CN113902060A - Group user identification method, device, equipment and storage medium - Google Patents
Group user identification method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113902060A CN113902060A CN202111330639.2A CN202111330639A CN113902060A CN 113902060 A CN113902060 A CN 113902060A CN 202111330639 A CN202111330639 A CN 202111330639A CN 113902060 A CN113902060 A CN 113902060A
- Authority
- CN
- China
- Prior art keywords
- user
- users
- group
- community
- homologous
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 43
- 230000000694 effects Effects 0.000 claims abstract description 34
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Animal Behavior & Ethology (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Security & Cryptography (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a group user identification method, a device, equipment and a storage medium, wherein the method comprises the following steps: reading user basic information to obtain a user association relation; calculating the user association relationship according to a group recognition algorithm, dividing the user into a plurality of user groups according to the user association relationship, and if the number of users in the user groups meets a first preset rule, determining that the user is a group member; acquiring homologous users with homologous relations according to the real-time information of the users; judging whether a first user participating in the activity belongs to a community member or not according to the community member; if yes, confirming the first user belongs to the community user; if not, acquiring a second user having a homologous relation with the first user from the homologous users; judging whether the second user belongs to a community member or not; and if the second user belongs to the group member, determining that the first user also belongs to the group member. The embodiment of the invention adopts offline full group identification and real-time homologous fitting to carry out real-time group identification, thereby improving the timeliness and the accuracy of group identification.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a group user identification method, a group user identification device, group user identification equipment and a storage medium.
Background
The common group user identification methods mainly include an unsupervised method, a traditional supervised method and a graph neural network supervised method, wherein:
the unsupervised method firstly needs to construct an association graph, namely, confirm nodes and relations (edges), and then adopts label propagation, a maximum connectivity graph and the like to divide communities.
The traditional supervised method is equivalent to a node classification problem, and a classification model is trained and predicted by extracting the characteristics of the nodes.
The graph neural network method mainly learns the service characteristics and the network topological structure of the nodes and is used for predicting unknown data.
The current mainstream group user identification method is an unsupervised identification method, and group identification is performed by using algorithms such as community discovery and the like according to a constructed relation map based on the constructed relation map. However, for the current unsupervised identification method, clustering is mainly performed according to the associated graph, and in the real e-commerce environment, the number of users is in billions, which can well identify the group relationship under the offline condition, but in the real-time task, the large-batch node calculation consumes a long time, and the real-time task requirement is difficult to meet.
Therefore, the existing group user identification method cannot prevent risks caused by group behaviors in real time and cannot stop damage in time.
Disclosure of Invention
In view of this, embodiments of the present invention provide a group user identification method, apparatus, device and storage medium, so as to solve the problem that the existing group cannot be identified in real time due to too long group calculation time.
In order to achieve the above object, the present invention provides a group user identification method, comprising the steps of:
reading user basic information to obtain a user association relation;
calculating the user association relation according to a group recognition algorithm, dividing the user into a plurality of user groups according to the user association relation, and if the number of users in the user groups meets a first preset rule, determining that the users are group members;
acquiring homologous users with homologous relations according to the real-time information of the users;
judging whether a first user participating in the activity belongs to the community member or not according to the community member;
if not, acquiring a second user having a homologous relationship with the first user from the homologous users;
judging whether the second user belongs to the community member; if the second user belongs to the group member, determining that the first user also belongs to the group member;
and if so, confirming that the first user belongs to the community member.
Optionally, the reading the user basic information to obtain the user association relationship includes the following steps:
reading user basic information to obtain at least one medium of a plurality of users;
the at least one medium comprises a bank account, an IP address, a mobile phone number, an international mobile equipment identification code used for logging in and the service time of the account;
and if the bank account numbers are the same, and/or the IP addresses are the same, and/or the mobile phone numbers are the same, and/or the international mobile equipment identification codes used for logging belong to the same model or the same, and/or the service time of the account numbers is within a preset time range, confirming that the association relationship exists among the users.
Optionally, the calculating the user association relationship according to a group identification algorithm divides the user into a plurality of user groups, and if the number of users in the user group meets a first preset rule, the user is determined to be a group member, including the following steps:
reading the user association relation;
clustering calculation is carried out on a plurality of users by adopting a group recognition algorithm, and the plurality of users are divided into a plurality of user groups;
and if the number of the clustered users in the user group meets a first preset rule, taking the users in the user group as group members.
Optionally, the community identification algorithm comprises the steps of:
initializing a label of each node in the user association relation, wherein the label of each node is unique; wherein, the home node is x, the initialization label is
Setting the iteration times t, for each node
Where X is the set of all nodes, resulting in
judging whether the label of each node is not changed or the iteration times are met, and if the label of each node is not changed or the iteration times are met, ending the process; if not, setting t to t +1 and re-traversing.
Optionally, the obtaining of the homologous users having the homologous relationship according to the user real-time information includes the following steps:
acquiring user real-time information, wherein the user real-time information comprises: log messages and/or protocol messages and/or operation records;
processing the real-time information of the user by adopting a real-time streaming operation calculation mode to obtain homologous users with homologous relations;
the homologous relation is that the bank accounts of the users are the same, and/or the IP addresses are the same, and/or the mobile phone numbers are the same, and/or the international mobile equipment identification codes used for logging belong to the same model or are the same, and/or the accounts perform the same operation within the preset time.
Optionally, the determining, according to the community member, whether the first user participating in the activity belongs to the community member includes:
judging whether the account of the first user belongs to accounts of the group members;
if so, the first user belongs to the community member;
and if not, the first user does not belong to the community member.
Optionally, the group user identification method further includes the following steps:
and if the first user is the group member, forbidding the first user to participate in the activity.
In addition, to achieve the above object, the present invention provides a group user identification apparatus, including:
the information reading unit is used for reading the basic information of the user and obtaining the user association relation;
the user dividing unit is used for calculating the user association relation according to a group recognition algorithm, so that the user is divided into a plurality of user groups, and if the number of the users in the user groups meets a first preset rule, the user is confirmed to be a group member;
the homologous computing unit is used for obtaining homologous users with homologous relations according to the real-time information of the users;
the community confirming unit is used for judging whether a first user participating in the activity belongs to the community members or not according to the community members;
if not, acquiring a second user having a homologous relationship with the first user from the homologous users; judging whether the second user belongs to the community member; if the second user belongs to the group member, determining that the first user also belongs to the group member;
and if so, confirming that the first user belongs to the community member.
Furthermore, to achieve the above object, the present invention also proposes an apparatus comprising: a memory, a processor and a community user identification program stored on said memory and executable on said processor, said community user identification program being configured to implement the steps of the community user identification method as described above.
Furthermore, to achieve the above object, the present invention also proposes a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, implements the steps of the community user identification method as described above.
The invention obtains the user association relationship by reading the user basic information; calculating the user association relation according to a group recognition algorithm, dividing the user into a plurality of user groups according to the user association relation, and if the number of users in the user groups meets a first preset rule, determining that the users are group members; acquiring homologous users with homologous relations according to the real-time information of the users; judging whether a first user participating in the activity belongs to the community member or not according to the community member; if yes, confirming that the first user belongs to the community member; if not, acquiring a second user having a homologous relationship with the first user from the homologous users; judging whether the second user belongs to the community member; and if the second user belongs to the group member, determining that the first user also belongs to the group member. Therefore, real-time group identification is carried out by adopting offline full group identification and real-time homologous fitting, the problem that the existing group cannot be identified in real time due to overlong group calculation time is solved, and the timeliness and the accuracy of group identification are improved.
Drawings
Fig. 1 is a schematic flow chart of a group user identification method according to the present invention.
Fig. 2 is an exemplary diagram of an association diagram between users provided by the present invention.
Fig. 3 is an exemplary diagram of the result of the community clustering algorithm provided by the present invention.
Fig. 4 is a schematic flow chart of a community member identification method provided by the present invention.
Fig. 5 is a schematic flow chart of a method for identifying a homologous user according to the present invention.
Fig. 6 is another schematic flow chart of a group user identification method according to the present invention.
Fig. 7 is a block diagram of a community user identification apparatus according to an embodiment of the present invention.
Fig. 8 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In the following description, suffixes such as "module", "component", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no specific meaning in itself. Thus, "module", "component" or "unit" may be used mixedly.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
In one embodiment, as shown in fig. 1, the present invention provides a community user identification method, including:
And 102, calculating the user association relation according to a group identification algorithm, dividing the user into a plurality of user groups, and if the number of the users in the user groups meets a first preset rule, determining that the user is a group member.
For a shopping application, if a user uses APP to log in, access, place an order, etc., a large amount of user data is left. In the real-time group identification process, whether group members exist or not can be judged according to the existing or ever-increasing total user data. While the relevant data of the user can be stored in a database, a table, etc., the embodiment is illustrated as being stored in the database.
In this embodiment, the user basic information may be read from the database first, and at least one medium of a plurality of users may be obtained for the plurality of users; specifically, the at least one medium includes a bank account, an IP address, a mobile phone number, an international mobile equipment identification code used for logging in, and a service time of the account.
If the bank accounts are the same, the IP addresses are the same, the mobile phone numbers are the same, the international mobile equipment identification codes used for logging in belong to the same model or the same, and/or the service time of the accounts is within a preset time range, the fact that the multiple users have the association relation is confirmed.
For example, the obtained basic user information may be one or more of a bank account, an IP address, a mobile phone number, an international mobile equipment identification code used for login, and a use time of the account, where, taking the mobile phone number as an example, if the mobile phone numbers used by the user 1 and the user 2 are the same and both are 138 × 5675, it is considered that the user 1 and the user 2 have an association relationship, and if the mobile phone numbers are not the same, it is considered that the user 1 and the user 2 do not have an association relationship.
In this embodiment, after the association relationship among the users is confirmed, the association relationship among the users may be further read, and then a group recognition algorithm is used to perform cluster calculation on the users, so as to divide the users into a plurality of user groups. Specifically, the group identification algorithm may divide the user into groups of different sizes, the group identification algorithm may be an algorithm such as tag propagation and Louvian, and the tag propagation algorithm is taken as an example in this embodiment, that is, the specific group identification algorithm may be:
initializing the label of each node in the user association relation, wherein the label of each node is unique(ii) a Wherein, the home node is x, the initialization label is
Setting the iteration times t, for each node
Where X is the set of all nodes, resulting in
judging whether the label of each node is not changed or the iteration times are met, and if the label of each node is not changed or the iteration times are met, ending the process; if not, setting t to t +1 and re-traversing.
Referring also to fig. 2, fig. 2 is an example of a graph of associations between users (i.e., each node in the graph).
Further, the user groups are clustered, and a group clustering algorithm may be applied to the results, please refer to fig. 3, where fig. 3 is an example of the results after the group clustering algorithm. Where U1, U2, U3, and U4 represent four users within the first community 201, and U5, U6, U7, and U8 represent four users within the second community 202.
And if the number of the clustered users in the user group meets a first preset rule, taking the users in the user group as group members. The first preset rule may be: taking the number of group members as an example, if the number of group members is greater than or equal to N, the group is considered to be a group; otherwise it is not a community (N is a positive integer). That is, if the number of members in the group meets the first preset rule requirement, the group is considered as a group, and the members in the group are group members.
And 103, acquiring homologous users with homologous relations according to the real-time information of the users.
For a shopping application, in addition to historical user data and increasing user data, real-time online users are included. In the process of real-time group identification, whether different users are homologous users can be judged for real-time users.
In this embodiment, the user real-time information may be acquired first, and the acquisition mode may be obtained from a log message and/or a protocol message and/or an operation record transmitted in real time. And then, processing the real-time information of the user by adopting a real-time streaming operation calculation mode to obtain homologous users with homologous relations. Specifically, the homologous relationship may be that the bank accounts of the users are the same, and/or the IP addresses are the same, and/or the mobile phone numbers are the same, and/or the international mobile equipment identifiers used for login belong to the same model or are the same, and/or the accounts perform the same operation within a preset time, that is, as long as one or more of the homologous relationships exist between the users, the users are considered as homologous users having the homologous relationship.
For example, the information related to the user obtained from the log message transmitted in real time may be one or more of a bank account number, an IP address, a mobile phone number, an international mobile equipment identifier used for login, and a use time of the account number, where, taking the mobile phone number as an example, if the mobile phone numbers used by the user 3 and the user 4 are the same and are 187 × 3521, the user 3 and the user 4 are considered to be homologous users having a homologous relationship.
And 104, judging whether the first user participating in the activity belongs to the community member according to the community member.
After obtaining the real-time homologous relationship and the group members in the database, in this embodiment, for the first user participating in the discount activity of the shopping application program in real time, first, whether the account of the first user participating in the activity belongs to the account of the group members is determined according to the group members. If yes, go to step 105, otherwise, go to step 106.
And 105, if yes, confirming that the first user belongs to the community member.
And if the account of the first user participating in the activity belongs to the account of the group member, confirming that the first user belongs to the group member, and forbidding the first user to participate in the activity.
If the account of the first user participating in the activity does not belong to the account of the group members, further obtaining a second user having a homologous relationship with the first user from the homologous users, that is, obtaining at least one medium of the first user, including one or more of a bank account, an IP address, a mobile phone number, an international mobile equipment identification code used for login, and a use time of the account, and then searching for the second user having the homologous relationship with the first user from the homologous relationship. It will be appreciated that the second user does not refer solely to a user, and may include a plurality of users having a same source relationship with the first user.
After obtaining a second user having a same source relationship with the first user, further judging whether the second user belongs to the community member; if the account of the second user belongs to an account in the community members, it can be confirmed that the first user also belongs to the community members.
In the embodiment of the invention, the user association relation is obtained by reading the user basic information; calculating the user association relation according to a group recognition algorithm, dividing the user into a plurality of user groups according to the user association relation, and if the number of users in the user groups meets a first preset rule, determining that the users are group members; acquiring homologous users with homologous relations according to the real-time information of the users; judging whether a first user participating in the activity belongs to the community member or not according to the community member; if yes, confirming that the first user belongs to the community member; if not, acquiring a second user having a homologous relationship with the first user from the homologous users; judging whether the second user belongs to the community member; and if the second user belongs to the group member, determining that the first user also belongs to the group member. Therefore, real-time group identification is carried out by adopting offline full group identification and real-time homologous fitting, the problem that the existing group cannot be identified in real time due to overlong group calculation time is solved, and the timeliness and the accuracy of group identification are improved.
In another embodiment, for a shopping application, if a user uses the APP to log in, access, place an order, etc., a large amount of user data is left. In the real-time group identification process, whether group members exist or not can be judged according to the existing or ever-increasing total user data. As shown in fig. 4, the present invention provides a community member identification method, including:
Since the relevant data of the user can be stored in a database, a table, or the like, the present embodiment is explained as being stored in the database.
In this embodiment, the user basic information may be read from the database first, and at least one medium of a plurality of users may be obtained for the plurality of users; specifically, the at least one medium includes a bank account, an IP address, a mobile phone number, an international mobile equipment identification code used for logging in, and a service time of the account.
If the bank accounts are the same, the IP addresses are the same, the mobile phone numbers are the same, the international mobile equipment identification codes used for logging in belong to the same model or the same, and/or the service time of the accounts is within a preset time range, the fact that the multiple users have the association relation is confirmed.
For example, the obtained basic user information may be one or more of a bank account, an IP address, a mobile phone number, an international mobile equipment identification code used for login, and a use time of the account, where, taking the mobile phone number as an example, if the mobile phone numbers used by the user 1 and the user 2 are the same and both are 138 × 5675, it is considered that the user 1 and the user 2 have an association relationship, and if the mobile phone numbers are not the same, it is considered that the user 1 and the user 2 do not have an association relationship.
In this embodiment, after the association relationship among the users is confirmed, the association relationship among the users may be further read, and then a group recognition algorithm is used to perform cluster calculation on the users, so as to divide the users into a plurality of user groups. Specifically, the group identification algorithm may divide the user into groups of different sizes, the group identification algorithm may be an algorithm such as tag propagation and Louvian, and the tag propagation algorithm is taken as an example in this embodiment, that is, the specific group identification algorithm may be:
initializing a label of each node in the user association relation, wherein the label of each node is unique; wherein, the home node is x, the initialization label is
Setting the iteration times t, for each node
Where X is the set of all nodes, resulting in
judging whether the label of each node is not changed or the iteration times are met, and if the label of each node is not changed or the iteration times are met, ending the process; if not, setting t to t +1 and re-traversing.
Referring also to fig. 2, fig. 2 is an example of a graph of associations between users (i.e., each node in the graph).
Further, the user groups are clustered, and a group clustering algorithm may be applied to the results, please refer to fig. 3, where fig. 3 is an example of the results after the group clustering algorithm. Where U1, U2, U3, and U4 represent four users within the first community 201, and U5, U6, U7, and U8 represent four users within the second community 202.
And step 404, if the number of the clustered users in the user group meets a first preset rule, taking the users in the user group as group members.
In this embodiment, if the number of the clustered users in the user group meets a first preset rule, the users in the user group are used as group members. The first preset rule may be: taking the number of group members as an example, if the number of group members is greater than or equal to N, the group is considered to be a group; otherwise it is not a community (N is a positive integer). That is, if the number of members in the group meets the first preset rule requirement, the group is considered as a group, and the members in the group are group members.
In the embodiment of the invention, the group identification is carried out by using the group identification algorithm through the historical user data and the continuously increased stored user data, so that the existing group members can be obtained, and a foundation is provided for the subsequent real-time group identification.
In another embodiment, for a shopping application, in addition to historical user data and increasing user data, real-time online users are included. In the process of real-time group identification, whether different users are homologous users can be judged for real-time users. As shown in fig. 5, the present invention provides a method for identifying a same source user, where the method includes:
and step 501, acquiring real-time information of a user.
And 502, processing the real-time information of the user by adopting a real-time streaming operation calculation mode to obtain homologous users with homologous relations.
In this embodiment, the user real-time information may be acquired first, and the acquisition mode may be obtained from a log message and/or a protocol message and/or an operation record transmitted in real time. And then, processing the real-time information of the user by adopting a real-time streaming operation calculation mode to obtain homologous users with homologous relations. Specifically, the homologous relationship may be that the bank accounts of the users are the same, and/or the IP addresses are the same, and/or the mobile phone numbers are the same, and/or the international mobile equipment identifiers used for login belong to the same model or are the same, and/or the accounts perform the same operation within a preset time, that is, as long as one or more of the homologous relationships exist between the users, the users are considered as homologous users having the homologous relationship.
For example, the information related to the user obtained from the log message transmitted in real time may be one or more of a bank account number, an IP address, a mobile phone number, an international mobile equipment identifier used for login, and a use time of the account number, where, taking the mobile phone number as an example, if the mobile phone numbers used by the user 3 and the user 4 are the same and are 187 × 3521, the user 3 and the user 4 are considered to be homologous users having a homologous relationship.
In the embodiment of the invention, the homologous users with homologous relations are obtained by carrying out real-time calculation and real-time storage on the real-time information of the users, and a foundation is provided for the subsequent real-time group identification.
In another embodiment, after obtaining the real-time affiliation and community members in the database, a determination may be made as to whether the first user participating in the shopping application's offer in real-time is a community user. As shown in fig. 6, the present invention provides a community user identification method, including:
In this embodiment, for a first user participating in a discount activity of the shopping application in real time, first, whether an account of the first user participating in the activity belongs to accounts of group members is determined according to the group members. If yes, go to step 604, otherwise go to step 602.
If the account of the first user participating in the activity does not belong to the account of the group members, further obtaining a second user having a homologous relationship with the first user from the homologous users, that is, obtaining at least one medium of the first user, including one or more of a bank account, an IP address, a mobile phone number, an international mobile equipment identification code used for login, and a use time of the account, and then searching for the second user having the homologous relationship with the first user from the homologous relationship. It will be appreciated that the second user does not refer solely to a user, and may include a plurality of users having a same source relationship with the first user.
After obtaining a second user having a same source relationship with the first user, further judging whether the second user belongs to the community member; if the account of the second user belongs to the account of the community member, it can be confirmed that the first user also belongs to the community member, go to step 604, otherwise, go to step 605.
And step 604, confirming that the first user belongs to a community user.
And if the account of the first user participating in the activity belongs to the account of the group member, confirming that the first user belongs to the group member, namely the first user is the group user, and forbidding the first user to participate in the activity.
If the account of the first user participating in the activity does not belong to the account of the group member, confirming that the first user does not belong to the group member, confirming that the first user belongs to the normal user, and allowing the first user to participate in the activity.
In the embodiment of the invention, the real-time group identification is carried out through the offline full group identification and the real-time homologous fitting, so that the problem that the existing group cannot be identified in real time due to overlong group calculation time is solved, and the timeliness and the accuracy of the group identification are improved.
In addition, an embodiment of the present invention further provides a group user identification apparatus, and referring to fig. 7, the group user identification apparatus includes:
an information reading unit 701, configured to read basic information of a user and obtain a user association relationship;
the user dividing unit 702 is configured to calculate the user association relationship according to a group identification algorithm, so as to divide the user into a plurality of user groups, and if the number of users in the user groups meets a first preset rule, determine that the user is a group member;
the homologous computing unit 703 is configured to obtain homologous users having a homologous relationship according to the user real-time information;
a community confirming unit 704, configured to determine whether the first user participating in the activity belongs to the community member according to the community member;
if not, acquiring a second user having a homologous relationship with the first user from the homologous users;
judging whether the second user belongs to the community member; if the second user belongs to the group member, determining that the first user also belongs to the group member;
and if so, confirming that the first user belongs to the community member.
In the embodiment of the invention, the real-time group identification is carried out through the offline full group identification and the real-time homologous fitting, so that the problem that the existing group cannot be identified in real time due to overlong group calculation time is solved, and the timeliness and the accuracy of the group identification are improved.
It should be noted that each unit in the apparatus may be configured to implement each step in the method, and achieve the corresponding technical effect, which is not described herein again.
Referring to fig. 8, fig. 8 is a schematic structural diagram of a device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 8, the apparatus may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include standard wired interfaces, wireless interfaces (e.g., WI-FI, 4G, 5G interfaces). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 8 does not constitute a limitation of the device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 8, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a community user identification program.
In the device shown in fig. 8, the network interface 1004 is mainly used for data communication with an external network; the user interface 1003 is mainly used for receiving input instructions of a user; the apparatus calls the community user identification program stored in the memory 1005 by the processor 1001 and performs the following operations:
reading user basic information to obtain a user association relation;
calculating the user association relation according to a group recognition algorithm, dividing the user into a plurality of user groups according to the user association relation, and if the number of users in the user groups meets a first preset rule, determining that the users are group members;
acquiring homologous users with homologous relations according to the real-time information of the users;
judging whether a first user participating in the activity belongs to the community member or not according to the community member;
if not, acquiring a second user having a homologous relationship with the first user from the homologous users; judging whether the second user belongs to the community member; if the second user belongs to the group member, determining that the first user also belongs to the group member;
and if so, confirming that the first user belongs to the community member.
Optionally, the reading the user basic information to obtain the user association relationship includes the following steps:
reading user basic information to obtain at least one medium of a plurality of users;
the at least one medium comprises a bank account, an IP address, a mobile phone number, an international mobile equipment identification code used for logging in and the service time of the account;
and if the bank account numbers are the same, and/or the IP addresses are the same, and/or the mobile phone numbers are the same, and/or the international mobile equipment identification codes used for logging belong to the same model or the same, and/or the service time of the account numbers is within a preset time range, confirming that the association relationship exists among the users.
Optionally, the calculating the user association relationship according to a group identification algorithm divides the user into a plurality of user groups, and if the number of users in the user group meets a first preset rule, the user is determined to be a group member, including the following steps:
reading the user association relation;
clustering calculation is carried out on a plurality of users by adopting a group recognition algorithm, and the plurality of users are divided into a plurality of user groups;
and if the number of the clustered users in the user group meets a first preset rule, taking the users in the user group as group members.
Optionally, the community identification algorithm comprises the steps of:
initializing a label of each node in the user association relation, wherein the label of each node is unique; wherein, the home node is x, the initialization label is
Setting the iteration times t, for each node
Where X is the set of all nodes, resulting in
judging whether the label of each node is not changed or the iteration times are met, and if the label of each node is not changed or the iteration times are met, ending the process; if not, setting t to t +1 and re-traversing.
Optionally, the obtaining of the homologous users having the homologous relationship according to the user real-time information includes the following steps:
acquiring user real-time information, wherein the user real-time information comprises: log messages and/or protocol messages and/or operation records;
processing the real-time information of the user by adopting a real-time streaming operation calculation mode to obtain homologous users with homologous relations;
the homologous relation is that the bank accounts of the users are the same, and/or the IP addresses are the same, and/or the mobile phone numbers are the same, and/or the international mobile equipment identification codes used for logging belong to the same model or are the same, and/or the accounts perform the same operation within the preset time.
Optionally, the determining, according to the community member, whether the first user participating in the activity belongs to the community member includes:
judging whether the account of the first user belongs to accounts of the group members;
if so, the first user belongs to the community member;
and if not, the first user does not belong to the community member.
Optionally, the group user identification method further includes the following steps:
and if the first user is the group member, forbidding the first user to participate in the activity.
In the embodiment of the invention, the real-time group identification is carried out through the offline full group identification and the real-time homologous fitting, so that the problem that the existing group cannot be identified in real time due to overlong group calculation time is solved, and the timeliness and the accuracy of the group identification are improved.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where a community user identification program is stored on the computer-readable storage medium, and when executed by a processor, the community user identification program implements the following operations:
reading user basic information to obtain a user association relation;
calculating the user association relation according to a group recognition algorithm, dividing the user into a plurality of user groups according to the user association relation, and if the number of users in the user groups meets a first preset rule, determining that the users are group members;
acquiring homologous users with homologous relations according to the real-time information of the users;
judging whether a first user participating in the activity belongs to the community member or not according to the community member;
if not, acquiring a second user having a homologous relationship with the first user from the homologous users; judging whether the second user belongs to the community member; if the second user belongs to the group member, determining that the first user also belongs to the group member;
and if so, confirming that the first user belongs to the community member.
Optionally, the reading the user basic information to obtain the user association relationship includes the following steps:
reading user basic information to obtain at least one medium of a plurality of users;
the at least one medium comprises a bank account, an IP address, a mobile phone number, an international mobile equipment identification code used for logging in and the service time of the account;
and if the bank account numbers are the same, and/or the IP addresses are the same, and/or the mobile phone numbers are the same, and/or the international mobile equipment identification codes used for logging belong to the same model or the same, and/or the service time of the account numbers is within a preset time range, confirming that the association relationship exists among the users.
Optionally, the calculating the user association relationship according to a group identification algorithm divides the user into a plurality of user groups, and if the number of users in the user group meets a first preset rule, the user is determined to be a group member, including the following steps:
reading the user association relation;
reading the user association relation;
clustering calculation is carried out on a plurality of users by adopting a group recognition algorithm, and the plurality of users are divided into a plurality of user groups;
and if the number of the clustered users in the user group meets a first preset rule, taking the users in the user group as group members.
Optionally, the community identification algorithm comprises the steps of:
initializing a label of each node in the user association relation, wherein the label of each node is unique; wherein, the home node is x, the initialization label is
Setting the iteration times t, for each node
Where X is the set of all nodesTo obtain
judging whether the label of each node is not changed or the iteration times are met, and if the label of each node is not changed or the iteration times are met, ending the process; if not, setting t to t +1 and re-traversing.
Optionally, the obtaining of the homologous users having the homologous relationship according to the user real-time information includes the following steps:
acquiring user real-time information, wherein the user real-time information comprises: log messages and/or protocol messages and/or operation records;
processing the real-time information of the user by adopting a real-time streaming operation calculation mode to obtain homologous users with homologous relations;
the homologous relation is that the bank accounts of the users are the same, and/or the IP addresses are the same, and/or the mobile phone numbers are the same, and/or the international mobile equipment identification codes used for logging belong to the same model or are the same, and/or the accounts perform the same operation within the preset time.
Optionally, the determining, according to the community member, whether the first user participating in the activity belongs to the community member includes:
judging whether the account of the first user belongs to accounts of the group members;
if so, the first user belongs to the community member;
and if not, the first user does not belong to the community member.
Optionally, the group user identification method further includes the following steps:
and if the first user is the group member, forbidding the first user to participate in the activity.
In the embodiment of the invention, the real-time group identification is carried out through the offline full group identification and the real-time homologous fitting, so that the problem that the existing group cannot be identified in real time due to overlong group calculation time is solved, and the timeliness and the accuracy of the group identification are improved.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, a controller, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A community user identification method, characterized in that the method comprises the steps of:
reading user basic information to obtain a user association relation;
calculating the user association relation according to a group recognition algorithm, dividing the user into a plurality of user groups according to the user association relation, and if the number of users in the user groups meets a first preset rule, determining that the users are group members;
acquiring homologous users with homologous relations according to the real-time information of the users;
judging whether a first user participating in the activity belongs to the community member or not according to the community member;
if not, acquiring a second user having a homologous relationship with the first user from the homologous users;
judging whether the second user belongs to the community member; if the second user belongs to the group member, determining that the first user also belongs to the group member;
and if so, confirming that the first user belongs to the community member.
2. The community user identification method according to claim 1, wherein said reading user basic information to obtain user association relationship comprises the following steps:
reading user basic information to obtain at least one medium of a plurality of users;
the at least one medium comprises a bank account, an IP address, a mobile phone number, an international mobile equipment identification code used for logging in and the service time of the account;
and if the bank account numbers are the same, and/or the IP addresses are the same, and/or the mobile phone numbers are the same, and/or the international mobile equipment identification codes used for logging belong to the same model or the same, and/or the service time of the account numbers is within a preset time range, confirming that the association relationship exists among the users.
3. The group user identification method according to claim 1, wherein the user association is calculated according to a group identification algorithm, so as to divide the user into a plurality of user groups, and if the number of users in the user group satisfies a first preset rule, the user is determined to be a group member, comprising the steps of:
reading the user association relation;
clustering calculation is carried out on a plurality of users by adopting a group recognition algorithm, and the plurality of users are divided into a plurality of user groups;
and if the number of the clustered users in the user group meets a first preset rule, taking the users in the user group as group members.
4. The community user identification method according to claim 3, characterized in that said community identification algorithm comprises the steps of:
initializing a label of each node in the user association relation, wherein the label of each node is unique; wherein, the home node is x, the initialization label is
Setting the iteration times t, for each node
Where X is the set of all nodes, resulting in
judging whether the label of each node is not changed or the iteration times are met, and if the label of each node is not changed or the iteration times are met, ending the process; if not, setting t to t +1 and re-traversing.
5. The community user identification method according to claim 1, wherein said obtaining of homologous users having homologous relationships according to real-time user information comprises the steps of:
acquiring user real-time information, wherein the user real-time information comprises: log messages and/or protocol messages and/or operation records;
processing the real-time information of the user by adopting a real-time streaming operation calculation mode to obtain homologous users with homologous relations;
the homologous relation is that the bank accounts of the users are the same, and/or the IP addresses are the same, and/or the mobile phone numbers are the same, and/or the international mobile equipment identification codes used for logging belong to the same model or are the same, and/or the accounts perform the same operation within the preset time.
6. The community user identification method according to claim 1, wherein said determining whether a first user participating in an activity belongs to said community member based on said community member comprises the steps of:
judging whether the account of the first user belongs to accounts of the group members;
if so, the first user belongs to the community member;
and if not, the first user does not belong to the community member.
7. The community user identification method according to claim 1, further comprising the steps of:
and if the first user is the group member, forbidding the first user to participate in the activity.
8. A community user identification apparatus, characterized in that the community user identification apparatus comprises:
the information reading unit is used for reading the basic information of the user and obtaining the user association relation;
the user dividing unit is used for calculating the user association relation according to a group recognition algorithm, so that the user is divided into a plurality of user groups, and if the number of the users in the user groups meets a first preset rule, the user is confirmed to be a group member;
the homologous computing unit is used for obtaining homologous users with homologous relations according to the real-time information of the users;
the community confirming unit is used for judging whether a first user participating in the activity belongs to the community members or not according to the community members;
if not, acquiring a second user having a homologous relationship with the first user from the homologous users; judging whether the second user belongs to the community member; if the second user belongs to the group member, determining that the first user also belongs to the group member;
and if so, confirming that the first user belongs to the community member.
9. An electronic device, characterized in that the electronic device comprises: memory, a processor and a community user identification program stored on the memory and executable on the processor, the community user identification program being configured to implement the steps of the community user identification method according to any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the community user identification method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111330639.2A CN113902060A (en) | 2021-11-11 | 2021-11-11 | Group user identification method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111330639.2A CN113902060A (en) | 2021-11-11 | 2021-11-11 | Group user identification method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113902060A true CN113902060A (en) | 2022-01-07 |
Family
ID=79194038
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111330639.2A Pending CN113902060A (en) | 2021-11-11 | 2021-11-11 | Group user identification method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113902060A (en) |
-
2021
- 2021-11-11 CN CN202111330639.2A patent/CN113902060A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635872B (en) | Identity recognition method, electronic device and computer program product | |
| CN112148987B (en) | Message pushing method based on target object activity and related equipment | |
| CN106844407B (en) | Tag network generation method and system based on data set correlation | |
| US20180248879A1 (en) | Method and apparatus for setting access privilege, server and storage medium | |
| CN112613917A (en) | Information pushing method, device and equipment based on user portrait and storage medium | |
| CN111090807B (en) | Knowledge graph-based user identification method and device | |
| CN113378899B (en) | Abnormal account identification method, device, equipment and storage medium | |
| CN113412607B (en) | Content pushing method and device, mobile terminal and storage medium | |
| CN111259952A (en) | Abnormal user identification method and device, computer equipment and storage medium | |
| CN110224859A (en) | The method and system of clique for identification | |
| CN109658120B (en) | Service data processing method and device | |
| CN112487284A (en) | Bank customer portrait generation method, equipment, storage medium and device | |
| CN111612085A (en) | Method and device for detecting abnormal point in peer-to-peer group | |
| CN115883187A (en) | Method, device, equipment and medium for identifying abnormal information in network traffic data | |
| CN113902060A (en) | Group user identification method, device, equipment and storage medium | |
| CN114282940A (en) | Method and apparatus for intention recognition, storage medium, and electronic device | |
| CN114092268A (en) | User community detection method and device, computer equipment and storage medium | |
| CN110874465B (en) | Mobile equipment entity identification method and device based on semi-supervised learning algorithm | |
| CN112163155A (en) | Information processing method, device, equipment and storage medium | |
| CN112764923A (en) | Computing resource allocation method and device, computer equipment and storage medium | |
| CN115604000B (en) | Override detection method, device, equipment and storage medium | |
| CN113255710B (en) | Method, device, equipment and storage medium for classifying mobile phone numbers | |
| CN113726785B (en) | Network intrusion detection method and device, computer equipment and storage medium | |
| CN117391076B (en) | Acquisition method and device of identification model of sensitive data, electronic equipment and medium | |
| CN113468389B (en) | User portrait establishment method and device based on feature sequence comparison |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |