits (application specific integrated circuit, ASIC), or one or more microprocessors (digital signal processor, DSP), or, one or more field programmable gate arrays (field programmable gate array, FPGA), etc. For another example, when one of the above modules is implemented in the form of a processing element scheduling program code, the processing element may be a general-purpose processor, such as a central processing unit (central processing unit, CPU) or other processors that can call program codes. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server or data center Transmission to another website site, computer, server, or data center by wired (eg, coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (eg, infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, or a magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, a solid state disk (SSD)).

Further, according to the embodiments of the present application, the present application also provides an electronic device and a readable storage medium.

Fig. 11 is a block diagram of an electronic device used to implement the method for merging multiple user identities according to the embodiment of the present application. Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the applications described and/or claimed herein.

As shown in FIG. 11 , the electronic device includes: one or more processors 1101 , a memory 1102 , and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and can be mounted on a common motherboard or otherwise as desired. The processor may process instructions executed within the electronic device, including instructions stored in or on the memory, to display graphical information of a GUI on an external input/output device such as a display device coupled to an interface. In other implementations, multiple processors and/or multiple buses may be used with multiple memories and multiple memories, if desired. Likewise, multiple electronic devices may be connected, with each device providing some of the necessary operations (eg, as a server array, a set of blade servers, or a multi-processor system). In FIG. 11, a processor 1101 is taken as an example.

The memory 1102 is a non-transitory computer-readable storage medium provided in this application. Wherein, the memory stores instructions executable by at least one processor, so that the at least one processor executes the method for fusing multiple user identities provided in this application. The non-transitory computer-readable storage medium of the present application stores computer instructions, and the computer instructions are used to make a computer execute the method for fusing multiple user identities provided in the present application.

The memory 1102, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as the program instructions/modules corresponding to the method for the fusion of multiple user identities in the embodiment of the present application ( For example, the acquisition module 1001, the processing module 1002 and the determination module 1003 shown in Fig. 10). The processor 1101 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions and modules stored in the memory Y02, that is, realizes the method of fusion of multiple user identities in the above method embodiments.

The memory 1102 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of an electronic device fused with multiple user identities Wait. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the storage 1102 may optionally include storages that are set remotely relative to the processor 1101, and these remote storages may be connected to the electronic device that integrates multiple user identities 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.

The electronic device with multiple user identities fused may also include: an input device 1103 and an output device 1104 . The processor 1101, the memory 1102, the input device 1103, and the output device 1104 may be connected through a bus or in other ways, and connection through a bus is taken as an example in FIG. 11 .

The input device 1103 can receive input digital or character information, and generate key signal input related to user settings and function control of electronic equipment fused with multiple user identities, such as touch screen, small keyboard, mouse, trackpad, touchpad, and pointer , one or more mouse buttons, trackballs, joysticks, and other input devices. The output device 1104 may include a display device, an auxiliary lighting device (eg, LED), a tactile feedback device (eg, a vibration motor), and the like. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.

These computing programs (also referred to as programs, software, software applications, or codes) include machine instructions for a programmable processor and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine language calculation program. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or means for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with the user, the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and may be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.

The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.

A computer system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.

The embodiment of the present application also provides a method for merging multiple user identities, including:

According to at least two identity characteristics of the user identity data, determine the association relationship of the at least two identity characteristics;

According to the association relationship of the at least two identity features, the identity group of the same user is determined.

For the specific implementation principles of this embodiment, refer to the descriptions of the above-mentioned embodiments shown in FIG. 1 to FIG. 9 , and will not be repeated here.

According to the technical solution of the embodiment of the application, by acquiring user identity data, a graph network is constructed according to at least two identity features of the user identity data, and the graph network includes: nodes representing identity features and connecting edges representing identity feature relationships , according to the association relationship between nodes in the graph network, and the association relationship between nodes and connection edges, the identity group of the same user is determined, and the identity group includes: a plurality of identity features. In this technical solution, the identity features of user identity data are associated in the form of graph network, not only can accurately determine the identity group corresponding to multiple identity features of the same user, but also it can be applied to any scene, avoiding the Issues of limited use.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present application may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present application can be achieved, no limitation is imposed herein.

The above specific implementation methods are not intended to limit the protection scope of the present application. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims (10)

1. A method for merging multiple user identities, comprising: Obtaining user identity data, the user identity data having at least two identity characteristics; Constructing a graph network according to at least two identity features of the user identity data, the graph network including: nodes representing identity features and connection edges representing association relationships of identity features; According to the connection relationship between nodes in the graph network, the connection relationship between nodes and connection edges, determine the identity group of the same user, the identity group includes: a plurality of identity features; The determining the identity group of the same user according to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges includes: determining the number of connections between adjacent nodes in the graph network according to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges; Based on the number of connections between adjacent nodes in the graph network and a preset number of thresholds, a first connection relationship and a second connection relationship are determined, and the first connection relationship is that the number of connections between adjacent nodes is greater than the number of times A threshold connection relationship, the second connection relationship is a connection relationship in which the number of connections between adjacent nodes is less than or equal to the number of times threshold; According to the first connection relationship and the second connection relationship, starting from the target node, traversing the nodes of the graph network in sequence, and determining the identity group of the user corresponding to the target node; The determining the identity group of the same user according to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges also includes: Determine the association relationship between nodes according to the connection relationship between nodes in the graph network, the connection relationship between nodes and connection edges, and the attribute information of each node; Based on the association relationship between the nodes, aggregate the nodes in the graph network to form a strongly related group; according to the identity group of the user corresponding to the target node and the strongly related group, determine the identity group of the same user . 2. The method according to claim 1, wherein said acquiring user identity data comprises: Obtain preset configuration information, the configuration information including: data source type, data source path, extraction method and extraction cycle; Extract the user identity data from the data source corresponding to the data source type according to the data source path, the extraction method and the extraction cycle. 3. The method according to claim 2, wherein the configuration information further comprises: field mapping relationship; The method also includes: According to the field mapping relationship, the acquired user identity data is parsed in sequence, and at least two identity features of the user identity data are extracted. 4. The method according to any one of claims 1-3, wherein the method further comprises: According to the identity group of the same user, determine a plurality of user identity features associated with the target identity feature in the identity group, and the target identity feature is any one of the user identity features included in the identity group; Pushing a message to at least one identity feature among the plurality of user identity features. 5. The method according to claim 4, wherein, according to the identity group of the same user, determining a plurality of user identity features associated with the target identity feature in the identity group comprises: Retrieve, traverse and filter nodes in the identity group of the same user, and determine multiple user identity features associated with the target identity feature in the identity group. 6. The method according to any one of claims 1-3, wherein the method further comprises: In the form of a graph database, storing the corresponding relationship between nodes and connection edges in the graph network; The graph database includes: point storage, connection edge storage and attribute storage; The point storage includes: node primary key, attribute information owned by the node and connection edges connected by the node; The storage of the connection edge includes: the primary key of the connection edge, the starting point and the termination point connected by the connection edge, and the attribute information carried by the connection edge; The attribute storage includes: the attribute primary key, the meaning represented by the attribute, and the specific content represented by the attribute. 7. The method according to claim 6, wherein the node primary key, the connection edge primary key, and the attribute primary key are all stored in the form of an index. 8. A device for merging multiple user identities, comprising: An acquisition module, configured to acquire user identity data, where the user identity data has at least two identity characteristics; A processing module, configured to construct a graph network according to at least two identity features of the user identity data, the graph network including: nodes representing identity features and connection edges representing association relationships of identity features; A determining module, configured to determine the identity group of the same user according to the connection relationship between nodes in the graph network, the connection relationship between nodes and connection edges, and the identity group includes: a plurality of identity characteristics; The determining module is specifically configured to determine the number of connections between adjacent nodes in the graph network according to the connection relationship between nodes in the graph network and the connection relationship between nodes and connection edges, based on the graph network The number of connections between adjacent nodes and the preset number of times threshold determine the first connection relationship and the second connection relationship, the first connection relationship is a connection relationship in which the number of connections between adjacent nodes is greater than the number of times threshold, The second connection relationship is a connection relationship in which the number of connections between adjacent nodes is less than or equal to the number of times threshold; according to the first connection relationship and the second connection relationship, starting from the target node, traversing outwards in sequence The nodes of the graph network determine the identity group of the user corresponding to the target node; according to the connection relationship between nodes in the graph network, the connection relationship between nodes and connection edges, and the attribute information of each node, Determine the association relationship between the nodes; based on the association relationship between the nodes, aggregate the nodes in the graph network to form a strongly related group; according to the identity group of the user corresponding to the target node and the strongly related group , to determine the identity group of the same user. 9. An electronic device, characterized in that it comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1-7. Methods. 10. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make the computer execute the method according to any one of claims 1-7.

Images