WO2020259054A1

WO2020259054A1 - Associated account analysis method and apparatus, and computer-readable storage medium

Info

Publication number: WO2020259054A1
Application number: PCT/CN2020/086930
Authority: WO
Inventors: 周亮
Original assignee: 京东数字科技控股有限公司
Priority date: 2019-06-28
Filing date: 2020-04-26
Publication date: 2020-12-30
Also published as: CN110287688B; CN110287688A

Abstract

Provided are an associated account analysis method and apparatus, and a computer-readable storage medium, which relate to the technical field of big data analysis. The associated account analysis method comprises: according to account information, establishing an association relationship between an account and a number identifier, wherein the number identifier is a mobile phone number or the number of an identity card; according to login information, establishing an association relationship between the account and a login terminal; establishing a relationship diagram according to the association relationships between the account and the number identifier and between the account and the login terminal, wherein the account, the number identifier and the login terminal are vertexes, and the vertexes with association relationships are in communication; and according to the relationship diagram, determining an account, with the shortest path between the accounts being smaller than a preset first threshold, as an associated account. By this method, the capability of identifying the associated account can be improved, thus improving account management capability, and facilitating network security management and control.

Description

Associated account analysis method, device and computer readable storage medium

Cross references to related applications

This application is based on the application with the CN application number 201910572269.X and the application date on June 28, 2019, and claims its priority. The disclosure of the CN application is hereby incorporated into this application as a whole.

Technical field

The present disclosure relates to the technical field of big data analysis, in particular to an associated account analysis method, device and computer-readable storage medium.

Background technique

In the process of user account management, account identification is often carried out by means of real-name account information and registered mobile phone number. On the one hand, the real-name account management system can improve security, prevent online fraud, or achieve rapid recovery of losses, on the other hand, it can be targeted during business promotion and improve promotion efficiency.

Summary of the invention

According to an aspect of some embodiments of the present disclosure, an associated account analysis method is proposed, which includes: establishing an association relationship between an account and a number identification according to account information, where the number identification is a mobile phone number or an ID number; The relationship between the account and the login terminal; establish a relationship graph based on the relationship between the account and the number identification and the relationship between the account and the login terminal, where the account, the number identification, and the login terminal are the vertices, and the vertices with the associated relationship are connected; and according to The relationship diagram determines that an account whose shortest path between accounts is less than a predetermined first threshold is an associated account.

In some embodiments, the associated account analysis method further includes: determining the association relationship between the account and the number identifier according to the account data information associated with the account, and the association weight of the association relationship between the account and the login terminal, as the corresponding association relationship The weight of the path between the vertices, where the account data information includes one or more of order information, login information, or delivery information; and the weight of the path in the shortest path of the associated account is determined by the sum of the weights of the paths The similarity.

In some embodiments, the weight of the association relationship is greater than 0, and the association relationship is negatively correlated with at least one of the number of occurrences in the account data information or the predetermined importance of the event to which the association relationship appears in the account data information.

In some embodiments, determining that an account whose shortest path between accounts is less than a predetermined first threshold is an associated account includes: determining an account whose shortest path to a predetermined seed account is less than a predetermined first threshold is a target account; and determining that the target account is The associated account of the predetermined seed account.

In some embodiments, establishing the relationship graph includes: generating an account, number identification, and abstract vertex identification of the login terminal, and recording the corresponding relationship between the abstract vertex identification and the account; and connecting the abstract vertex identification with an association relationship to generate the relationship graph; determining the account Accounts with the shortest path between them less than a predetermined first threshold being associated accounts include: taking the abstract vertex identifier of the predetermined seed account as a starting point, determining that the distance from the predetermined seed account in the relationship graph is less than the predetermined first threshold and has a corresponding relationship with the account Abstract vertex identifier; and according to the corresponding relationship between the abstract vertex identifier and the account, the determined abstract vertex identifier is restored to the account.

In some embodiments, the associated account analysis method further includes: selecting the previously predetermined second threshold account as the key associated account of the account according to the descending order of the weight of the path.

In some embodiments, the side lengths in the relationship graph are positively correlated with weights; according to the relationship graph, it is determined that the account whose shortest path between accounts is less than the predetermined first threshold is the associated account: According to the shortest path algorithm, it is determined that the path length is less than the predetermined value. The predetermined second threshold of the distance accounts for the key associated accounts of the accounts.

In some embodiments, the associated account analysis method further includes: storing at least one of the associated account or key associated account of each account; and supplementing the account real-name system information according to at least one of the associated account or the key associated account.

In some embodiments, the associated account analysis method further includes: storing at least one of the associated account or key associated account of each account; and reducing the push of information to at least one of the associated account or the key associated account according to the promotion of the information The effect adjusts at least one of the predetermined first threshold or the predetermined second threshold.

In some embodiments, determining according to the relationship graph that the account whose shortest path between accounts is less than a predetermined first threshold is an associated account includes: calculating the source vertices according to the breadth-first search BFS algorithm and all vertices that can be accessed within the predetermined first threshold distance ;According to the Dijkstra algorithm, calculate the first predetermined number of vertices to reach the source vertex within the range of all vertices that can be accessed; and determine the account corresponding to the first predetermined number of vertices as the associated account of the source vertex account.

According to an aspect of other embodiments of the present disclosure, an associated account analysis device is provided, including: an association relationship establishing unit configured to establish an association relationship between an account and a number identifier according to account information, and establish an account and log in according to login information The association relationship between terminals; where the number identifier is a mobile phone number or ID number; the relationship graph generating unit is configured to establish a relationship diagram based on the account and number identifier and the association relationship between the account and the login terminal, where the account and number identifier The login terminal is a vertex, and the vertices with an association relationship are connected; and the associated account determination unit is configured to determine, according to the relationship graph, an account whose shortest path between accounts is less than a predetermined first threshold is an associated account.

According to an aspect of still other embodiments of the present disclosure, an associated account analysis device is provided, including: a memory; and a processor coupled to the memory, and the processor is configured to execute any of the above based on instructions stored in the memory Associated account analysis method.

According to an aspect of still other embodiments of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored, which when executed by a processor, implement the steps of any of the above associated account analysis methods.

Description of the drawings

The drawings described here are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure, and do not constitute an improper limitation of the present disclosure. In the attached picture:

FIG. 1 is a flowchart of some embodiments of the associated account analysis method of the present disclosure.

FIG. 2 is a schematic diagram of vertex relationships of some embodiments in the associated account analysis method of the present disclosure.

FIG. 3 is a flowchart of other embodiments of the associated account analysis method of the present disclosure.

FIG. 4 is a flowchart of still other embodiments of the associated account analysis method of the present disclosure.

FIG. 5 is a schematic diagram of some embodiments of account conversion in the associated account analysis method of the present disclosure.

FIG. 6 is a schematic diagram of some embodiments of the associated account analysis device of the present disclosure.

FIG. 7 is a schematic diagram of other embodiments of the associated account analysis device of the present disclosure.

FIG. 8 is a schematic diagram of still other embodiments of the associated account analysis device of the present disclosure.

Detailed ways

The technical solutions of the present disclosure will be further described in detail below through the accompanying drawings and embodiments.

The flowchart of some embodiments of the associated account analysis method of the present disclosure is shown in FIG. 1 and includes steps 101-104.

In step 101, an association relationship between the account and the number identification is established according to the account information. In some embodiments, the number identification is a mobile phone number or an ID number. In some embodiments, the account information may include an account number, and one or more of the user's name, contact information, or ID number.

In step 102, an association relationship between the account and the login terminal is established according to the login information.

In some embodiments, the order of execution of

steps

101 and 102 is in no particular order.

In step 103, a relationship diagram is established according to the association relationship between the account number and the number identification and the login terminal, and the account number, the number identification, and the login terminal are the vertices, as shown in FIG. 2. In the relationship graph, vertices with an association relationship are connected. For example, if two accounts are logged in using the same terminal, the vertices of the two accounts are connected to the corresponding vertices of the login terminal.

In step 104, an account whose shortest path between accounts is less than a predetermined first threshold is determined as an associated account according to the relationship graph. In some embodiments, the path length between vertices may be determined based on the shortest path algorithm.

The inventor found that in related technologies, if account A and account B have the same mobile phone number, then account B will be identified as an associated account (or vest account) of account A. If account C and account A do not match on the login terminal and mobile phone number, they will be recognized as unassociated accounts. However, if the account C and the account B are the same on the login terminal, the account C is likely to be the vest account of the account A at this time, and this situation is often not recognized. In addition, it is very complicated and time-consuming to use a relational database to identify related accounts within a million-level seed users in a large-scale account.

Through the method in the above embodiment, the relationship diagram of account, number identification, and login terminal can be established based on account information and login information, and the associated account can be determined according to the shortest path between the accounts, thereby improving the ability to identify the associated account, thereby improving Account management capabilities are conducive to network security management and control.

In some embodiments, in order to reduce the amount of calculation, a predetermined seed account can be selected as needed. For example, the target account whose association relationship needs to be analyzed is used as the predetermined seed account, and the shortest path length to the vertices of other accounts is determined from the predetermined seed account. This avoids excessive calculations due to starting point traversal and improves calculation efficiency.

In some embodiments, the predetermined first threshold may be set as the threshold of the shortest path length. If the shortest path length between accounts is less than the predetermined first threshold, the two are associated account relationships; if it is greater than or equal to the predetermined first threshold, exclude Its associated account relationship.

In some embodiments, the upper limit of the associated account of the source account can also be set. According to the order of the shortest path length, the number of associated accounts of the source account is not greater than the preset upper limit, so as to avoid excessive association between accounts and reduce Probability of error.

In some embodiments, the weight of the association relationship between the account and the number identification, and the login terminal may also be determined according to the account data information associated with the account. When the relationship graph is generated, the weight of the relationship is used as the weight of the path between the vertices of the corresponding relationship. The size of the weight is negatively related to the strength of the relationship, such as the inverse of the strength of the relationship. The account data information may include one or more of order information, login information, or delivery information corresponding to the account. In some embodiments, the weight of the association relationship may be determined according to at least one of the number of occurrences of the association relationship in the account data information or the predetermined importance of the event to which the association relationship appears in the account data information, for example, an order event The weight of is 2, and the reciprocal of the number of shopping orders associated with the mobile phone number multiplied by 2 is the weight between the mobile phone number and the account number generated by the order event; the weight of the login event is 1, then the user account is on a certain device The reciprocal of the number of login times multiplied by 1 is the weight between the login terminal and the account due to the login event. According to the sum of the weights of the paths in the shortest path of the associated accounts, the similarity between the associated accounts can be determined. The sum of the weights is negatively correlated with the similarity, for example, in a negative ratio. After the associated accounts are filtered out, the number of associated accounts is further determined. The degree of similarity between the accounts helps to further measure the degree of association between accounts.

The flowcharts of other embodiments of the associated account analysis method of the present disclosure are shown in FIG. 3, and include steps 301 to 307.

In step 301, an association relationship between the account and the number identification is established according to the account information.

In step 302, an association relationship between the account and the login terminal is established according to the login information.

In some embodiments,

steps

301 and 302 are performed in no particular order.

In step 303, a relationship diagram is established according to the association relationship between the account number and the number identification and the login terminal, and then step 304 and step 305 are performed respectively.

In step 304, the weight of the association relationship is determined according to the account data information, as the weight of the path between the vertices of the corresponding association relationship, and step 306 is performed.

In step 305, an account whose shortest path between accounts is less than a predetermined first threshold is determined as an associated account according to the relationship graph, and step 306 is performed.

In some embodiments, the Dijkstra algorithm can be improved based on the calculation of the first N shortest paths within the distance K from a vertex (K and N are positive integers), and the source vertex is called root. Then the calculation process of the algorithm is:

First, find all the vertices accessible within the distance K from the root vertex according to the BFS algorithm. The set of these vertices is denoted as U.

According to the Dijkstra algorithm, the first N shortest paths to the root vertex are calculated within the range of the vertices recorded by U. Because the Dijkstra algorithm is an algorithm that generates the shortest paths in increasing order of path length, there is no need to find all the shortest paths of the root vertex. Path, the shortest path generated N times is the first N shortest paths among all the shortest paths, and N is a positive integer.

In step 306, the similarity between the associated accounts is determined according to the sum of the weights of the paths in the shortest path of the associated accounts.

In step 307, the key associated accounts are selected in the descending order of the weight of the path, for example, the first predetermined second threshold account is selected as the key associated accounts of the accounts in the descending order of the weight of the shortest path.

Through this method, the weight of the association relationship can be determined according to the number of events, weight, etc., so as to exclude the account association caused by accidental events in the screening process, and further ensure the reliability of the association between accounts.

In some embodiments, when generating the relationship graph, the side length can be set to be positively related to the path weight. For example, the side length is equal to the path weight, then the side length is negatively related to the strength of the association relationship, and the stronger the association strength, the side length Shorter. Furthermore, the shortest path algorithm is used to calculate the second predetermined threshold associated accounts whose path length is less than the first predetermined threshold, that is, the second predetermined threshold associated accounts with the shortest path (highest similarity) within the first predetermined threshold.

Through such a method, a predetermined number of associated accounts with the closest similarity can be obtained through a one-time shortest path calculation, and the associated strength is ensured to be greater than the predetermined requirement, the calculation efficiency is improved, and the calculation pressure on the device is reduced.

The flowchart of still other embodiments of the associated account analysis method of the present disclosure is shown in FIG. 4, and includes steps 401-405.

In step 401, an association relationship between the account number, the number identification, and the login terminal is established.

In step 402, the account number, number identifier, and abstract vertex identifier of the login terminal are generated, and the correspondence between the abstract vertex identifier and the account is recorded.

In some embodiments, as shown in FIG. 5, in the original edge data file including order information, login information, or receipt information associated with the account, each row of records represents an edge, and each edge contains a starting vertex. , The weight value of the ending vertex and edge. Each edge record is divided into three columns, the first column is the user account, the second column is the phone number or device number, and the third column is the weight value of the edge. The first two columns represent the starting and ending vertices of the edge, and the third column is the weight information of the edge. The seed user data file stores the accounts of all seed users. By specifying the account of the seed user, the associated account of the seed user's account can be obtained in a targeted manner, which improves the pertinence and execution efficiency.

Generate abstract graph data based on the original edge data and seed user data. For the original edge data, generate a unique corresponding continuous value (abstract vertex) for each user account, device number, and mobile phone number in the original edge, and store it in the abstract graph abstraction The edge data file is input as edge data, and the mapping relationship between the user account and its corresponding abstract vertices is saved. For seed user data, the abstract vertex data of each seed user account is obtained according to the mapping relationship between the user account and the abstract vertex, and stored in the abstract graph vertex data file as the vertex data input.

For example, in Figure 5, user account 1 is abstracted as identity 0, mobile phone number 1 is abstracted as identity 1, mobile phone number 2 is abstracted as identity 2, device number 1 (login terminal identity) is abstracted as identity 3, and user account 2 is abstracted as identity 4. Device number 2 is abstracted as logo 5, user account 3 is abstracted as logo 6, mobile phone number 3 is abstracted as logo 7, and device number 3 is abstracted as logo 8. The vertex data identifiers corresponding to seed user accounts 1 and 3 are 0 and 6, respectively.

In step 403, the abstract vertex identifiers with association relationships are connected to generate a relationship graph.

In step 404, using the abstract vertex identifier of the predetermined seed account as a starting point, determine the abstract vertex identifier in the relationship graph that has a corresponding relationship with the account whose distance from the predetermined seed account is less than a predetermined first threshold.

In some embodiments, the graph can be represented in the form of an adjacency matrix in the memory by loading the abstract graph edge data and vertex data, and then execute the shortest path algorithm to calculate the first N of each seed user vertex within K steps for the purpose of the user account The shortest path to the vertex. The destination vertex of each shortest path is the associated account of the seed user, and the sum of the weights on the path (path weight) is the degree of account similarity. The maximum N shortest paths calculated by each seed user obtain the maximum N associated account information of the seed user, and all the calculated associated account vertices and seed account vertices information are output to the result file.

In step 405, according to the corresponding relationship between the abstract vertex identifier and the account, the determined abstract vertex identifier is restored to the account.

Through this method, the original data can be abstracted and then the graph calculation can be performed, which reduces the amount of data that needs to be processed during graph calculation, improves the accuracy of the calculation, and also improves the efficiency of the calculation.

In some embodiments, as shown in FIG. 4, the associated account analysis method may further include

steps

406 and 407.

In step 406, at least one of the associated account and the key associated account of each account is stored.

In step 407, the account real-name system information is supplemented according to at least one of the associated account or the key associated account. For example, for two accounts whose similarity is greater than a predetermined similarity threshold, it can be considered that they belong to the same user, and both have the same real-name information.

Through this method, it is possible to supplement user real-name information and improve network supervision.

In addition, when searching for a user who does not have real-name information, the identity of the user without real-name information can be determined by investigating the real-name user of its associated account, thereby increasing the probability of successful network security tracing.

In some embodiments, step 408 can also be performed in the account data application.

In step 408, push information to at least one of the associated account or the key associated account is reduced.

In the promotion of e-commerce products, in order to discover more potential valuable users, the data of colleagues of known high-value users (seed users) will be calculated based on the address information, and then marketing information will be sent to these colleagues by SMS. Through the method in the above embodiment, the user's vest account can be identified and excluded first, and repeated push of information to the same user is avoided, which not only improves operation efficiency, but also saves SMS costs.

In some embodiments, the predetermined first threshold and the predetermined second threshold mentioned above can be modified according to the execution effect in

steps

407 and 408, and the generation rule of the association weight in the weight determination process, the weight of the event, etc. can also be modified. , So as to continuously modify the parameters during the operation and application process to further improve the accuracy.

A schematic diagram of some embodiments of the associated account analysis device of the present disclosure is shown in FIG. 6. The association relationship establishment unit 601 can establish an association relationship between an account and a number identifier according to account information, and establish an association relationship between an account and a login terminal according to login information. In some embodiments, the number identification is a mobile phone number or an ID number.

The relationship graph generating unit 602 can establish a relationship graph according to the association relationship between the account number, the number identification and the login terminal, and the account number, the number identification, and the login terminal are the vertices.

The associated account determination unit 603 can establish a relationship graph according to the associated relationship between the account, the number identification and the login terminal, and the account, the number identification, and the login terminal are the apex.

Such an associated account analysis device can establish a relationship diagram of account, number identification, and login terminal based on account information and login information, and determine the associated account based on the shortest path between the accounts, thereby improving the ability to identify associated accounts and thereby improving account management capabilities , Which is conducive to network security management and control.

In some embodiments, as shown in FIG. 6, the associated account analysis device may further include a weight determination unit 604 and a similarity determination unit 605. The weight determination unit 604 can determine the account number and the number identification according to the account data information associated with the account number. The weight of the association relationship between the registration terminals is used as the weight of the path between the vertices of the corresponding association when the relationship graph is generated. The similarity determination unit 605 can determine the similarity between the associated accounts according to the sum of the weights of the paths in the shortest path of the associated accounts. The sum of the weights is negatively correlated with the similarity, for example, in a negative ratio, so that after the associated accounts are filtered out, Further determining the degree of similarity between related accounts is helpful to further measure the degree of connection between accounts.

In some embodiments, the relationship graph generating unit 602 may set the side length to be positively related to the path weight when generating the relationship graph. If the side length is equal to the path weight, the side length is negatively related to the strength of the association relationship, and the relationship strength The stronger the side length the shorter. Furthermore, the associated account determination unit 603 uses the shortest path algorithm to calculate the second predetermined threshold whose path length is less than the first predetermined threshold. The number of associated accounts is the second predetermined threshold with the shortest path (highest similarity) within the first predetermined threshold. Link accounts.

Such an associated account analysis device can obtain a predetermined number of associated accounts with the closest similarity through a one-time shortest path calculation, and ensure that the associated strength is greater than a predetermined requirement, improve computing efficiency, and reduce computing pressure on equipment.

In some embodiments, the associated account analysis device may further include an associated information application unit 606, which can supplement real-name account information based on associated accounts and key associated accounts. For example, when the similarity of two accounts is greater than a predetermined similarity threshold, it can be considered that the users belong to the same user, and the two accounts have the same real-name information. Such an associated account analysis device can supplement user real-name information and improve network supervision. In addition, when searching for a user who does not have real-name information, the associated information application unit 606 can determine the identity of the user without real-name information by investigating the real-name user of the associated account, thereby increasing the probability of successful security tracking.

In some embodiments, the associated information application unit 606 can reduce information pushes to at least one of an associated account or a key associated account, so that the user’s vest account is first identified and excluded during the operation process, so as to avoid repeatedly pushing information to the same user , While improving operational efficiency, it also saves SMS costs.

In some embodiments, the associated account analysis device may further include a threshold adjustment unit 607, which can modify the predetermined first threshold and the predetermined second threshold mentioned above according to the operating effect of the associated information application unit 606, and can also modify the weight determination process. The generation rules of the correlation weights in the middle, the weights of events, etc., are continuously revised during the operation and application process to further improve the accuracy.

A schematic structural diagram of an embodiment of the associated account analysis device of the present disclosure is shown in FIG. 7. The associated account analysis device includes a memory 701 and a processor 702. Wherein: the memory 701 may be a magnetic disk, flash memory or any other non-volatile storage medium. The memory is used to store the instructions in the corresponding embodiment of the above associated account analysis method. The processor 702 is coupled to the memory 701 and can be implemented as one or more integrated circuits, such as a microprocessor or a microcontroller. The processor 702 is configured to execute instructions stored in the memory, which can improve the ability to identify associated accounts, thereby improving account management capabilities, and is beneficial to network security management and control.

In an embodiment, as shown in FIG. 8, the associated account analysis device 800 includes a memory 801 and a processor 802. The processor 802 is coupled to the memory 801 through the BUS bus 803. The associated account analysis device 800 can also be connected to an external storage device 805 via a storage interface 804 to call external data, and can also be connected to a network or another computer system (not shown) via a network interface 806. No more detailed introduction here.

In this embodiment, storing data instructions through a memory and processing the above instructions through a processor can improve the ability to identify associated accounts, thereby improving account management capabilities, which is beneficial to network security management and control.

In another embodiment, a computer-readable storage medium has computer program instructions stored thereon, which, when executed by a processor, implement the steps of the method in the corresponding embodiment of the associated account analysis method. Those skilled in the art should understand that the embodiments of the present disclosure may be provided as methods, devices, or computer program products. Therefore, the present disclosure may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. .

The present disclosure is described with reference to flowcharts and/or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present disclosure. It should be understood that each process and/or block in the flowchart and/or block diagram and the combination of processes and/or blocks in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are generated It is a device that realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.

So far, the present disclosure has been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solutions disclosed herein.

The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure can be implemented by software, hardware, firmware or any combination of software, hardware, and firmware. The above-mentioned order of the steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless specifically stated otherwise. In addition, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, and these programs include machine-readable instructions for implementing the method according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure and not to limit it; although the present disclosure has been described in detail with reference to preferred embodiments, those of ordinary skill in the art should understand that: The disclosed specific implementations are modified or equivalent replacements of some technical features; without departing from the spirit of the technical solutions of the present disclosure, they should all be covered in the scope of the technical solutions claimed by the present disclosure.

Claims

An associated account analysis method, including:

Establishing an association relationship between the account number and the number identification according to the account information, where the number identification is a mobile phone number or an ID number;

Establish an association relationship between the account and the login terminal according to the login information;

Establish a relationship graph based on the account number and the number identification and the association relationship between the account number and the login terminal, wherein the account number, the number identification, and the login terminal are vertices, and the vertices with the association relationship are connected; and

According to the relationship graph, it is determined that an account whose shortest path between accounts is less than a predetermined first threshold is an associated account.
The associated account analysis method according to claim 1, further comprising:

Determine the association relationship between the account and the number identification and the association relationship between the account and the login terminal according to the account data information associated with the account, as the weight of the path between the vertices of the corresponding association relationship, where: The account data information includes one or more of order information, login information or delivery information; and

Determine the similarity between the associated accounts according to the sum of the weights of the paths in the shortest path of the associated accounts.
The associated account analysis method according to claim 2, wherein the weight of the associated relationship is greater than 0, and the associated relationship and the number of occurrences in the account data information, or the associated relationship in the account data information At least one item of the predetermined importance of the attributable event at the time of occurrence is negatively correlated.
The associated account analysis method according to claim 1, wherein the determining that an account whose shortest path between accounts is less than a predetermined first threshold is an associated account comprises:

Determining that the account whose shortest path to the predetermined seed account is less than the predetermined first threshold is the target account;

It is determined that the target account is an associated account of the predetermined seed account.
The associated account analysis method according to claim 4, wherein:

The establishment of the relationship diagram includes:

Generating the account number, the number identifier, and the abstract vertex identifier of the login terminal, and recording the corresponding relationship between the abstract vertex identifier and the account; and

Connecting abstract vertex identifiers with associated relationships to generate the relationship graph;

The determining that an account whose shortest path between accounts is less than a predetermined first threshold is an associated account includes:

Using the abstract vertex identifier of the predetermined seed account as a starting point, determine the abstract vertex identifier in the relationship graph whose distance from the predetermined seed account is less than a predetermined first threshold and has a corresponding relationship with the account; and

According to the corresponding relationship between the abstract vertex identifier and the account, the determined abstract vertex identifier is restored to the account.
The associated account analysis method according to claim 2, further comprising:

According to the descending order of the weight of the path, the previously predetermined second threshold account is selected as the key associated account of the account.
The method according to claim 3, wherein the side length in the relationship graph is positively related to the weight;

The determining that an account whose shortest path between accounts is less than a predetermined first threshold according to the relationship diagram is an associated account is: determining, according to the shortest path algorithm, an account whose path length is less than the predetermined second threshold below the predetermined distance as the account Focus on associated accounts.
The associated account analysis method according to claim 6 or 7, further comprising:

Store at least one of the associated account or key associated account of each account; and

Supplement the real-name account information according to at least one of the associated account or key associated account.
The associated account analysis method according to claim 6 or 7, further comprising:

Store at least one of the associated account or key associated account of each account; and

Reduce pushing information to at least one of the associated account or key associated account, and adjust at least one of the predetermined first threshold or the predetermined second threshold according to the promotion effect of the information.
The associated account analysis method according to claim 1, wherein the determining that the account whose shortest path between accounts is less than a predetermined first threshold according to the relationship diagram is an associated account comprises:

According to the breadth-first search BFS algorithm, find all the vertices that can be accessed within the predetermined first threshold distance of the source vertex;

According to the Dijkstra algorithm, calculate the predetermined number of vertices before reaching the source vertex within the range of all the vertices that can be accessed; and

It is determined that the account corresponding to the first predetermined number of vertices is the associated account of the source vertex account.
An associated account analysis device, including:

The association relationship establishment unit is configured to establish an association relationship between an account and a number identification according to account information, and establish an association relationship between an account and a login terminal according to login information; wherein the number identification is a mobile phone number or an ID number;

The relationship graph generating unit is configured to establish a relationship graph according to the association relationship between the account and the number identification and the account and the login terminal, wherein the account, the number identification, and the login terminal are vertices, and the vertices with the association relationship are connected ;with

The associated account determination unit is configured to determine, according to the relationship diagram, an account whose shortest path between accounts is less than a predetermined first threshold is an associated account.
An associated account analysis device, including:

A memory; and a processor coupled to the memory, the processor being configured to execute the method according to any one of claims 1 to 10 based on instructions stored in the memory.
A computer-readable storage medium having computer program instructions stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 10 are realized.