CN110189092B

CN110189092B - Method and device for evaluating audit group members

Info

Publication number: CN110189092B
Application number: CN201910286652.9A
Authority: CN
Inventors: 连琨; 曹胡
Original assignee: Advanced New Technologies Co Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2019-04-10
Filing date: 2019-04-10
Publication date: 2023-06-09
Anticipated expiration: 2039-04-10
Also published as: CN116720829A; CN110189092A

Abstract

The application provides an auditing group member assessment method and device, wherein the method comprises the following steps: acquiring auditing behavior data of auditing group members in an item aiming at auditing of the item case in the running process of the item; calculating audit action scores and interaction scores of the audit group members for project case audit based on the audit action data; clustering the auditing group members based on the auditing action scores, the interaction scores and case auditing result data of the auditing group members to obtain abnormal members in the auditing group members; and clearing and backing the abnormal member in the audit group member from the project audit group to which the abnormal member belongs. According to the method, the audit group members are clustered according to the scoring result and the audit result of the audit group members, abnormal members in the audit group members are obtained according to the clustering result, and clearing and annealing are performed, so that the member quality and audit rationality of the audit group members are ensured.

Description

Method and device for evaluating audit group members

Technical Field

The application relates to the technical field of data processing, in particular to an auditing group member assessment method. The present application is also directed to an audit group member assessment apparatus, a computing device, and a computer-readable storage medium.

Background

With the development of the internet, many internet insurance modes are introduced in the market, in the internet insurance mode, participants can join in insurance business after reaching a specified admittance condition, and after being audited by an audit group member of an audit group, the insurance case of the insurance mode decides whether to settle a claim, and the insurance mode is popular among users due to the advantages of low payment amount, large audience scale, relatively fair and fair, and the like.

The 'audit group' in the insurance business mode is an insurance mediation mechanism by which the participants in insurance can participate in the claim settlement decision link in the insurance case, and is a business innovation of the insurance industry. The mechanism specifically refers to a participating person with voting rights of a certain number and an insurance case which occurs in the process of determining the insurance operation, and the system for determining whether the insurance case should be subjected to claim settlement is similar to a cosmetical group in the national judicial system of the Yingmei system.

The members of the insurance audit group are very important roles in the insurance business, the current members of the insurance audit group can have voting rights of related project cases after a series of authentications pass, the quality of the members of the insurance audit group is the basis of effective operation of the insurance audit group, but during the audit of the insurance cases, part of members of the insurance audit group often do not participate in audit for a long time or vote according to voting rules, audit order is disturbed, the insurance audit group loses confidence, and the members of the insurance audit group with problems cannot be processed or penalized in time.

Disclosure of Invention

In view of the foregoing, the present application provides a method for evaluating members of an audit group to solve the technical drawbacks of the prior art. An audit group member assessment apparatus, a computing device, and a computer-readable storage medium are also provided.

The application provides an auditing group member assessment method, which comprises the following steps:

acquiring auditing behavior data of auditing group members in an item aiming at auditing of the item case in the running process of the item;

calculating audit action scores and interaction scores of the audit group members for project case audit based on the audit action data;

clustering the auditing group members based on the auditing action scores, the interaction scores and case auditing result data of the auditing group members to obtain abnormal members in the auditing group members;

and carrying out clearing processing on the abnormal member in the project audit group to which the abnormal member belongs.

Optionally, the audit behavior data includes at least one of the following:

auditing action behavior data and interaction behavior data;

wherein the audit action behavior data comprises at least one of:

the retention time of the auditing group member on a material page of the auditing material of the project case, and the retention time of the auditing group member on a viewpoint page of the auditing viewpoint of the project case;

The audit interactive behavior data comprises at least one of the following:

the number of votes by the auditing group members in the process of auditing the project case, the number of views issued by the auditing group members in the process of auditing the project case, the number of comments issued by the auditing group members in the process of auditing the project case, and the number of praise of the auditing group members in the process of auditing the project case.

Optionally, the audit action score is calculated by the following method:

calculating the ratio of the stay time of each page of the project case to the invited times of the member of the auditing group, which is invited to participate in auditing the project case, and taking the ratio as the average stay time of each page;

calculating the product of the average stay time and the weight of each page of the project case as a first product corresponding to each page;

summing the first products of the project cases as the audit action scores.

Optionally, the interaction score is calculated in the following manner:

calculating the ratio of the times of each audit action of the audit group member to the invited times of the audit group member invited to participate in auditing the project case in the process of auditing the project case, and taking the ratio as the average times of each audit action;

Calculating the product of the average times and the weights of all the auditing behaviors to be used as a second product of all the auditing behaviors;

summing the second products of the project cases as the interaction score.

Optionally, the clustering the auditing group members based on the auditing action scores, the interaction scores and the case auditing result data of the auditing group members, to obtain abnormal members in the auditing group members, includes:

acquiring the case auditing result data of the auditing group members;

determining audit action scoring levels and interaction levels of the audit group members according to the audit action scores and the interaction scores;

clustering the auditing group members according to the case auditing result data, the auditing action scoring grade and the interaction grade;

and determining an abnormal member list in the audit group members according to the clustering result.

Optionally, after the step of calculating the audit action score and the interaction score of the audit group member for the project case audit based on the audit action data is performed, the step of clustering the audit group member based on the audit action score, the interaction score and the case audit result data of the audit group member, before the step of obtaining the abnormal member in the audit group member is performed, includes:

Judging whether the interaction score is lower than a preset interaction score threshold of the project;

if yes, clearing and processing is carried out on the auditing group members with the interaction scores lower than the preset interaction score threshold in the project auditing group;

and if not, executing the step of clustering the auditing group members based on the auditing action scores, the interaction scores and the case auditing result data of the auditing group members to obtain abnormal members in the auditing group members.

judging whether the audit action score is lower than a preset audit action score threshold value of the project;

if yes, clearing processing is carried out on the auditing group members with the auditing action scores lower than the preset auditing action score threshold value in the project auditing group;

judging whether the interaction score is lower than a preset interaction score threshold of the project and whether the audit action score is lower than a preset audit action score threshold of the project;

if yes, clearing processing is carried out on the auditing group members of which the interaction score is lower than the preset interaction score threshold and the auditing action score is lower than the preset auditing action score threshold in the project auditing group;

acquiring auditing node behavior data of each auditing node of the auditing group member in the project operation process;

calculating an liveness score of the audit group member based on the audit node behavior data;

judging whether the liveness score is lower than a liveness score preset threshold value of the item;

if yes, clearing and processing is carried out on the auditing group members of which the liveness score is lower than the preset threshold value of the liveness score in the project auditing group;

if not, executing the step of clustering the auditing group members based on the auditing action scores, the interaction scores and the case auditing result data of the auditing group members to obtain abnormal members in the auditing group members;

wherein, the audit node behavior data comprises:

Pre-audit behavioral data, in-audit behavioral data, post-audit behavioral data.

Optionally, the liveness score is calculated by the following method:

calculating the product of the preset score and the preset weighting of each audit node in the project to be used as a node product;

and summing the node products of all the auditing nodes in the project to be used as the liveness score.

acquiring a language release word stock of the auditing group member based on the auditing behavior data;

judging whether the number of times of occurrence of the pre-recorded non-standard vocabulary in the language publication word stock is larger than a preset threshold value;

if yes, clearing and backing processing is carried out on the auditing group members of which the occurrence times of the nonstandard words in the language publishing word library are larger than the preset threshold value in the item auditing group;

judging whether the language published word stock contains a pre-entered nonstandard word;

if yes, judging whether the interaction score is lower than a preset interaction score threshold of the project;

if yes, performing clear processing on the project audit group members, wherein the interaction score is lower than the preset interaction score threshold value, and the audit group members containing the nonstandard vocabulary in the language release word stock are in the project audit group;

And if the interaction score is not lower than the preset interaction score threshold of the project, executing the step of clustering the auditing group members based on the auditing action score, the interaction score and the case auditing result data of the auditing group members to obtain abnormal members in the auditing group members.

The application also provides an audit group member assessment device, comprising:

the acquisition module is configured to acquire auditing behavior data of auditing group members in the project aiming at auditing of the project case in the running process of the project;

a computing module configured to compute audit action scores and interaction scores for the audit group members for project case audits based on the audit action data;

the clustering module is configured to cluster the auditing group members based on the auditing action scores, the interaction scores and case auditing result data of the auditing group members to obtain abnormal members in the auditing group members;

and the clearing module is configured to clear the abnormal member in the project audit group to which the abnormal member belongs.

The present application also provides a computing device comprising:

a memory and a processor;

The memory is for storing computer-executable instructions, and the processor is for executing the computer-executable instructions:

The present application also provides a computer readable storage medium storing computer instructions that when executed by a processor perform the steps of the audit group member assessment method described above.

Compared with the prior art, the application has the following advantages:

the application provides an auditing group member assessment method and device, wherein the method comprises the following steps: acquiring auditing behavior data of auditing group members in an item aiming at auditing of the item case in the running process of the item; calculating audit action scores and interaction scores of the audit group members for project case audit based on the audit action data; clustering the auditing group members based on the auditing action scores, the interaction scores and case auditing result data of the auditing group members to obtain abnormal members in the auditing group members; and carrying out clearing processing on the abnormal member in the project audit group to which the abnormal member belongs.

According to the auditing group member assessment method, auditing behavior data of the auditing group members aiming at project cases in the project operation process are obtained, the auditing group members are scored according to the auditing behavior data, the auditing group members are clustered according to the scoring result and the auditing result of the auditing group members, abnormal members in the auditing group members are obtained according to the clustering result and are cleared, and the member quality and auditing rationality of the auditing group members are guaranteed.

Drawings

FIG. 1 is a process flow diagram of an audit group member assessment method provided in an embodiment of the present application;

FIG. 2 is a flowchart of a process for auditing a group member assessment method applied to a health risk scenario, provided in an embodiment of the present application;

FIG. 3 is a schematic diagram of an audit group member assessment apparatus provided in an embodiment of the present application;

fig. 4 is a block diagram of a computing device provided in an embodiment of the present application.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is, however, susceptible of embodiment in many other ways than those herein described and similar generalizations can be made by those skilled in the art without departing from the spirit of the application and the application is therefore not limited to the specific embodiments disclosed below.

The terminology used in the one or more embodiments of the specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the specification. As used in this specification, one or more embodiments and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any or all possible combinations of one or more of the associated listed items.

It should be understood that, although the terms first, second, etc. may be used in one or more embodiments of this specification to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first may also be referred to as a second, and similarly, a second may also be referred to as a first, without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.

The application provides an auditing group member evaluation method, and also provides an auditing group member evaluation device, a computing device and a computer readable storage medium. The following detailed description, together with the drawings of the embodiments provided herein, respectively, describes the steps of the method one by one.

The embodiment of the auditing group member assessment method provided by the application is as follows:

referring to FIG. 1, a process flow diagram of an audit group member assessment method provided by the present embodiment is shown; referring to fig. 2, a process flow diagram of an audit group member assessment method applied to a health risk scenario is shown.

Step S102, audit behavior data of audit group members in the project for project case audit in the project operation process are obtained.

The items described in the embodiments of the present application include insurance items, crowd funding items, investment items, and the like, which are not limited herein. The insurance comprises health insurance, serious disease insurance, medical insurance, nursing insurance, accidental injury insurance and the like. Accordingly, the project cases include insurance cases, crowd-sourcing cases, investment cases, and the like, which are not limited herein.

In the embodiment of the application, the audit group member refers to an audit group member participating in the project, and the audit group member comprises: an insurance audit group member participating in the insurance project, a crowd funding audit group member participating in the crowd funding project, an investment audit group member participating in the investment project, and the like.

Taking health insurance as an example, the audit group member is selected from participants joining the health insurance, specifically, the participants join in the health insurance audit group member authentication after applying for joining the health insurance audit group, and the participants join in the health insurance audit group after passing the health insurance audit group member authentication of the health insurance audit group, so as to become the health insurance audit group member of the health insurance; the project case is a health insurance case which is generated in the process that the participant participates in the health insurance and is required to apply for claims.

The embodiment of the application takes the evaluation of the behaviors of the health risk auditing group members in the process of participating in the health risk auditing as an example, and describes the auditing group member evaluation method provided by the embodiment of the application.

In this embodiment of the present application, after the auditing group member of the project performs auditing with respect to a plurality of project cases generated in the project operation process, audit behavior data of the auditing group member is obtained, where the audit behavior data includes at least one of the following:

And auditing action behavior data and interaction behavior data.

The audit action data includes a material page stay time of the audit group member in the audit material of the project case, a viewpoint page stay time of the audit group member in the audit viewpoint of the project case, and the like, and in addition, the audit action data may also be stay time of other pages related to the project case except the above page, such as a case content page, a case claim settlement page, and the like, which are not limited herein.

The audit interactive behavior data includes voting times of the audit group members in the process of auditing the project cases, view publishing times of the audit group members in the process of auditing the project cases, comment publishing times of the audit group members in the process of auditing the project cases, praise times of the audit group members in the process of auditing the project cases, and the like, and besides, the audit interactive behavior data can also be interactive behavior data of other audit process of auditing the project cases except the behaviors, such as click times of the project cases, and the like, and is not limited herein.

For example, in a scenario that an item is a health insurance, a health insurance audit group member is a health insurance audit group member, after the health insurance participant applies to join a health insurance audit group and passes through authentication of the health insurance audit group, the health insurance audit group member becomes the health insurance audit group member of the health insurance, after the health insurance audit group member carries out audit on a health insurance case generated in a health insurance operation process, audit behavior data of the health insurance audit group member is obtained, the audit behavior data comprises audit action data and audit interaction behavior data, wherein the audit action data comprises a material page stay time of the health insurance audit group member in an audit material of the health insurance case, a view page stay time of the health insurance audit group member in a view point of the health insurance case, the audit interaction behavior data comprises a voting number of the health insurance audit group member in the process of the health insurance case, a view number of the health insurance group member in the process of the health insurance case, a comment number of the health insurance group member in the process of the health insurance case, and a view number of the health insurance group member in the health case of the health case.

Therefore, after the auditing members audit the project cases, the auditing behavior data of the auditing members are automatically obtained, so that the auditing members can be evaluated based on the auditing behavior data.

And step S104, calculating audit action scores and interaction scores of the audit group members for project case audit based on the audit action data.

After the auditing behavior data of the auditing group member for the project case auditing is obtained, the auditing action score and the interaction score of the auditing group member for the project case auditing are calculated according to the auditing behavior data.

In an alternative implementation provided in the examples of the present application, the audit action score is calculated as follows:

summing the first products of the project cases as the audit action scores.

In this embodiment, the average residence time of each page is calculated as follows:

the corresponding relation between the stay time of each page and the weight of each page is shown in the following table:

referring to the table above, the average stay length of the material page= Detail stay duration/invited times, and similarly, the average stay length of the viewpoint page= Opoion stay duration/invited times;

audit action score = (average dwell time of material page × page weight dsd% of material page +) + (average dwell time of view page × page weight osd% of view page).

For example, after the residence time of the material page of the health risk auditing group member is 8min, the residence time of the view page is 12min, the auditing action score of the health risk auditing group member is calculated, the number of times that the health risk auditing group member is invited to audit the health risk case is 2, the page weight of the material page is 50%, the page weight of the view page is 50%, based on this, the auditing action score= (average residence time of the material page is equal to the page weight dsd% of the material page) + (residence time of the view page is equal to the page weight osd% of the view page), that is, 8×50%/2+12×50%/2=5, and the auditing action score of the health risk auditing group member is 5.

Further, the interaction score may be calculated by the following method:

summing the second products of the project cases as the interaction score.

In this embodiment, the average number of times of each audit action is calculated as follows:

the corresponding relation between the times of each audit behavior and the audit behavior weight is shown in the following table:

referring to the table above, the average number of voting actions=volume count/invited times, similarly, the average number of posting viewpoint actions=opoion count/invited times, the average number of posting Comment actions=command count/invited times, the average number of Praise count/invited times;

interaction score = average number of voting behaviors × voting behavior weight a% + average number of posting viewpoint behaviors × viewpoint behavior weight b% + average number of posting comment behaviors × comment behavior weight c% + average number of praise behaviors × praise behavior weight d%.

For example, when the number of votes by the health risk auditing group member in the process of auditing the health risk case is 2 times, the number of views by the health risk auditing group member in the process of auditing the health risk case is 4 times, the number of comments by the health risk auditing group member in the process of auditing the health risk case is 4 times, the number of praise by the health risk auditing group member in the process of auditing the health risk case is 2 times, wherein the voting behavior weight is 50%, the view posting weight is 20%, the comment action weight is 20%, the praise action weight is 10%, and based on the above, the interaction score=the average number of voting behaviors is a% + the average number of posting view behaviors is b% + the average number of praise behavior weights c% + the average number of praise point behaviors is 2% + 50%/2+4 x 20%/2+2+2%/2+2%/2.4% = 1.4% and the interaction score is 1, and the health risk group member is the interaction score is 1.

In practical applications, the audit action score and the interaction score may be obtained by other calculation methods, and the data in the audit action score and the interaction score calculation process may be other data besides the data provided above, which is not limited herein.

According to the embodiment of the invention, the audit action scores and the interaction scores of the audit group members are calculated, and the audit actions and the interaction actions of the audit group members in the audit project cases are scored, so that the audit group members are evaluated through the scores, and the audit group members with poor historical audit actions or improper interaction actions can be conveniently distinguished.

And step S106, clustering the auditing group members based on the auditing action scores, the interaction scores and the case auditing result data of the auditing group members to obtain abnormal members in the auditing group members.

After the auditing action score and the interaction score are calculated, case auditing result data of the auditing group members are obtained, and the auditing group members are clustered based on the auditing result data, the auditing action score and the interaction score, so that abnormal members in the auditing group members are obtained.

Based on the specific calculation manner of the audit action score and the interaction score provided in the above optional embodiment, optionally, in the embodiment of the present application, the case audit result data based on the audit action score, the interaction score, and the audit group member clusters the audit group member to obtain an abnormal member in the audit group member, by implementing the following manner:

Acquiring the case auditing result data of the auditing group members;

For example, after the audit action score and the interaction score of the health risk audit group member are obtained through calculation, health risk case audit result data of the health risk audit group member is obtained, the health risk case audit result data comprises voting options of the health risk audit group member, voting results and final audit results of the health risk case, and an audit action score grade and an interaction grade of the health risk audit group member are determined according to the audit action score and the interaction score, wherein the audit action score is higher than 60 and is higher than 60, the audit action score is lower than 60 and is higher than 20 and is lower than 20, the interaction score is higher than 60 and is lower than 20;

After the grade determination is completed, clustering the health risk auditing group members based on the health risk case auditing result data and the grades of the auditing action scores and the interaction scores, clustering the health risk auditing group members with the auditing action scores being low in auditing action scores, the interaction scores being low in interaction scores and the health risk case auditing result data being similar as abnormal members, and determining an abnormal member list in the health risk auditing group.

According to the embodiment of the invention, the auditing action score and the interaction score of the auditing group members are graded, so that the workload of a clustering process is reduced, the auditing group members are clustered through the auditing action score grade, the interaction score grade and the auditing result data of the auditing group members, and the auditing group members with low auditing action score and interaction score and similar auditing result data are distinguished as abnormal members, so that the follow-up clearing process is facilitated.

Based on the specific calculation manner of the audit action score and the interaction score provided in the above optional implementation manner, in an optional implementation manner of the embodiment of the present application, after calculating the audit action score and the interaction score of the audit group member for the project case audit based on the audit action data, and clustering the audit group member based on the audit action score, the interaction score and the case audit result data of the audit group member, before obtaining the abnormal member in the audit group member, the method includes:

if not, the following step S108 is performed.

Based on the specific calculation manner of the audit action score and the interaction score provided in the foregoing optional implementation manner, in a second optional implementation manner of the embodiment of the present application, after calculating the audit action score and the interaction score of the audit group member for the project case audit based on the audit action data, and clustering the audit group member based on the audit action score, the interaction score and the case audit result data of the audit group member, before obtaining the abnormal member in the audit group member, the method includes:

if not, the following step S108 is performed.

Based on the specific calculation manners of the audit action score and the interaction score provided in the foregoing optional implementation manner, optionally, after calculating the audit action score and the interaction score of the audit group member for the project case audit based on the audit action data, and clustering the audit group member based on the audit action score, the interaction score and the case audit result data of the audit group member, before obtaining the abnormal member in the audit group member, the method includes:

if not, the following step S108 is performed.

Optionally, in a fourth optional implementation manner of the embodiment of the present application, after calculating, based on the audit behavior data, audit action scores and interaction scores of the audit group members for project case audit, and clustering the audit group members based on the audit action scores, the interaction scores and case audit result data of the audit group members, before obtaining abnormal members in the audit group members, the method includes:

if not, the following step S108 is executed;

in this alternative embodiment, the audit node behavior data includes:

On this basis, optionally, the liveness score is calculated in the following manner:

calculating the product of the preset score and the preset weighting of each audit node in the project; as a node product;

According to the embodiment of the application, the interaction scores, the audit action scores and the liveness scores of the audit group members are analyzed and calculated, so that clear measurement standards are provided for the interaction times, the audit actions and the liveness of the audit group members, the audit members with lower interaction times or activity times and poorer audit actions are conveniently distinguished, and the workload of a clustering process is reduced.

For example, after calculating the audit action score and the interaction score of the health risk audit group member for the health risk case audit based on the audit action data, and clustering the health risk audit group member based on the audit action score, the interaction score and the case audit result data of the health risk audit group member, before obtaining abnormal members in the health risk audit group member, obtaining audit node behavior data of each audit node of the health risk audit group member in the health risk operation process, and calculating the liveness score of the health risk audit group member based on the audit node behavior data, the liveness score is calculated by:

the corresponding relation between the auditing node behavior data and the preset score and the preset weight is shown in the following table:

the activity score is calculated by multiplying all the audit node behavior data by the corresponding preset score and preset weighting, and summing the obtained products: 10 x 10% + 10%20 x 20: ++10 x 10% +20 x 20% +10 x 10% = 10, based on the above calculation of the liveness score, judging whether the liveness score is lower than a liveness score preset threshold value 8 of the health risk or not; if the activity score is lower than 8, carrying out clearing processing on the health risk audit group members of which the activity score is lower than the preset threshold value of the activity score; and if the activity score of the health risk auditing group member is 10 and is not lower than the activity score threshold value 8, not conducting clearing, and executing the following steps of clustering the health risk auditing group member based on the auditing action score, the interaction score and the health risk case auditing result data of the health risk auditing group member to obtain abnormal member steps in the health risk auditing group member.

The audit node behavior data in the liveness score calculation process may be, in addition to the audit nodes and the audit node behavior data provided above, corresponding audit node behavior data in other audit nodes, which is not limited herein.

if not, the following step S108 is performed.

For example, an irregular vocabulary is recorded in advance in the health risk, a language publication word stock of the health risk auditing group member is obtained after the health risk auditing group member audits the health risk case, whether the number of times of occurrence of the pre-recorded irregular vocabulary in the language publication word stock of the health risk auditing group member is greater than a preset threshold value is 2 times is judged, if so, the health risk auditing group member with the number of occurrence of the irregular vocabulary being greater than the preset threshold value is subjected to a clearing process, and if not, the health risk auditing group member is clustered based on the auditing action score, the interaction score and case auditing result data of the auditing group member, so that abnormal member steps in the health risk auditing group member are obtained.

According to the embodiment of the invention, through pre-inputting the nonstandard vocabulary, the language publishing of the auditing group member is explicitly standardized, so that the auditing group member with the nonstandard or abusive language publishing can be discovered and cleared in time, the quality of the auditing group member is improved, and the language of the auditing group member is standardized.

Based on the specific calculation manner of the audit action score and the interaction score provided in the above optional embodiment, optionally, after calculating the audit action score and the interaction score of the audit group member for the project case audit based on the audit action data, and clustering the audit group member based on the audit action score, the interaction score and the case audit result data of the audit group member, before obtaining the abnormal member in the audit group member, the method includes:

If the interaction score is not lower than the preset interaction score threshold of the item, the following step S108 is executed.

According to the embodiment of the invention, the abnormal members in the project audit group are determined by clustering the audit group members, so that the abnormal members can be conveniently subjected to the clearing operation, the workload of manually distinguishing the abnormal members is reduced, and the efficiency of clearing low-quality audit group members is improved.

And S108, clearing and backing the abnormal member in the project audit group to which the abnormal member belongs.

After determining the abnormal member in the auditing group members, the abnormal member is cleared from the item auditing group to which the abnormal member belongs.

According to the method and the device, the abnormal members in the audit group members are automatically cleared, the process of manually clearing the abnormal members is omitted, the labor cost is saved, and meanwhile clear processing accuracy is guaranteed.

For example, after determining an abnormal member in the health risk audit group members, clearing the abnormal member from the health risk audit group, and after the clearing is completed, the abnormal member is no longer a health risk audit group member of the health risk audit group.

The following is a further explanation of the method for evaluating an audit group member provided in the present application, taking the application of the audit group member provided in the present application in a health risk scenario as an example with reference to fig. 2:

Step S202, audit behavior data of health risk audit group members are obtained.

In a scene that the project is a health insurance, the health insurance audit group member is a health insurance audit group member, the health insurance participants apply for joining the health insurance audit group, and become the health insurance audit group member of the health insurance after the participants pass the authentication of the health insurance audit group, participate in auditing the health insurance cases generated in the running process of the health insurance, and acquire audit behavior data of the health insurance audit group member in the process of auditing the health insurance cases.

Step S204, calculating interaction scores and auditing action scores.

And calculating the audit action score and the interaction score of the health risk audit group member according to the audit behavior data obtained in the steps.

Step S206, judging whether the auditing action score and the interaction score are lower than a preset threshold.

After the audit action score and the interaction score of the health risk audit group member are calculated, judging whether the audit action score and the interaction score of the health risk audit group member are lower than a preset threshold, if any one of the audit action score and the interaction score is lower than the preset threshold, executing step S208, and if both the audit action score and the interaction score are not lower than the preset threshold, executing step S210.

And step S208, clearing and reversing the health risk auditing group members.

After the execution of step S206 is completed, if any one of the audit action score and the interaction score is lower than the preset threshold, a clearing process is performed on the health risk audit group member of which any one of the audit action score and the interaction score is lower than the preset threshold from the health risk audit group, and after the clearing process is completed, the member is no longer a health risk audit group member of the health risk audit group.

Step S210, health risk node data of health risk auditing group members are obtained.

After the execution of step S206 is completed, if the audit action score and the interaction score are not lower than the preset threshold, health risk node behavior data of each audit node of the health risk audit group member in the health risk running process is obtained.

Step S212, calculating the liveness score of the health risk auditing group member.

After the health risk node behavior data of the health risk audit group member is obtained in the step S210, an liveness score of the health risk audit group member is calculated based on the health risk node behavior data.

Step S214, judging whether the liveness score is lower than a preset threshold.

After the activity score of the health risk auditing group member is obtained in the step S212, it is determined whether the activity score is lower than the activity score preset threshold of the health risk, if so, step S216 is executed, and if not, step S218 is executed.

And step S216, carrying out clear processing on the health risk auditing group members.

And clearing the health risk auditing group members with the liveness score lower than the preset threshold value of the liveness score from the health risk auditing group, wherein after the clearing is finished, the members are no longer health risk auditing group members of the health risk auditing group.

Step S218, judging whether the language-published word stock of the health risk auditing group contains an irregular word.

Recording an irregular vocabulary in the health risk in advance, acquiring a language-published word stock of the health risk auditing group member after the health risk auditing group member audits the health risk case, judging whether the number of times of occurrence of the pre-recorded irregular vocabulary in the language-published word stock of the health risk auditing group member is larger than a preset threshold value of occurrence times of the irregular vocabulary, and executing step S220 if the number of occurrence times of the pre-recorded irregular vocabulary is larger than the preset threshold value of occurrence times of the irregular vocabulary; if not, step S222 is executed.

Step S220, clear and back processing is carried out on the health risk auditing group members.

And carrying out clearing processing on the health risk auditing group members with the occurrence times of the nonstandard vocabularies being larger than a preset threshold value from the health risk auditing group, wherein after the clearing processing is finished, the members are no longer health risk auditing group members of the health risk auditing group.

Step S222, clustering the health risk auditing group members.

And acquiring health risk case audit result data of the health risk audit group members, wherein the health risk case audit result data comprises voting options of the health risk audit group members, voting results and final audit results of the health risk cases, and determining audit action scoring grades and interaction grades of the health risk audit group members according to the audit action scores and the interaction scores, wherein the audit action scores are higher than 60 and are classified into audit action scores, the audit action scores are lower than 20, the interaction scores are classified into interaction scores and are classified into interaction scores, the audit action scores are lower than 60 and are higher than 20, the audit action scores are lower than 20, and after the classification determination is completed, the health risk group members are clustered based on the health risk case audit result data, the audit action scores and the interaction scores and the health risk score abnormal health risk score group members are clustered into health risk score abnormal score groups.

Step S224, judging whether the health risk auditing group member is an abnormal member.

After determining the list of abnormal members in the health risk audit group, the step S222 determines whether the health risk audit group member is an abnormal member, if yes, step S226 is executed, if not, it indicates that the health risk audit group member is not an abnormal member, and the health risk audit group member is not processed.

In step S226, the clearing process is performed on the abnormal member.

And carrying out clearing processing on the abnormal member from the health risk auditing group, wherein after the clearing processing is finished, the abnormal member is no longer a health risk auditing group member of the health risk auditing group.

An embodiment of an audit group member assessment device provided in the present application is as follows:

referring to fig. 3, a schematic diagram of an embodiment of an audit group member assessment apparatus is provided.

In the foregoing embodiment, a method for evaluating an audit group member is provided, and in response, an audit group member evaluating apparatus is also provided, which is described below with reference to fig. 3.

Since the apparatus embodiments are substantially similar to the method embodiments, the description is relatively simple, and reference should be made to the corresponding descriptions of the method embodiments provided above for relevant parts. The device embodiments described below are merely illustrative.

The application provides an audit group member assessment device, comprising:

the acquiring module 302 is configured to acquire auditing behavior data of auditing group members in the project for auditing of the project case in the running process of the project;

a calculation module 304 configured to calculate an audit action score and an interaction score for the audit group member for project case audit based on the audit action data;

a clustering module 306 configured to cluster the audit group members based on the audit action score, the interaction score, and case audit result data of the audit group members, to obtain abnormal members of the audit group members;

the clearing module 308 is configured to clear the abnormal member in the project audit group to which the abnormal member belongs.

Optionally, the audit behavior data includes at least one of the following:

auditing action behavior data and interaction behavior data;

wherein the audit action behavior data comprises at least one of:

The audit interactive behavior data comprises at least one of the following:

Optionally, the audit action score is calculated by the following method:

summing the first products of the project cases as the audit action scores.

Optionally, the interaction score is calculated in the following manner:

summing the second products of the project cases as the interaction score.

Optionally, the clustering module 306 includes:

an audit result acquisition sub-module configured to acquire the case audit result data of the audit group member;

a rank determination sub-module configured to determine an audit action score rank and an interaction rank of the audit group members based on the audit action score and the interaction score;

the clustering sub-module is configured to cluster the auditing group members according to the case auditing result data, the auditing action scoring grade and the interaction grade;

and the list determination submodule is configured to determine an abnormal member list in the audit group members according to the clustering result.

Optionally, the auditing group member evaluation device further includes:

a first interaction score determination module configured to determine whether the interaction score is below a preset interaction score threshold for the item; if yes, a second clearing module is operated, and if not, the clustering module 306 is operated;

And the second clearing module is configured to clear and clear the auditing group members with the interaction scores lower than the preset interaction score threshold in the project auditing group.

Optionally, the auditing group member evaluation device further includes:

an audit action score determining module configured to determine whether the audit action score is below a preset audit action score threshold for the item; if yes, a first clearing module is operated, and if not, the clustering module 306 is operated;

the first clearing module is configured to clear and clear the auditing group members with the auditing action scores lower than the preset auditing action score threshold value in the project auditing group.

Optionally, the auditing group member evaluation device further includes:

a score determination module configured to determine whether the interaction score is below a preset interaction score threshold for the item and the audit action score is below a preset audit action score threshold for the item; if yes, executing an interactive first clearing module, and if not, executing the clustering module 306;

the interaction first clearing module is configured to clear and clear the members of the auditing group with the interaction score lower than the preset interaction score threshold and the auditing action score lower than the preset auditing action score threshold in the project auditing group.

Optionally, the auditing group member evaluation device further includes:

the node data acquisition module is configured to acquire audit node behavior data of each audit node of the audit group member in the project operation process;

an liveness score calculation module configured to calculate liveness scores of the audit group members based on the audit node behavioral data;

the activity judging module is configured to judge whether the activity score is lower than an activity score preset threshold of the item; if yes, executing an activity clearing module, and if not, executing the clustering module 306;

the liveness clearing module is configured to clear and clear the members of the auditing group with the liveness score lower than the preset threshold value of the liveness score in the project auditing group;

wherein, the audit node behavior data comprises:

Optionally, the liveness score is calculated by the following method:

Optionally, the auditing group member evaluation device further includes:

the first word stock acquisition module is configured to acquire a language published word stock of the auditing group member based on the auditing behavior data;

the first language judging module is configured to judge whether the number of times of occurrence of the pre-recorded irregular vocabulary in the language publishing lexicon is larger than a preset threshold value; if yes, executing a language clearing module, and if not, executing the clustering module 306;

and the language clearing and backing module is configured to clear and backing the auditing group members with the occurrence times of the nonstandard words larger than the preset threshold value in the language publication word stock in the item auditing group.

Optionally, the auditing group member evaluation device further includes:

the second word stock obtaining module is configured to obtain a language published word stock of the auditing group member based on the auditing behavior data;

the second language judging module is configured to judge whether the language published word stock contains a pre-recorded irregular word or not; if yes, executing a second interaction score judging module, and if not, executing the clustering module 306;

the second interaction score judging module is configured to judge whether the interaction score is lower than a preset interaction score threshold of the item; if yes, executing an interactive language clearing module, and if not, executing the clustering module 306;

The interactive language clearing module is configured to clear and clear the auditing group members containing the nonstandard vocabulary in the language publishing word stock in the project auditing group, wherein the interactive score is lower than the preset interactive score threshold value.

An embodiment of a computing device provided herein is as follows:

fig. 4 is a block diagram illustrating a configuration of a computing device 400 according to an embodiment of the present description. The components of the computing device 400 include, but are not limited to, a memory 410 and a processor 420. Processor 420 is coupled to memory 410 via bus 430 and database 450 is used to hold data.

Computing device 400 also includes access device 440, access device 440 enabling computing device 400 to communicate via one or more networks 460. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. The access device 440 may include one or more of any type of network interface, wired or wireless (e.g., a Network Interface Card (NIC)), such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.

In one embodiment of the present description, the above-described components of computing device 400, as well as other components not shown in FIG. 4, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device shown in FIG. 4 is for exemplary purposes only and is not intended to limit the scope of the present description. Those skilled in the art may add or replace other components as desired.

Computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smart phone), wearable computing device (e.g., smart watch, smart glasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 400 may also be a mobile or stationary server.

The present application provides a computing device comprising a memory 410, a processor 420, and computer instructions stored on the memory and executable on the processor, the processor 420 for executing computer executable instructions to:

Optionally, the audit behavior data includes at least one of the following:

auditing action behavior data and interaction behavior data;

wherein the audit action behavior data comprises at least one of:

the audit interactive behavior data comprises at least one of the following:

Optionally, the audit action score is calculated by the following method:

summing the first products of the project cases as the audit action scores.

Optionally, the interaction score is calculated in the following manner:

summing the second products of the project cases as the interaction score.

Acquiring the case auditing result data of the auditing group members;

wherein, the audit node behavior data comprises:

Optionally, the liveness score is calculated by the following method:

An embodiment of a computer readable storage medium provided in the present application is as follows:

embodiments of the present application also provide a computer readable storage medium storing computer instructions that, when executed by a processor, are configured to:

Optionally, the audit behavior data includes at least one of the following:

auditing action behavior data and interaction behavior data;

wherein the audit action behavior data comprises at least one of:

the audit interactive behavior data comprises at least one of the following:

Optionally, the audit action score is calculated by the following method:

summing the first products of the project cases as the audit action scores.

Optionally, the interaction score is calculated in the following manner:

summing the second products of the project cases as the interaction score.

Acquiring the case auditing result data of the auditing group members;

wherein, the audit node behavior data comprises:

Optionally, the liveness score is calculated by the following method:

The above is an exemplary version of a computer-readable storage medium of the present embodiment. It should be noted that, the technical solution of the storage medium and the technical solution of the above-mentioned auditing member evaluation method belong to the same concept, and the details of the technical solution of the storage medium which are not described in detail can be referred to the description of the technical solution of the above-mentioned auditing member evaluation method.

The computer instructions include computer program code that may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

It should be noted that, for the sake of simplicity of description, the foregoing method embodiments are all expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily all necessary for the present application.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.

The above-disclosed preferred embodiments of the present application are provided only as an aid to the elucidation of the present application. Alternative embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the application and the practical application, to thereby enable others skilled in the art to best understand and utilize the application. This application is to be limited only by the claims and the full scope and equivalents thereof.

Claims

1. A method of auditing group membership assessment, comprising:

obtaining auditing behavior data of auditing group members in an item aiming at auditing of the item cases in the running process of the item, wherein the auditing group members refer to auditing group members participating in the item;

clearing and backing the abnormal member in the project audit group to which the abnormal member belongs;

wherein, the audit action score is calculated by the following method:

Summing the first products of the project cases as the audit action scores.

2. The audit team member assessment method according to claim 1 wherein the audit behavioral data includes at least one of:

auditing action behavior data and interaction behavior data;

wherein the audit action behavior data comprises at least one of:

the audit interactive behavior data comprises at least one of the following:

3. The method of auditing team member assessment according to claim 1, wherein the interaction score is calculated by:

summing the second products of the project cases as the interaction score.

4. The method for evaluating members of an audit group according to claim 3, wherein clustering the members of the audit group based on the audit action scores, the interaction scores, and case audit result data of the members of the audit group, obtaining abnormal members of the audit group, comprises:

acquiring the case auditing result data of the auditing group members;

5. The method for evaluating an audit group member according to claim 3 wherein after said step of calculating audit action scores and interaction scores for project case audits by said audit group members based on said audit action data is performed, said step of clustering said audit group members based on said audit action scores, said interaction scores and case audit result data of said audit group members, prior to performing the step of obtaining abnormal members of said audit group members, comprises:

6. The method for evaluating an audit group member according to claim 3 wherein after said step of calculating audit action scores and interaction scores for project case audits by said audit group members based on said audit action data is performed, said step of clustering said audit group members based on said audit action scores, said interaction scores and case audit result data of said audit group members, prior to performing the step of obtaining abnormal members of said audit group members, comprises:

7. The method for evaluating an audit group member according to claim 3 wherein after said step of calculating audit action scores and interaction scores for project case audits by said audit group members based on said audit action data is performed, said step of clustering said audit group members based on said audit action scores, said interaction scores and case audit result data of said audit group members, prior to performing the step of obtaining abnormal members of said audit group members, comprises:

8. The method according to claim 1, wherein after the step of calculating the audit action score and the interaction score of the audit group member for the project case audit based on the audit behavior data is performed, the step of clustering the audit group members based on the audit action score, the interaction score, and the case audit result data of the audit group member, before the step of obtaining abnormal members among the audit group members is performed, includes:

Wherein, the audit node behavior data comprises:

9. The method of auditing group member assessment according to claim 8, wherein the liveness score is calculated by:

10. The method according to claim 1, wherein after the step of calculating the audit action score and the interaction score of the audit group member for the project case audit based on the audit behavior data is performed, the step of clustering the audit group members based on the audit action score, the interaction score, and the case audit result data of the audit group member, before the step of obtaining abnormal members among the audit group members is performed, includes:

11. The method for evaluating an audit group member according to claim 3 wherein after said step of calculating audit action scores and interaction scores for project case audits by said audit group members based on said audit action data is performed, said step of clustering said audit group members based on said audit action scores, said interaction scores and case audit result data of said audit group members, prior to performing the step of obtaining abnormal members of said audit group members, comprises:

12. An audit group membership evaluation device, comprising:

the system comprises an acquisition module, a verification module and a verification module, wherein the acquisition module is configured to acquire verification behavior data of a verification group member in a project aiming at project case verification in the running process of the project, and the verification group member refers to a verification group member participating in the project;

The clearing module is configured to clear the abnormal member in the project audit group to which the abnormal member belongs;

wherein, the audit action score is calculated by the following method:

summing the first products of the project cases as the audit action scores.

13. A computing device, comprising:

a memory and a processor;

wherein, the audit action score is calculated by the following method:

summing the first products of the project cases as the audit action scores.

14. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 11.