WO2022142903A1

WO2022142903A1 - Identity recognition method and apparatus, electronic device, and related product

Info

Publication number: WO2022142903A1
Application number: PCT/CN2021/133117
Authority: WO
Inventors: 尹义
Original assignee: 深圳云天励飞技术股份有限公司
Priority date: 2020-12-31
Filing date: 2021-11-25
Publication date: 2022-07-07
Also published as: CN112669187B; CN112669187A

Abstract

An identity recognition method and apparatus, an electronic device, and a related product. The method comprises: acquiring identity information, family member information, and the movement trajectory in a preset time period of each community member in a community (301); inputting the identity information and the movement trajectory in a preset time period of each community member into a trained defrauded person recognition model to predict a first identity identifier of each community member (302); on the basis of the identity information, family member information, and the movement trajectory in a preset time period of each community member, performing identity type recognition to determine a second identity identifier of each community member (303); and, on the basis of the first identity identifier and the second identity identifier of each community member, implementing collision to determine a target community member in the community (304). The embodiments of the present application are conducive to improving the effect of anti-fraud publicity.

Description

Identification methods, devices, electronic equipment and related products

This application claims the priority of the Chinese patent application filed on December 31, 2020 with the application number 202011645088.4 and the invention name is "identification method, device, electronic equipment and related products", the entire contents of which are incorporated by reference in this application.

technical field

The present application relates to the technical field of information identification, and in particular to an identification method, device, electronic device and related products.

Background technique

As the government departments continue to crack down on social security cases, social security contact cases are quickly detected and the incidence rate continues to decrease; however, the incidence rate of non-contact social security cases (for example, telecommunication fraud) has bucked the trend. Upward trend. The crackdown and detection of non-contact cases has also become a very difficult task for government departments. At present, there are two main ways for government departments to crack down on non-contact cases: to detect non-contact cases that have already occurred through various clues and means;

However, the current anti-fraud propaganda aimed at vulnerable people in the community is mostly cast-net propaganda, which is not targeted, resulting in high propaganda costs and low effectiveness.

SUMMARY OF THE INVENTION

The embodiments of the present application provide an identity recognition method, device, electronic device and related products, which can screen out target community members from the community, and improve the anti-fraud pertinence and publicity effect.

In a first aspect, the embodiments of the present application provide an identity recognition method, including:

Obtain the identity information, family member information and activity trajectories of each community member in the community within a preset time period;

The identity information of each community member and the activity track within the preset time period are input into the deceived person identification model that has completed the training, and the first identity of each community member is predicted. The first identity identifier includes whether each of the community members is a deceived person;

Identify the identity type according to the identity information of each community member, family member information and the activity track within a preset time period, determine the second identity of each community member, and determine the second identity of each community member. The second identification includes whether each of the community members is a potentially vulnerable person;

According to the collision between the first identification and the second identification of each community member, the target community member in the community is determined.

In a second aspect, an embodiment of the present application provides an identification device, including:

The transceiver unit is used to obtain the identity information of each community member in the community, family member information and activity track within a preset time period;

The processing unit is used to input the identity information of each community member and the activity track within a preset time period into the deceived person identification model that has completed the training, and predict the first identity of each community member, the The first identification of each community member includes whether the community member is a deceived person; the identity type is identified according to the identity information of each community member, family member information and activity track within a preset time period , determine the second identity of each community member, and the second identity of each community member includes whether each community member is a potentially vulnerable person; according to the first identity of each community member The identifier and the second identity identifier are used to determine the target community members in the community.

In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, the processor is connected to a memory, the memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory , so that the electronic device performs the method according to the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program causes a computer to execute the method according to the first aspect.

In a fifth aspect, an embodiment of the present application provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer is operable to cause the computer to execute as described in the first aspect Methods.

Implementing the embodiments of the present application has the following beneficial effects:

It can be seen that, in the embodiment of the present application, the identity recognition device predicts the first identity of each community member through the deceived person identification model that has completed the training; and obtains the second identity of each community member through feature analysis; and According to the first identification and the second identification of each community member, the target community member in the community is determined. Since the user's identity is analyzed from multiple dimensions, the determined target community members are comprehensive and accurate. In addition, the target community members are used as the target of anti-fraud publicity, so that targeted anti-fraud publicity can be carried out for these target community members, without the need for casting net publicity, which reduces the cost of publicity and improves the effect of publicity.

Description of drawings

1 is a schematic structural diagram of an identity recognition system provided by an embodiment of the present application;

2 is a schematic diagram of an identity identification method provided by an embodiment of the present application;

3 is a schematic flowchart of an identity identification method provided by an embodiment of the present application;

4 is a schematic flowchart of another identity identification method provided by an embodiment of the present application;

FIG. 5 is a block diagram of functional units of an identification device provided by an embodiment of the present application;

FIG. 6 is a schematic structural diagram of an identification device provided by an embodiment of the present application.

Detailed ways

In order to understand the present application, the technical terms involved in the present application are explained and explained first.

Class deceived person: Identify each community person through the trained deceived person identification model, get the probability that each community person belongs to the deceived person, and regard the community person whose probability is greater than the threshold as the class deceived person. Since the deceived person identification model is obtained by training the information of historically deceived persons, the class of deceived persons is to screen out the community personnel whose classification probability is greater than the threshold from the dimension of comparing the information of community personnel with the information of historically deceived persons.

Potentially gullible persons: based on identity information, family member information, and activity trajectories within a preset period of time to identify qualified community members, that is, from the dimension of each community member's own identity information, screen out of eligible community members.

Referring to FIG. 1 , FIG. 1 is a schematic structural diagram of an identity recognition system provided by an embodiment of the present application. The identity recognition system includes an identity recognition device 10 and an image acquisition device 20. The identity recognition device 10 and the image acquisition device maintain a communication connection. The image acquisition device 20 is installed in the community and is used to obtain the itinerary of community members in the community.

Based on the identity recognition system shown in FIG. 1 , the image acquisition device 20 collects the facial image of each community member in the community, and uploads the facial image of each community member to the identity recognition device 10, wherein the facial image carries the geographic location information; the identity recognition device 10 determines the daily travel trajectory of each community member according to the facial image of each person, and creates a file database for each community member according to the daily travel trajectory of each community member (that is, realizes one file per person), wherein , the archives of each community member includes the identity information of each community member, family member information and the daily activity track of each community member. In this way, the identity recognition device 10 can obtain the identity information of each community member, family member information and the activity track within a preset time period from the archives of each community member in the process of identity recognition, The identity information of each community member and the activity trajectory within the preset time period are input into the deceived person identification model that has completed the training, and the first identity identification of each community member is predicted, that is, whether each community member is a deceived person or not; then , according to the identity information of each community member, family member information and the activity track within a preset time period, determine the second identity of each community member, that is, determine whether each community member is a potentially vulnerable person; finally, The target community members in the community are determined by colliding with the first identification and the second identification of each community member. Among them, the target community members are the target of anti-fraud propaganda.

It can be seen that, in the embodiment of the present application, the identification device 10 and the image acquisition device 20 cooperate with each other to screen out target community members (targets of anti-fraud propaganda) from the community; Targeted anti-fraud publicity is carried out without the need to cast a net, which reduces the cost of publicity and improves the effect of publicity.

Referring to FIG. 2, FIG. 2 is a schematic diagram of an identity identification method provided by an embodiment of the present application. The method is applied to an identity recognition device.

As shown in Figure 2, the identification device first trains a deceived person identification model through historical deceived people in the community and semi-supervised learning, and then uses the trained deceived person identification model to identify all community personnel in the community, and obtains each The first identification of the community members is to determine whether each community member is a deceived person; in addition, the identification device obtains the identity characteristics of each potential deceived group by summarizing and analyzing the potential deceived groups in the community; The characteristics of each potential deceived group are used to establish the identification model corresponding to each kind of potential deceived group. This application takes the establishment of four identification models: housewife identification model, unemployed person identification model, retired old person identification model and school-age single youth identification model as examples to illustrate. ; Then, through these four identification models, identify the identity types of all community members in the community, and obtain the second identity of each community member, that is, determine whether each community member is a potential vulnerable person, and determine which types of potentially gullible persons. Finally, the identity recognition device collides with the identified quasi-deceived persons and potential deceived persons, determines the target community members in the community, and uses the target community members as anti-fraud propaganda objects.

It can be seen that, in the embodiment of the present application, through the establishment of the model, the identity recognition device can screen out the target community members from the community, and use the target community members as anti-fraud propaganda objects; in this way, these target community members can be targeted. Targeted anti-fraud publicity eliminates the need for net-casting publicity, which reduces publicity costs and improves publicity effects.

Referring to FIG. 3, FIG. 3 is a schematic flowchart of an identity recognition method provided by an embodiment of the present application. The method is applied to an identity recognition device. The method includes the following steps:

301: The identity recognition device acquires identity information, family member information, and activity tracks within a preset time period of each community member in the community.

It should be understood that this application takes the identification of community members in one community as an example, and the identification process of community members in other communities is similar to the identification method of the community, and will not be described again.

Exemplarily, the identity recognition device can create a file for each community member in the community, obtain the archive of each community member, and realize one file per person, wherein the archive of each community member in the community includes each community member. identity information, family member information, and daily activity information. Specifically, the identity recognition device can obtain the identity information and family member information of each community member, wherein the identity information and family member information can be read by the identity recognition device from other devices, and each can be read from the community management system. The identity information of each community member, wherein the identity information of each community member includes the name, gender, age and ID number of each community member, etc., and the family member information includes the marriage information and child information of each community member; In addition, the identification device can obtain the facial images of the community members at each activity location from the image acquisition equipment at the front end of the community, and determine the daily activity track of each community member according to the facial images of the community members at each activity location; , store the identity information of each community member, family member information, and each community member's daily activity track in association, and realize the establishment of a file library for each community member in the community.

Therefore, the identity recognition device can read the identity information, family member information and activities within a preset time period of each community member from the archives of each community member according to one or more identification information of each community member trajectory. For example, according to the ID number of each community member, the archive database corresponding to each community member can be determined, and the identity information, family member information and information of each community member in the preset time period can be read from the archive database. Movement tracking.

302: The identity recognition device inputs the identity information of each community member and the activity track within the preset time period into the trained deceived person recognition model, and predicts the first identity identifier of each community member, and the The first identification of each community member includes whether each community member is a deceived person.

Wherein, the preset time period may be one day, two days, one week, one month or other values.

The deceived person identification model is a deceived person identification model that has been trained in advance.

Exemplarily, the identification information of the historically defrauded person may be obtained, wherein the identification information is used to identify the identity of the historically defrauded person, for example, the identification information may be the name, ID number, mobile phone number, etc. of the historically defrauded person; Determine the archive established for the historically deceived person according to the identification information of the historically deceived person, and obtain the historically deceived person's identity information (for example, age and gender) and historical activity track from the archives of the historically deceived person, and The identity information and historical activity trajectories of the historically deceived persons are taken as negative samples; then, the identification information of the historically defrauded persons is obtained, and the archives established by the historically defrauded persons are determined according to the identification information of the historically defrauded persons. Read the identity information, case information and historical activity track of the historically not deceived person from the archive database of the undeceived person, and use the identity information, case information and historical activity track of the historically not defrauded person as a positive sample. Finally, the deceived person identification model is trained by using the negative samples and positive samples, that is, the model parameters of the deceived person identification model are adjusted to obtain the deceived person identification model that has completed the training.

Among them, the identity information of the above-mentioned historically deceived persons and those who have not been deceived in history include but are not limited to gender, age, education, and work; among which, the case information of historically defrauded persons includes but is not limited to: history of deceived persons time and location).

It should be understood that the above-mentioned historically deceived persons and historically not deceived persons may be community members in the community, or may not be community members of this community. This is not limited.

Exemplarily, the daily activity trajectory of each community member in a preset time period can be digitized, and a feature vector corresponding to the daily activity trajectory can be obtained. For example, multiple activity locations can be preset. location, the dimension corresponding to the activity location is set to 1, and if the activity location is not reached on the day, the dimension corresponding to the activity location is set to 0, and the feature vector corresponding to the daily activity track is obtained; then, the preset The eigenvectors corresponding to the daily activity trajectories in the time period are spliced (vertically spliced) to obtain a first matrix. For example, if the first eigenvector is [0,01,0] and the second eigenvector is [0,1,0,0], after vertical splicing, the first matrix obtained is

Similarly, the identity information (ie, gender and age) of each community member is vectorized (ie, mapped), and the feature vector corresponding to the identity information is obtained. For example, gender female can be represented by a feature vector whose value is all 1, Male gender can be represented by an eigenvector whose value is all 0, and age can be represented by a corresponding binary number; finally, the eigenvector corresponding to the identity information is spliced (vertically spliced) with the above-mentioned first matrix to obtain the input data; finally , input the input data of each community member into the trained deceived person identification model, and get the probability that each community member belongs to the deceived person. When the probability is greater than or equal to the threshold, determine the community member as a class of deceived people , in the case that the probability is less than the threshold, it is determined that the community member is not a deceived person.

303: The identity recognition device performs identity type recognition according to the identity information of each community member, family member information and the activity track within a preset time period, and determines the second identity of each community member, and each The second identification of each community member includes whether each of the community members is a potentially gullible person.

Exemplarily, according to the travel trajectory of each community member in the preset time period, determine the travel status of each community member in the preset time period; The travel status in the time period is input into the identity recognition model (that is, input into the housewife recognition model, the unemployed person recognition model, the retired old person recognition model and the marriageable single youth recognition model shown in Figure 2 respectively), and each community member is determined. The second identification of each community member is to determine whether each community member is a potential gullible person. Among them, the types of potential gullible persons include but are not limited to the following: housewives, unemployed persons, retirees, and young single marriageable persons.

Specifically, the identity information of each community member, family member information, and travel status within a preset time period are input into the housewife identification model. If it is recognized that the travel of community member A within the preset time period is irregular, and carry children, and the gender of the community member A is female, then determine the second identity of the community member A as a housewife, wherein the community member A is any community member in the community;

Input the identity information, family member information and travel status of each community member into the unemployed person identification model. If it is recognized that the travel of community member A in the first sub-preset time period is regular , and the travel in the second sub-preset time period is irregular, and the age of community member A belongs to the first age group, it is determined that the second identity of community member A is an unemployed person, wherein the first sub-preset The time period and the second sub-preset time period are two sub-time periods in the preset time period, and the first sub-preset time period is located before the second preset time period. For example, if the preset time period is one month, the first sub-preset time period may be the first half of the month, and the second sub-preset time period may be the second half of the month. Among them, the first age group is the working age group, for example, 18-60 years old;

Input the identity information, family member information and travel status of each community member into the retirement identification model within the preset time period. Accompany, and the age of community member A belongs to the second preset age group, determine that the second identity of community member A is a retired old man, wherein the second age group can be 60-80 years old;

Input the identity information, family member information, and travel status of each community member into the marriageable single youth identification model within the preset time period. And the marital status of community member A is unmarried, and the age group of community member A belongs to the third age group, and the second identity of community member A is determined to be a marriageable single youth, of which the third age group can be 23-35.

304: The identification device collides according to the first identification and the second identification of each community member, and determines a target community member in the community.

Exemplarily, in the case that the first identity of the community member A is a deceived person, and the second identity is a potential fraudulent person, determine that the community member A is a first-level target community member in the community; In the case that the first identity of the community member A is a quasi-deceived person, and the second identity is not a person who is easily deceived, determine that the community member A is a secondary target community member in the community; in the community member A In the case that the second identity of the person is not a deceived person, and the second identity is a potentially deceptive person, determine that the community member A is a secondary target community member in the community.

Among them, the anti-fraud publicity for the first-level target community members is stronger than the second-level target personnel. For example, offline publicity and one-to-one publicity for the anti-fraud of the first-level target personnel can be carried out, and only online publicity for the second-level target personnel. , and encourage secondary target personnel to learn anti-fraud knowledge online.

It can be seen that, in the embodiment of the present application, the identity recognition device predicts the first identity of each community member through the deceived person identification model that has completed the training; and obtains the second identity of each community member through feature analysis; and The target community members in the community are determined according to the collision between the first identification and the second identification of each community member. Since the user's identity is analyzed from multiple dimensions, the determined target community members are comprehensive and accurate. In addition, the target community members are used as the target of anti-fraud publicity, so that targeted anti-fraud publicity can be carried out for these target community members, without the need for net-casting publicity, which reduces the cost of publicity and improves the effect of publicity.

Referring to FIG. 4 , FIG. 4 is a schematic flowchart of another identity identification method provided by an embodiment of the present application. The method is applied to an identity recognition device. The content of this embodiment is the same as that of the embodiment shown in FIG. 3 , and the description is not repeated here. The method of this embodiment includes the following steps:

401: The identity recognition device acquires identity information, family member information, and activity tracks within a preset time period of each community member in the community.

402: The identity recognition device inputs the identity information of each community member and the activity track within a preset time period into the trained deceived person recognition model, and predicts the first identity of each community member, and the The first identification of each community member includes whether each community member is a deceived person.

403: The identity recognition device identifies the identity type according to the identity information of each community member, family member information, and the activity track within a preset time period, and determines the second identity of each community member, and each The second identification of each community member includes whether each of the community members is a potentially gullible person.

404: The identification device collides according to the first identification and the second identification of each community member, and determines a target community member in the community.

405: The identification device acquires the number of historically deceived persons in the community.

406: The identification device determines the vulnerability index of the community according to the number of historical deceived persons in the community and the number of community members whose second identity is identified as a potential vulnerable person in the community, wherein the community The Fraud Index of is used to indicate that the community members within said community are at risk of being gullible.

Exemplarily, the deceived index of the community may be obtained according to the number of historically deceived persons in the community, the number of potential deceptive persons and a preset weight coefficient. Exemplarily, the deceived index of the community can be expressed by formula (1):

Index=L ₁ *A+L ₂ formula (1);

Among them, Index is the vulnerability index of the community, L ₁ is the number of historically deceived people in the community, L ₂ is the number of potential deceived people in the community, A is the preset weight coefficient, and the value is greater than 1.

It can be seen that, in the embodiment of the present application, the identity recognition device predicts the first identity of each community member through the deceived person identification model that has completed the training; and obtains the second identity of each community member through feature analysis; and According to the first identification and the second identification of each community member, the target community member in the community is determined. Since the user's identity is analyzed from multiple dimensions, the determined target community members are comprehensive and accurate. In addition, target community members are used as anti-fraud propaganda objects, so that targeted anti-fraud propaganda can be carried out for these target community members, without the need for casting net propaganda, which reduces propaganda costs and improves propaganda effects. And calculate the gullibility index of the community, so that each community can be targeted for publicity, focusing on the community with a higher gullibility index.

In some possible implementations, after the second identification of each community member is determined, the number of each type of potentially vulnerable persons may be counted, that is, the number of housewives, the number of unemployed persons, the number of retirees The number and the number of single young marriageable people, then, according to the number of potential gullible people of each type, the four types of potential gullible people are ranked, and the ranking results Potentially vulnerable persons shall formulate targeted publicity plans to further improve the pertinence of anti-fraud publicity. In addition, the total number of potentially gullible people in the community can be counted.

Referring to FIG. 5, FIG. 5 is a block diagram of functional units of an identification device provided by an embodiment of the present application. The identification device 500 includes: a transceiver unit 501 and a processing unit 502, wherein:

The transceiver unit 501 is used to obtain the identity information, family member information and activity track within a preset time period of each community member in the community;

The processing unit 502 is configured to input the identity information of each community member and the activity track within a preset time period into the deceived person identification model that has completed the training, and predict the first identity of each community member, so The first identity identifier of each community member includes whether each community member is a deceived person; the identity type is carried out according to the identity information of each community member, family member information and the activity track within a preset time period. Identify, determine the second identity of each community member, and the second identity of each community member includes whether each community member is a potential gullible person; according to the first identification of each community member The identity identifier and the second identity identifier determine the target community members in the community.

In some possible implementations, before acquiring the identity information of each community member in the community, the family member information and the activity track within a preset time period, the processing unit 502 is further configured to provide each community member in the community Personnel establishes an archive, wherein the archive of each community member includes the identity information of each community member, family member information, and the daily activity track of each community member;

In terms of acquiring the identity information, family member information and activity track within a preset time period of each community member in the community, the processing unit 502 is specifically used for:

The identity information, family member information and activity track within a preset time period of each community member are acquired from the archives of each community member.

In some possible implementations, before acquiring the identity information of each community member in the community, the family member information and the activity track within a preset time period, the transceiver unit 501 is further configured to acquire the identification information of the historically deceived person, Determine the archive of the historically cheated person according to the identification information of the historically cheated person, obtain the identity information, case information and historical activity track of the historically cheated person from the archives of the historically cheated person, and store the historically cheated person. The identity information, case information, and historical activity trajectories of the deceived persons are taken as negative samples; the identification information of the historically defrauded persons is obtained, and the archives of the historically defrauded persons are determined according to the identification information of the historically defrauded persons. Obtain the identity information and historical activity trajectories of the historically undeceived persons from the archives of the undeceived persons, and use the identity information and historical activity trajectories of the historically undeceived persons as positive samples;

The processing unit is further configured to use the negative samples and the positive samples to perform model training to obtain the trained deceived person identification model.

In some possible implementations, identifying the identity category according to the identity information of each community member, family member information and the activity track within a preset time period, and determining the second identity of each community member In one aspect, the processing unit 502 is specifically configured to:

According to the travel trajectory of each community member within the preset time period, determine the travel status of each community member within the preset time period;

The identity information of each community member, family member information and travel status within the preset time period are input into the identity recognition model to determine the second identity of each community member.

In some possible implementations, the potentially deceived persons include housewives, unemployed persons, retirees and young single marriageable young people, the identity information of each community member includes gender and age, and the identity information of each community member Family member information including marital status and child status;

In terms of inputting the identity information, family member information and travel status of each community member into the identity recognition model and determining the second identity of each community member, the processing unit 502 , specifically for:

Input the identity information of each community member, family member information and travel status within the preset time period into the housewife identification model, if it is recognized that the travel of community member A within the preset time period is irregular , and carry a child, and the gender of the community member A is female, determine that the second identity of the community member A is a housewife;

Input the identity information of each community member, family member information and travel status within the preset time period into the unemployed person identification model. is regular, and the travel within the second sub-preset time period is irregular, and the age of the community member A belongs to the first age group, and the second identity of the community member A is determined to be an unemployed person , wherein the first sub-preset time period and the second sub-preset time period are two sub-time periods of the preset time period, and the first sub-preset time period is located in the second sub-preset time period before the sub-preset time period;

Input the identity information, family member information and travel status of each community member into the retirement identification model within the preset time period, if it is identified that the community member A has no spouse during the trip within the preset time period Accompanied by children, and the age of the community member A belongs to the second age group, it is determined that the second identity of the community member A is a retired old man;

Input the identity information, family member information and travel status of each community member into the marriageable single youth identification model within the preset time period, if it is identified that the community member A is traveling within the preset time period No heterosexual companionship, and the marital status of the community member A is unmarried, and the age of the community member A belongs to the third age group, determine that the second identity of the community member A is a marriageable single youth;

Wherein, the community member A is any member of the community.

In some possible implementations, in terms of determining the target community member in the community according to the collision between the first identification and the second identification of each community member, the processing unit 502 is specifically configured to:

In the case that the first identity of the community member A is a quasi-deceived person, and the second identity is a potentially deceptive person, determine that the community member A is a first-level target community member in the community;

In the case that the first identity of the community member A is a quasi-deceived person, and the second identification is not a potentially vulnerable person, determine that the community member A is a secondary target community member in the community;

In the case where the second identity of the community member A is not a deceived person, and the second identity is a potential vulnerable person, determine that the community member A is a secondary target community member in the community;

Wherein, the community member A is any member of the community, and the anti-fraud publicity for the first-level target community members in the community is greater than that of the second-level target community members.

In some possible implementations, the transceiver unit 501 is further configured to acquire the number of historically deceived persons in the community; the processing unit 502 is further configured to obtain the number of historically deceived persons in the community and the The number of community members whose second identity is identified as potential gullible persons determines the gullibility index of the community, wherein the gullibility index of the community is used to indicate that the community members in the community are at risk of being deceived.

Referring to FIG. 6 , FIG. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in FIG. 6 , the electronic device 600 includes a transceiver 601 , a processor 602 and a memory 603 . They are connected by bus 604 . The memory 603 is used to store computer programs and data, and can transmit the data stored in the memory 603 to the processor 602 .

The processor 602 is used to read the computer program in the memory 603 to perform the following operations:

Control the transceiver 601 to obtain the identity information, family member information and activity track within a preset time period of each community member in the community;

In some possible implementations, the processor 602 is further configured to read the computer program in the memory 603 for execution before acquiring the identity information of each community member in the community, the family member information and the activity track within a preset time period The following operations: establish an archive for each community member in the community, wherein the archive of each community member includes the identity information of each community member, family member information and the daily data of each community member Movement tracking;

In terms of acquiring the identity information, family member information and activity track within a preset time period of each community member in the community, the processor 602 is specifically configured to perform the following operations: obtain all the community members from the archives of each community member. The identity information, family member information, and activity trajectories of each community member within a preset time period are described.

In some possible implementations, the processor 602 is further configured to read the computer program in the memory 603 for execution before acquiring the identity information of each community member in the community, the family member information and the activity track within a preset time period Do the following:

The control transceiver 601 obtains the identification information of the historically deceived person, determines the archive of the historically defrauded person according to the identification information of the historically deceived person, and obtains the identity information of the historically deceived person from the archives of the historically deceived person , case information and historical activity trajectories, taking the identity information, case information and historical activity trajectories of the historically defrauded persons as negative samples;

Obtain the identification information of the person who has not been cheated in history, determine the archive of the person who has not been cheated in history according to the identification information of the person who has not been cheated in history, and obtain the identity of the person who has not been cheated in history from the archive library of the person who has not been cheated in history information and historical activity trajectories, taking the identity information and historical activity trajectories of the historically unspoofed persons as positive samples;

Model training is performed using the negative samples and the positive samples, and the trained deceived person identification model is obtained.

In some possible implementations, identifying the identity type according to the identity information of each community member, family member information and the activity track within a preset time period, to determine the second identity of each community member In one aspect, the processor 602 is specifically configured to perform the following operations:

In terms of inputting the identity information, family member information and travel status of each community member into the identity recognition model to determine the second identity of each community member, the processor 602 Specifically used to do the following:

Wherein, the community member A is any member of the community.

In some possible implementations, the processor 602 is specifically configured to perform the following operations in determining the target community personnel in the community according to the collision between the first identity identifier and the second identity identifier of each community member:

In some possible implementations, the processor 602 is further configured to read the computer program in the memory 603 to perform the following operations:

Control the transceiver 601 to obtain the number of historically deceived persons in the community;

According to the number of historically deceived persons in the community and the number of community members whose second identities are identified as potential vulnerable persons in the community, the deception index of the community is determined, wherein the deception index of the community is determined by In order to indicate that community members within the community are at risk of being gullible.

Specifically, the transceiver 601 may be the transceiver unit 501 of the identification device 500 of the embodiment shown in FIG. 5 , and the processor 602 may be the processing unit 502 of the identification device 500 of the embodiment described in FIG. 5 .

It should be understood that the electronic devices in this application may include smart phones (such as Android mobile phones, iOS mobile phones, Windows Phone mobile phones, etc.), tablet computers, handheld computers, notebook computers, MID (Mobile Internet Devices, referred to as: MID) or wearable devices, etc. The above electronic devices are only examples, not exhaustive, including but not limited to the above electronic devices. In practical applications, the above-mentioned electronic devices may also include: intelligent vehicle-mounted terminals, computer devices, and the like.

Embodiments of the present application further provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any one of the identification methods described in the foregoing method embodiments some or all of the steps.

Embodiments of the present application further provide a computer program product, the computer program product comprising a non-transitory computer-readable storage medium storing a computer program, the computer program being operable to cause a computer to execute the methods described in the foregoing method embodiments Some or all of the steps of any identification method.

It should be noted that, for the sake of simple description, the foregoing method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence. Because in accordance with the present application, certain steps may be performed in other orders or concurrently. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components may be combined or Integration into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, and can also be implemented in the form of software program modules.

The integrated unit, if implemented in the form of a software program module and sold or used as a stand-alone product, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art, or all or part of the technical solution, and the computer software product is stored in a memory, Several instructions are included to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash disk , Read-only memory (English: Read-Only Memory, referred to as: ROM), random access device (English: Random Access Memory, referred to as: RAM), magnetic disk or optical disk, etc.

Claims

A method for identification, comprising:

Obtain the identity information, family member information and activity trajectories of each community member in the community within a preset time period;

The identity information of each community member and the activity track within the preset time period are input into the deceived person identification model that has completed the training, and the first identity of each community member is predicted. The first identity identifier includes whether each of the community members is a deceived person;

Identify the identity type according to the identity information of each community member, family member information and the activity track within a preset time period, determine the second identity of each community member, and determine the second identity of each community member. The second identification includes whether each of the community members is a potentially deceptive person;

According to the collision between the first identification and the second identification of each community member, the target community member in the community is determined.
The method according to claim 1, characterized in that, before acquiring the identity information of each community member in the community, family member information and activity track within a preset time period, the method further comprises:

establishing an archive for each community member in the community, wherein the archive of each community member includes the identity information of each community member, family member information and the daily activity track of each community member;

The obtaining of the identity information, family member information and activity track within a preset time period of each community member in the community includes:

The identity information, family member information and activity track within a preset time period of each community member are acquired from the archives of each community member.
The method according to claim 2, characterized in that, before acquiring the identity information of each community member in the community, family member information and activity track within a preset time period, the method further comprises:

Obtain the identification information of the historically defrauded person, determine the archive of the historically defrauded person according to the identification information of the historically deceived person, and obtain the historically deceived person's identity information, case information and Historical activity trajectories, taking the identity information, case information and historical activity trajectories of the historically deceived persons as negative samples;

Obtain the identification information of the person who has not been cheated in history, determine the archive of the person who has not been cheated in history according to the identification information of the person who has not been cheated in history, and obtain the identity of the person who has not been cheated in history from the archive library of the person who has not been cheated in history information and historical activity trajectories, taking the identity information and historical activity trajectories of the historically unspoofed persons as positive samples;

Model training is performed using the negative samples and the positive samples, and the trained deceived person identification model is obtained.
The method according to any one of claims 1-3, wherein the identity type identification is performed according to the identity information of each community member, the family member information and the activity track within a preset time period, Determine the second identity of each community member, including:

According to the travel trajectory of each community member within the preset time period, determine the travel status of each community member within the preset time period;

The identity information of each community member, family member information and travel status within the preset time period are input into the identity recognition model to determine the second identity of each community member.
The method according to claim 4, wherein the potentially deceived persons include housewives, unemployed persons, retirees and marriageable single youths, the identity information of each community person includes gender and age, and the Family member information of each community member including marital status and child status;

The inputting the identity information, family member information and travel status of each community member into the identity recognition model to determine the second identity of each community member, including:

Input the identity information of each community member, family member information and travel status within the preset time period into the housewife identification model, if it is identified that the travel of community member A within the preset time period is irregular , and carry children, and the gender of the community member A is female, determine that the second identity of the community member A is a housewife;

Input the identity information of each community member, family member information and travel status within the preset time period into the unemployed person identification model. is regular, and the travel within the second sub-preset time period is irregular, and the age of the community member A belongs to the first age group, and the second identity of the community member A is determined to be an unemployed person , wherein the first sub-preset time period and the second sub-preset time period are two sub-time periods of the preset time period, and the first sub-preset time period is located in the second sub-preset time period before the sub-preset time period;

Input the identity information, family member information and travel status of each community member into the retirement identification model within the preset time period, if it is identified that the community member A has no spouse during the trip within the preset time period Accompanied by children, and the age of the community member A belongs to the second age group, it is determined that the second identity of the community member A is a retired old man;

Input the identity information of each community member, family member information and travel status within the preset time period into the marriageable single youth identification model, if it is identified that the community member A is traveling within the preset time period No heterosexual companionship, and the marital status of the community member A is unmarried, and the age of the community member A belongs to the third age group, determine that the second identity of the community member A is a marriageable single youth;

Wherein, the community member A is any member of the community.
The method according to any one of claims 1-5, wherein the target community member in the community is determined according to the collision between the first identity identifier and the second identity identifier of each community member ,include:

In the case that the first identity of the community member A is a quasi-deceived person, and the second identity is a potentially deceptive person, determine that the community member A is a first-level target community member in the community;

In the case that the first identity of the community member A is a quasi-deceived person, and the second identification is not a potentially vulnerable person, determine that the community member A is a secondary target community member in the community;

In the case where the second identity of the community member A is not a deceived person, and the second identity is a potential vulnerable person, determine that the community member A is a secondary target community member in the community;

Wherein, the community member A is any member of the community, and the anti-fraud publicity for the first-level target community members in the community is greater than that of the second-level target community members.
The method according to any one of claims 1-6, wherein the method further comprises:

Obtain the number of historically deceived persons in said community;

According to the number of historically deceived persons in the community and the number of community members whose second identities are identified as potential vulnerable persons in the community, the deception index of the community is determined, wherein the deception index of the community is determined by In order to indicate that community members within the community are at risk of being gullible.
An identification device, characterized in that it includes:

The transceiver unit is used to obtain the identity information of each community member in the community, family member information and activity track within a preset time period;

The processing unit is used to input the identity information of each community member and the activity track within a preset time period into the deceived person identification model that has completed the training, and predict the first identity of each community member, the The first identification of each community member includes whether the community member is a deceived person; the identity type is identified according to the identity information of each community member, family member information and activity track within a preset time period , determine the second identity of each community member, and the second identity of each community member includes whether each community member is a potentially vulnerable person; according to the first identity of each community member The identifier and the second identity identifier are used to determine the target community members in the community.
An electronic device, comprising: a processor and a memory, the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, to cause the electronic device to perform the method of any one of claims 1-7.
A computer-readable storage medium, characterized in that, the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1-7.