Information matching evaluation system and method based on virtual HR agent

The initial screening and interview of applicants were carried out through virtual HR agents, and the final screening matching was performed in combination with personality test results, which solved the problems of low accuracy of person-position matching and insufficient resume authenticity in the existing technology, and achieved efficient and accurate recruitment matching .

CN118569824BActive Publication Date: 2024-11-15NAN JING SHU ZHI FU NENG KE JI YOU XIAN GONG SI
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411054503.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-15
Estimated Expiration
2044-08-02

AI Technical Summary

Technical Problem

The existing virtual HR assistants based on AI technology have problems such as low matching accuracy and insufficient resume authenticity in human-job matching, which cannot meet the needs of enterprises for accurate human-job matching and intelligent evaluation.

Method used

By constructing a virtual HR agent, the candidates are initially screened and interviewed, the resume score is corrected based on the interview results, and the final screening is performed in combination with the personality test results, and the matching algorithm is optimized to improve the matching accuracy.

Benefits of technology

It improves recruitment efficiency and matching accuracy, reduces the workload of HR, ensures accurate matching between candidates and positions, avoids the problem of insufficient resume authenticity, and corrects resume information through objective methods, reducing human subjectivity.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118569824B_ABST
    Figure CN118569824B_ABST
Patent Text Reader

Abstract

The present invention discloses an information matching evaluation system and method based on a virtual HR agent, and relates to the field of artificial intelligence technology, which includes: constructing a virtual HR role agent; setting job information of a recruitment position; obtaining a job application resume and extracting job application information; obtaining a preliminary screening resume and entering an interview based on a resume matching strategy configured by the virtual HR role agent; the virtual HR role agent interviews the applicant of the preliminary screening resume, obtains score data, and corrects the job application information based on the score data; obtains the applicant's personality test results and the corrected job application information, and obtains a final screening resume based on the virtual HR role agent; configures a feedback terminal, obtains feedback information based on the feedback terminal, and optimizes and adjusts the matching algorithm of the virtual HR role agent. The present invention can improve information matching during job application to achieve the effect of information-based job matching, effectively improve recruitment efficiency, and enhance recruitment fairness and objectivity.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more specifically to an information matching evaluation system and method based on a virtual HR agent. Background Art

[0002] With the rapid development of information technology, the field of human resource management is undergoing unprecedented changes. Traditional human resource management methods can no longer meet the needs of rapid development of enterprises, especially in the recruitment process. Faced with a large amount of job search information and complex job matching requirements, how to efficiently and accurately complete the matching of people and jobs has become a major challenge facing enterprises. In recent years, the rise of artificial intelligence technology has provided a new perspective and approach to solving this problem. Among them, the recruitment system based on intelligent agents has gradually become a hot spot for research and application.

[0003] At present, a number of virtual HR assistants based on AI technology have emerged in the market. They can assist HR personnel in completing daily resume screening work, greatly improving work efficiency. However, these virtual HR assistants still have many deficiencies in terms of intelligence and application depth, and cannot meet the urgent needs of enterprises for accurate job matching and intelligent evaluation. On the one hand, the matching degree of resumes is obtained only through matching between resumes and positions. The matching method is relatively simple and the accuracy of talent matching is not high; on the other hand, there are problems with the authenticity of the information in the resume, so the resumes matched in this way are uncertain, which will cause the problem of reduced accuracy.

[0004] The existing Chinese patent with publication number CN111737486A discloses a person-job matching method and storage device based on knowledge graph and deep learning, which includes: S101: storing the candidate resume, the best historical resume and recruitment information into the knowledge graph, and obtaining the first candidate resume feature, the second candidate resume feature, the best historical resume feature and the recruitment requirement feature according to the knowledge graph; S102: obtaining the matching degree of the candidate resume, and obtaining competitiveness analysis data through the second candidate resume feature and the recruitment requirement feature; S103: obtaining the satisfaction of the candidate resume and outputting the matching information of the candidate resume. The invention can replace manual measurement to measure whether a resume meets the recruitment requirements of the job and whether the HR at the enterprise end is satisfied with the resume, and can accurately and efficiently obtain the matching results of the resume and the position. The efficiency of resume screening and matching is high, which greatly reduces the time and energy of employers and job seekers, and improves the overall management level of enterprise personnel recruitment.

[0005] Although this method of constructing a resume knowledge graph and a recruitment knowledge graph can extract relevant information more directly, and combined with deep learning methods, it can extract relevant features for matching, output resume matching information and resume satisfaction, and efficiently obtain matching results between resumes and positions, thereby increasing matching efficiency. However, the problems raised in the background technology still exist. Due to the problem of insufficient authenticity of resumes, direct matching based on resumes may result in limited matching accuracy, and the method of matching only through resumes is relatively simple, and the reliability of resume screening needs to be improved. Summary of the invention

[0006] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an information matching and evaluation system and method based on a virtual HR agent, which can perform preliminary matching between the recruitment position requirements and the resume application information based on the virtual HR role agent to obtain preliminary screening resumes, and then modify the application information based on the interview results, and match it with the recruitment position requirements again to obtain final screening resumes.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] On the one hand, the present invention provides an information matching evaluation method based on a virtual HR agent, which specifically includes the following steps:

[0009] S1: Building a virtual HR role agent;

[0010] S2: Set the job information of the recruitment position;

[0011] S3: Get the resume of the applicant, traverse the resume and extract the application information;

[0012] S4: Based on the resume matching strategy configured by the virtual HR role agent, obtain the initial screening resume to enter the interview;

[0013] S5: the virtual HR role agent interviews the applicants whose resumes have been initially screened, obtains score data, and modifies the application information based on the score data;

[0014] S6: Obtain the personality test results and the corrected application information of the applicant, and obtain the final screening resume based on the virtual HR role agent;

[0015] S7: Configure a feedback terminal, obtain feedback information based on the feedback terminal, and optimize and adjust the matching algorithm of the virtual HR role agent based on the feedback information.

[0016] As a further improvement of the present invention, the job information includes initial screening recruitment requirements and final screening recruitment requirements, the application information includes initial screening application information and final screening application information, and the resume matching strategy specifically includes the following steps:

[0017] S41: the initial screening recruitment requirements include a recruitment element set, the initial screening application information includes an application element set, traversing the application element set and matching with the recruitment element set in sequence;

[0018] S42: Determine whether the application factor set matches the recruitment factor set; if the recruitment factor set does not match the application factor set, delete the application resume; if the recruitment factor set matches the application factor set, retain the application resume and determine whether the final screening application information matches the final screening recruitment requirements to obtain the initial screening resume.

[0019] As a further improvement of the present invention, the step of determining whether the final screening application information matches the final screening recruitment requirements to obtain the initial screening resume specifically includes the following steps:

[0020] S421: The final screening recruitment requirements include an intention element set, and an expected score is configured for the intention element set, and the expected score is composed of an expected score vector ;

[0021] S422: The final screening application information includes a screening element set. The screening element set is scored based on the virtual HR role agent to obtain the resume score of the screening element, and the resume score of the screening element is formed into a resume score vector ;

[0022] S423: Calculating the person-job matching degree based on the expected score vector and the resume score vector;

[0023] S424: configure the person-job matching threshold;

[0024] If the person-job matching degree is not less than the person-job matching degree threshold, the resume will be retained as a preliminary screening resume for interview;

[0025] When the person-job matching degree is less than the person-job matching degree threshold, the resume is deleted.

[0026] As a further improvement of the present invention, the calculation formula of the person-job matching degree is as follows:

[0027]

[0028] Among them, S represents the matching degree between people and positions; represents the expected score of the i-th element of the intention element set in the expected score vector; Represents the resume score of the i-th element in the screening element set in the resume score vector; Indicates the weight coefficient of the corresponding scoring item; Represents the limiting factor.

[0029] As a further improvement of the present invention, the score data is used to correct the resume score of the screening element set, the score data includes a professional score set, an ability score, and an expression score set, and the resume score of the screening element set includes a first screening element resume score, a second screening element resume score, a third screening element resume score, and a fourth screening element resume score. The correction method specifically includes:

[0030] The professional score set is used to correct the resume score of the first screening factor, the ability score is used to correct the resume score of the second screening factor, the expression score set is used to correct the resume score of the third screening factor, and the correction method of the resume score of the fourth screening factor is to assign a value to the resume score of the fourth screening factor.

[0031] As a further improvement of the present invention, the professional score set includes a first professional score and a second professional score, and the professional score set is used to modify the resume score of the first screening factor in a specific manner as follows:

[0032]

[0033] in, represents the revised resume score of the first screening factor, Indicates the first professional rating, represents the average score of the first major, Indicates the second professional score, represents the average score of the second major, Represents the resume score of the first screening factor, is the weight coefficient.

[0034] As a further improvement of the present invention, the specific manner in which the ability score is used to correct the resume score of the second screening factor is:

[0035]

[0036] in, represents the revised resume score of the second screening factor, Indicates ability rating, represents the average ability score, Represents the resume score of the second screening factor.

[0037] As a further improvement of the present invention, the expression score set includes a first expression score, a second expression score and a third expression score, and the specific manner in which the expression score set is used to modify the resume score of the third screening factor is:

[0038]

[0039] in, It represents the revised resume score of the third screening factor, represents the first expression score, represents the average of the first expression scores; represents the second expression score, represents the average of the second expression scores; represents the third expression rating score, represents the average score of the third expression, Indicates the resume score of the third screening factor, is the weight coefficient.

[0040] As a further improvement of the present invention, obtaining the final screening resume specifically includes the following steps:

[0041] S61: The position information also includes personality requirements. The personality requirements of the position information are encoded and added to the expected score vector to generate a new expected score vector. ,in, Indicates character requirement coding;

[0042] S62: Encode the obtained candidate personality test results and generate a new resume scoring vector with the revised resume scoring vector ,in Indicates the candidate's personality test result code;

[0043] S63: Calculate the final person-job matching degree based on the new expected score vector and the new resume score vector. The calculation formula is as follows:

[0044]

[0045] in, Indicates the final person-job matching degree, represents the expected score of the jth recruitment factor in the new expected score vector, represents the jth resume score in the new resume score vector, Indicates the weight coefficient of the corresponding scoring item;

[0046] S64: Arrange the final person-job matching degree from high to low, and select the top N matching items as the final screening resumes based on recruitment requirements.

[0047] In a second aspect, the present invention provides an information matching evaluation system based on a virtual HR agent, including a virtual HR construction module, a recruitment demand module, a resume management module, a resume initial screening module, a scoring correction module, a resume final screening module, and a feedback optimization module, wherein:

[0048] The virtual HR building module is used to build and manage virtual HR role agents and configure matching rules and parameters;

[0049] The recruitment requirements module is used to set recruitment position information, including initial screening recruitment requirements, final screening recruitment requirements and personality requirements;

[0050] The resume management module is used to manage the applicant's application information, including receiving, storing, and extracting the application information in the resume;

[0051] The resume screening module performs preliminary screening of the applicant resumes based on the resume matching strategy, which specifically includes a scoring vector unit and a resume matching unit, where:

[0052] The scoring vector unit is used to obtain the expected scoring vector and the resume scoring vector;

[0053] The resume matching unit is used to calculate the matching degree between people and positions;

[0054] The scoring correction module is used to obtain score data and correct the application information based on the score data to obtain a new resume scoring vector;

[0055] The resume final screening module is used to determine the final screening resume by combining the personality test results of the applicant and the new resume scoring vector;

[0056] The feedback optimization module obtains feedback information based on the feedback terminal, and optimizes and adjusts the matching algorithm of the virtual HR role agent based on the feedback information.

[0057] Beneficial effects of the present invention:

[0058] Through automated resume screening and preliminary screening processes, the workload of HR personnel has been greatly reduced and recruitment efficiency has been improved. The virtual HR role agent can quickly traverse a large number of application resumes and conduct preliminary screening based on preset matching strategies, effectively shortening the recruitment cycle.

[0059] The resume matching strategy based on the virtual HR role agent can more accurately evaluate the matching degree between applicants and recruitment positions by comprehensively considering the applicants' initial screening information (such as age, education, major, etc.) and final screening information (such as work experience, skills, etc.), and configuring the corresponding expected score vector; it can improve the information matching during the application process to achieve the effect of information-based job matching, which not only improves the accuracy of recruitment, but also helps companies find talents that are more suitable for job requirements;

[0060] After the initial screening, the virtual HR role agent interviews the applicants and modifies the resume scoring vector based on the interview scoring results. The interview score can be used to correct a certain inflated value in the resume. This step corrects the application information in the resume to avoid the problem of insufficient resume authenticity, and corrects it in an objective way, avoiding human subjectivity and further enhancing the accuracy of person-job matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 A flow chart of the information matching evaluation method based on virtual HR agent provided by the present invention;

[0062] Figure 2 A flowchart of obtaining a preliminary screening resume in the information matching evaluation method based on a virtual HR agent provided by the present invention;

[0063] Figure 3 A schematic diagram of the structure of the information matching evaluation system based on the virtual HR agent provided by the present invention;

[0064] Figure 4 An interactive schematic diagram of the information matching evaluation system based on the virtual HR agent provided by the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0067] In order to keep the following description of the embodiments of the present invention clear and concise, detailed descriptions of well-known functions and well-known components are omitted.

[0068] Example 1

[0069] refer to Figure 1 and Figure 2 As shown, the specific implementation of the information matching evaluation method based on the virtual HR agent of the present invention includes the following steps:

[0070] S1: Building a virtual HR role agent;

[0071] The virtual HR role agent collects a large-scale industry database of various recruitment scenarios, job descriptions, candidate resumes and interview feedback, parses the text information in the resumes through a natural language processing model, and uses historical recruitment data and machine learning algorithms to train the virtual HR role agent to identify the skills and experience of applicants. The virtual HR role agent integrates natural language processing, machine learning, and deep learning.

[0072] S2: Set the job information of the recruitment position;

[0073] The position information includes initial screening recruitment requirements, final screening recruitment requirements and personality requirements;

[0074] The initial screening recruitment requirements include a recruitment element set; the final screening recruitment requirements include an intention element set.

[0075] S3: Get the resume of the applicant, traverse the resume and extract the application information;

[0076] The application information includes initial screening application information and final screening application information;

[0077] The initial screening application information includes an application element set; the final screening application information includes a screening element set.

[0078] S4: Based on the resume matching strategy configured by the virtual HR role agent, obtain the initial screening resume and enter the interview.

[0079] The resume matching strategy specifically includes the following steps:

[0080] S41: traversing the application factor set and matching it with the recruitment factor set in sequence;

[0081] In this embodiment, the matching of the application factor set and the recruitment factor set specifically includes age matching, education matching and major matching; including the following matching logic rules:

[0082] If the age of the applicant does not exceed the recruitment requirements, the age matching requirement is met;

[0083] If the education level of the applicant resume meets or exceeds the recruitment requirements, the education level matching requirement is met. For example, if the second recruitment factor in the recruitment factor set requires a bachelor's degree, and the second application factor in the application factor set is a bachelor's degree or a master's degree, both meet the education level matching requirement;

[0084] The major of the application resume is determined through fuzzy matching. The major name is converted into a vector representation through Word2Vec, and the similarity between the major vector of the application resume and the required major vector is calculated; when the calculated similarity is greater than the preset threshold, the major matching requirements are met.

[0085] S42: Determine whether the application factor set matches the recruitment factor set; if the recruitment factor set does not match the application factor set, delete the application resume; if the recruitment factor set matches the application factor set, retain the application resume and determine whether the final screening application information matches the final screening recruitment requirements to obtain the initial screening resume.

[0086] The matching of the final screening recruitment requirements and the final screening application information specifically includes:

[0087] S421: configuring an expected score for the intention element set, and composing the expected score into an expected score vector ;

[0088] in, represents the expected score of the first intention factor, Indicates the expected score of the second intention factor, Expected score of the third intention factor, It indicates the expected score of the fourth intention factor;

[0089] In this embodiment, the expected score of the first intention factor is selected as the expected score of technical requirements, the expected score of the second intention factor is selected as the expected score of work experience requirements, the expected score of the third intention factor is selected as the expected score of communication ability requirements, and the expected score of the fourth intention factor is selected as the expected score of certificate qualifications.

[0090] S422: Scoring the screening factor set based on the virtual HR role agent and obtaining the resume scores of the screening factors, and composing the resume scores of the screening factors into a resume score vector ;

[0091] in, Represents the resume score of the first screening factor, Represents the resume score of the second screening factor, Indicates the resume score of the third screening factor, Represents the fourth screening factor, resume score.

[0092] The ways to get resume scores include:

[0093] The virtual HR role agent is configured with a keyword library, each keyword in the keyword library has its corresponding score, and the resume score of each screening element in the screening element set is obtained by matching each element in the screening element set in the final screening application information with the keyword in the keyword library, including the first screening element resume score, the second screening element resume score, the third screening element resume score and the fourth screening element resume score;

[0094] In this embodiment, the first screening factor resume scoring is selected as the technical ability resume scoring, the second screening factor resume scoring is selected as the work experience resume scoring, the third screening factor resume scoring is selected as the communication ability resume scoring, and the fourth screening factor resume scoring is selected as the certificate qualification resume scoring;

[0095] For example, if the keyword database includes "more than two years of relevant work experience", the corresponding score is 60 points; if "more than three years of relevant work experience", the corresponding score is 80 points; if the corresponding work experience in the application resume is "two years of work experience", the corresponding work experience resume score is 60 points;

[0096] The keyword library includes "Computer Level 2 Certificate", the corresponding score is 10 points, and "English Level 4", the corresponding score is 5 points. If the corresponding certificate qualifications in the application resume include "Computer Level 2 Certificate" and "English Level 4", the corresponding certificate qualification resume score is 15 points.

[0097] S423: Calculate the person-job matching degree based on the expected score vector and the resume score vector, and the formula is as follows:

[0098]

[0099] Among them, S represents the matching degree between people and positions. The closer the value is to 1, the higher the matching degree between people and positions. represents the expected score of the i-th recruitment requirement in the intention element set in the expected score vector; Represents the resume score of the i-th element in the screening element set in the resume score vector; Indicates the weight coefficient of the corresponding scoring item; Represents a limiting factor to ensure that the matching score is between 0 and 1.

[0100] S424: configuring a person-job matching threshold, wherein the person-job matching threshold is set according to recruitment requirements;

[0101] Compare the calculated person-job matching degree with the person-job matching degree;

[0102] If the person-job matching degree is not less than the person-job matching degree threshold, the resume will be retained for the interview;

[0103] When the person-job matching degree is less than the person-job matching degree threshold, the resume is deleted.

[0104] S5: The virtual HR role agent interviews the applicants whose resumes have been initially screened, obtains score data, and modifies the application information based on the score data.

[0105] The score data is used to modify the resume score of the screening element set, the score data includes a professional score set, an ability score, and an expression score set, the resume score of the screening element set includes a first screening element resume score, a second screening element resume score, a third screening element resume score, and a fourth screening element resume score, and the modification method specifically includes:

[0106] The professional score set is used to modify the resume score of the first screening factor, the ability score is used to modify the resume score of the second screening factor, the expression score set is used to modify the resume score of the third screening factor, and the modification method of the resume score of the fourth screening factor is assigned by the resume score of the fourth screening factor, that is, .

[0107] In this embodiment, the score data includes the applicant's professional knowledge interview score, professional skills interview score, job knowledge test interview score, communication and expression ability interview score, teamwork ability interview score, and logical thinking ability interview score;

[0108] The score data is obtained based on the video interview of the applicant by the virtual HR role agent; for example, by designing theoretical or practical knowledge test questions for the position, the applicant's mastery of the professional knowledge required for the position is directly measured, including multiple-choice questions, short-answer questions or case analysis, and the virtual HR role agent obtains the position knowledge test interview score based on the answers.

[0109] The professional score set includes a first professional score and a second professional score. The professional score set is used to correct the resume score of the first screening factor obtained based on the virtual HR role agent in the following specific manner:

[0110]

[0111] in, represents the revised resume score of the first screening factor, Indicates the first professional rating, It represents the average score of the first major, which is the ratio of the total score of the first major of all applicants to the total number of applicants. Indicates the second professional score, represents the average score of the second major, Indicates the resume score of the fourth application factor, is the weight coefficient, which is set based on experience;

[0112] In this embodiment, the resume score of the first screening factor is selected as the technical ability resume score, the first professional score included in the professional score set is selected as the professional knowledge interview score, and the second professional score is selected as the professional skills interview score.

[0113] The specific method of using the ability score to correct the resume score of the second screening factor obtained based on the virtual HR role agent is as follows:

[0114]

[0115] in, represents the revised resume score of the second screening factor, Indicates ability rating, represents the average ability score, Indicates the fifth application factor resume score;

[0116] In this embodiment, the second screening factor resume score is selected as the work experience resume score, and the ability score is selected as the job knowledge interview score.

[0117] The expression score set includes a first expression score, a second expression score and a third expression score. The specific method of using the expression score set to correct the resume score of the third screening factor obtained based on the virtual HR role agent is as follows:

[0118]

[0119] Among them, among them, It represents the revised resume score of the third screening factor, represents the first expression score, represents the average of the first expression scores; represents the second expression score, represents the average of the second expression scores; represents the third expression rating score, represents the average score of the third expression, Indicates the score of the fifth application factor, resume. is the weight coefficient, which is set based on experience;

[0120] In this embodiment, the third screening factor resume score is selected as the communication ability resume score, the first expression score is selected as the communication expression ability interview score, the second expression score is selected as the teamwork ability interview score, and the third expression score is selected as the logical thinking ability interview score.

[0121] S6: Obtain the applicant's personality test results and the revised final screening application information score, and obtain the final screening resume based on the virtual HR role agent.

[0122] Obtaining the final screening resume includes the following steps:

[0123] S61: Encode the personality requirements of the job information and add them to the final screening recruitment requirement score vector to generate a new expected score vector ,in, Indicates character requirement coding;

[0124] S62: Encode the obtained candidate personality test results and generate a new resume score vector from the revised final screening application information score vector ,in Indicates the result code of the candidate's personality test;

[0125] S63: Calculate the final person-job matching degree based on the new scoring vector and the new resume scoring vector. The calculation formula is as follows:

[0126]

[0127] in, Indicates the final person-job matching degree, represents the expected score of the jth recruitment factor in the new expected score vector, represents the jth resume score in the new resume score vector, Indicates the weight coefficient of the corresponding scoring item, which is set based on experience;

[0128] S64: Arrange the final person-job matching degree from high to low, and select the top N matching items as the final screening resumes according to the recruitment requirements;

[0129] The virtual HR role intelligent body also includes generating a personalized evaluation report for each resume, wherein the personalized evaluation report includes a person-job matching score, a score for each resume item in the final screened application information, and a revised score for each item in the final screened application information; the personalized evaluation report is presented to the recruiter in a visual manner, and the final screened resume is recommended to the recruiter.

[0130] S7: configuring a feedback terminal, obtaining feedback information based on the feedback terminal, and optimizing and adjusting the matching algorithm of the virtual HR role agent based on the feedback information;

[0131] Specifically, it allows HR or applicants to adjust parameters and re-match; based on actual recruitment results and feedback, continuously adjust and optimize the matching algorithm of the intelligent agent to improve the accuracy and efficiency of person-job matching.

[0132] Example 2

[0133] refer to Figure 3 and Figure 4As shown, it is the second embodiment of the present invention; based on the same inventive concept as embodiment 1, this embodiment introduces a specific implementation method of the information matching evaluation system based on the virtual HR agent, including a virtual HR construction module, a recruitment demand module, a resume management module, a resume initial screening module, a scoring correction module, a resume final screening module, and a feedback optimization module, wherein:

[0134] The virtual HR building module is used to build and manage virtual HR role agents, configure matching rules and parameters, and ensure that they can match people with positions and conduct assessments according to preset logic;

[0135] The recruitment requirements module is used to set recruitment position information, including initial screening recruitment requirements, final screening recruitment requirements and personality requirements;

[0136] The resume management module is used to manage the applicants' application information, including receiving, storing, and extracting the initial screening application information and the final screening application information in the resume;

[0137] The resume screening module conducts preliminary screening of the applicant resumes based on the resume matching strategy to ensure that the resumes entering the interview meet the basic requirements. Specifically, it includes the scoring unit and the resume matching unit, among which:

[0138] The scoring vector unit is used to obtain the expected scoring vector and the resume scoring vector;

[0139] The resume matching unit is used to calculate the matching degree between people and positions;

[0140] The scoring correction module is used to obtain score data and correct the application information based on the score data to obtain a new resume scoring vector;

[0141] The resume final screening module is used to combine the applicant's personality test results and the new resume scoring vector for final screening and determine the final screening resume;

[0142] The feedback optimization module obtains feedback information based on the feedback terminal, and optimizes and adjusts the matching algorithm of the virtual HR role agent based on the feedback information.

[0143] Working principle and its effect:

[0144] Through automated resume screening and preliminary screening processes, the workload of HR personnel has been greatly reduced and recruitment efficiency has been improved. The virtual HR role agent can quickly traverse a large number of application resumes and conduct preliminary screening based on preset matching strategies, effectively shortening the recruitment cycle.

[0145] The resume matching strategy based on the virtual HR role agent can more accurately evaluate the matching degree between applicants and recruitment positions by comprehensively considering the applicants' initial screening information (such as age, education, major, etc.) and final screening information (such as work experience, skills, etc.), and configuring the corresponding expected score vector; it can improve the information matching during the application process to achieve the effect of information-based job matching, which not only improves the accuracy of recruitment, but also helps companies find talents that are more suitable for job requirements;

[0146] After the initial screening, the virtual HR role agent interviews the applicants and modifies the resume scoring vector based on the interview score data. The interview score can be used to correct a certain inflated value in the resume. This step modifies the application information in the resume to avoid the problem of insufficient resume authenticity, and makes corrections in an objective way, avoiding human subjectivity and further enhancing the accuracy of person-job matching.

[0147] In addition, although exemplary embodiments have been described in the present invention, the scope includes any and all embodiments based on the present invention with equivalent elements, modifications, omissions, combinations (e.g., various embodiments intersecting schemes), adaptations or changes. The elements in the claims will be interpreted broadly based on the language adopted in the claims, and are not limited to the examples described in this specification or during the execution of this application, and the examples will be interpreted as non-exclusive. Therefore, this specification and examples are intended to be considered as examples only, and the true scope and spirit are indicated by the claims and the full scope of their equivalents.

[0148] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more schemes thereof) may be used in combination with each other. For example, a person of ordinary skill in the art may use other embodiments when reading the above description. In addition, in the above-mentioned specific embodiments, various features may be grouped together to simplify the present invention. This should not be interpreted as an intention that a disclosed feature that is not required to be protected is necessary for any claim. On the contrary, the subject matter of the present invention may be less than all the features of a particular disclosed embodiment. Thus, the claims are incorporated herein into the specific embodiments as examples or embodiments, wherein each claim is independently a separate embodiment, and it is considered that these embodiments may be combined with each other in various combinations or arrangements. The scope of the present invention should be determined with reference to the appended claims and the full scope of equivalent forms granted by these claims.

[0149] The above embodiments are only exemplary embodiments of the present invention and are not intended to limit the present invention. The protection scope of the present invention is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present invention within the essence and protection scope of the present invention, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present invention.

Claims

1. An information matching evaluation method based on a virtual HR agent, characterized in that: The specific steps include: S1: Building a virtual HR role agent; S2: Set the job information of the recruitment position; S3: Get the resume of the applicant, traverse the resume and extract the application information; S4: Based on the resume matching strategy configured by the virtual HR role agent, obtain the initial screening resume to enter the interview; S5: the virtual HR role agent interviews the applicants whose resumes have been initially screened, obtains score data, and modifies the application information based on the score data; S6: Obtain the personality test results and the corrected application information of the applicant, and obtain the final screening resume based on the virtual HR role agent; S7: configuring a feedback terminal, obtaining feedback information based on the feedback terminal, and optimizing and adjusting the matching algorithm of the virtual HR role agent based on the feedback information; The job information includes initial screening recruitment requirements and final screening recruitment requirements, the application information includes initial screening application information and final screening application information, and the resume matching strategy specifically includes the following steps: S41: the initial screening recruitment requirements include a recruitment element set, the initial screening application information includes an application element set, traversing the application element set and matching with the recruitment element set in sequence; S42: Determine whether the application factor set matches the recruitment factor set; if the recruitment factor set does not match the application factor set, delete the application resume; if the recruitment factor set matches the application factor set, retain the application resume and determine whether the final screening application information matches the final screening recruitment requirements to obtain the initial screening resume; The step of determining whether the final screening application information matches the final screening recruitment requirements to obtain the initial screening resume specifically includes the following steps: S421: The final screening recruitment requirements include an intention element set, and an expected score is configured for the intention element set, and the expected score is composed of an expected score vector ; S422: The final screening application information includes a screening element set. The screening element set is scored based on the virtual HR role agent to obtain the resume score of the screening element, and the resume score of the screening element is formed into a resume score vector ; S423: Calculating the person-job matching degree based on the expected scoring vector and the resume scoring vector; S424: configure the person-job matching threshold; If the person-job matching degree is not less than the person-job matching degree threshold, the resume will be retained as a preliminary screening resume for interview; When the person-job matching degree is less than the person-job matching degree threshold, the resume is deleted; The score data is used to modify the resume score of the screening element set, the score data includes a professional score set, an ability score, and an expression score set, the resume score of the screening element set includes a first screening element resume score, a second screening element resume score, a third screening element resume score, and a fourth screening element resume score, and the modification method specifically includes: The professional score set is used to modify the resume score of the first screening factor, the ability score is used to modify the resume score of the second screening factor, the expression score set is used to modify the resume score of the third screening factor, and the modification method of the resume score of the fourth screening factor is assigned by the resume score of the fourth screening factor; The professional score set includes a first professional score and a second professional score. The professional score set is used to modify the resume score of the first screening factor in a specific manner as follows: ; in, represents the revised resume score of the first screening factor, Indicates the first professional rating, represents the average score of the first major, Indicates the second professional score, represents the average score of the second major, Represents the resume score of the first screening factor, is the weight coefficient.

2. The information matching evaluation method based on virtual HR agent according to claim 1 is characterized in that: The calculation formula for the person-job matching degree is as follows: ; Among them, S represents the matching degree between people and positions; represents the expected score of the i-th element of the intention element set in the expected score vector; Represents the resume score of the i-th element in the screening element set in the resume score vector; Indicates the weight coefficient of the corresponding scoring item; Represents the limiting factor.

3. The information matching evaluation method based on virtual HR agent according to claim 2 is characterized in that: The specific method of using the ability score to correct the resume score of the second screening factor is: ; in, represents the revised resume score of the second screening factor, Indicates ability rating, represents the average ability score, Represents the resume score of the second screening factor.

4. The information matching evaluation method based on virtual HR agent according to claim 3 is characterized in that: The expression score set includes a first expression score, a second expression score and a third expression score. The specific method of using the expression score set to modify the resume score of the third screening factor is: ; in, It represents the revised resume score of the third screening factor, represents the first expression score, represents the average of the first expression scores; represents the second expression score, represents the average of the second expression scores; represents the third expression rating score, represents the average score of the third expression, Indicates the resume score of the third screening factor, is the weight coefficient.

5. The information matching evaluation method based on virtual HR agent according to claim 4 is characterized in that: Obtaining the final screening resume includes the following steps: S61: The position information also includes personality requirements. The personality requirements of the position information are encoded and added to the expected score vector to generate a new expected score vector. ,in, Indicates character requirement coding; S62: Encode the obtained candidate personality test results and generate a new resume scoring vector with the revised resume scoring vector ,in Indicates the candidate's personality test result code; S63: Calculate the final person-job matching degree based on the new expected score vector and the new resume score vector. The calculation formula is as follows: ; in, Indicates the final person-job matching degree, represents the expected score of the jth recruitment factor in the new expected score vector, represents the jth resume score in the new resume score vector, Indicates the weight coefficient of the corresponding scoring item; S64: Arrange the final person-job matching degree from high to low, and select the top N matching items as the final screening resumes based on recruitment requirements.

6. An information matching evaluation system based on a virtual HR agent, implemented according to the information matching evaluation method based on a virtual HR agent according to any one of claims 1 to 5, characterized in that: It includes virtual HR construction module, recruitment demand module, resume management module, resume initial screening module, score correction module, resume final screening module and feedback optimization module, among which: The virtual HR building module is used to build and manage virtual HR role agents and configure matching rules and parameters; The recruitment requirements module is used to set recruitment position information, including initial screening recruitment requirements, final screening recruitment requirements and personality requirements; The resume management module is used to manage the applicant's application information, including receiving, storing, and extracting the application information in the resume; The resume screening module performs preliminary screening of the applicant resumes based on the resume matching strategy, which specifically includes a scoring vector unit and a resume matching unit, where: The scoring vector unit is used to obtain the expected scoring vector and the resume scoring vector; The resume matching unit is used to calculate the matching degree between people and positions; The scoring correction module is used to obtain score data and correct the application information based on the score data to obtain a new resume scoring vector; The resume final screening module is used to determine the final screening resume by combining the personality test results of the applicant and the new resume scoring vector; The feedback optimization module obtains feedback information based on the feedback terminal, and optimizes and adjusts the matching algorithm of the virtual HR role agent based on the feedback information.