A business risk control method, device, equipment and storage medium thereof

Abstract

The embodiment of the present application belongs to the field of artificial intelligence technology, and is applied to the recruitment interview and claims settlement scenario. It involves a business risk control method, device, equipment and storage medium thereof, which obtains the character portrait information, expected job treatment information and submitted recruitment position information of the target object; uses the character portrait information and job treatment information as the test matching data; obtains all the preliminary screening recruitment positions output by the job recommendation matching model according to the test matching data and the job matching degree corresponding to each preliminary screening recruitment position; performs clustering processing; identifies the clustering processing result to which the recruitment position information submitted by the target object belongs, and generates an interview result claim form in combination with the claim form generation strategy. By extending the claim settlement business to the recruitment application scenario, the application prediction result can be obtained by combining the character portrait information and the expected job treatment information, and the interview result claim form is generated based on the application prediction result, thus avoiding blind underwriting on the application risk.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and is applied in recruitment, interview and claims settlement scenarios, and in particular to a business risk control method, apparatus, device and storage medium thereof. Background Art

[0002] Currently, automated recognition and classification technology for claims systems has become a hot research area. Current AI assistants for claims systems are primarily implemented through manually written rules and algorithms, resulting in low efficiency and accuracy.

[0003] Currently, AI-based comprehensive interview evaluation algorithms are extremely scarce. This is primarily due to the fact that most companies still rely on the traditional recruitment model of manually reviewing and screening resumes, followed by preliminary interviews via phone calls. Major job search websites screen resumes through intelligent job matching, which uses information such as the person's and company's attributes and tags to calculate the match between the applicant and the position. Insurance companies that underwrite interview results based solely on intelligent job matching face significant claims risks. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to propose a business risk control method, device, equipment and storage medium thereof to solve the problem that when underwriting interview results, the insurance is only based on intelligent job matching, and there is still a large risk of claims.

[0005] In order to solve the above technical problems, the embodiments of the present application provide a business risk control method, which adopts the following technical solutions:

[0006] A business risk control method comprises the following steps:

[0007] Obtain the target object's character portrait information;

[0008] Obtaining the job remuneration information expected by the target object;

[0009] Obtaining the recruitment information submitted by the target object;

[0010] Input the character portrait information and the job remuneration information as test matching data into the trained job recommendation matching model;

[0011] Obtaining all the preliminary screening recruitment positions output by the trained position recommendation matching model based on the test matching data and the position matching degree corresponding to each preliminary screening recruitment position;

[0012] Use the preset clustering algorithm to cluster the initial screening recruitment positions with different job matching degrees to obtain the clustering results;

[0013] Identify the clustering processing results to which the recruitment position information submitted by the target object belongs, and obtain the application prediction results based on the clustering processing results;

[0014] Generate an interview result claim form based on the application prediction results and a preset claim form generation strategy.

[0015] Furthermore, the step of obtaining the target object's character portrait information specifically includes:

[0016] By extracting text information from the interview resume document submitted by the target object, the target object's work skills, work experience, educational background, age information, and personality information are obtained;

[0017] The target object's work skills, work experience, educational background, age information, and personality information are used as the character portrait information;

[0018] The step of obtaining the job remuneration information expected by the target object specifically includes:

[0019] By extracting text information from the interview resume document submitted by the target object, the salary information and company benefits information required by the target object are obtained;

[0020] The salary information and company benefits information required by the target object are used as the target object's expected job benefits information;

[0021] The step of obtaining the recruitment position information submitted by the target object specifically includes:

[0022] Identify the job title submitted by the target subject based on the delivery direction of the interview resume document submitted by the target subject;

[0023] The recruitment position name is used as the recruitment position information.

[0024] Furthermore, before executing the step of inputting the character portrait information and the job remuneration information as test matching data into the trained job recommendation matching model, the method further includes:

[0025] Obtaining the full historical recruitment data from a preset recruitment platform, wherein the recruitment data includes the job titles and the corresponding candidate qualification information for all job titles, wherein the candidate qualification information includes the candidate's work skills, work experience, educational background, age information, and the salary and benefits information that the company can provide;

[0026] Classify and organize the examination qualification information corresponding to all recruitment positions according to the recruitment position names to obtain classification and organization results;

[0027] Establishing a correlation between the classification results and the recruitment position titles;

[0028] The classification and sorting results corresponding to different recruitment positions are input into the position recommendation matching model to be trained in batches, and the position recommendation matching model is trained so that the position recommendation matching model can learn the examination restriction condition information corresponding to different recruitment positions, and obtain a trained position recommendation matching model.

[0029] Furthermore, the step of obtaining all the preliminary screening recruitment positions output by the trained position recommendation matching model based on the test matching data and the position matching degree corresponding to each preliminary screening recruitment position specifically includes:

[0030] Using the test matching data as first comparison data;

[0031] Sequentially screening out information on test-taking restrictions corresponding to different recruitment positions from the trained position recommendation matching model as second comparison data;

[0032] Calculating the similarity between the second comparison data and the first comparison data using a preset similarity algorithm;

[0033] If the similarity exceeds a preset similarity threshold, the recruitment position corresponding to the second comparison data is marked as a preliminary screening recruitment position, and the similarity is set as the position matching degree of the preliminary screening recruitment position.

[0034] Furthermore, before executing the step of clustering the initially screened recruitment positions with different job matching degrees using a preset clustering algorithm to obtain clustering processing results, the method further includes:

[0035] Sort all the initially screened recruitment positions according to the principle of job matching from high to low to obtain a sorting sequence;

[0036] The step of using a preset clustering algorithm to cluster the initially screened recruitment positions with different job matching degrees to obtain clustering processing results specifically includes:

[0037] Selecting the first initial screening recruitment position from the sorting sequence as the initial center point of the cluster;

[0038] Clustering the pre-screened recruitment positions included in the sorted sequence in sequence from the initial cluster center using a K-nearest neighbor algorithm, and setting a success priority for each clustering result according to the order of clustering, wherein the success priority of an earlier clustering result is higher than the success priority of a later clustering result. The K value in the K-nearest neighbor algorithm represents the number of pre-screened recruitment positions in each clustering result.

[0039] After executing the step of clustering the initially screened recruitment positions with different job matching degrees using a preset clustering algorithm and obtaining clustering processing results, the method further includes:

[0040] According to the application success priority corresponding to each clustering processing result, the application success priority corresponding to all the initial screening recruitment positions is determined.

[0041] Furthermore, before executing the step of identifying the clustering processing result to which the recruitment position information submitted by the target object belongs and obtaining the application prediction result based on the clustering processing result, the method further includes:

[0042] Obtain the application success confidence values ​​pre-set for different application success priorities;

[0043] The step of identifying the clustering processing result to which the recruitment position information submitted by the target object belongs, and obtaining the application prediction result based on the clustering processing result, specifically includes:

[0044] Identify the clustering processing result to which the recruitment position information submitted by the target object belongs as the target clustering processing result;

[0045] Obtaining a corresponding confidence value of successful application according to the successful application priority corresponding to the target clustering processing result;

[0046] The corresponding application success confidence value is set as the application prediction result of the recruitment position information submitted by the target object.

[0047] Furthermore, before executing the step of generating the interview result claim form based on the application prediction result and the preset claim form generation strategy, the method further includes:

[0048] Based on the full historical recruitment data in the recruitment platform, the actual recruitment confidence of the job posting submitted by the target object is identified, wherein the actual recruitment confidence is determined by the ratio of the number of successful interviews for the job posting published by the target company to the total number of interviews. If the ratio does not exceed the set ratio threshold, the actual recruitment confidence is 0; if the ratio exceeds the set ratio threshold, the actual recruitment confidence is 1;

[0049] The step of generating an interview result claim form based on the application prediction result and a preset claim form generation strategy includes:

[0050] If the actual recruitment confidence is 0, an interview result claim form is generated according to the application prediction result and a preset claim form generation strategy, wherein the preset claim form generation strategy includes: regardless of whether the application success confidence value corresponding to the application prediction result is high or low, as long as the actual recruitment confidence is 0, the interview failure claim amount set in the interview result claim form is lower;

[0051] The step of generating the interview result claim form based on the application prediction result and the preset claim form generation strategy also includes:

[0052] If the actual recruitment confidence is 1, an interview result claim form is generated based on the application prediction result and the preset claim form generation strategy, wherein the preset claim form generation strategy includes: if the actual recruitment confidence is 1, the higher the application success confidence value corresponding to the application prediction result, the higher the interview failure claim amount set in the interview result claim form.

[0053] In order to solve the above technical problems, the embodiment of the present application also provides a business risk control device, which adopts the following technical solutions:

[0054] A business risk control device, comprising:

[0055] A character portrait information acquisition module is used to obtain character portrait information of the target object;

[0056] A job benefits information acquisition module is used to acquire the job benefits information expected by the target object;

[0057] A recruitment position information acquisition module is used to obtain the recruitment position information submitted by the target object;

[0058] A model input module is used to input the character portrait information and the job remuneration information as test matching data into the trained job recommendation matching model;

[0059] A model output module is used to obtain all the preliminary screening recruitment positions output by the trained position recommendation matching model based on the test matching data and the position matching degree corresponding to each preliminary screening recruitment position;

[0060] The clustering processing module is used to perform clustering processing on the initial screening recruitment positions with different job matching degrees using a preset clustering algorithm to obtain clustering processing results;

[0061] An application prediction result obtaining module is used to identify the clustering processing result to which the recruitment position information submitted by the target object belongs, and obtain an application prediction result based on the clustering processing result;

[0062] The interview result claim form generation module is used to generate an interview result claim form based on the application prediction results and a preset claim form generation strategy.

[0063] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0064] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the business risk control method described above when executing the computer-readable instructions.

[0065] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0066] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the business risk control method as described above.

[0067] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0068] The business risk control method described in the embodiment of the present application obtains the character portrait information, expected job treatment information and submitted recruitment position information of the target object; uses the character portrait information and job treatment information as test matching data; obtains all the preliminary screening recruitment positions output by the trained job recommendation matching model based on the test matching data and the job matching degree corresponding to each preliminary screening recruitment position; clusters the preliminary screening recruitment positions with different job matching degrees; identifies the clustering processing results to which the recruitment position information submitted by the target object belongs, and obtains the application prediction results based on the clustering processing results, and generates an interview result claim form in combination with the claim form generation strategy. The business risk control method described in the present application can extend the claims business to the recruitment application scenario, and can obtain the application prediction results in combination with the character portrait information, expected job treatment information and submitted recruitment position information, and generate an interview result claim form based on the application prediction results, thereby avoiding blind underwriting by the underwriter and reducing corporate losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0070] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0071] Figure 2 This is a flow chart of an embodiment of a business risk control method according to the present application;

[0072] Figure 3 This is a flowchart of a specific embodiment of training a job recommendation matching model in the business risk control method described in this application;

[0073] Figure 4 yes Figure 2 A flowchart of a specific embodiment of step 205 is shown;

[0074] Figure 5 yes Figure 2 A flowchart of a specific embodiment of step 207 is shown;

[0075] Figure 6 This is a schematic diagram of the structure of an embodiment of a business risk control device according to the present application;

[0076] Figure 7 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0077] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0078] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0079] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0080] like Figure 1 As shown, system architecture 100 may include a terminal device 101, a network 102, and a server 103. Terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. Network 102 is a medium for providing a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0081] The user can use the terminal device 101 to interact with the server 103 via the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0082] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer and a desktop computer, etc.

[0083] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0084] It should be noted that the business risk control method provided in the embodiments of the present application is generally executed by a terminal device, and accordingly, the business risk control device is generally set in the terminal device.

[0085] It should be understood that Figure 1The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0086] Continue to refer Figure 2 , shows a flow chart of an embodiment of a business risk control method according to the present application. The business risk control method includes the following steps:

[0087] Step 201, obtaining the character portrait information of the target object;

[0088] Specifically, the character portrait information of the target object refers to the multi-dimensional representation data of the target object. Depending on the application scenario, the multi-dimensional representation data contained in the character portrait information is also different.

[0089] Step 202: Obtain the job remuneration information desired by the target object;

[0090] Specifically, the job remuneration information expected by the target object generally includes salary information, company welfare information, five insurances and one fund information, holiday rest information, etc.

[0091] Step 203: Obtain the job posting information submitted by the target object;

[0092] Specifically, the job information submitted by the target object should basically include the job title, the restrictive conditions set by the recruiter, and job description information.

[0093] Step 204: Input the character portrait information and the job remuneration information as test matching data into the trained job recommendation matching model;

[0094] Step 205: Obtain all the preliminary screening recruitment positions output by the trained position recommendation matching model based on the test matching data and the position matching degree corresponding to each preliminary screening recruitment position;

[0095] The trained job recommendation matching model is used to conduct an initial screening of recruitment positions, and the job matching degree corresponding to each initially screened recruitment position is obtained, so as to facilitate the subsequent prediction of the probability of passing the interview.

[0096] Step 206: clustering the initially screened recruitment positions with different job matching degrees using a preset clustering algorithm to obtain clustering results;

[0097] Step 207: Identify the clustering processing result to which the recruitment position information submitted by the target object belongs, and obtain the application prediction result based on the clustering processing result;

[0098] Step 208: Generate an interview result claim form based on the application prediction result and a preset claim form generation strategy.

[0099] In this embodiment, by obtaining the character portrait information, expected job benefit information and submitted recruitment position information of the target object; using the character portrait information and job benefit information as test matching data; obtaining all the preliminary screening recruitment positions output by the trained job recommendation matching model based on the test matching data and the job matching degree corresponding to each preliminary screening recruitment position; clustering processing is performed on the preliminary screening recruitment positions with different job matching degrees; identifying the clustering processing result to which the recruitment position information submitted by the target object belongs, and obtaining the application prediction result based on the clustering processing result, and generating an interview result claim form in combination with the claim form generation strategy. The business risk control method described in this application can extend the claims business to the recruitment application scenario, and can obtain the application prediction result in combination with the character portrait information, expected job benefit information and submitted recruitment position information, and generate an interview result claim form based on the application prediction result, thereby avoiding blind underwriting by the underwriter and reducing corporate losses.

[0100] In this embodiment, the step of obtaining the character portrait information of the target object specifically includes: extracting text information from the interview resume document submitted by the target object to obtain the target object's work skills, work experience, educational background, age information, and personality information; and using the target object's work skills, work experience, educational background, age information, and personality information as the character portrait information.

[0101] In this embodiment, the step of obtaining the job benefit information expected by the target object specifically includes: extracting text information from the interview resume document submitted by the target object to obtain the salary information and company welfare benefit information required by the target object; and using the salary information and company welfare benefit information required by the target object as the job benefit information expected by the target object.

[0102] In this embodiment, the step of obtaining the recruitment position information submitted by the target object specifically includes: identifying the recruitment position name submitted by the target object based on the delivery direction of the interview resume document submitted by the target object; and using the recruitment position name as the recruitment position information.

[0103] Continue to refer Figure 3 In some optional implementations, before executing step 204, a step of training a job recommendation matching model is also included. Figure 3 This is a flowchart of a specific embodiment of training a job recommendation matching model in the business risk control method described in this application, including the following steps:

[0104] Step 301: Obtaining the entire historical recruitment data from a preset recruitment platform, wherein the recruitment data includes the job titles and the corresponding candidate qualification information for all job titles, wherein the candidate qualification information includes the candidate's work skills, work experience, educational background, age information, and the salary and benefits information that the company can provide;

[0105] Step 302: Classify and sort the examination qualification information corresponding to all recruitment positions according to the recruitment position names to obtain classification and sorting results;

[0106] Step 303: Constructing a correlation between the classification results and the job titles;

[0107] In step 304, the classification and sorting results corresponding to different recruitment positions are input into the position recommendation matching model to be trained in batches, and the position recommendation matching model is trained so that the position recommendation matching model can learn the examination restriction condition information corresponding to different recruitment positions, thereby obtaining a trained position recommendation matching model.

[0108] By adopting machine learning methods and combining the historical full recruitment data in the preset recruitment platform to train the job recommendation matching model, the job recommendation matching model can learn the test restriction condition information corresponding to different recruitment positions, so that in subsequent actual use, a certain number of recruitment positions that meet the requirements can be directly screened out based on the test matching data, which is more intelligent and automated.

[0109] Continue to refer Figure 4 , in some optional implementations, Figure 4 yes Figure 2 The flowchart of a specific embodiment of step 205 shown includes the following steps:

[0110] Step 401: using the test matching data as first comparison data;

[0111] Step 402: sequentially filter out the test qualification information corresponding to different recruitment positions from the trained position recommendation matching model as second comparison data;

[0112] Step 403: Calculate the similarity between the second comparison data and the first comparison data using a preset similarity algorithm;

[0113] Specifically, the similarity algorithm, such as a cosine similarity algorithm, is used to calculate the similarity between the second comparison data and the first comparison data using a preset similarity algorithm. This algorithm is then combined with a preset similarity threshold to perform a preliminary screening of recruitment positions, thereby ensuring that the initially screened recruitment positions have a high degree of relevance to the target candidates.

[0114] Step 404: If the similarity exceeds a preset similarity threshold, the recruitment position corresponding to the second comparison data is marked as a preliminary screening recruitment position, and the similarity is set as the position matching degree of the preliminary screening recruitment position.

[0115] By setting the similarity as the job matching degree of the initially screened recruitment positions, the initial recruitment positions can be clustered according to the job matching degrees.

[0116] In this embodiment, before executing the step of clustering the initial screening recruitment positions with different job matching degrees using a preset clustering algorithm and obtaining the clustering processing results, the method also includes: sorting all the initial screening recruitment positions according to the principle of job matching degree from high to low to obtain a sorting sequence.

[0117] All the initially screened recruitment positions are sorted from high to low according to the principle of job matching degree to obtain a sorting sequence, so that when clustering is performed later, clustering can be performed directly from the sorting sequence according to the sequence position, which is faster than random clustering.

[0118] In this embodiment, the step of using a preset clustering algorithm to cluster the preliminary screening recruitment positions with different job matching degrees to obtain the clustering processing results specifically includes: selecting the first preliminary screening recruitment position from the sorting sequence as the initial center point of the cluster; using the K-nearest neighbor algorithm to cluster the preliminary screening recruitment positions included in the sorting sequence from the initial center point of the cluster, and setting the application success priority for each clustering processing result according to the clustering order, wherein the application success priority of the earlier clustering processing result is higher than the application success priority of the later clustering processing result, and the K value in the K-nearest neighbor algorithm represents the number of preliminary screening recruitment positions in each clustering processing result.

[0119] Specifically, for example: if the K value is 6, the first 6 preliminary screening recruitment positions are obtained from the first position in the sorting sequence for clustering, and then the 7th to 12th preliminary screening recruitment positions in the sorting sequence are selected for clustering, and so on, until all the preliminary screening recruitment positions in the sorting sequence are clustered, and the clustering is completed.

[0120] If the number of initial screening recruitment positions remaining in the sorting sequence is less than K, they are clustered into one category.

[0121] The K-nearest neighbor algorithm is used to cluster the initial screening recruitment positions contained in the sorting sequence from the initial center point of the cluster. Clustering is combined with the sorting sequence, which is faster and can set the application success priority for different clustering results in combination with the sorting sequence, which is convenient for subsequent application result prediction.

[0122] In this embodiment, after executing the step of clustering the initial screening recruitment positions with different job matching degrees using a preset clustering algorithm and obtaining the clustering processing results, the method also includes: determining the application success priorities corresponding to all initial screening recruitment positions based on the application success priority corresponding to each clustering processing result.

[0123] In this embodiment, before executing the step of identifying the clustering processing results to which the recruitment position information submitted by the target object belongs and obtaining the application prediction results based on the clustering processing results, the method also includes: obtaining the application success confidence values ​​pre-set for different application success priorities.

[0124] Specifically, the higher the priority of a successful application, the greater the confidence value of the successful application set for it.

[0125] Continue to refer Figure 5 , in some optional implementations, Figure 5 yes Figure 2 The flowchart of a specific embodiment of step 207 shown includes the following steps:

[0126] Step 501: Identify the clustering processing result to which the recruitment position information submitted by the target object belongs as the target clustering processing result;

[0127] Step 502: Obtain a corresponding confidence value of successful application based on the successful application priority corresponding to the target clustering processing result;

[0128] Step 503: Set the corresponding application success confidence value as the application prediction result of the recruitment position information submitted by the target object.

[0129] Specifically, the confidence value of successful application may be a probability value or a probability value corresponding to successful application, and its value is within the interval range of (0, 1).

[0130] In this embodiment, before executing the step of generating the interview result claim form according to the application prediction result and the preset claim form generation strategy, the method further includes: identifying the actual recruitment confidence of the recruitment position information submitted by the target object based on the historical full recruitment data in the recruitment platform, wherein the actual recruitment confidence is determined by the ratio of the number of successful interviews for the recruitment position information published by the target company to the total number of interviews. If the ratio does not exceed the set ratio threshold, the actual recruitment confidence is 0; if the ratio exceeds the set ratio threshold, the actual recruitment confidence is 1;

[0131] Specifically, by identifying the actual recruitment confidence of the recruitment position information submitted by the target object, it is convenient for auxiliary insurance institutions to identify situations where there are long-term recruitments but no actual job vacancies, so as to avoid interview underwriting risks.

[0132] In this embodiment, the step of generating an interview result claim form based on the application prediction result and the preset claim form generation strategy includes: if the actual recruitment confidence is 0, generating an interview result claim form based on the application prediction result and the preset claim form generation strategy, wherein the preset claim form generation strategy includes: regardless of whether the application success confidence value corresponding to the application prediction result is high or low, as long as the actual recruitment confidence is 0, the interview failure claim amount set in the interview result claim form is lower.

[0133] In this case, that is, the interviewing company has no shortage of people or no positions, the high or low confidence value of the successful application has little correlation with the interview result. Even if all conditions are met, the candidate will not be hired. Therefore, the lower the interview failure claim amount set in the interview result claim form.

[0134] In this embodiment, the step of generating an interview result claim form based on the application prediction result and the preset claim form generation strategy also includes: if the actual recruitment confidence is 1, generating an interview result claim form based on the application prediction result and the preset claim form generation strategy, wherein the preset claim form generation strategy includes: if the actual recruitment confidence is 1, the higher the application success confidence value corresponding to the application prediction result, the higher the interview failure claim amount set in the interview result claim form.

[0135] In this case, that is, the interviewing company is truly short of people or has job vacancies, the higher the confidence value of successful application, the easier it is to be hired. Therefore, the interview failure claim amount set in the interview result claim form is positively correlated with the successful application confidence value.

[0136] This application obtains the character portrait information, expected job treatment information and submitted recruitment position information of the target object; uses the character portrait information and job treatment information as test matching data; obtains all the preliminary screening recruitment positions output by the trained job recommendation matching model based on the test matching data and the job matching degree corresponding to each preliminary screening recruitment position; clusters the preliminary screening recruitment positions with different job matching degrees; identifies the clustering processing results to which the recruitment position information submitted by the target object belongs, and obtains the application prediction results based on the clustering processing results, and generates an interview result claim form in combination with the claim form generation strategy. The business risk control method described in this application can extend the claims business to the recruitment application scenario, and can obtain the application prediction results in combination with the character portrait information, expected job treatment information and submitted recruitment position information, and generate an interview result claim form based on the application prediction results, thereby avoiding blind underwriting by the underwriter and reducing corporate losses.

[0137] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0138] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0139] In the embodiment of the present application, by obtaining the character portrait information, expected job treatment information and submitted recruitment position information of the target object; using the character portrait information and job treatment information as the test matching data; obtaining all the preliminary screening recruitment positions output by the trained job recommendation matching model according to the test matching data and the job matching degree corresponding to each preliminary screening recruitment position; clustering processing is performed on the preliminary screening recruitment positions with different job matching degrees; identifying the clustering processing result to which the recruitment position information submitted by the target object belongs, and obtaining the application prediction result based on the clustering processing result, and generating the interview result claim form in combination with the claim form generation strategy. The business risk control method described in the present application can extend the claims business to the recruitment application scenario, can combine the character portrait information, expected job treatment information and submitted recruitment position information to obtain the application prediction result, and generate the interview result claim form according to the application prediction result, thereby avoiding the blind underwriting of the underwriter and reducing the loss of the enterprise.

[0140] Further references Figure 6 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a business risk control device. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0141] like Figure 6 As shown, the business risk control device 600 of this embodiment includes: a character portrait information acquisition module 601, a job remuneration information acquisition module 602, a recruitment position information acquisition module 603, a model input module 604, a model output module 605, a clustering processing module 606, a job application prediction result acquisition module 607, and an interview result claim form generation module 608. Among them:

[0142] Character portrait information acquisition module 601, used to acquire character portrait information of a target object;

[0143] The job remuneration information acquisition module 602 is used to obtain the job remuneration information expected by the target object;

[0144] Recruitment position information acquisition module 603, used to obtain the recruitment position information submitted by the target object;

[0145] The model input module 604 is used to input the character portrait information and the job remuneration information as test matching data into the trained job recommendation matching model;

[0146] The model output module 605 is used to obtain all the preliminary recruitment positions output by the trained position recommendation matching model based on the test matching data and the position matching degree corresponding to each preliminary recruitment position;

[0147] The clustering processing module 606 is used to perform clustering processing on the initial screening recruitment positions with different job matching degrees using a preset clustering algorithm to obtain clustering processing results;

[0148] The application prediction result obtaining module 607 is used to identify the clustering processing result to which the recruitment position information submitted by the target object belongs, and obtain the application prediction result based on the clustering processing result;

[0149] The interview result claim form generation module 608 is used to generate an interview result claim form based on the application prediction result and a preset claim form generation strategy.

[0150] This application obtains the character portrait information, expected job treatment information and submitted recruitment position information of the target object; uses the character portrait information and job treatment information as test matching data; obtains all the preliminary screening recruitment positions output by the trained job recommendation matching model based on the test matching data and the job matching degree corresponding to each preliminary screening recruitment position; clusters the preliminary screening recruitment positions with different job matching degrees; identifies the clustering processing results to which the recruitment position information submitted by the target object belongs, and obtains the application prediction results based on the clustering processing results, and generates an interview result claim form in combination with the claim form generation strategy. The business risk control method described in this application can extend the claims business to the recruitment application scenario, and can obtain the application prediction results in combination with the character portrait information, expected job treatment information and submitted recruitment position information, and generate an interview result claim form based on the application prediction results, thereby avoiding blind underwriting by the underwriter and reducing corporate losses.

[0151] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware using computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium. When executed, the program can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0152] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0153] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of the computer device in this embodiment.

[0154] The computer device 7 includes a memory 7a, a processor 7b, and a network interface 7c that are interconnected via a system bus. Figure 7Only a computer device 7 having components memory 7a, processor 7b, and network interface 7c is shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art will understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0155] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0156] The memory 7a includes at least one type of readable storage medium, including flash memory, a hard disk, a multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, a magnetic disk, an optical disk, etc. In some embodiments, the memory 7a may be an internal storage unit of the computer device 7, such as the hard disk or internal memory of the computer device 7. In other embodiments, the memory 7a may also be an external storage device of the computer device 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash memory card, etc. Of course, the memory 7a may also include both the internal storage unit of the computer device 7 and its external storage device. In this embodiment, the memory 7a is typically used to store the operating system and various application software installed on the computer device 7, such as computer-readable instructions for a business risk control method. In addition, the memory 7a can also be used to temporarily store various types of data that have been output or are to be output.

[0157] In some embodiments, the processor 7b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 7b is typically used to control the overall operation of the computer device 7. In this embodiment, the processor 7b is used to execute computer-readable instructions stored in the memory 7a or process data, such as computer-readable instructions for executing the business risk control method.

[0158] The network interface 7c may include a wireless network interface or a wired network interface. The network interface 7c is generally used to establish a communication connection between the computer device 7 and other electronic devices.

[0159] The computer device proposed in this embodiment belongs to the field of artificial intelligence technology and is applied to recruitment interview and claims scenarios. This application obtains the character portrait information, expected job treatment information and submitted recruitment position information of the target object; uses the character portrait information and job treatment information as test matching data; obtains all the preliminary screening recruitment positions output by the trained job recommendation matching model based on the test matching data and the job matching degree corresponding to each preliminary screening recruitment position; clusters the preliminary screening recruitment positions with different job matching degrees; identifies the clustering processing results to which the recruitment position information submitted by the target object belongs, and obtains the application prediction results based on the clustering processing results, and generates the interview result claim form in combination with the claim form generation strategy. The business risk control method described in this application can extend the claims business to the recruitment application scenario, and can obtain the application prediction results in combination with the character portrait information, expected job treatment information and submitted recruitment position information, and generate the interview result claim form based on the application prediction results, thereby avoiding blind underwriting by the underwriter and reducing corporate losses.

[0160] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the business risk control method as described above.

[0161] The computer-readable storage medium proposed in this embodiment belongs to the field of artificial intelligence technology and is applied to recruitment interview and claims scenarios. This application obtains the character portrait information, expected job treatment information and submitted recruitment position information of the target object; uses the character portrait information and job treatment information as test matching data; obtains all the preliminary screening recruitment positions output by the trained job recommendation matching model based on the test matching data and the job matching degree corresponding to each preliminary screening recruitment position; clusters the preliminary screening recruitment positions with different job matching degrees; identifies the clustering processing results to which the recruitment position information submitted by the target object belongs, and obtains the application prediction results based on the clustering processing results, and generates the interview result claim form in combination with the claim form generation strategy. The business risk control method described in this application can extend the claims business to the recruitment application scenario, and can obtain the application prediction results in combination with the character portrait information, expected job treatment information and submitted recruitment position information, and generate the interview result claim form based on the application prediction results, thereby avoiding blind underwriting by the underwriter and reducing corporate losses.

[0162] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of this application, or the part that contributes to the existing technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of this application.

[0163] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present application specification and the accompanying drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present application.

Claims

1. A business risk control method, characterized in that: The steps include: Obtain the target object's character portrait information; Obtaining the job remuneration information expected by the target object; Obtaining the recruitment information submitted by the target object; Inputting the character portrait information and the job remuneration information as test matching data into a trained job recommendation matching model, wherein, before executing the step of inputting the character portrait information and the job remuneration information as test matching data into the trained job recommendation matching model, the method further includes: Obtaining the full historical recruitment data from a preset recruitment platform, wherein the recruitment data includes the job titles and the corresponding candidate qualification information for all job titles, wherein the candidate qualification information includes the candidate's work skills, work experience, educational background, age information, and the salary and benefits information that the company can provide; Classify and organize the examination qualification information corresponding to all recruitment positions according to the recruitment position names to obtain classification and organization results; Establishing a correlation between the classification results and the recruitment position titles; Inputting the classification and sorting results corresponding to different recruitment positions into the position recommendation matching model to be trained in batches, training the position recommendation matching model so that the position recommendation matching model learns the test-restriction condition information corresponding to different recruitment positions, and obtaining a trained position recommendation matching model; Obtaining all the preliminary screening recruitment positions output by the trained position recommendation matching model based on the test matching data and the position matching degree corresponding to each preliminary screening recruitment position; Use the preset clustering algorithm to cluster the initial screening recruitment positions with different job matching degrees to obtain the clustering results; Identify the clustering processing results to which the recruitment position information submitted by the target object belongs, and obtain the application prediction results based on the clustering processing results; Generate an interview result claim form based on the application prediction results and a preset claim form generation strategy.

2. The business risk control method according to claim 1, characterized in that: The step of obtaining the target object's character portrait information specifically includes: By extracting text information from the interview resume document submitted by the target object, the target object's work skills, work experience, educational background, age information, and personality information are obtained; The target object's work skills, work experience, educational background, age information, and personality information are used as the character portrait information; The step of obtaining the job remuneration information expected by the target object specifically includes: By extracting text information from the interview resume document submitted by the target object, the salary information and company benefits information required by the target object are obtained; The salary information and company benefits information required by the target object are used as the target object's expected job benefits information; The step of obtaining the recruitment position information submitted by the target object specifically includes: Identify the job title submitted by the target subject based on the delivery direction of the interview resume document submitted by the target subject; The recruitment position name is used as the recruitment position information.

3. The business risk control method according to claim 1, characterized in that: The step of obtaining all the initially screened recruitment positions output by the trained position recommendation matching model based on the test matching data and the position matching degree corresponding to each initially screened recruitment position specifically includes: Using the test matching data as first comparison data; Sequentially screening out information on test-taking restrictions corresponding to different recruitment positions from the trained position recommendation matching model as second comparison data; Calculating the similarity between the second comparison data and the first comparison data using a preset similarity algorithm; If the similarity exceeds a preset similarity threshold, the recruitment position corresponding to the second comparison data is marked as a preliminary screening recruitment position, and the similarity is set as the position matching degree of the preliminary screening recruitment position.

4. The business risk control method according to claim 1, characterized in that: Before executing the step of clustering the initially screened recruitment positions with different job matching degrees using a preset clustering algorithm to obtain clustering processing results, the method further includes: Sort all the initially screened recruitment positions according to the principle of job matching from high to low to obtain a sorting sequence; The step of using a preset clustering algorithm to cluster the initially screened recruitment positions with different job matching degrees to obtain clustering processing results specifically includes: Selecting the first initial screening recruitment position from the sorting sequence as the initial center point of the cluster; Clustering the pre-screened recruitment positions included in the sorted sequence in sequence from the initial cluster center using a K-nearest neighbor algorithm, and setting a success priority for each clustering result according to the order of clustering, wherein the success priority of an earlier clustering result is higher than the success priority of a later clustering result. The K value in the K-nearest neighbor algorithm represents the number of pre-screened recruitment positions in each clustering result. After executing the step of clustering the initially screened recruitment positions with different job matching degrees using a preset clustering algorithm and obtaining clustering processing results, the method further includes: According to the application success priority corresponding to each clustering processing result, the application success priority corresponding to all the initial screening recruitment positions is determined.

5. The business risk control method according to claim 4, characterized in that: Before executing the step of identifying the clustering processing result to which the recruitment position information submitted by the target object belongs and obtaining the application prediction result based on the clustering processing result, the method further includes: Obtain the application success confidence values ​​pre-set for different application success priorities; The step of identifying the clustering processing result to which the recruitment position information submitted by the target object belongs, and obtaining the application prediction result based on the clustering processing result, specifically includes: Identify the clustering processing result to which the recruitment position information submitted by the target object belongs as the target clustering processing result; Obtaining a corresponding confidence value of successful application according to the successful application priority corresponding to the target clustering processing result; The corresponding application success confidence value is set as the application prediction result of the recruitment position information submitted by the target object.

6. The business risk control method according to claim 5, characterized in that: Before executing the step of generating the interview result claim form based on the application prediction result and the preset claim form generation strategy, the method further includes: Based on the full historical recruitment data in the recruitment platform, the actual recruitment confidence of the job posting submitted by the target object is identified, wherein the actual recruitment confidence is determined by the ratio of the number of successful interviews for the job posting published by the target company to the total number of interviews. If the ratio does not exceed the set ratio threshold, the actual recruitment confidence is 0; if the ratio exceeds the set ratio threshold, the actual recruitment confidence is 1; The step of generating an interview result claim form based on the application prediction result and a preset claim form generation strategy includes: If the actual recruitment confidence is 0, an interview result claim form is generated according to the application prediction result and a preset claim form generation strategy, wherein the preset claim form generation strategy includes: regardless of whether the application success confidence value corresponding to the application prediction result is high or low, as long as the actual recruitment confidence is 0, the interview failure claim amount set in the interview result claim form is lower; The step of generating the interview result claim form based on the application prediction result and the preset claim form generation strategy also includes: If the actual recruitment confidence is 1, an interview result claim form is generated based on the application prediction result and the preset claim form generation strategy, wherein the preset claim form generation strategy includes: if the actual recruitment confidence is 1, the higher the application success confidence value corresponding to the application prediction result, the higher the interview failure claim amount set in the interview result claim form.

7. A business risk control device, characterized in that: The business risk control device is used to implement the steps of the business risk control method according to any one of claims 1 to 6, and the business risk control device includes: A character portrait information acquisition module is used to obtain character portrait information of the target object; A job benefits information acquisition module is used to acquire the job benefits information expected by the target object; A recruitment position information acquisition module is used to obtain the recruitment position information submitted by the target object; A model input module is configured to input the character portrait information and the job remuneration information as test matching data into a trained job recommendation matching model, wherein before executing the step of inputting the character portrait information and the job remuneration information as test matching data into the trained job recommendation matching model, the method further comprises: Obtaining the full historical recruitment data from a preset recruitment platform, wherein the recruitment data includes the job titles and the corresponding candidate qualification information for all job titles, wherein the candidate qualification information includes the candidate's work skills, work experience, educational background, age information, and the salary and benefits information that the company can provide; Classify and organize the examination qualification information corresponding to all recruitment positions according to the recruitment position names to obtain classification and organization results; Establishing a correlation between the classification results and the recruitment position titles; Inputting the classification and sorting results corresponding to different recruitment positions into the position recommendation matching model to be trained in batches, training the position recommendation matching model so that the position recommendation matching model learns the test-restriction condition information corresponding to different recruitment positions, and obtaining a trained position recommendation matching model; A model output module is used to obtain all the preliminary screening recruitment positions output by the trained position recommendation matching model based on the test matching data and the position matching degree corresponding to each preliminary screening recruitment position; The clustering processing module is used to perform clustering processing on the initial screening recruitment positions with different job matching degrees using a preset clustering algorithm to obtain clustering processing results; An application prediction result obtaining module is used to identify the clustering processing result to which the recruitment position information submitted by the target object belongs, and obtain an application prediction result based on the clustering processing result; The interview result claim form generation module is used to generate an interview result claim form based on the application prediction results and a preset claim form generation strategy.

8. A computer device, characterized in that: It includes a memory and a processor, the memory stores computer-readable instructions, and the processor implements the steps of the business risk control method according to any one of claims 1 to 6 when executing the computer-readable instructions.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the business risk control method according to any one of claims 1 to 6.

Images