Intelligent voice interaction recruitment matching method and system based on large language model

Abstract

The invention relates to the technical field of intelligent recruitment matching, and particularly discloses an intelligent voice interaction recruitment matching method and system based on a large language model, and the method comprises the steps: receiving recruitment demands and interview questions uploaded by a recruitment end, and storing the recruitment demands and interview questions in a knowledge base; receiving a job hunting request which is uploaded by a job hunter and contains resume information, retrieving the knowledge base based on the resume information, and screening out a matched recruitment end; sending the matched recruitment end as a recommended post to the job seeker, and receiving a selection request of the job seeker; an interview environment is created based on interview questions in the knowledge base, interview is performed on the job seeker, and an evaluation result is generated; and generating an interview condition oriented to the recruitment end and job hunting suggestions oriented to the job hunters based on the evaluation result. According to the invention, the matching degree between the job seeker and the post is improved, the occurrence of invalid interviews is reduced, the job seeker is helped to better prepare interviews, the interview passing rate is improved, the recruiter can more quickly screen out proper candidates, and the recruitment efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent recruitment matching, and in particular to an intelligent voice interaction recruitment matching method and system based on a large language model. Background Art

[0002] With the development of information technology, traditional recruitment methods have gradually failed to meet the needs of efficient and accurate matching. Existing online recruitment systems are usually limited to information release and simple matching recommendations, lacking in-depth job requirements analysis and job seeker skill assessment. In addition, job seekers have limited resources in interview preparation and simulation, making it difficult to accurately match the needs of employers. The shortcomings of existing technologies are as follows:

[0003] Online recruitment system: lack of in-depth job requirement analysis and job seeker skill assessment, limited interview preparation and simulation resources for job seekers, making it difficult to accurately match the needs of employers.

[0004] Voice assessment tools: They rely on manual judgment, are highly subjective, inefficient, and have difficulty providing immediate feedback, and cannot meet the needs of users in interviews and training. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent voice interaction recruitment matching method and system based on a large language model to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent voice interaction recruitment matching method based on a large language model, the method comprising:

[0008] Receive recruitment requirements and interview questions uploaded by the recruitment end and store them in the knowledge base;

[0009] Receive job application requests containing resume information uploaded by job seekers, search the knowledge base based on the resume information, and select matching recruitment terminals;

[0010] Send the matched recruitment end as a recommended position to the job seeker, and receive the job seeker's selection request;

[0011] Create an interview environment based on the interview questions in the knowledge base, interview job applicants, and generate evaluation results;

[0012] Based on the evaluation results, interview situations for recruiters and job search suggestions for job seekers are generated.

[0013] As a further solution of the present invention: the step of receiving the recruitment requirements and interview questions uploaded by the recruitment terminal and storing them in the knowledge base includes:

[0014] Receive recruitment applications sent by the recruitment end and open the information filling port;

[0015] Receive recruitment requirements uploaded by the recruitment end based on the information filling port;

[0016] Based on the information filling port, the interview questions uploaded by the recruitment end are received, and the relevant test questions are crawled based on the large network model to expand the interview questions;

[0017] Using the recruitment end as an index, the recruitment needs and all interview questions on the recruitment end are counted and stored in the knowledge base.

[0018] As a further solution of the present invention: the step of receiving a job application request containing resume information uploaded by a job seeker, searching a knowledge base based on the resume information, and selecting a matching recruitment terminal comprises:

[0019] Receive job applications uploaded by job seekers and open information filling ports;

[0020] Receive resume information and job application intention based on the information filling port;

[0021] Based on the large language model, recruitment needs are matched in the knowledge base according to resume information and job-seeking intentions, and matching recruitment ends are screened out.

[0022] As a further solution of the present invention: the step of generating interview situations for the recruiter and job-seeking suggestions for the job seeker based on the evaluation results includes:

[0023] Read the evaluation results and feed them back to the recruitment end. When receiving the follow-up request sent by the recruitment end, enter the next recruitment process;

[0024] The assessment results are read, job search suggestions are generated based on the assessment results, and the feedback is given to the job seekers.

[0025] The technical solution of the present invention also provides an intelligent voice interaction recruitment matching system based on a large language model, the system comprising:

[0026] The knowledge base creation module is used to receive recruitment requirements and interview questions uploaded by the recruitment end and store them in the knowledge base;

[0027] The recruitment end screening module is used to receive job application requests containing resume information uploaded by job seekers, search the knowledge base based on the resume information, and screen out matching recruitment ends;

[0028] The job posting module is used to send the matching recruitment end as a recommended job post to the job seeker and receive the job seeker's selection request;

[0029] The mock interview module is used to create an interview environment based on the interview questions in the knowledge base, interview job applicants, and generate evaluation results;

[0030] The evaluation result analysis module is used to generate interview situations for recruiters and job search suggestions for job seekers based on the evaluation results.

[0031] As a further solution of the present invention: the knowledge base creation module includes:

[0032] The first port opening unit is used to receive the recruitment application sent by the recruitment end and open the information filling port;

[0033] A recruitment demand receiving unit, used for receiving recruitment demands uploaded by a recruitment terminal based on an information filling port;

[0034] The test question expansion unit is used to receive the interview questions uploaded by the recruitment end based on the information filling port, crawl relevant test questions based on the network big model, and expand the interview questions;

[0035] The statistical unit is used to count the recruitment needs and all interview questions on the recruitment side with the recruitment side as the index, and store them in the knowledge base.

[0036] As a further solution of the present invention: the recruitment end screening module includes:

[0037] The second port opening unit is used to receive job application requests uploaded by job seekers and open an information filling port;

[0038] A job search information receiving unit, used for receiving resume information and job search intention based on an information filling port;

[0039] The matching and screening unit is used to match recruitment needs in the knowledge base based on resume information and job-seeking intentions based on a large language model, and screen out matching recruitment terminals.

[0040] As a further solution of the present invention: the evaluation result analysis module includes:

[0041] The first feedback unit is used to read the evaluation results and feed them back to the recruitment end. When a follow-up request sent by the recruitment end is received, the next recruitment process is entered;

[0042] The second feedback unit is used to read the evaluation results, generate job search suggestions based on the evaluation results, and feed back to the job seeker.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention discloses a recruitment and job search intelligent matching and interview simulation system, which realizes efficient matching between recruiters and job seekers through a data upload module, a knowledge base module, an intelligent matching module, an interview simulation module and a result feedback module. The system automatically recommends suitable positions, simulates interviews and provides feedback, improves the matching efficiency of recruitment and job search, provides job seekers with a fully simulated interview drill and provides recruiters with an opportunity to initially screen resumes.

[0044] The present invention improves the matching degree between job seekers and positions, reduces the occurrence of invalid interviews, helps job seekers better prepare for interviews, and improves the interview pass rate. Recruiters can more quickly screen out suitable candidates and improve recruitment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0046] Figure 1 This is a flowchart of the intelligent voice interaction recruitment matching method based on a large language model. DETAILED DESCRIPTION

[0047] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0048] Figure 1 The flowchart of the intelligent voice interaction recruitment matching method based on the large language model is provided in the embodiment of the present invention. The method includes:

[0049] Step S100: receiving recruitment requirements and interview questions uploaded by the recruitment end, and storing them in the knowledge base;

[0050] Step S200: receiving a job application containing resume information uploaded by a job seeker, searching a knowledge base based on the resume information, and screening out matching recruitment terminals;

[0051] Step S300: sending the matched recruitment end as a recommended position to the job seeker, and receiving the job seeker's selection request;

[0052] Step S400: creating an interview environment based on the interview questions in the knowledge base, interviewing the job seeker, and generating an evaluation result;

[0053] Step S500: Generate interview information for the recruiter and job-seeking suggestions for the job seeker based on the evaluation results.

[0054] In one example of the technical solution of the present invention, a platform for completing the above process is provided, and the platform includes:

[0055] Data upload module: Recruiters use this module to publish recruitment requirements and upload interview questions, and job seekers use this module to publish job requirements and upload resume information.

[0056] Knowledge base module: This module stores job requirements, interview questions, resume information of job seekers uploaded by recruiters, and interview questions crawled from the Internet.

[0057] Intelligent matching module: When a job seeker requests a recommendation for a suitable job, the big model (displayed in the form of a digital human, supporting voice calls) searches the knowledge base, screens out positions that match the job seeker's conditions, and makes recommendations.

[0058] Interview simulation module: After the job seeker selects the recommended position, the system starts a simulated interview, focusing on the recruiter's requirements and the skills required for the position, and conducts an in-depth assessment.

[0059] Results feedback module: After the interview, the system will inform the job seeker whether he / she has passed the interview, comment on his / her performance, and provide suggestions for improvement. The system will also inform the recruiter of the interview results and ask whether to continue to follow up.

[0060] The workflow of the above platform is:

[0061] 1. Recruiters upload information: Recruiters publish recruitment positions and specific requirements through the system and upload interview questions.

[0062] 2. Job seekers upload information: Job seekers publish their job application intentions and personal resume information through the system.

[0063] 3. Data storage: All uploaded data and interview questions crawled from the web are stored in the knowledge base.

[0064] 4. Job recommendation: When job seekers request recommendations for suitable jobs, the big model searches the knowledge base to screen and recommend suitable jobs.

[0065] 5. Mock interview: After the job seeker selects a position, the system starts a mock interview, focusing on the skills and other requirements required for the position.

[0066] 6. Result feedback: After the interview, the system provides feedback and informs the job seeker of the interview result, and also informs the recruiter of the interview situation.

[0067] 7. Recruiter follow-up: Recruiters choose whether to continue following up with job seekers based on system notifications.

[0068] Furthermore, the step of receiving the recruitment requirements and interview questions uploaded by the recruitment end and storing them in the knowledge base includes:

[0069] Receive recruitment applications sent by the recruitment end and open the information filling port;

[0070] Receive recruitment requirements uploaded by the recruitment end based on the information filling port;

[0071] Based on the information filling port, the interview questions uploaded by the recruitment end are received, and the relevant test questions are crawled based on the large network model to expand the interview questions;

[0072] Using the recruitment end as an index, the recruitment needs and all interview questions on the recruitment end are counted and stored in the knowledge base.

[0073] The above content describes the interaction process between the execution platform of this method and the recruitment end. The information filling port is used to receive information uploaded by the recruitment end. The format is not limited. When facing the recruitment end, the received information includes recruitment needs and interview questions. The recruitment needs can be a collection of some keywords. After receiving the interview questions, relevant test questions are crawled based on the large network model, and the interview questions are expanded. Finally, the recruitment needs and all interview questions of the same recruitment end are connected and stored in the knowledge base.

[0074] Specifically, the step of receiving a job application containing resume information uploaded by a job seeker, searching a knowledge base based on the resume information, and selecting a matching recruitment terminal includes:

[0075] Receive job applications uploaded by job seekers and open information filling ports;

[0076] Receive resume information and job application intention based on the information filling port;

[0077] Based on the large language model, recruitment needs are matched in the knowledge base according to resume information and job-seeking intentions, and matching recruitment ends are screened out.

[0078] The above content limits the interaction stage between the execution subject of this method and the job seeker. Similarly, an information filling port is opened, and the resume information and job-seeking intention sent by the job seeker are received based on the information filling port. Then, with the help of the information matching means of the large language model, the recruitment needs are matched in the knowledge base according to the resume information and job-seeking intention, and the recruitment end that successfully matches is selected as the screened recruitment end.

[0079] Furthermore, the step of generating interview information for the recruiter and job search suggestions for the job seeker based on the evaluation results includes:

[0080] Read the evaluation results and feed them back to the recruitment end. When receiving the follow-up request sent by the recruitment end, enter the next recruitment process;

[0081] The assessment results are read, job search suggestions are generated based on the assessment results, and the feedback is given to the job seekers.

[0082] In an example of the technical solution of the present invention, the application of the evaluation results is also divided into two parts. One part is for the recruitment side. The system notifies the recruiter of the interview results of the job seeker, and the recruiter decides whether to follow up: the recruiter decides whether to continue to follow up based on the job seeker's interview performance. If the follow-up is continued, the next step of the recruitment process will be entered; if the follow-up is abandoned, the process ends; the other part is for the job seeker, notifying the job seeker of the interview results: the system feeds back the interview results to the job seeker and provides improvement suggestions.

[0083] As a preferred implementation of the technical solution of the present invention, a comprehensive workflow is provided as follows:

[0084] 1. Data preparation stage:

[0085] Recruiters upload recruitment requirements: Recruiters upload specific job requirements and interview questions through the system, and this information will be stored in the knowledge base.

[0086] Job seekers upload resume information: Job seekers upload their resumes and job application intentions through the system, and this information will also be stored in the knowledge base.

[0087] Interview questions crawled from the web: The system automatically crawls relevant interview questions from the web and stores them in the knowledge base for subsequent use.

[0088] 2. Job recommendation and interview simulation stage:

[0089] Job seekers request recommended positions: Job seekers request recommendations for positions that match their qualifications through the system.

[0090] Big model searches the knowledge base: The big model in the form of a digital human will search the knowledge base to screen out positions that match the job seeker's conditions.

[0091] Recommend suitable positions: The system recommends suitable positions to job seekers.

[0092] Job seekers select a position: Job seekers select one of the recommended positions for a mock interview.

[0093] Start a mock interview: The system starts a mock interview based on the requirements of the selected position, focusing on assessing skills and requirements related to the position.

[0094] Evaluate job applicant performance: The system evaluates the job applicant's interview performance.

[0095] Feedback on interview results: The system generates feedback on interview results.

[0096] 3. Subsequent operation stage:

[0097] Notify job seekers of interview results: The system will provide feedback on interview results to job seekers and provide suggestions for improvement.

[0098] Notify the recruiter of the interview result: The system notifies the recruiter of the job seeker's interview result.

[0099] Recruiters decide whether to follow up: Recruiters decide whether to continue to follow up based on the job seeker's interview performance. If they continue to follow up, they will move to the next step of the recruitment process; if they give up following up, the process ends.

[0100] As a preferred embodiment of the technical solution of the present invention, the present invention also provides an intelligent voice interaction recruitment matching system based on a large language model, the system comprising:

[0101] The knowledge base creation module is used to receive recruitment requirements and interview questions uploaded by the recruitment end and store them in the knowledge base;

[0102] The recruitment end screening module is used to receive job application requests containing resume information uploaded by job seekers, search the knowledge base based on the resume information, and screen out matching recruitment ends;

[0103] The job posting module is used to send the matching recruitment end as a recommended job post to the job seeker and receive the job seeker's selection request;

[0104] The mock interview module is used to create an interview environment based on the interview questions in the knowledge base, interview job applicants, and generate evaluation results;

[0105] The evaluation result analysis module is used to generate interview situations for recruiters and job search suggestions for job seekers based on the evaluation results.

[0106] Furthermore, the knowledge base creation module includes:

[0107] The first port opening unit is used to receive the recruitment application sent by the recruitment end and open the information filling port;

[0108] A recruitment demand receiving unit, used for receiving recruitment demands uploaded by a recruitment terminal based on an information filling port;

[0109] The test question expansion unit is used to receive the interview questions uploaded by the recruitment end based on the information filling port, crawl relevant test questions based on the network big model, and expand the interview questions;

[0110] The statistical unit is used to count the recruitment needs and all interview questions on the recruitment side with the recruitment side as the index, and store them in the knowledge base.

[0111] Specifically, the recruitment screening module includes:

[0112] The second port opening unit is used to receive job application requests uploaded by job seekers and open an information filling port;

[0113] A job search information receiving unit, used for receiving resume information and job search intention based on an information filling port;

[0114] The matching and screening unit is used to match recruitment needs in the knowledge base based on resume information and job-seeking intentions based on a large language model, and screen out matching recruitment terminals.

[0115] In addition, the evaluation result analysis module includes:

[0116] The first feedback unit is used to read the evaluation results and feed them back to the recruitment end. When a follow-up request sent by the recruitment end is received, the next recruitment process is entered;

[0117] The second feedback unit is used to read the evaluation results, generate job search suggestions based on the evaluation results, and feed back to the job seeker.

[0118] In the technical solution of the present invention, a specific implementation method is provided as follows:

[0119] 1. Recruiters upload recruitment information: Recruiters fill in job requirements and upload interview questions through the system interface.

[0120] 2. Job seekers upload job information: Job seekers upload their resumes and job application intentions through the system.

[0121] 3. Knowledge base data storage: All data is stored in the knowledge base for easy subsequent retrieval.

[0122] 4. Job recommendation and mock interview: The system recommends jobs based on the job seeker’s request. After the job seeker selects a job, the system automatically starts a mock interview.

[0123] 5. Result feedback and notification: After the interview, the system automatically generates a feedback report and notifies relevant parties.

[0124] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent voice interaction recruitment matching method based on a large language model, characterized in that: The method comprises: Receive recruitment requirements and interview questions uploaded by the recruitment end and store them in the knowledge base; Receive job application requests containing resume information uploaded by job seekers, search the knowledge base based on the resume information, and select matching recruitment terminals; Send the matched recruitment end as a recommended position to the job seeker, and receive the job seeker's selection request; Create an interview environment based on the interview questions in the knowledge base, interview job applicants, and generate evaluation results; Based on the evaluation results, interview situations for recruiters and job search suggestions for job seekers are generated.

2. The intelligent voice interaction recruitment matching method based on a large language model according to claim 1 is characterized in that: The step of receiving the recruitment requirements and interview questions uploaded by the recruitment terminal and storing them in the knowledge base includes: Receive recruitment applications sent by the recruitment end and open the information filling port; Receive recruitment requirements uploaded by the recruitment end based on the information filling port; Based on the information filling port, the interview questions uploaded by the recruitment end are received, and the relevant test questions are crawled based on the large network model to expand the interview questions; Using the recruitment end as an index, the recruitment needs and all interview questions on the recruitment end are counted and stored in the knowledge base.

3. The intelligent voice interaction recruitment matching method based on a large language model according to claim 1 is characterized in that: The step of receiving a job application request containing resume information uploaded by a job seeker and searching a knowledge base based on the resume information to select a matching recruitment terminal comprises: Receive job applications uploaded by job seekers and open information filling ports; Receive resume information and job application intention based on the information filling port; Based on the large language model, recruitment needs are matched in the knowledge base according to resume information and job-seeking intentions, and matching recruitment ends are screened out.

4. The intelligent voice interaction recruitment matching method based on a large language model according to claim 1 is characterized in that: The step of generating interview information for the recruiter and job search suggestions for the job seeker based on the evaluation results includes: Read the evaluation results and feed them back to the recruitment end. When receiving the follow-up request sent by the recruitment end, enter the next recruitment process; The assessment results are read, job search suggestions are generated based on the assessment results, and the feedback is given to the job seekers.

5. An intelligent voice interactive recruitment matching system based on a large language model, characterized in that: The system comprises: The knowledge base creation module is used to receive recruitment requirements and interview questions uploaded by the recruitment end and store them in the knowledge base; The recruitment end screening module is used to receive job application requests containing resume information uploaded by job seekers, search the knowledge base based on the resume information, and screen out matching recruitment ends; The job posting module is used to send the matching recruitment end as a recommended job post to the job seeker and receive the job seeker's selection request; The mock interview module is used to create an interview environment based on the interview questions in the knowledge base, interview job applicants, and generate evaluation results; The evaluation result analysis module is used to generate interview situations for recruiters and job search suggestions for job seekers based on the evaluation results.

6. The intelligent voice interactive recruitment matching system based on a large language model according to claim 5 is characterized in that: The knowledge base creation module includes: The first port opening unit is used to receive the recruitment application sent by the recruitment end and open the information filling port; A recruitment demand receiving unit, used for receiving recruitment demands uploaded by a recruitment terminal based on an information filling port; The test question expansion unit is used to receive the interview questions uploaded by the recruitment end based on the information filling port, crawl relevant test questions based on the network big model, and expand the interview questions; The statistical unit is used to count the recruitment needs and all interview questions on the recruitment side with the recruitment side as the index, and store them in the knowledge base.

7. The intelligent voice interactive recruitment matching system based on a large language model according to claim 5 is characterized in that: The recruitment end screening module includes: The second port opening unit is used to receive job application requests uploaded by job seekers and open an information filling port; A job search information receiving unit, used for receiving resume information and job search intention based on an information filling port; The matching and screening unit is used to match recruitment needs in the knowledge base based on resume information and job-seeking intentions based on a large language model, and screen out matching recruitment terminals.

8. The intelligent voice interactive recruitment matching system based on a large language model according to claim 5 is characterized in that: The evaluation result analysis module includes: The first feedback unit is used to read the evaluation results and feed them back to the recruitment end. When a follow-up request sent by the recruitment end is received, the next recruitment process is entered; The second feedback unit is used to read the evaluation results, generate job search suggestions based on the evaluation results, and feed back to the job seeker.

Images