CN117056594A - User identification method and device based on interaction relationship and electronic equipment - Google Patents
User identification method and device based on interaction relationship and electronic equipment Download PDFInfo
- Publication number
- CN117056594A CN117056594A CN202310953917.2A CN202310953917A CN117056594A CN 117056594 A CN117056594 A CN 117056594A CN 202310953917 A CN202310953917 A CN 202310953917A CN 117056594 A CN117056594 A CN 117056594A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- individual
- enterprise
- determining
- 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
- 230000003993 interaction Effects 0.000 title claims abstract description 535
- 238000000034 method Methods 0.000 title claims abstract description 120
- 238000004891 communication Methods 0.000 claims abstract description 250
- 230000002452 interceptive effect Effects 0.000 claims description 23
- 230000002457 bidirectional effect Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 4
- 230000006855 networking Effects 0.000 claims 2
- 230000006399 behavior Effects 0.000 abstract description 13
- 238000010295 mobile communication Methods 0.000 abstract description 11
- 230000008569 process Effects 0.000 description 24
- 238000004364 calculation method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 238000003491 array Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000012804 iterative process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000006185 dispersion Substances 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 101100261006 Salmonella typhi topB gene Proteins 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 101150032437 top-3 gene Proteins 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Telephonic Communication Services (AREA)
Abstract
The application provides a user identification method and device based on interaction relation and electronic equipment, wherein the method comprises the following steps: acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; determining first credibility information of the individual user according to user information of the individual user and first communication interaction data; determining second credibility information of the individual user according to user information of the enterprise user and second communication interaction data; determining third credibility information of the individual user according to third communication interaction data based on a preset influence score of the Internet of things equipment; and identifying whether the individual user is an illegal user in a preset time period according to the first credibility information, the second credibility information and the third credibility information. The scheme can improve the accuracy of personal user credibility information and the accuracy of user identification, and provides reliable basis for the management of illegal behaviors in the field of mobile communication.
Description
Technical Field
The present application relates to the field of mobile communications technologies, and in particular, to a user identification method and apparatus based on an interaction relationship, and an electronic device.
Background
With the development of communication technology, the communication interaction volume between mobile users is increased, and meanwhile, great challenges are brought to the management of offensive behaviors such as nuisance calls, spam messages, fraud calls and the like. In the related art, the offending user is judged by recognizing the credibility of the user, but the accuracy of the existing scheme of judging the credibility of the user is low, so that it is difficult to accurately recognize the offending user.
Disclosure of Invention
In order to solve the problems, the application provides a user identification method and device based on interaction relationship and electronic equipment.
According to a first aspect of the present application, there is provided a user identification method based on interactive relationship, comprising: acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; the communication interaction data comprise first communication interaction data among individual users, second communication interaction data among the individual users and the enterprise users and third communication interaction data among the individual users and the Internet of things equipment in the preset time period; determining first credibility information of the individual user according to the user information of the individual user and the first communication interaction data; determining second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data; determining third credibility information of the personal user according to the third communication interaction data based on a preset influence score of the Internet of things equipment; and identifying whether the individual user is an illegal user in the preset time period according to the first credibility information, the second credibility information and the third credibility information.
According to a second aspect of the present application, there is provided a user identification method based on interactive relations, comprising: acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; the communication interaction data comprise first communication interaction data between individual users and second communication interaction data between the individual users and the enterprise users in the preset time period; determining first credibility information of the individual user according to the user information of the individual user and the first communication interaction data; determining second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data; and identifying whether the individual user is an illegal user in the preset time period according to the first credibility information and the second credibility information.
According to a third aspect of the present application, there is provided a user identification method based on interactive relations, comprising: acquiring communication interaction data and user information of an individual user in a preset time period; the communication interaction data comprise first communication interaction data between the individual users and third communication interaction data between the individual users and the Internet of things equipment in the preset time period; determining first credibility information of the individual user according to the user information of the individual user and the first communication interaction data; determining third credibility information of the personal user according to the third communication interaction data based on a preset influence score of the Internet of things equipment; and identifying whether the individual user is an illegal user in the preset time period according to the first credibility information and the third credibility information.
According to a fourth aspect of the present application, there is provided a user identification method based on interactive relations, comprising: acquiring first communication interaction data between individual users and user information of the individual users within a preset time period; determining initial credibility information of the individual user according to the user information; according to the first communication interaction data, determining the interaction times between the personal user and each called user when the personal user is used as a calling user; performing iterative operation according to the interaction times with each called user and the initial credibility information when the personal user is used as a calling user, and obtaining first credibility information of the personal user; and identifying whether the individual user is an illegal user in the preset time period according to the first credibility information.
According to a fifth aspect of the present application, there is provided a user identification device based on interactive relations, comprising: the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; the communication interaction data comprise first communication interaction data among individual users, second communication interaction data among the individual users and the enterprise users and third communication interaction data among the individual users and the Internet of things equipment in the preset time period; the first determining module is used for determining first credibility information of the personal user according to the user information of the personal user and the first communication interaction data; the second determining module is used for determining second credibility information of the personal user according to the user information of the enterprise user and the second communication interaction data; the third determining module is used for determining third credibility information of the personal user according to the third communication interaction data based on the influence score of the preset internet of things equipment; the identification module is used for identifying whether the individual user is an illegal user in the preset time period according to the first credibility information, the second credibility information and the third credibility information.
According to a sixth aspect of the present application, there is provided a user identification device based on interactive relations, comprising: the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; the communication interaction data comprise first communication interaction data between individual users and second communication interaction data between the individual users and the enterprise users in the preset time period; the first determining module is used for determining first credibility information of the personal user according to the user information of the personal user and the first communication interaction data;
the second determining module is used for determining second credibility information of the personal user according to the user information of the enterprise user and the second communication interaction data; the identification module is used for identifying whether the individual user is an illegal user in the preset time period according to the first credibility information and the second credibility information.
According to a seventh aspect of the present application, there is provided a user identification device based on interactive relations, comprising: the acquisition module is used for acquiring communication interaction data and user information of the individual user in a preset time period; the communication interaction data comprise first communication interaction data between the individual users and third communication interaction data between the individual users and the Internet of things equipment in the preset time period; the first determining module is used for determining first credibility information of the personal user according to the user information of the personal user and the first communication interaction data; the third determining module is used for determining third credibility information of the personal user according to the third communication interaction data based on the influence score of the preset internet of things equipment; the identification module is used for identifying whether the individual user is an illegal user in the preset time period according to the first credibility information and the third credibility information.
According to an eighth aspect of the present application, there is provided a user identification device based on interactive relationship, comprising: the first acquisition module is used for acquiring first communication interaction data between individual users and user information of the individual users in a preset time period; the first determining module is used for determining initial credibility information of the individual user according to the user information; the second determining module is used for determining the interaction times with each called user when the personal user is used as a calling user according to the first communication interaction data; the second acquisition module is used for carrying out iterative operation according to the interaction times of the personal user with each called user and the initial credibility information when the personal user is used as a calling user, so as to acquire first credibility information of the personal user; and the identification module is used for identifying whether the individual user is an illegal user in the preset time period according to the first credibility information.
According to a ninth aspect of the present application, there is provided an electronic apparatus comprising: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement the user identification method based on an interaction relationship described in the first aspect, or implement the user identification method based on an interaction relationship described in the second aspect, or implement the user identification method based on an interaction relationship described in the third aspect, or implement the user identification method based on an interaction relationship described in the fourth aspect.
According to a tenth aspect of the present application, there is provided a computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform the interactive relation based user identification method according to the first aspect, or to perform the interactive relation based user identification method according to the second aspect, or to perform the interactive relation based user identification method according to the third aspect, or to perform the interactive relation based user identification method according to the fourth aspect.
According to the technical scheme, the credibility information of the personal user is determined based on the communication interaction between the personal users, the communication interaction between the personal users and the enterprise users and the communication interaction between the personal users and the Internet of things equipment, the influence of all interaction objects with interactive relation with the personal users on the credibility information of the personal users can be fully considered, the enterprise users and the Internet of things equipment are both applied to the identification process of the personal users, the accuracy of the credibility information of the personal users can be improved, the accuracy of user identification can be improved, and a reliable basis is provided for the treatment of illegal behaviors in the field of mobile communication.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flowchart of a user identification method based on interaction relation according to an embodiment of the present application;
FIG. 2 is a flow chart of an implementation process for determining first confidence information of an individual user in an embodiment of the present application;
FIG. 3 is a flow chart of determining second confidence information for an individual user in an embodiment of the present application;
FIG. 4 is a flow chart of determining the total score of an individual user as affected by an enterprise user in an embodiment of the application;
FIG. 5 is a flow chart of determining the score of an individual user as affected by each enterprise user in one embodiment of the application;
FIG. 6 is a flow chart of determining the score of an individual user affected by each of the second type of enterprise users in an embodiment of the present application;
FIG. 7 is a flow chart of determining third confidence information for an individual user in an embodiment of the present application;
FIG. 8 is a flow chart of determining a total score of an individual user affected by an Internet of things device in an embodiment of the application;
FIG. 9 is a flowchart of another user identification method based on interaction relationship according to an embodiment of the present application;
FIG. 10 is a flowchart of a user identification method based on interaction relationship according to an embodiment of the present application;
FIG. 11 is a flowchart of a user identification method based on interaction relationship according to an embodiment of the present application;
FIG. 12 is a block diagram of a user identification device based on interaction relationship according to an embodiment of the present application;
FIG. 13 is a block diagram illustrating another user identification device based on interaction according to an embodiment of the present application;
FIG. 14 is a block diagram illustrating a further exemplary interactive relationship-based user identification device according to an embodiment of the present application;
FIG. 15 is a block diagram illustrating a further exemplary interactive relationship-based user identification device according to an embodiment of the present application;
fig. 16 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
With the development of communication technology, the communication interaction volume between mobile users is increased, and meanwhile, great challenges are brought to the management of offensive behaviors such as nuisance calls, spam messages, fraud calls and the like.
In the related technology, the credibility of the user is judged through the communication interaction behavior of the user, so that different governance strategies are adopted for users with different credibility. The method for judging the credibility of the user mainly comprises the following steps: (1) And modeling based on the user characteristic data by using the characteristics of the user, such as the age of the user, package information, telephone charge information and the like, and predicting the score of the user by using a machine learning algorithm, such as a random forest and the like. (2) Based on social network propagation theory, the main idea is that the value of one user can be transferred to other users through interaction behaviors, and the value of the user which is greatly referred by other high-quality users is also higher. The method generally uses a graph calculation algorithm to carry out iterative solution on the user interaction matrix, and finally obtains the influence or importance degree of the user in the interaction network. However, since the accuracy of the confidence result of the judgment user is low, it is difficult to realize the identification of the offending user.
In order to solve the problems, the application provides a user identification method and device based on interaction relationship and electronic equipment.
In the technical scheme of the application, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated. The user personal information involved is acquired, stored and applied in the event of contending for user consent.
Fig. 1 is a flowchart of a user identification method based on an interaction relationship according to an embodiment of the present application. It should be noted that, the user identification method based on the interaction relationship provided by the embodiment of the present application may be used in the user identification device based on the interaction relationship in the embodiment of the present application, and the user identification device based on the interaction relationship in the embodiment of the present application may be configured in an electronic device. As shown in fig. 1, the method may include the steps of:
step 101, acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; the communication interaction data comprise first communication interaction data among the individual users, second communication interaction data among the individual users and the enterprise users and third communication interaction data among the individual users and the Internet of things equipment in a preset time period.
In some embodiments of the present application, the preset time period may be a time period including the current time and a certain time range before the current time. Since the communication interaction data is changed with time, the communication interaction data in a period of time before the current time can be used as data for judging whether the user violates the rule in the period of time. It should be noted that, the user identification method based on the interaction relationship according to the embodiment of the present application may be executed once every preset time period.
The personal user refers to a user who opens an account with a personal identity, and the enterprise user refers to a user who opens an account with an enterprise identity. The individual users may be a plurality of individual users in a city, or an area. The user information of the individual user is the user information of each individual user, and can comprise relevant information such as user level, identity card information, client identification, level code, city, gender and the like. The user information of the enterprise user may include information about the number of users covered by the enterprise user, the amount of messages sent by the enterprise user, and the like.
In some embodiments of the present application, the first communication interaction data refers to data of communication interaction between individual users, where a communication interaction manner may be a telephone, a short message, a 5G message, a video call, etc., and in practical application, data corresponding to a corresponding communication interaction manner may be selected for different application scenarios. The second communication interaction data refers to communication interaction data between the personal user and the enterprise user, and the communication interaction mode between the personal user and the enterprise user can comprise short message messages, 5G information, telephones, 5G video calls, questionnaires, voice messages and the like.
In some embodiments of the present application, the internet of things device may be an internet of things ammeter, internet of things water meter, etc., may also be an intelligent home appliance, such as an air conditioner, a sweeping robot, a door lock, etc., and may also be an internet of things terminal device applied to the field of industrial production, such as a handheld terminal device, etc. The third communication interaction data can be interaction data when the personal user pays, reminding information sent by the internet of things equipment, control instruction data sent by the personal user to the internet of things equipment and the like.
Step 102, determining first credibility information of the individual user according to user information of the individual user and the first communication interaction data.
Wherein the first confidence information may be a confidence score determined based on user information of the individual user and interactions between the individual users.
As an example, the determining the first credibility information of the individual user according to the user information of the individual user and the first communication interaction data may include: based on a preset machine learning model, acquiring an initial credibility score of each individual user according to user information of each individual user; according to the first communication interaction data, the interaction relation among the individual users can be determined, and based on a social propagation algorithm, the first credibility information of each individual user is determined according to the initial credibility score of each individual user and the interaction relation among the individual users.
It should be noted that, for different application scenarios, communication interaction data of different personal user interaction modes may be selected. For example, aiming at harassment call illegal user treatment scenes, the first communication interaction data mainly consider call interaction data among individual users, and communication interaction data corresponding to other interaction modes may cause unnecessary interference; aiming at the spam message illegal user treatment scene, the first communication interaction data can be selected based on the message interaction data among individual users.
Step 103, determining second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data.
It can be understood that, because some enterprise users, such as large enterprises and schools, only send information to other specific groups such as enterprise staff, students, teachers and the like, and meanwhile, some offensive numbers are generally only used for dialing nuisance calls and other actions, and have less interaction with the enterprise users, the method has an important role in evaluating the credibility of the individual users according to the interaction information of the individual users and the enterprise users.
Wherein the second confidence information for the individual user may be a confidence score for the individual user determined based on the impact of the enterprise user.
As an embodiment, determining the second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data may include: for each individual user, if at least one enterprise user has communication interaction with the individual user, determining influence information of each enterprise user according to user information of each enterprise user; according to the second communication interaction data, the interaction times and the interaction relation between each enterprise user and the individual user can be determined; determining influence coefficients of the individual users influenced by each enterprise user according to the interaction times and the interaction relation between each enterprise user and the individual user; according to the influence coefficient of the individual user influenced by each enterprise user, weighting and summing the influence information of each enterprise user to obtain second credibility information of the individual user; if the enterprise users with which the personal users have communication interactions are 0, the second credibility information of the personal users is null.
And 104, determining third credibility information of the individual user according to third communication interaction data based on the influence score of the preset Internet of things equipment.
It can be appreciated that with the continuous popularization and development of the 5G technology, more and more internet of things devices are added into the communication network, and interaction between the personal user and the internet of things devices is more and more frequent, and meanwhile, interaction between the personal user and the internet of things devices is generally less for illegal users, so that communication interaction data between the personal user and the internet of things devices can be considered when the credibility information of the personal user is determined.
The influence score of the internet of things equipment is based on the influence of different internet of things equipment on the judgment of the credibility of the individual user, and the influence score of the internet of things equipment can be a value between 0 and 1. Usually, for example, the influence score of the internet of things ammeter, the internet of things water meter, or the internet of things equipment in the field of industrial production is higher, and the influence score of the intelligent household appliances and other internet of things equipment is lower.
In some embodiments of the present application, based on the impact score of the preset internet of things device, an implementation manner of determining the third credibility information of the individual user according to the third communication interaction data may include: for each individual user, according to the third communication interaction data, the Internet of things equipment with which the individual user has communication interaction can be determined; if one or more Internet of things devices with communication interaction with the personal user exist, the influence scores of the plurality of Internet of things devices can be summed to obtain third credibility information of the personal user; if the internet of things equipment with communication interaction with the personal user does not exist, the point credibility information of the personal user is null.
Step 105, identifying whether the individual user is an illegal user in a preset time period according to the first credibility information, the second credibility information and the third credibility information.
In some embodiments of the present application, the implementation manner of identifying whether the individual user is an offending user within the preset time period according to the first reliability information, the second reliability information, and the third reliability information may include: determining the credibility information of the individual user according to the first credibility information, the second credibility information and the third credibility information; and identifying whether the individual user is an illegal user in a preset time period according to the credibility information of the individual user.
As an example, for each individual user, the first reliability information, the second reliability information, and the third reliability information of the individual user may be weighted and summed, and the weighted and summed result is determined as the reliability information of the individual user; if the credibility information is a credibility score for representing the credibility of the individual user, a credibility score threshold value can be preset, the credibility score of the individual user is compared with the credibility score threshold value, if the credibility score of the individual user is smaller than the credibility score threshold value, the individual user is identified as an illegal user in a preset time period, and otherwise, the individual user is identified as a non-illegal user in the preset time period.
According to the user identification method based on the interaction relationship, the credibility information of the individual users is determined based on the communication interaction between the individual users, the communication interaction between the individual users and the enterprise users and the communication interaction between the individual users and the Internet of things equipment, the influence of all interaction objects having interaction relationship with the individual users on the credibility information of the individual users can be fully considered, the enterprise users and the Internet of things equipment are both applied to the identification process of the individual users, the accuracy of the credibility information of the individual users can be improved, the accuracy of user identification can be improved, and a reliable basis is provided for the treatment of illegal behaviors in the field of mobile communication.
Next, description will be made regarding an implementation procedure for determining first credibility information of an individual user.
Fig. 2 is a flowchart of an implementation process for determining first credibility information of an individual user in an embodiment of the present application. As shown in fig. 2, the implementation procedure based on step 102 of fig. 1 in the above embodiment may include:
step 201, determining initial credibility information of the individual user according to user information of the individual user.
It can be appreciated that, since the user information of the individual user may include information related to the user reliability, the initial reliability information of the individual user may be determined first based on the user information of the individual user. Wherein the initial confidence information may be an initial confidence score determined based on user information of the individual user.
As an example, the weight values corresponding to different fields in the user information may be preset, and the scores corresponding to the different values in each field may be set at the same time, so that the scores corresponding to the contents of each field in the user information of each individual user may be determined according to the user information of each individual user, and then the initial credibility scores of each individual user may be obtained by performing weighted summation based on the weight values corresponding to each individual user.
As another example, the implementation process of determining initial trust information of an individual user based on user information of the individual user may include: determining user characteristic information of the individual user according to the user information of the individual user, wherein the user characteristic information comprises user attribute characteristic information, user level characteristic information and user region characteristic information; inputting the user characteristic information into a preset initial scoring machine learning model to obtain initial credibility information; the initial scoring machine learning module learns to obtain the mapping relation between the user characteristic information of the individual user and the initial credibility information. Wherein the user characteristic information may be a characteristic vector determined based on the user information. The user attribute characteristic information may include information of the sex, age, education level, telephone, occupation, certificate, etc. of the individual user. The user level characteristic information may include information of a star level of an individual user, a star level rating time, whether a real name is available, and the like. The user region characteristic information may include information of a city or the like.
Step 202, according to the first communication interaction data, the interaction times between the personal user and each called user are determined when the personal user is used as a calling user.
That is, for each individual user, in the first communication interaction data, it is determined whether or not there is communication interaction data of the user as a calling user, and if there is communication interaction data of the individual user as a host user, the number of interactions with each called user is determined based on the communication interaction data when the individual user is the calling user.
And 203, performing iterative operation according to the interaction times and the initial credibility information of each called user when the personal user is used as a calling user, and obtaining the first credibility information of the personal user.
It will be appreciated that the more individual users interact with a person, the more important the person is in explaining the person, while the more important the calling user is, the more important the called user will be. In the related art, the influence degree of the same calling user on all called users is the same, and the influence of the interaction times is not considered. For example, in a period of time, a user with more communication times with the calling user contacts the calling user more closely, and a user with lower communication times with the calling user contacts the calling user more closely, so that the influence of the interaction times between individual users on each individual user is different, and the interaction times need to be considered when performing iterative calculation based on the interaction data.
In some embodiments of the present application, the implementation process for obtaining the first credibility information of the individual user may include: according to the interaction times between the personal user and each called user when the personal user is used as a calling user, determining the interaction duty ratio between the personal user and each called user when the personal user is used as the calling user; and carrying out iterative operation according to the interaction duty ratio and the initial credibility information between the personal user and each called user when the personal user is used as a calling user based on a webpage ranking Pagerank algorithm, and obtaining first credibility information.
As an example, if there is interaction with the called user B, the called user C, and the called user D when the personal user a is the calling user, the number of interactions with the called user B is R AB The interaction times with the called user C is R AC The interaction times with the called user D is R AD The interaction duty cycle between personal user a and called user b=r AB /(R AB +R AC +R AD ) Interaction duty cycle=r between personal user a and called user C AC /(R AB +R AC +R AD ) Interaction duty cycle=r between personal user a and called user D AD /(R AB +R AC +R AD )。
Taking the individual user u as an example, in performing an iterative operation according to the interaction duty ratio and the initial credibility information between the individual user and each called user when the individual user is used as a calling user, the individual user u can be expressed in each iterative process by the following formula:
Wherein V represents the set of calling subscribers having a communication interaction with the individual subscriber u; v (V) i Indicating an ith caller having a communication interaction with the individual user u; n is the number of calling subscribers having a communication interaction with the individual subscriber u;is V (V) i As an interaction ratio between the calling subscriber and the individual subscriber u, wherein +.>Is V (V) i As number of interactions with individual user u when calling user,/->Represents V i As the interaction times with all called users when the calling user; />Representing calling subscriber V i The reliability information iteration value in the current iteration process; cu represents the trust information iteration value obtained by the personal user u through the current iteration calculation.
To more clearly illustrate the above iterative process, it is illustrated by way of example. If there are 4 individual users, individual user u, individual user v, individual user w, and individual user x, respectively, the number of interactions between the calling user and each called user is represented by the following table 1. As shown in table 1 Rvu represents the number of interactions with the called user u when the individual user v is the calling user, and so on.
TABLE 1 Interactive relationship Table between personal users
| u | v | w | x | |
| u | 0 | Rvu | Rwu | 0 |
| v | Ruv | 0 | Rwv | Rxv |
| w | Ruw | 0 | 0 | Rxw |
| x | Rux | Rvx | 0 |
If the initial credibility information of the personal user u is Cu 0 The initial credibility information of the individual user v is Cv 0 The initial credibility information of the individual user w is Cw 0 For personal useThe initial credibility information of the user x is Cx 0 The first iterative process may be represented by the following formulas (2) - (5):
wherein Cu is 1 The credibility information of the personal user u after the first round of iteration is provided; cv 1 The credibility information of the individual user v after the first iteration is provided; cw (Cw) 1 The credibility information of the individual user w after the first iteration is provided; cx (x) 1 The credibility information of the individual user x after the first iteration is provided. And performing multiple iterations based on the first iteration process and the like until the change of the credibility information after the two iterations meets the preset range, and ending the iterations to obtain the first credibility information of each individual user.
According to the user identification method based on the interaction relationship, the initial credibility information of the personal user is determined based on the information of the personal user, and iterative operation is carried out according to the interaction times and the initial credibility information of each called user when the personal user is used as a calling user, so that the first credibility information of the personal user is obtained. According to the method and the device, the interaction times are introduced in the iterative calculation process, and are used as the basis of the user contact compactness, so that the obtained result is higher in accuracy than the related technology, and the accuracy of user identification can be improved.
Fig. 3 is a flowchart of determining second credibility information of an individual user in an embodiment of the present application. As shown in fig. 3, based on the above embodiment, the implementation procedure of step 103 in fig. 1 may include the following steps:
step 301, determining the total score of the individual user affected by the enterprise user according to the user information of the enterprise user and the second communication interaction data.
It can be appreciated that, since enterprise users typically interact with a specific user group, and illegal users typically only use to make nuisance calls or send nuisance short messages, etc., there is less interaction with the enterprise users, the user information and the second communication interaction data of the enterprise users have an important role in evaluating the credibility of the individual users.
In some embodiments of the present application, the impact score of the enterprise user may be determined according to the user information of the enterprise user, and then the number of interactions between the individual user and the enterprise user may be determined according to the second communication interaction data, and the closeness between the individual user and the enterprise user may be determined according to the number of interactions between the individual user and the enterprise, and the total score of the individual user affected by the enterprise user may be determined according to the impact score of the enterprise user and the closeness between the individual user and the enterprise user.
Step 302, ranking the total score of the individual user affected by the enterprise user, and determining second credibility information of the individual user according to the ranking result.
In some embodiments of the present application, the total score of each individual user affected by the enterprise user may be grouped into a set M, where the number of elements in the set M is n, where n is the number of individual users. And ordering the elements in M from small to large, and determining second credibility information of the individual user according to the positions of the elements in M after ordering.
As an example, the second confidence information of the individual user may be a percentile, as shown in equation (6). If the total score of the individual user u affected by the enterprise user is the largest in the set M after the sorting, the second credibility information of the individual user u is 1; if the total score of the individual user u affected by the enterprise user after the sorting is 75% of the score number in the set M, the second credibility information of the individual user u is 0.75.
Bu＝percentile(M，Mu) (6)
Wherein Bu is the second credibility information of the individual user u; m is the total score of each individual user affected by the enterprise user to form a set; mu is the total impact score of individual user u by the enterprise user.
According to the user identification method based on the interaction relation, according to the user information of the enterprise user and the second communication interaction data, the total score of the individual user influenced by the enterprise user is determined, the total score of the individual user influenced by the enterprise user is ranked, and the second credibility information of the individual user is determined according to the ranking result. According to the scheme, communication interaction data of the personal user and the enterprise user are introduced, and the credibility score of the personal user is further determined based on the user information and the interaction information of the enterprise user, so that the credibility of the personal user can be estimated more comprehensively, and the accuracy of user identification can be improved.
FIG. 4 is a flow chart of determining the total score of an individual user as affected by an enterprise user in an embodiment of the application. It should be noted that the number of enterprise users is at least one. As shown in fig. 4, based on the above embodiment, the implementation procedure of step 301 in fig. 3 may include:
step 401, determining an influence score of each enterprise user according to the user information of each enterprise user.
In some embodiments of the application, the impact score for an enterprise user may be an impact parameter value for the enterprise user when computing trust information for an individual user. For example, the more targeted the interaction between the enterprise user and the individual user, the higher the impact of the enterprise user on the calculation of the trust information of the individual user.
As one possible implementation, the user information of each enterprise user includes a normal message amount sent by each enterprise user, a total message amount sent by each enterprise user, a personal user amount covered by each enterprise user, and an interaction amount of each enterprise user with users of respective territories. The influence score for each enterprise user includes a first influence score, a second influence score, and a third influence score. The first influence score, the second influence score, and the third influence score may each be a value between 0-1. The implementation process for determining the influence score of each enterprise user according to the user information of each enterprise user comprises the following steps:
Step 401-1, determining a first impact score for each enterprise user based on the normal message volume and the total message volume.
It will be appreciated that, for example, business users who send promotional information, advertising information, or other offending messages, the objects that they send are targeted and the content that they send is not useful in indicating user identity information. The first impact score for the enterprise user may be determined based on the circumstances under which the enterprise user sent the offending message.
In some embodiments of the application, the first impact score for the enterprise user is an impact score for the enterprise user determined based on a condition that the enterprise user sent the offending message. The normal message volume sent by each enterprise user refers to the message volume remaining after the violation message is removed from the total message volume sent by each enterprise user.
As one example, a ratio of a normal message volume to a total message volume sent by each enterprise user may be determined as a first impact score for each enterprise user. If the violation message sent by the enterprise user is smaller, the reliability of the enterprise user is higher, and the first influence score of the enterprise user is larger.
Step 401-2, sorting the individual user quantity covered by each enterprise user from large to small, and determining a second influence score of each enterprise user according to the sorting result.
It can be appreciated that the more individual users a given enterprise user covers, the less targeted the interaction between the enterprise user and the individual users can be generally considered, for example, the more individual users the enterprise user has a certain public attribute, such as an operator, a bank, etc. And the interaction between the enterprise users, such as schools, enterprises and the like, which cover fewer personal users, and the personal users has stronger pertinence, and is helpful to indicate the identity of the interaction object. The greater the amount of individual users each enterprise user covers, the greater its impact on the individual users.
In some embodiments of the present application, the individual user volume covered by each enterprise user may be ranked from large to small, and the location of each enterprise user in the ranking result may be determined according to the ranking result, with the percentile of the location of each enterprise user in the ranking result being the second impact score for each enterprise user. The closer the second impact score of an enterprise user is to 1, the less the enterprise user is covered by individual users, and the greater the impact on evaluating individual users.
It should be noted that, considering that a normal individual user generally interacts with an enterprise user with a low second influence score such as an operator bank, and that an offending user generally interacts with the enterprise user with a low second influence score, the offending user has a certain influence on the individual user for the enterprise user with the second influence score close to 0, so that the second influence score of the enterprise user with the percentile less than 0.1 may be set to 0.1.
Step 401-3, determining a third impact score of each enterprise user according to the interaction amount of each enterprise user with the users in each region.
Because enterprise users with stronger pertinence such as enterprises and public institutions, schools and the like mostly originate from the same region, and the regions of the objects interacted by some enterprise users with weaker pertinence are scattered, the interaction quantity of the enterprise users and the users in each region can be used as another factor for evaluating the influence of the enterprise users.
In some embodiments of the present application, the determining the third impact score for each enterprise user according to the interaction amount of each enterprise user with the users of the respective territories may include: for each enterprise user, ordering the interaction quantity of the enterprise user and the users of each region from large to small, and determining the sum of the interaction quantities of N regions before ordering based on an ordering result; determining the total interaction quantity of the enterprise user and the users in all regions according to the interaction quantity of the enterprise user and the users in all regions; and determining the ratio of the sum of the interaction amounts of the N regions before the ordering to the total interaction amount as a third influence score of the enterprise user.
As an example, N may be 3, and the above calculation is shown in formula (7):
wherein Pc is a third impact score for the enterprise user; n (N) top3 Representing the sum of the interaction amounts of the first 3 regions; nall represents the total interaction volume of the enterprise user in each region within a set period of time.
It should be noted that, in the embodiment of the present application, the user information of each enterprise user includes the normal message amount sent by each enterprise user, the total message amount sent by each enterprise user, the individual user amount covered by each enterprise user, and the interaction amount between each enterprise user and the user in each region, which may be data in a period of time, where the period of time may be the same as or different from the preset period of time in the above embodiment.
Step 402, determining the score of the individual user affected by each enterprise user according to the influence score of each enterprise user and the second communication interaction data.
In some embodiments of the present application, the interaction amount and the interaction type of the individual user and each enterprise user may be determined according to the second communication interaction data, where the interaction type includes a message type and a call type; according to the interaction type of the individual user and each enterprise user, determining the weight values of three influence scores of each enterprise user; according to the weight value of the influence score, carrying out weighted summation on the first influence score, the second influence score and the third influence score of each enterprise user; determining the closeness of the personal user and each enterprise user according to the interaction quantity of the personal user and each enterprise user; and determining the influence scores of the individual users by the enterprise users according to the closeness of the individual users and each enterprise user and the weighted summation result.
Step 403, determining the total score of the individual user affected by the enterprise user according to the score of the individual user affected by each enterprise user.
It will be appreciated that the greater the number of enterprise users with whom the individual user has interactions, the greater the degree of trustworthiness of that individual user will be explained. In some embodiments of the present application, for each individual user, the score of the individual user affected by each enterprise user may be summed to obtain a total score of each individual user affected by the enterprise user.
According to the user identification method based on the interaction relation, according to the user information of each enterprise user, influence calculation of the enterprise user is conducted from three dimensions of the violation message proportion, the coverage user quantity and the region distribution, according to the influence score of the enterprise user and the second communication interaction data, the score of the personal user influenced by each enterprise user is determined, and according to the score of the personal user influenced by each enterprise user, the total score of the personal user influenced by the enterprise user is determined, so that second credibility information of the personal user is determined. According to the scheme, the influence scores of the enterprise users are calculated from a plurality of different dimensions, the influence of the enterprise users can be comprehensively considered, and therefore the accuracy of the second credibility information of the individual users can be improved, and the accuracy of user identification is further improved.
FIG. 5 is a flow chart of determining the score of an individual user as affected by each enterprise user in one embodiment of the application. As shown in fig. 5, based on the above embodiment, the implementation of step 402 in fig. 4 may include the following steps:
step 501, determining the interaction type between the individual user and each enterprise user according to the second communication interaction data; wherein the interaction type comprises a call type and a message type.
In the embodiment of the application, the interaction modes between the personal user and the enterprise user can comprise short message intersecting lines, 5G messages, telephones, 5G video calls, file surveys, voice attentions and the like, so that the interaction modes between the personal user and the enterprise user can be divided into call types and message types. The message types may include, among others, a short message, a 5G message, a questionnaire, etc., sent by the enterprise user to the individual user. Such as balance reminders, verification code delivery, user satisfaction surveys, and the like. Call types may include telephone, video call, etc. types of interactions.
Step 502, dividing at least one enterprise user into i first-class enterprise users and j second-class enterprise users according to the interaction type; wherein i and j are integers greater than or equal to 0, the interaction type corresponding to the first type enterprise user comprises a call type, and the interaction type corresponding to the second type enterprise user only comprises a message type.
As an example, enterprise users corresponding to when the interaction type between the individual user and the enterprise user includes a call type may be classified as first type enterprise users; and dividing enterprise users corresponding to the interaction types between the personal users and the enterprise users only including the message types into second-type enterprise users.
In step 503, a score of the individual user affected by each of the first type of enterprise users is determined according to the first impact scores of each of the first type of enterprise users.
It can be appreciated that if the interaction type between the individual user and the enterprise user includes a call type, such as a call behavior between the individual user and an operator, a bank manual customer service, or the like, the reliability of the individual user may be considered to be high, and the calculation of the second reliability information of the individual user does not depend on whether the enterprise user has pertinence to the interaction object, so that the score of the individual user affected by each first type of enterprise user may be determined based on the first influence score for characterizing the illegal messaging situation of the enterprise user.
Step 504, determining the score of the individual user affected by each second type enterprise user according to the influence score of each second type enterprise user and the second communication interaction data.
If only the information type interaction exists between the personal user and the enterprise user, the second credibility calculation for the personal user is mainly dependent on the pertinence of the enterprise user to the interaction object, so that the stronger the pertinence of the enterprise user to the interaction object is, the larger the influence of the enterprise user to the personal user is.
In some embodiments of the present application, the implementation of step 504 may include: determining a comprehensive influence score of each second-class enterprise user according to the first influence score, the second influence score and the third influence score of each second-class enterprise user; determining the closeness between the individual user and each second-class enterprise user according to the second communication interaction data; and determining the score of the personal user influenced by each second type enterprise user according to the closeness of the personal user and each second type enterprise user and the comprehensive influence score of each second type enterprise user.
And aiming at each individual user, carrying out summation calculation on the influence scores of the individual user and the second type enterprise user to obtain the total score of the individual user influenced by the enterprise user.
According to the user identification method based on the interaction relation, based on the interaction type between the personal user and the enterprise user, the enterprise user with the interaction type being the call type is divided into the first enterprise user, the enterprise user with the interaction type only comprising the message type is divided into the second enterprise user, and the score of the user influenced by each enterprise user is calculated for the first enterprise user and the second enterprise user respectively. According to the scheme, the scores of the individual users influenced by the enterprise users are respectively determined for the enterprise users under different interaction types, so that the accuracy of the credibility information calculation of the individual users can be effectively improved, and the accuracy of user identification can be further improved.
Next, a description will be given of a process of determining a score of an individual user affected by each of the second type of enterprise users.
FIG. 6 is a flow chart of a method for determining the impact scores of individual users with each of the second type of enterprise users in accordance with an embodiment of the present application. As shown in fig. 6, based on the above embodiment, the implementation procedure of step 504 in fig. 5 may include the following steps:
step 601, determining a comprehensive influence score of each second type enterprise user according to the first influence score, the second influence score and the third influence score of each second type enterprise user.
In some embodiments of the present application, the first influence score, the second influence score, and the third influence score of each second type enterprise user may be weighted and summed, where the weight value of each influence score may be preset, and the weighted and summed result is used as the integrated influence score of each second type enterprise user.
In other embodiments of the present application, the product of the first impact score, the second impact score, and the third impact score for each of the second type of enterprise users may be used as the composite impact score for each of the second type of enterprise users.
Because the second influence score and the third influence score of the enterprise user have relevance, when the coverage number of the enterprise user is small, the regional dispersion of the enterprise user is also low, so in order to avoid that the comprehensive influence score of the enterprise user is too low due to the low regional dispersion, the step 601 can be further implemented by the following ways: comparing the second influence scores of the second type enterprise users with a preset influence threshold value aiming at each second type enterprise user; if the second influence score of the second type enterprise user is larger than the influence threshold, determining a comprehensive influence score of the second type enterprise user according to the first influence score, the second influence score and the third influence score of the second type enterprise user; and if the second influence score of the second type enterprise user is smaller than or equal to the influence threshold, determining the comprehensive influence score of the second type enterprise user according to the first influence score and the second influence score of the second type enterprise user.
For example, the implementation process of step 601 is shown in formula (8), and if the second influence score of the second type enterprise user is greater than the influence threshold, the product of the first influence score, the second influence score and the third influence score of the second type enterprise user is used as the comprehensive influence score of the second type enterprise user; and if the second influence score of the second type enterprise user is smaller than or equal to the influence threshold, taking the product of the first influence score and the second influence score of the second type enterprise user as the comprehensive influence score of the second type enterprise user.
Wherein Pa is a first impact score of the enterprise user; pb is the second influence score of the enterprise user; pc is a third influence score of the enterprise user; θ is the influence threshold.
Step 602, determining the score of the individual user affected by each second type enterprise user according to the second communication interaction data and the comprehensive influence score of each second type enterprise user.
As an example, the closeness of the individual user to each of the second type enterprise users may be determined based on the second communication interaction data, and then the score of the individual user affected by each of the second type enterprise users may be determined based on the aggregate impact score of each of the second type enterprise users and the closeness of the individual user to each of the second type enterprise users.
It will be appreciated that the personal user may include one-way interactions with the second type of enterprise user as well as two-way interactions. If only one-way interaction exists between the personal user and the second type enterprise user, the more the number of one-way interactions is, the more closely the two are related, and the larger the influence obtained by propagation is. If there is a two-way interaction between the individual user and the second type of enterprise user, it may also be determined that the relationship between them is relatively tight. Therefore, to characterize the tightness of the connection between the individual user and the second type of enterprise user, this can be represented by a computational closeness.
In some embodiments of the present application, the implementation of step 602 in fig. 6 may include the steps of:
step 602-1, determining the interaction direction or the unidirectional interaction times of the individual user and each second-class enterprise user according to the second communication interaction data.
In some embodiments of the present application, if the interaction direction between the individual user and a certain second type of enterprise user only includes one-way interaction, the number of one-way interactions between the individual user and the second type of enterprise user may be determined according to the second type of communication interaction data. If the interaction direction of the personal user and a certain second type of enterprise user comprises bidirectional interaction, the unidirectional interaction times between the personal user and the second type of enterprise user can be no longer required to be acquired.
Step 602-2, determining the closeness of the individual user and each second type enterprise user according to the interaction direction or the unidirectional interaction times of the individual user and each second type enterprise user.
In some embodiments of the present application, the closeness is a degree of closeness characterizing the connection between the individual user and the second type of enterprise user, and the closeness may be a value between 0-1. For each second-class enterprise user, if the interaction direction of the personal user and the second-class enterprise user is unidirectional interaction, the closeness between the personal user and each second-class enterprise user can be determined according to the unidirectional interaction times of the personal user and the second-class enterprise user. If the interaction direction of the personal user and the second type enterprise user is bidirectional interaction, the personal user and the second type enterprise user can be considered to have closer contact, and the compactness of the personal user and the second type enterprise user can be directly determined to be 1.
As an example, if the interaction direction of the personal user and the second type of enterprise user is unidirectional interaction, according to the unidirectional interaction times of the personal user and the second type of enterprise user, the implementation manner of determining the closeness between the personal user and the second type of enterprise user may include: and determining the closeness of the personal user and the second type enterprise user according to the unidirectional interaction times of the personal user and the second type enterprise user based on a preset mapping relation of the unidirectional interaction times and the closeness.
As another example, the unidirectional interaction times reference value may be preset, and the unidirectional interaction times reference value of each second-class enterprise user may be the same or different. For example, for each second-class enterprise user, the unidirectional interaction times of the second-class enterprise user and each individual user may be ranked, and the median in the ranking result may be determined as the unidirectional interaction times reference value of the second-class enterprise user. As shown in formula (9), if the number of the unidirectional interactions between the individual user and the second type enterprise user is greater than the reference value of the unidirectional interactions, the compactness between the individual user and the second type enterprise user may be determined to be 1, otherwise, the ratio of the number of the unidirectional interactions between the individual user and the second type enterprise user and the reference value of the unidirectional interactions may be used as the compactness between the individual user and the second type enterprise user.
Wherein, eui is the closeness of the individual user to the second type enterprise user i; i.e med The value can be a median in the unidirectional interaction times sequencing of the second type enterprise user i and each individual user; rui is the number of unidirectional interactions of the individual user with the second type of enterprise user i.
Step 602-3, determining the score of the individual user affected by each second type of enterprise user based on the closeness of the individual user to each second type of enterprise user and the integrated impact score of each second type of enterprise user.
As one possible implementation, the product of the closeness of the individual user to each of the second type of enterprise users and the aggregate impact score of each of the second type of enterprise users may be determined as the score of the individual user's impact by each of the second type of enterprise users.
According to the user identification method based on the interaction relation, the comprehensive influence score of each second-class enterprise user is determined through the first influence score, the second influence score and the third influence score of each second-class enterprise user, and the score of the individual user influenced by each second-class enterprise user is determined according to the second communication interaction data and the comprehensive influence score of each second-class enterprise user. Meanwhile, when the score of the personal user influenced by the second type enterprise user is determined, the closeness between the personal user and the second type enterprise user is introduced, so that the accuracy of determining the score of the personal user influenced by the second type enterprise user is improved, the accuracy of credibility information of the personal user can be further improved, and the accuracy of user identification can be further improved.
Fig. 7 is a flowchart of determining third credibility information of an individual user in an embodiment of the present application. As shown in fig. 7, based on the above embodiment, the implementation procedure of step 104 in fig. 1 may include:
and step 701, determining the total score of the personal user influenced by the Internet of things equipment according to the third communication interaction data based on the influence score of the Internet of things equipment.
As a possible implementation manner, the number of interactions between the individual user and each internet of things device can be determined according to the third communication interaction data; according to the interaction times between the personal user and each Internet of things device, the total interaction times between the personal user and all Internet of things devices are calculated; determining the ratio of the number of interactions between the personal user and each Internet of things device according to the number of interactions between the personal user and each Internet of things device and the total number of interactions between the personal user and all Internet of things devices; and carrying out weighted summation on the influence scores of the internet of things equipment with which the personal user interacts according to the interaction times ratio between the personal user and each internet of things equipment to obtain the total score of the personal user influenced by the internet of things equipment.
Step 702, sorting the total score of the personal user affected by the internet of things device, and determining third credibility information of the personal user according to the sorting result.
In some embodiments of the present application, the total score of each individual user affected by the internet of things device may be grouped into a set N, where the number of elements in the set N is N, where N is the number of individual users. And ordering the elements in the N from small to large, and determining third credibility information of the individual user according to the positions of the elements in the N after ordering.
As an example, the third confidence information for the individual user may be a percentile, as shown in equation (10). If the total score of the personal user u affected by the internet of things equipment is the largest in the set N after the sorting, the third credibility information of the personal user u is 1; if the total score of the sequenced personal user u affected by the internet of things device is 75% of the score number in the set N, the third credibility information of the personal user u is 0.75.
Du＝percentile(N，Nu) (10)
Wherein Du is third credibility information of the individual user u; n is a total score of each individual user influenced by the Internet of things equipment to form a set; nu is the total score of the individual user u affected by the internet of things device.
According to the user identification method based on the interaction relation, based on the influence score of the Internet of things equipment, the total score of the personal user influenced by the Internet of things equipment is determined according to the third communication interaction data, the total score of the personal user influenced by the Internet of things equipment is ordered, and the third credibility information of the personal user is determined according to the ordering result. According to the scheme, the third credibility information of the personal user is determined by introducing interaction between the personal user and the Internet of things equipment, so that the accuracy of user identification is improved.
Next, a description will be given of a process of determining a total score of an individual user affected by the internet of things device.
Fig. 8 is a flowchart of determining a total score of an individual user affected by an internet of things device in an embodiment of the application. As shown in fig. 8, based on the above embodiment, the implementation procedure of step 702 in fig. 7 may include:
step 801, determining m first internet of things devices performing unidirectional interaction with a personal user and n second internet of things devices performing bidirectional interaction with the personal user according to third communication interaction data; wherein m and n are integers greater than or equal to 0.
It can be appreciated that according to the third communication interaction data, the internet of things device having interaction with the individual user can be determined, and meanwhile, the interaction direction between the individual user and each internet of things device can be determined, namely, only one-way interaction exists or two-way interaction exists. The unidirectional interaction means that only the internet of things device sends a message to the personal user, the bidirectional interaction means that the internet of things device can send a message to the personal user, and meanwhile, the personal user can send a command to the internet of things device, for example, an air conditioner is set remotely, a door is opened remotely, and the like.
Step 802, determining the score of the personal user affected by the first internet of things device according to the influence score of each first internet of things device.
In some embodiments of the present application, the total impact score of each first internet of things device may be determined according to the impact score of each first internet of things device; and determining the score of the personal user influenced by the first Internet of things equipment according to the total influence score of the first Internet of things equipment based on a preset one-way interaction influence coefficient.
As an example, for each individual user, the influence score of each first internet of things device may be summed and calculated, and the summed result may be used as the total influence score of the first internet of things device; and determining the product of the unidirectional interaction influence coefficient and the total influence score of the first Internet of things equipment as the score of the personal user influenced by the first Internet of things equipment.
Step 803, determining the score of the individual user affected by the second internet appliance according to the impact score of each second internet appliance.
In some embodiments of the present application, the determining, according to the influence score of each second internet-enabled device, the score of the individual user affected by the second internet-enabled device may include: determining a total influence score of the second internet of things device according to the influence score of each second internet of things device; and determining the score of the personal user influenced by the second internet-of-things device according to the total influence score of the second internet-of-things device based on the preset bidirectional interaction influence coefficient.
It should be noted that, because the credibility of the personal user performing the bidirectional interaction with the internet of things device is higher, the bidirectional interaction influence coefficient is generally greater than the unidirectional interaction influence coefficient, for example, the ratio of the unidirectional interaction influence coefficient to the bidirectional interaction influence coefficient may be 1:2.
As an example, for each individual user, the influence score for each second networked device may be summed and the summed result may be taken as the total influence score for the second networked device; and determining the product of the bidirectional interaction influence coefficient and the total influence score of the second internet-of-things equipment as the influence score of the personal user by the second internet-of-things equipment.
Step 804, determining the total score of the individual user affected by the internet of things device according to the score of the individual user affected by the first internet of things device and the score of the individual user affected by the second internet of things device.
In some embodiments of the present application, the score of the individual user affected by the first internet of things device and the score of the individual user affected by the second internet of things device may be summed to obtain a total score of the individual user affected by the internet of things device, where the calculation process is shown in formula (11):
Wherein Nu is the total score of the individual user u affected by the internet of things device; m is the number of first internet of things devices with which the personal user u interacts; n is the number of second networked devices with which the individual user u has interactions; eu (Eu) i The influence score of the ith first Internet of things device with interaction with the personal user u is obtained; eu (Eu) j An influence score for a j-th second networked device with which the personal user u has an interaction; d is a unidirectional interaction influence coefficient; e is a bi-directional interaction influence coefficient.
According to the user identification method based on the interaction relation, based on third communication interaction data, the internet of things equipment which has interaction with the individual user is divided into first internet of things equipment which has unidirectional interaction with the individual user and second internet of things equipment which has bidirectional interaction with the individual user according to the interaction direction, the score of the individual user influenced by the first internet of things equipment and the score of the individual user influenced by the second internet of things equipment are respectively determined according to the respective influence scores, and the total score of the individual user influenced by the internet of things equipment is determined according to the score of the individual user influenced by the first internet of things equipment and the score of the individual user influenced by the second internet of things equipment. According to the scheme, the total score of the personal user influenced by the Internet of things equipment is determined by considering different interaction directions, so that the accuracy of third credibility information calculation is improved, and the accuracy of user identification can be improved.
Fig. 9 is a flowchart of another user identification method based on interaction relationship according to an embodiment of the present application. As shown in fig. 9, the method includes the steps of:
step 901, acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; the communication interaction data comprise first communication interaction data between individual users and second communication interaction data between the individual users and enterprise users in a preset time period.
Step 902, determining first credibility information of the individual user according to user information of the individual user and the first communication interaction data.
Step 903, determining second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data.
It should be noted that, the implementation process of steps 901-903 may refer to the implementation manner in fig. 1-6 of the foregoing embodiments, and will not be described herein.
Step 904, identifying whether the individual user is an illegal user in a preset time period according to the first credibility information and the second credibility information.
In some embodiments of the present application, the implementation manner of identifying whether the individual user is an offending user within the preset time period according to the first credibility information and the second credibility information may include: determining the credibility information of the individual user according to the first credibility information and the second credibility information; and identifying whether the individual user is an illegal user in a preset time period according to the credibility information of the individual user.
As an example, for each individual user, the first and second credibility information of the individual user may be weighted and summed, and the weighted and summed result is determined as the credibility information of the individual user; if the credibility information is a credibility score for representing the credibility of the individual user, a credibility score threshold value can be preset, the credibility score of the individual user is compared with the credibility score threshold value, if the credibility score of the individual user is smaller than the credibility score threshold value, the individual user is identified as an illegal user in a preset time period, and otherwise, the individual user is identified as a non-illegal user in the preset time period.
According to the user identification method based on the interaction relationship, based on communication interaction between individual users and enterprise users, the influence of all interaction objects having interaction relationship with the individual users on the credibility information of the individual users can be fully considered, the enterprise users can be applied to the identification process of the individual users, the accuracy of the credibility information of the individual users can be improved, the accuracy of user identification can be improved, and reliable basis is provided for the management of illegal behaviors in the field of mobile communication.
Fig. 10 is a flowchart of another user identification method based on interaction relationship according to an embodiment of the present application. As shown in fig. 10, the method may include:
step 1001, acquiring communication interaction data and user information of an individual user in a preset time period; the communication interaction data comprise first communication interaction data between the individual users in a preset time period and third communication interaction data between the individual users and the Internet of things equipment.
Step 1002, determining first credibility information of the individual user according to user information of the individual user and the first communication interaction data.
Step 1003, determining third credibility information of the individual user according to third communication interaction data based on the influence score of the preset internet of things equipment.
It should be noted that, the implementation process of steps 1001-1003 may refer to the implementation manner in fig. 1, 2, 7 and 8 in the above embodiment, and will not be described herein.
Step 1004, identifying whether the individual user is an illegal user in a preset time period according to the first credibility information and the third credibility information.
In some embodiments of the present application, the implementation manner of identifying whether the individual user is an offending user within the preset time period according to the first reliability information and the third reliability information may include: determining the credibility information of the individual user according to the first credibility information and the third credibility information; and identifying whether the individual user is an illegal user in a preset time period according to the credibility information of the individual user.
As an example, for each individual user, the first reliability information and the third reliability information of the individual user may be weighted and summed, and the weighted and summed result is determined as the reliability information of the individual user; if the credibility information is a credibility score for representing the credibility of the individual user, a credibility score threshold value can be preset, the credibility score of the individual user is compared with the credibility score threshold value, if the credibility score of the individual user is smaller than the credibility score threshold value, the individual user is identified as an illegal user in a preset time period, and otherwise, the individual user is identified as a non-illegal user in the preset time period.
According to the user identification method based on the interaction relationship, based on the communication interaction between the personal users and the Internet of things equipment, the influence of all interaction objects with the personal users on the credibility information of the personal users can be fully considered, and in the identification process from the Internet of things equipment to the personal users, the accuracy of the credibility information of the personal users can be improved, the accuracy of user identification can be improved, and a reliable basis is provided for the management of illegal behaviors in the field of mobile communication.
Fig. 11 is a flowchart of another user identification method based on interactive relationship according to an embodiment of the present application. As shown in fig. 11, the method may include:
step 1101, acquiring first communication interaction data between individual users and user information of the individual users in a preset time period.
Step 1102, determining initial credibility information of the individual user according to the user information.
Step 1103, determining the interaction times with each called user when the personal user is used as the calling user according to the first communication interaction data.
Step 1104, performing iterative operation according to the interaction times and the initial credibility information of each called user when the personal user is used as the calling user, and obtaining the first credibility information of the personal user.
It should be noted that, the implementation of steps 1101-1104 may be referred to the implementation of fig. 1 and 2 in the above embodiment, and will not be described herein.
Step 1105, identifying whether the individual user is an offending user within a preset time period according to the first credibility information.
As an example, the first confidence information may be a confidence score for representing the confidence of the individual user, and the first confidence information may be compared with a confidence score threshold, and if the first confidence information of the individual user is smaller than the confidence score threshold, the individual user is identified as an offending user in the preset time period, otherwise, the individual user is identified as a non-offending user in the preset time period.
According to the user identification method based on the interaction relationship, initial credibility information of the personal user is firstly determined through the user information, iterative calculation is carried out according to the interaction times and the initial credibility information of each called user when the personal user is used as a calling user, so that first credibility information of the personal user is obtained, and whether the personal user is an illegal user in a preset time period is identified according to the first credibility information. The method and the device introduce the interaction times into iterative computation based on the interaction characteristics among users in the field of mobile communication, express the basis of the contact compactness among individual users through the interaction times, and enable the obtained first credibility information to be more accurate, so that the accuracy of user identification can be improved.
In order to achieve the above embodiments, the present application provides a user identification device based on an interaction relationship.
Fig. 12 is a block diagram of a user identification device based on an interaction relationship according to an embodiment of the present application. As shown in fig. 12, the apparatus includes:
an acquisition module 1210, configured to acquire communication interaction data, user information of an individual user, and user information of an enterprise user that performs communication interaction with the individual user in a preset period; the communication interaction data comprise first communication interaction data among the individual users, second communication interaction data among the individual users and the enterprise users and third communication interaction data among the individual users and the Internet of things equipment in a preset time period;
A first determining module 1220, configured to determine first credibility information of the individual user according to the user information of the individual user and the first communication interaction data;
a second determining module 1230, configured to determine second credibility information of the individual user according to user information of the enterprise user and second communication interaction data;
a third determining module 1240, configured to determine third credibility information of the individual user according to third communication interaction data based on a preset influence score of the internet of things device;
the identifying module 1250 is configured to identify whether the individual user is an offending user within a preset time period according to the first reliability information, the second reliability information, and the third reliability information.
In some embodiments of the present application, the first determining module 1220 is specifically configured to:
determining initial credibility information of the individual user according to user information of the individual user;
according to the first communication interaction data, determining the interaction times between the personal user and each called user when the personal user is used as a calling user;
and carrying out iterative operation according to the interaction times and the initial credibility information of each called user when the personal user is used as a calling user, and obtaining the first credibility information of the personal user.
As an example, the first determining module 1220 is specifically configured to:
determining user characteristic information of the individual user according to the user information of the individual user; the user characteristic information comprises user attribute characteristic information, user level characteristic information and user region characteristic information.
Inputting the user characteristic information into a preset initial scoring machine learning model to obtain initial credibility information; the initial scoring machine learning module learns to obtain the mapping relation between the user characteristic information of the individual user and the initial credibility information.
In some embodiments of the present application, the first determining module 1220 is further configured to:
according to the interaction times between the personal user and each called user when the personal user is used as a calling user, determining the interaction duty ratio between the personal user and each called user when the personal user is used as the calling user;
and carrying out iterative operation according to the interaction duty ratio and the initial credibility information between the personal user and each called user when the personal user is used as a calling user based on a webpage ranking Pagerank algorithm, and obtaining first credibility information.
In some embodiments of the application, the second determining module 1230 includes:
a first determining unit 1231 configured to determine a total score of the individual user affected by the enterprise user according to the user information of the enterprise user and the second communication interaction data;
And a second determining unit 1232 for ordering the total score of the individual user affected by the enterprise user, and determining the second credibility information of the individual user according to the ordering result.
As one possible implementation, the number of enterprise users is at least one; the first determining unit 1231 specifically is configured to:
determining an influence score of each enterprise user according to the user information of each enterprise user;
determining the score of the individual user influenced by each enterprise user according to the influence score of each enterprise user and the second communication interaction data;
and determining the total score of the individual user influenced by the enterprise user according to the score of the individual user influenced by each enterprise user.
As an example, the user information of each enterprise user includes a normal message amount sent by each enterprise user, a total message amount sent by each enterprise user, a personal user amount covered by each enterprise user, and an interaction amount of each enterprise user with users of respective territories; the influence score for each enterprise user includes a first influence score, a second influence score, and a third influence score; the first determining unit 1231 is further configured to:
determining a first influence score for each enterprise user based on the normal message quantity and the total message quantity;
Sequencing the individual user quantity covered by each enterprise user from large to small, and determining a second influence score of each enterprise user according to the sequencing result;
and determining a third influence score of each enterprise user according to the interaction quantity of each enterprise user and the users in the regions.
In some embodiments of the present application, the first determining unit 1231 is further configured to:
determining the interaction type between the individual user and each enterprise user according to the second communication interaction data; the interaction type comprises a call type and a message type;
dividing at least one enterprise user into i first-class enterprise users and j second-class enterprise users according to the interaction type; wherein i and j are integers greater than or equal to 0, the interaction type corresponding to the first type enterprise user comprises a call type, and the interaction type corresponding to the second type enterprise user only comprises a message type;
the first influence score of each first type of enterprise user is determined as the score of the individual user influenced by each first type of enterprise user.
Determining a comprehensive influence score of each second-class enterprise user according to the first influence score, the second influence score and the third influence score of each second-class enterprise user;
And determining the score of the personal user influenced by each second type enterprise user according to the second communication interaction data and the comprehensive influence score of each second type enterprise user.
As a possible implementation, the first determining unit 1231 is further configured to:
comparing the second influence scores of the second type enterprise users with a preset influence threshold value aiming at each second type enterprise user;
if the second influence score of the second type enterprise user is larger than the influence threshold, determining a comprehensive influence score of the second type enterprise user according to the first influence score, the second influence score and the third influence score of the second type enterprise user;
and if the second influence score of the second type enterprise user is smaller than or equal to the influence threshold, determining the comprehensive influence score of the second type enterprise user according to the first influence score and the second influence score of the second type enterprise user.
As a possible implementation, the first determining unit 1231 is further configured to:
according to the second communication interaction data, determining the interaction direction or the unidirectional interaction times of the individual user and each second type enterprise user;
determining the compactness of the individual user and each second-class enterprise user according to the interaction direction or the unidirectional interaction times of the individual user and each second-class enterprise user;
And determining the score of the personal user influenced by each second-type enterprise user according to the closeness of the personal user and each second-type enterprise user and the comprehensive influence score of each second-type enterprise user.
In some embodiments of the present application, the third determining module 1240 is specifically configured to:
based on the influence scores of the Internet of things equipment, determining total scores of the personal users influenced by the Internet of things equipment according to the third communication interaction data;
and sequencing the total score of the individual user influenced by the Internet of things equipment, and determining third credibility information of the individual user according to the sequencing result.
As a possible implementation manner, the third determining module 1240 is specifically configured to
According to the third communication interaction data, determining m first Internet of things devices which interact with the personal user in a one-way and n second Internet of things devices which interact with the personal user in a two-way; wherein m and n are integers greater than or equal to 0;
according to the influence score of each first Internet of things device, determining the score of the personal user influenced by the first Internet of things device;
determining the score of the personal user influenced by the second internet-of-things equipment according to the influence score of each second internet-of-things equipment;
And determining the total score of the individual user influenced by the Internet of things equipment according to the score of the individual user influenced by the first Internet of things equipment and the score of the individual user influenced by the second Internet of things equipment.
As an example, the third determination module 1240 is also to:
determining the total influence score of the first Internet of things equipment according to the influence score of each first Internet of things equipment;
and determining the score of the personal user influenced by the first Internet of things equipment according to the total influence score of the first Internet of things equipment based on a preset one-way interaction influence coefficient.
As an example, the third determination module 1240 is also to:
determining a total influence score of the second internet of things device according to the influence score of each second internet of things device;
and determining the score of the personal user influenced by the second internet-of-things device according to the total influence score of the second internet-of-things device based on the preset bidirectional interaction influence coefficient.
In some embodiments of the application, the identification module 1250 is specifically configured to:
determining the credibility information of the individual user according to the first credibility information, the second credibility information and the third credibility information;
and identifying whether the individual user is an illegal user in a preset time period according to the credibility information of the individual user.
As one example, the identification module 1250 also functions to:
and carrying out weighted summation according to the first credibility information, the second credibility information and the third credibility information, and determining the weighted summation result as credibility information of the individual user.
It should be noted that the explanation of the embodiment of the user identification method based on the interaction relationship described above is also applicable to the user identification device based on the interaction relationship in this embodiment, and will not be repeated here.
According to the user identification device based on the interaction relationship, the credibility information of the individual users is determined based on the communication interaction between the individual users, the communication interaction between the individual users and the enterprise users and the communication interaction between the individual users and the Internet of things equipment, the influence of all interaction objects having interaction relationship with the individual users on the credibility information of the individual users can be fully considered, the enterprise users and the Internet of things equipment are both applied to the identification process of the individual users, the accuracy of the credibility information of the individual users can be improved, the accuracy of user identification can be improved, and a reliable basis is provided for the treatment of illegal behaviors in the field of mobile communication.
Fig. 13 is a block diagram of another user identification device based on interaction relationship according to an embodiment of the present application. As shown in fig. 13, the apparatus includes:
an acquisition module 1310, configured to acquire communication interaction data, user information of an individual user, and user information of an enterprise user that performs communication interaction with the individual user in a preset period; the communication interaction data comprise first communication interaction data between individual users and second communication interaction data between the individual users and enterprise users in a preset time period;
a first determining module 1320, configured to determine first credibility information of the individual user according to user information of the individual user and the first communication interaction data;
a second determining module 1330, configured to determine second credibility information of the individual user according to user information of the enterprise user and second communication interaction data;
the identifying module 1340 is configured to identify whether the individual user is an offending user within a preset time period according to the first confidence information and the second confidence information.
It should be noted that the explanation of the embodiment of the user identification method based on the interaction relationship described above is also applicable to the user identification device based on the interaction relationship in this embodiment, and will not be repeated here.
According to the user identification device based on the interaction relationship, based on the communication interaction between the individual users and the enterprise user, the influence of all interaction objects having interaction relationship with the individual users on the credibility information of the individual users can be fully considered, the enterprise user can be applied to the identification process of the individual users, the accuracy of the credibility information of the individual users can be improved, the accuracy of user identification can be improved, and reliable basis is provided for the management of illegal behaviors in the field of mobile communication.
Fig. 14 is a block diagram of a user identification device based on an interactive relationship according to an embodiment of the present application. As shown in fig. 14, the apparatus includes:
an acquisition module 1410, configured to acquire communication interaction data and user information of an individual user in a preset period of time; the communication interaction data comprise first communication interaction data between the individual users and third communication interaction data between the individual users and the Internet of things equipment in a preset time period;
a first determining module 1420, configured to determine first credibility information of the individual user according to user information of the individual user and first communication interaction data;
A third determining module 1430, configured to determine third credibility information of the individual user according to third communication interaction data based on a preset influence score of the internet of things device;
the identifying module 1440 is configured to identify whether the individual user is an offending user within a preset time period according to the first reliability information and the third reliability information.
It should be noted that the explanation of the embodiment of the user identification method based on the interaction relationship described above is also applicable to the user identification device based on the interaction relationship in this embodiment, and will not be repeated here.
According to the user identification device based on the interaction relationship, based on the communication interaction between the personal users and the internet of things equipment, the influence of all interaction objects with the personal users on the credibility information of the personal users can be fully considered, and the internet of things equipment can be used for improving the accuracy of the credibility information of the personal users in the identification process of the personal users, and meanwhile, the accuracy of user identification can be improved, so that a reliable basis is provided for the management of illegal behaviors in the field of mobile communication.
Fig. 15 is a schematic diagram of another user identification device based on interaction relationship according to an embodiment of the present application. As shown in fig. 14, the apparatus includes:
A first obtaining module 1510, configured to obtain first communication interaction data between individual users and user information of the individual users in a preset period of time;
a first determining module 1520 for determining initial credibility information of the individual user according to the user information;
a second determining module 1530, configured to determine, according to the first communication interaction data, the number of interactions with each called user when the personal user is the calling user;
the second obtaining module 1540 is configured to perform iterative operation according to the number of interactions between the personal user and each called user when the personal user is the calling user and the initial reliability information, so as to obtain first reliability information of the personal user;
the identifying module 1550 is configured to identify whether the individual user is an offending user within a preset time period according to the first reliability information.
It should be noted that the explanation of the embodiment of the user identification method based on the interaction relationship described above is also applicable to the user identification device based on the interaction relationship in this embodiment, and will not be repeated here.
According to the user identification device based on the interaction relationship, initial credibility information of the personal user is firstly determined through the user information, iterative calculation is carried out according to the interaction times and the initial credibility information of each called user when the personal user is used as a calling user, so that first credibility information of the personal user is obtained, and whether the personal user is an illegal user in a preset time period is identified according to the first credibility information. The method and the device introduce the interaction times into iterative computation based on the interaction characteristics among users in the field of mobile communication, express the basis of the contact compactness among individual users through the interaction times, and enable the obtained first credibility information to be more accurate, so that the accuracy of user identification can be improved.
In order to achieve the above embodiments, the present application provides an electronic device.
Fig. 16 is a block diagram of an electronic device according to an embodiment of the present application. The electronic device may be a server, a computer, or the like. As shown in fig. 16, the electronic device includes:
memory 1610 and processor 1620, bus 1630 connecting the different components (including memory 1610 and processor 1620), memory 1610 storing processor 1620 executable instructions; wherein the processor 1620 is configured to execute the instructions to implement the interactive relationship-based user identification method according to the embodiments of the present disclosure.
Bus 1630 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 1600 typically includes a variety of electronic device readable media. Such media can be any available media that is accessible by electronic device 1600, including both volatile and nonvolatile media, removable and non-removable media. Memory 1610 may also include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 1640 and/or cache memory 1650. Electronic device 1600 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 1660 may be used to read and write non-removable, non-volatile magnetic media (not shown in FIG. 16, commonly referred to as a "hard disk drive"). Although not shown in fig. 16, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 1630 through one or more data media interfaces. Memory 1610 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the various embodiments of the disclosure.
Program/utility 1680 having a set (at least one) of program modules 1670 may be stored, for example, in memory 1610, such program modules 1670 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program module 1670 generally performs the functions and/or methods in the embodiments described in this disclosure.
The electronic device 1600 may also communicate with one or more external devices 1690 (e.g., keyboard, pointing device, display 1691, etc.), one or more devices that enable a user to interact with the electronic device 1600, and/or any device (e.g., network card, modem, etc.) that enables the electronic device 1600 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 1692. Also, electronic device 1500 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, e.g., the Internet, through network adapter 1693. As shown, network adapter 1693 communicates with other modules of electronic device 1600 over bus 1630. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 1600, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processor 1620 executes various functional applications and data processing by executing programs stored in the memory 1610.
It should be noted that, the implementation process and the technical principle of the electronic device in this embodiment refer to the foregoing explanation of the user identification method based on the interaction relationship in the embodiments of the present disclosure, and are not repeated herein.
In order to implement the above-described embodiments, the present disclosure also proposes a computer storage medium.
Wherein the instructions in the storage medium, when executed by the processor of the server, enable the server to perform the method of delivering multimedia resources based on internet applications as described above. Alternatively, the computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (23)
1. A user identification method based on interaction relationship, comprising:
acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; the communication interaction data comprise first communication interaction data among individual users, second communication interaction data among the individual users and the enterprise users and third communication interaction data among the individual users and the Internet of things equipment in the preset time period;
determining first credibility information of the individual user according to the user information of the individual user and the first communication interaction data;
determining second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data;
determining third credibility information of the personal user according to the third communication interaction data based on a preset influence score of the Internet of things equipment;
And identifying whether the individual user is an illegal user in the preset time period according to the first credibility information, the second credibility information and the third credibility information.
2. The method of claim 1, wherein said determining the first trustworthiness information of the individual user based on the user information of the individual user and the first communication interaction data comprises:
determining initial credibility information of the individual user according to the user information of the individual user;
according to the first communication interaction data, determining the interaction times between the personal user and each called user when the personal user is used as a calling user;
and carrying out iterative operation according to the interaction times of the personal user as the calling user and each called user and the initial credibility information to obtain the first credibility information of the personal user.
3. The method of claim 2, wherein determining the initial trustworthiness information of the individual user based on the user information of the individual user comprises:
determining user characteristic information of the individual user according to the user information of the individual user; the user characteristic information comprises user attribute characteristic information, user level characteristic information and user region characteristic information.
Inputting the user characteristic information into a preset initial scoring machine learning model to obtain the initial credibility information; the initial scoring machine learning module learns to obtain the mapping relation between the user characteristic information of the individual user and the initial credibility information.
4. The method according to claim 2, wherein the performing an iterative operation according to the initial reliability information and the number of interactions with each called user when the individual user is a calling user to obtain the first reliability information of the individual user includes:
according to the interaction times between the personal user and each called user when the personal user is used as a calling user, determining the interaction ratio between the personal user and each called user when the personal user is used as the calling user;
and carrying out iterative operation on the basis of a webpage ranking Pagerank algorithm according to the interaction duty ratio between the personal user and each called user when the personal user is used as a calling user and the initial credibility information, and obtaining the first credibility information.
5. The method of claim 1, wherein said determining second credibility information of said individual user based on user information of said enterprise user and said second communication interaction data comprises:
Determining the total score of the individual user influenced by the enterprise user according to the user information of the enterprise user and the second communication interaction data;
and sorting the total score of the individual user influenced by the enterprise user, and determining second credibility information of the individual user according to the sorting result.
6. The method of claim 5, wherein the number of enterprise users is at least one; the determining, according to the user information of the enterprise user and the second communication interaction data, a total score of the personal user affected by the enterprise user includes:
determining an influence score of each enterprise user according to the user information of each enterprise user;
determining the score of the individual user influenced by each enterprise user according to the influence score of each enterprise user and the second communication interaction data;
and determining the total score of the individual user influenced by the enterprise user according to the score of the individual user influenced by each enterprise user.
7. The method of claim 6, wherein the user information for each of the enterprise users comprises a normal message volume sent by each of the enterprise users, a total message volume sent by each of the enterprise users, a personal user volume covered by each of the enterprise users, and a user interaction volume of each of the enterprise users with respective territories; the influence score of each enterprise user comprises a first influence score, a second influence score and a third influence score; the determining the influence score of each enterprise user according to the user information of each enterprise user comprises the following steps:
Determining a first impact score for each of the enterprise users based on the normal message volume and the total message volume;
sequencing the individual user quantity covered by each enterprise user from large to small, and determining a second influence score of each enterprise user according to a sequencing result;
and determining a third influence score of each enterprise user according to the interaction quantity of each enterprise user and the users in the regions.
8. The method of claim 7, wherein said determining the score of the individual user affected by each of the enterprise users based on the influence score of each of the enterprise users and the second communication interaction data comprises:
determining the interaction type between the individual user and each enterprise user according to the second communication interaction data; wherein, the interaction type comprises a call type and a message type;
dividing the at least one enterprise user into i first-class enterprise users and j second-class enterprise users according to the interaction type; wherein i and j are integers greater than or equal to 0, the interaction type corresponding to the first type enterprise user comprises a call type, and the interaction type corresponding to the second type enterprise user only comprises a message type;
Determining a first influence score of each first type enterprise user as a score of the individual user influenced by each first type enterprise user;
determining the comprehensive influence score of each second-class enterprise user according to the first influence score, the second influence score and the third influence score of each second-class enterprise user;
and determining the score of the personal user influenced by each second type enterprise user according to the second communication interaction data and the comprehensive influence score of each second type enterprise user.
9. The method of claim 8, wherein the determining the aggregate influence score for each of the second type of enterprise users based on the first influence score, the second influence score, and the third influence score for each of the second type of enterprise users comprises:
comparing the second influence scores of the second type enterprise users with a preset influence threshold for each second type enterprise user;
if the second influence score of the second type enterprise user is greater than the influence threshold, determining a comprehensive influence score of the second type enterprise user according to the first influence score, the second influence score and the third influence score of the second type enterprise user;
If the second influence score of the second type enterprise user is smaller than or equal to the influence threshold, determining the comprehensive influence score of the second type enterprise user according to the first influence score and the second influence score of the second type enterprise user;
wherein the determining the score of the individual user affected by each of the second type enterprise users according to the second communication interaction data and the comprehensive influence score of each of the second type enterprise users comprises:
according to the second communication interaction data, determining the interaction direction or the unidirectional interaction times of the individual user and each second type enterprise user;
determining the compactness of the individual user and each second-type enterprise user according to the interaction direction or the unidirectional interaction times of the individual user and each second-type enterprise user;
and determining the score of the personal user influenced by each second type enterprise user according to the closeness of the personal user and each second type enterprise user and the comprehensive influence score of each second type enterprise user.
10. The method of claim 1, wherein the determining third credibility information of the individual user based on the third communication interaction data based on the influence score of the preset internet of things device comprises:
Based on the influence score of the Internet of things equipment, determining the total score of the personal user influenced by the Internet of things equipment according to the third communication interaction data;
and sorting the total score of the personal user influenced by the Internet of things equipment, and determining third credibility information of the personal user according to a sorting result.
11. The method of claim 10, wherein the determining the total score of the personal user affected by the internet of things device based on the impact score of the internet of things device according to the third communication interaction data comprises:
according to the third communication interaction data, determining m first internet of things devices which interact unidirectionally with the personal user and n second internet of things devices which interact bidirectionally with the personal user; wherein m and n are integers greater than or equal to 0;
determining the score of the personal user influenced by the first Internet of things equipment according to the influence score of each first Internet of things equipment;
determining the score of the personal user influenced by the second internet-of-things equipment according to the influence score of each second internet-of-things equipment;
and determining the total score of the individual user influenced by the Internet of things equipment according to the score of the individual user influenced by the first Internet of things equipment and the score of the individual user influenced by the second Internet of things equipment.
12. The method of claim 11, wherein determining the score of the individual user affected by the first internet of things device based on the impact score of each of the first internet of things devices comprises:
determining the total influence score of the first Internet of things equipment according to the influence score of each first Internet of things equipment;
based on a preset unidirectional interaction influence coefficient, determining the score of the personal user influenced by the first Internet of things equipment according to the total influence score of the first Internet of things equipment;
wherein the determining the score of the individual user affected by the second internet of things device according to the influence score of each second internet of things device comprises:
determining a total influence score of each second networking device according to the influence score of each second networking device;
and determining the score of the personal user influenced by the second internet-of-things device according to the total influence score of the second internet-of-things device based on a preset bidirectional interaction influence coefficient.
13. The method of any of claims 1-12, wherein the identifying whether the individual user is an offending user within the preset time period based on the first, second, and third confidence information comprises:
Determining the credibility information of the individual user according to the first credibility information, the second credibility information and the third credibility information;
and identifying whether the personal user is an illegal user in the preset time period according to the credibility information of the personal user.
14. The method of claim 13, wherein said determining the trustworthiness information of the individual user based on the first trustworthiness information, the second trustworthiness information, and the third trustworthiness information comprises:
and carrying out weighted summation according to the first credibility information, the second credibility information and the third credibility information, and determining a weighted summation result as credibility information of the individual user.
15. A user identification method based on interaction relationship, comprising:
acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; the communication interaction data comprise first communication interaction data between individual users and second communication interaction data between the individual users and the enterprise users in the preset time period;
Determining first credibility information of the individual user according to the user information of the individual user and the first communication interaction data;
determining second credibility information of the individual user according to the user information of the enterprise user and the second communication interaction data;
and identifying whether the individual user is an illegal user in the preset time period according to the first credibility information and the second credibility information.
16. A user identification method based on interaction relationship, comprising:
acquiring communication interaction data and user information of an individual user in a preset time period; the communication interaction data comprise first communication interaction data between the individual users and third communication interaction data between the individual users and the Internet of things equipment in the preset time period;
determining first credibility information of the individual user according to the user information of the individual user and the first communication interaction data;
determining third credibility information of the personal user according to the third communication interaction data based on a preset influence score of the Internet of things equipment;
and identifying whether the individual user is an illegal user in the preset time period according to the first credibility information and the third credibility information.
17. A user identification method based on interaction relationship, comprising:
acquiring first communication interaction data between individual users and user information of the individual users within a preset time period;
determining initial credibility information of the individual user according to the user information;
according to the first communication interaction data, determining the interaction times between the personal user and each called user when the personal user is used as a calling user;
performing iterative operation according to the interaction times with each called user and the initial credibility information when the personal user is used as a calling user, and obtaining first credibility information of the personal user;
and identifying whether the individual user is an illegal user in the preset time period according to the first credibility information.
18. A user identification device based on interaction relationship, comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; the communication interaction data comprise first communication interaction data among individual users, second communication interaction data among the individual users and the enterprise users and third communication interaction data among the individual users and the Internet of things equipment in the preset time period;
The first determining module is used for determining first credibility information of the personal user according to the user information of the personal user and the first communication interaction data;
the second determining module is used for determining second credibility information of the personal user according to the user information of the enterprise user and the second communication interaction data;
the third determining module is used for determining third credibility information of the personal user according to the third communication interaction data based on the influence score of the preset internet of things equipment;
the identification module is used for identifying whether the individual user is an illegal user in the preset time period according to the first credibility information, the second credibility information and the third credibility information.
19. A user identification device based on interaction relationship, comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring communication interaction data, user information of an individual user and user information of an enterprise user in communication interaction with the individual user in a preset time period; the communication interaction data comprise first communication interaction data between individual users and second communication interaction data between the individual users and the enterprise users in the preset time period;
The first determining module is used for determining first credibility information of the personal user according to the user information of the personal user and the first communication interaction data;
the second determining module is used for determining second credibility information of the personal user according to the user information of the enterprise user and the second communication interaction data;
the identification module is used for identifying whether the individual user is an illegal user in the preset time period according to the first credibility information and the second credibility information.
20. A user identification device based on interaction relationship, comprising:
the acquisition module is used for acquiring communication interaction data and user information of the individual user in a preset time period; the communication interaction data comprise first communication interaction data between the individual users and third communication interaction data between the individual users and the Internet of things equipment in the preset time period;
the first determining module is used for determining first credibility information of the personal user according to the user information of the personal user and the first communication interaction data;
the third determining module is used for determining third credibility information of the personal user according to the third communication interaction data based on the influence score of the preset internet of things equipment;
The identification module is used for identifying whether the individual user is an illegal user in the preset time period according to the first credibility information and the third credibility information.
21. A user identification device based on interaction relationship, comprising:
the first acquisition module is used for acquiring first communication interaction data between individual users and user information of the individual users in a preset time period;
the first determining module is used for determining initial credibility information of the individual user according to the user information;
the second determining module is used for determining the interaction times with each called user when the personal user is used as a calling user according to the first communication interaction data;
the second acquisition module is used for carrying out iterative operation according to the interaction times of the personal user with each called user and the initial credibility information when the personal user is used as a calling user, so as to acquire first credibility information of the personal user;
and the identification module is used for identifying whether the individual user is an illegal user in the preset time period according to the first credibility information.
22. An electronic device, comprising:
A processor;
a memory for storing executable instructions of the processor;
wherein the processor is configured to execute the instructions to implement the interaction relationship based user identification method of any of claims 1-14, or to implement the interaction relationship based user identification method of claim 15, or to implement the interaction relationship based user identification method of claim 16, or to implement the interaction relationship based user identification method of claim 17.
23. A computer readable storage medium, characterized in that instructions in the computer readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the interactive relation based user identification method of any one of claims 1-14, or to perform the interactive relation based user identification method of claim 15, or to perform the interactive relation based user identification method of claim 16, or to perform the interactive relation based user identification method of claim 17.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310953917.2A CN117056594A (en) | 2023-07-31 | 2023-07-31 | User identification method and device based on interaction relationship and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310953917.2A CN117056594A (en) | 2023-07-31 | 2023-07-31 | User identification method and device based on interaction relationship and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117056594A true CN117056594A (en) | 2023-11-14 |
Family
ID=88659970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310953917.2A Pending CN117056594A (en) | 2023-07-31 | 2023-07-31 | User identification method and device based on interaction relationship and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117056594A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130301823A1 (en) * | 2012-05-10 | 2013-11-14 | International Business Machines Corporation | Extracting social relations from calling time data |
| CN110505196A (en) * | 2019-07-02 | 2019-11-26 | 中国联合网络通信集团有限公司 | Internet of Things network interface card method for detecting abnormality and device |
| CN112153221A (en) * | 2020-09-16 | 2020-12-29 | 北京邮电大学 | Communication behavior identification method based on social network diagram calculation |
| CN115511606A (en) * | 2022-10-14 | 2022-12-23 | 深圳前海微众银行股份有限公司 | Object identification method, device, equipment and storage medium |
-
2023
- 2023-07-31 CN CN202310953917.2A patent/CN117056594A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130301823A1 (en) * | 2012-05-10 | 2013-11-14 | International Business Machines Corporation | Extracting social relations from calling time data |
| CN110505196A (en) * | 2019-07-02 | 2019-11-26 | 中国联合网络通信集团有限公司 | Internet of Things network interface card method for detecting abnormality and device |
| CN112153221A (en) * | 2020-09-16 | 2020-12-29 | 北京邮电大学 | Communication behavior identification method based on social network diagram calculation |
| CN115511606A (en) * | 2022-10-14 | 2022-12-23 | 深圳前海微众银行股份有限公司 | Object identification method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 全俊斌 等: "一种基于信令数据的业务推销类骚扰电话识别方法", 移动通信, no. 07, 15 July 2020 (2020-07-15), pages 97 - 100 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110992169A (en) | Risk assessment method, device, server and storage medium | |
| CN110070391B (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN106709318B (en) | A kind of recognition methods of user equipment uniqueness, device and calculate equipment | |
| CN107391692A (en) | The appraisal procedure and device of a kind of recommendation effect | |
| CN104836781A (en) | Method distinguishing identities of access users, and device | |
| CN108304935A (en) | Machine learning model training method, device and computer equipment | |
| CN112348659B (en) | User identification policy distribution method and device and electronic equipment | |
| CN108777701A (en) | A kind of method and device of determining receiver | |
| CN109146661A (en) | User type prediction technique, device, electronic equipment and storage medium | |
| KR20100002915A (en) | Behavior based method for filtering out unfair rating in trust model | |
| CN107038165B (en) | Service parameter acquisition method and device | |
| CN111639299A (en) | Method, system and storage medium for evaluating follow-up performance of client of business consultant | |
| CN111090729A (en) | Method, device, server and storage medium for identifying fraudulent group | |
| CN117056594A (en) | User identification method and device based on interaction relationship and electronic equipment | |
| CN110796379B (en) | Risk assessment method, device and equipment of business channel and storage medium | |
| CN113568739B (en) | User resource quota allocation method and device and electronic equipment | |
| CN111476511B (en) | Data display method and device for specific risks faced by server | |
| CN114399319A (en) | False enterprise identification method, device, equipment and medium based on prediction model | |
| CN113240323A (en) | Level evaluation method and device based on machine learning and related equipment | |
| CN110458707B (en) | Behavior evaluation method and device based on classification model and terminal equipment | |
| CN109635226A (en) | Early warning method for pushing, server and the storage medium of real estate data | |
| CN112015978A (en) | Customized information sending method and device and electronic equipment | |
| Kurosawa et al. | Service-choice behaviour modelling with latent perceptual variables | |
| CN115242482B (en) | Unauthorized access risk detection method and device, electronic equipment and readable storage medium | |
| CN116055335B (en) | Internet of vehicles intrusion detection model training method based on federal learning, intrusion detection method and equipment |
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 |