Artificial intelligence-based employee matching method and system

Abstract

The invention discloses an employee matching method and system based on artificial intelligence, and belongs to the technical field of human resource matching, and the method comprises the following steps: resume analysis: automatically analyzing a resume of a job seeker, and extracting key information; position description analysis: automatically analyzing the position description of the recruitment enterprise, and extracting key requirements; feature matching: performing feature extraction and matching on the key information of the job seeker and the position through a deep learning algorithm; similarity evaluation: according to a feature matching result, evaluating a matching degree between the job seeker and the position, and giving a matching score; and user interaction: the job seeker and the recruitment enterprise query a matching result and related information through a user interface. According to the invention, through technologies of deep learning, natural language processing and the like, resumes of job seekers and position description of recruitment enterprises are automatically analyzed, so that efficient and accurate matching between the job seekers and positions is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of human resource matching, and in particular to an employment matching method and system based on artificial intelligence. Background Art

[0002] With the development of technologies such as big data, cloud computing and artificial intelligence, the traditional human resource management model can no longer meet the needs of modern enterprises for high efficiency, accuracy and personalized management. Therefore, it is of great significance to develop a human resource management and optimization system based on big data. Summary of the invention

[0003] The technical task of the present invention is to address the above deficiencies and provide an artificial intelligence-based employment matching method and system that can automatically analyze job seekers' resumes and recruiting companies' job descriptions to achieve efficient and accurate matching between job seekers and positions.

[0004] The technical solution adopted by the present invention to solve its technical problem is:

[0005] An employment personnel matching method based on artificial intelligence, the implementation of which includes the following steps:

[0006] 1) Resume parsing: Automatically parse the resume of job seekers and extract key information;

[0007] 2) Job description parsing: Automatically parse the job description of the recruiting company and extract key requirements;

[0008] 3) Feature matching: Through deep learning algorithms, feature extraction and matching of key information of job seekers and positions are performed to achieve feature-level matching;

[0009] 4) Similarity assessment: Based on the feature matching results, the matching degree between the job seeker and the position is evaluated and a matching score is given as the basis for recommendation;

[0010] 5) User interaction: Job seekers and recruiting companies query matching results and related information through the user interface.

[0011] This method uses deep learning, natural language processing and other technologies to automatically analyze job seekers' resumes and recruiting companies' job descriptions, thereby achieving efficient and accurate matching between job seekers and positions.

[0012] Furthermore, the resume parsing, through a fixed-mode electronic resume template, collects personal resume information in sections. The resume is divided into modules such as personal basic information, education background, work experience, skills, awards and certificates. After personal information is entered, basic information such as name, gender, mobile phone number, address, etc. is extracted and stored through the fixed fields of transmission. Other information such as education background, work experience, skills, etc. are compared with the set initial field label library through the basic description of the information in the background, and the affiliated college, major and corresponding academic qualifications are screened out from the information. The quality of the educational background is judged according to the fixed college and subject dictionary in the database, such as whether it is a 985, 211 college, whether it is a C9 college, etc., and the education background score is comprehensively evaluated according to the colleges and universities at all levels of academic qualifications and the highest academic qualifications. The higher the highest academic qualification, the better the graduating college of each level of academic qualifications, and the higher the score, otherwise the lower the score, and the relevant information and scores are stored in association;

[0013] Work experience is matched and intercepted through the transmitted field information and the work experience keywords initially set in the background, such as company, position, years of work experience, etc., to obtain relevant work experience information, and calculate the experience score based on the company name and years of work in the position, such as the ranking of the company where the person works, for example: whether it is a top 500 company in the country, whether it is a state-owned enterprise or a central enterprise; the major category to which the position belongs, such as Java R&D positions belong to the computer industry, and years of work experience. The better the company and the longer the years of work experience, the higher the work experience score in the industry, and it is stored in association with the basic information of the person;

[0014] Skills and specialties: Specialties are extracted based on set keywords such as personality, awards, leadership, communication, etc. Different keywords have different set directional scores based on the keywords, forming a multilateral personal ability framework, which includes but is not limited to leadership, execution, communication, planning, stress resistance, etc. This item is stored in association and serves as the basis for subsequent person-job matching; for awards, corresponding certificate pictures must be provided, and awards are only recorded and associated with personal information for storage.

[0015] Furthermore, the job description is parsed and the company fills in the recruitment position. The information filled in includes but is not limited to salary, position, position label, required years of work experience, school level, required academic qualifications, etc. The background extracts data through this part of the label field and stores it in the database. Each label corresponds to a library table field, and the data is bound to the company's social credit code and position code to ensure the accuracy of the data.

[0016] Furthermore, the feature matching is performed based on the personal information features and scores obtained from the resume analysis, and compared with the company position label information obtained from the job description analysis. The information items of each person's information stored in the database will have a one-to-one correspondence with the field items in the database after the company fills in the information. The data under the corresponding relationship are compared, and the results are judged according to the set evaluation criteria.

[0017] Furthermore, in the similarity evaluation, the match of each field has a fixed matching score, if it is exactly the same, it is 3 points, if it is higher than the requirement, it is 2 points, if it is lower than the requirement, it is 1 point. For example: if the company's position requires a master's degree, the academic degree score of the personnel is 2 points, if it is a master's degree, it is 3 points, and if it is a bachelor's degree, it is 1 point; if the company provides a salary range of 6k-8k, and the employee requires a salary lower than the standard, it is 2 points, if it is exactly the standard, it is 3 points, and if it is higher than the standard, it is 1 point. The same is true for other parts. The standards for personnel looking for jobs and jobs looking for people are opposite. For example: if the individual's academic degree is a master's degree, the score for recruiting undergraduates in the position is 2 points, if it is a master's degree, it is 3 points, and if it is a doctorate, it is 1 point. Finally, a total matching score can be obtained, which is the matching similarity.

[0018] Furthermore, in the user interaction, individual users can view the final matching position information, and corporate users can see the matching personnel for each position. The matching degree is displayed in order from high to low, and users can evaluate the matching results. If the evaluation is high, the background will add similar tag matches to the initial tag library. If the evaluation is low, some similar tag matches will be removed.

[0019] The present invention also claims protection for an employment matching system based on artificial intelligence, comprising:

[0020] Resume parsing module, used to automatically parse job seekers' resumes and extract key information;

[0021] Job description parsing module, used to automatically parse job descriptions of recruiting companies and extract key requirements;

[0022] Feature matching module, used to extract and match key information of job seekers and positions through deep learning algorithms;

[0023] The similarity assessment module is used to evaluate the matching degree between job seekers and positions based on the feature matching results and give a matching score;

[0024] User interaction interface, which provides a user interface for job seekers and recruiting companies to query information, view matching results and interact;

[0025] The system achieves employment matching through the above method.

[0026] Furthermore, the system achieves employment matching in the following ways:

[0027] The resume parsing module first collects information about employed people and analyzes their skills, preferences and needs;

[0028] The job description parsing module collects job information and analyzes job requirements;

[0029] The feature matching module extracts and matches the key information of job seekers and positions; and through the similarity evaluation module, it calculates the matching degree between personnel and positions, recommends them to positions or employed persons based on the scores, and adjusts and optimizes through feedback information.

[0030] The present invention also claims protection for an employment personnel matching implementation device based on artificial intelligence, comprising at least one memory and a processor;

[0031] The at least one memory is used to store a machine-readable program;

[0032] The at least one processor is used to call the machine-readable program to implement the above method.

[0033] The present invention also claims protection for a computer-readable medium having computer instructions stored thereon, which implement the above method when executed by a processor.

[0034] Compared with the prior art, the employment personnel matching method and system based on artificial intelligence of the present invention has the following beneficial effects:

[0035] 1. Improve matching efficiency: It can reduce manual intervention and improve matching efficiency through automated resume and job description parsing.

[0036] 2. Accurate matching: Based on deep learning algorithms, it can achieve accurate matching between job seekers and positions.

[0037] 3. Personalized recommendation: Provide personalized recommendation services based on the characteristics of job seekers and job requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flowchart of an implementation method of an artificial intelligence-based employment matching method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The embodiment of the present invention provides an employment personnel matching method based on artificial intelligence, and the implementation of the method includes the following steps:

[0040] 1. Resume parsing: automatically parse the resume of job seekers and extract key information;

[0041] 2. Job description analysis: automatically analyze the job description of the recruiting company and extract key requirements;

[0042] 3. Feature matching: Extract and match the key information of job seekers and positions;

[0043] 4. Similarity assessment: Based on the feature matching results, the matching degree between the job seeker and the position is evaluated and a matching score is given as the basis for recommendation;

[0044] 5. User interaction: Job seekers and recruiting companies query matching results and related information through the user interface.

[0045] Among them, the resume parsing, through the electronic resume template of a fixed mode, collects personal resume information in sections. The resume is divided into modules such as personal basic information, education background, work experience, skills and specialties, awards and certificates. After the personal information is entered, basic information such as name, gender, mobile phone number, address, etc. are extracted and stored through the fixed fields of transmission. Other information such as education background, work experience, skills and specialties are compared with the set initial field label library through the basic description of the information in the background, and the affiliated colleges, majors studied and corresponding academic qualifications are screened out from the information. The quality of the educational background is judged according to the fixed college and subject dictionary in the database, such as whether it is a 985, 211 college, whether it is a C9 college, etc., and the education background score is comprehensively evaluated according to the colleges and universities at all levels of academic qualifications and the highest academic qualifications. The higher the highest academic qualification, the better the graduating colleges of each level of academic qualifications, and the higher the score, otherwise the lower the score, and the relevant information and scores are stored in association;

[0046] Work experience is matched and intercepted through the transmitted field information and the work experience keywords initially set in the background, such as company, position, years of work experience, etc., to obtain relevant work experience information, and calculate the experience score based on the company name and years of work in the position, such as the ranking of the company where the person works, for example: whether it is a top 500 company in the country, whether it is a state-owned enterprise or a central enterprise; the major category to which the position belongs, such as Java R&D positions belong to the computer industry, and years of work experience. The better the company and the longer the years of work experience, the higher the work experience score in the industry, and it is stored in association with the basic information of the person;

[0047] Skills and specialties: Specialties are extracted based on set keywords such as personality, awards, leadership, communication, etc. Different keywords have different set directional scores based on the keywords, forming a multilateral personal ability framework, which includes but is not limited to leadership, execution, communication, planning, stress resistance, etc. This item is stored in association and serves as the basis for subsequent person-job matching; for awards, corresponding certificate pictures must be provided, and awards are only recorded and associated with personal information for storage.

[0048] The job description is parsed, and the company fills in the recruitment position. The information filled in includes but is not limited to salary, position, position label, required years of work experience, school level, required academic qualifications, etc. The background extracts data through this part of the label field and stores it in the database. Each label corresponds to a library table field. The data is bound to the company's social credit code and position code to ensure the accuracy of the data.

[0049] The feature matching is based on the personal information features and scores obtained from the resume analysis, and is compared with the company position label information obtained from the job description analysis. The information items of each person's information stored in the database will have a one-to-one correspondence with the field items in the database after the company fills in the information. The data under the corresponding relationship are compared, and the results are judged according to the set evaluation criteria.

[0050] For the similarity assessment, each field has a fixed matching score. If they are exactly the same, it will be 3 points; if they are higher than the requirement, it will be 2 points; if they are lower than the requirement, it will be 1 point. For example, if the company's position requires a master's degree, the score for the academic degree of the personnel is 2 points, if they have a master's degree, it will be 3 points, and if they have a bachelor's degree, it will be 1 point. If the company provides a salary range of 6k-8k, and the employee requires a salary lower than the standard, it will be 2 points, if it is exactly the standard, it will be 3 points, and if it is higher than the standard, it will be 1 point. The same is true for other parts. The standards for personnel looking for positions and positions looking for people are opposite. For example, if the individual's academic degree is a master's degree, the score for recruiting undergraduates in the position is 2 points, if they have a master's degree, it will be 3 points, and if they have a doctorate, it will be 1 point. Finally, a total matching score can be obtained, which is the matching similarity.

[0051] In the user interaction, individual users can view the final matching position information, and corporate users can see the matching personnel for each position. The matching degree is displayed in order from high to low. Users can evaluate the matching results. If the evaluation is high, the background will add similar tag matches to the initial tag library. If the evaluation is low, some similar tag matches will be removed.

[0052] like Figure 1 The following is the employment matching process:

[0053] First, collect information on employed personnel and analyze their skills and preference requirements; then collect job information and analyze job requirements; calculate the matching degree between personnel and positions, recommend them to positions or employed personnel based on the scores, and make adjustments and optimizations through feedback information.

[0054] This method uses deep learning, natural language processing and other technologies to automatically analyze job seekers' resumes and recruiting companies' job descriptions, thereby achieving efficient and accurate matching between job seekers and positions.

[0055] The embodiment of the present invention also provides an employment personnel matching system based on artificial intelligence, including:

[0056] Resume parsing module, used to automatically parse job seekers' resumes and extract key information;

[0057] Job description parsing module, used to automatically parse job descriptions of recruiting companies and extract key requirements;

[0058] The feature matching module is used to extract and match the key information of job seekers and positions through deep learning algorithms to achieve feature-level matching;

[0059] The similarity assessment module is used to evaluate the matching degree between job seekers and positions based on the feature matching results and give a matching score as the basis for recommendation;

[0060] The user interaction interface provides a simple and easy-to-use user interface for job seekers and recruiting companies to query information, view matching results and interact.

[0061] The resume parsing module uses a fixed-mode electronic resume template to collect personal resume information in sections. The resume is divided into modules such as personal basic information, education background, work experience, skills, awards and certificates. After personal information is entered, basic information such as name, gender, mobile phone number, address, etc. is extracted and stored through the fixed fields transmitted. Other information such as education background, work experience, skills, etc. are compared with the set initial field label library through the basic description of the information in the background, and the affiliated college, major and corresponding academic qualifications are screened out from the information. The quality of the educational background is judged according to the fixed college and subject dictionary in the database, such as whether it is a 985, 211 college, whether it is a C9 college, etc., and the education background score is comprehensively evaluated according to the colleges and universities at all levels of academic qualifications and the highest academic qualifications. The higher the highest academic qualification, the better the graduating college of each level of academic qualifications, and the higher the score, otherwise the lower the score, and the relevant information and scores are stored in association;

[0062] Work experience is matched and intercepted through the transmitted field information and the work experience keywords initially set in the background, such as company, position, years of work experience, etc., to obtain relevant work experience information, and calculate the experience score based on the company name and years of work in the position, such as the ranking of the company where the person works, for example: whether it is a top 500 company in the country, whether it is a state-owned enterprise or a central enterprise; the major category to which the position belongs, such as Java R&D positions belong to the computer industry, and years of work experience. The better the company and the longer the years of work experience, the higher the work experience score in the industry, and it is stored in association with the basic information of the person;

[0063] Skills and specialties: Specialties are extracted based on set keywords such as personality, awards, leadership, communication, etc. Different keywords have different set directional scores based on the keywords, forming a multilateral personal ability framework, which includes but is not limited to leadership, execution, communication, planning, stress resistance, etc. This item is stored in association and serves as the basis for subsequent person-job matching; for awards, corresponding certificate pictures must be provided, and awards are only recorded and associated with personal information for storage.

[0064] In the job description parsing module, the company fills in recruitment positions, and the filled-in information includes but is not limited to salary, position, position label, required years of work experience, school level, required academic qualifications, etc. The background extracts data through these label fields and stores them in the database. Each label corresponds to a library table field, and the data is bound to the company's social credit code and position code to ensure the accuracy of the data.

[0065] The feature matching module compares the personal information features and scores obtained from the resume analysis with the company position label information obtained from the job description analysis. The information items of each person stored in the database will have a one-to-one correspondence with the field items in the database after the company fills in the information. The data under the corresponding relationship are compared and the results are judged according to the set evaluation criteria.

[0066] In the similarity assessment module, each field match has a fixed matching score, if it is exactly the same, it is 3 points, if it is higher than the requirement, it is 2 points, if it is lower than the requirement, it is 1 point. For example: if the company's position requires a master's degree, the academic degree score of the personnel is 2 points, if it is a master's degree, it is 3 points, and if it is a bachelor's degree, it is 1 point; if the company provides a salary range of 6k-8k, and the employee requires a salary lower than the standard, it is 2 points, if it is exactly the standard, it is 3 points, and if it is higher than the standard, it is 1 point. The same is true for other parts. The standards for personnel looking for jobs and jobs looking for people are opposite. For example: if the individual's academic degree is a master's degree, the score for recruiting undergraduates in the position is 2 points, if it is a master's degree, it is 3 points, and if it is a doctorate, it is 1 point. Finally, a total matching score can be obtained, which is the matching similarity.

[0067] In the user interaction interface, individual users can view the final matching position information, and corporate users can see the matching personnel for each position. The matching degree is displayed in order from high to low. Users can evaluate the matching results. If the evaluation is high, the background will add similar tag matches to the initial tag library. If the evaluation is low, some similar tag matches will be removed.

[0068] The system achieves employment matching in the following ways:

[0069] The resume parsing module first collects information about employed people and analyzes their skills, preferences and needs;

[0070] The job description parsing module collects job information and analyzes job requirements;

[0071] The feature matching module extracts and matches the key information of job seekers and positions; and through the similarity evaluation module, it calculates the matching degree between personnel and positions, recommends them to positions or employed persons based on the scores, and adjusts and optimizes through feedback information.

[0072] The embodiment of the present invention also provides an employment personnel matching implementation device based on artificial intelligence, comprising at least one memory and a processor;

[0073] The at least one memory is used to store a machine-readable program;

[0074] The at least one processor is used to call the machine-readable program to implement the artificial intelligence-based employment matching method described in the above embodiment.

[0075] The embodiment of the present invention further provides a computer-readable medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the processor executes the employment personnel matching method based on artificial intelligence described in the above embodiment. Specifically, a system or device equipped with a storage medium can be provided, on which software program codes implementing the functions of any of the above embodiments are stored, and a computer (or CPU or MPU) of the system or device reads and executes the program code stored in the storage medium.

[0076] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0077] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0078] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0079] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or written to a memory provided in an expansion unit connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or the expansion unit is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0080] The present invention is shown and described in detail above through the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above multiple embodiments, those skilled in the art can know that the code review methods in the above different embodiments can be combined to obtain more embodiments of the present invention, and these embodiments are also within the protection scope of the present invention.

Claims

1. An employment personnel matching method based on artificial intelligence, characterized in that: The implementation of this method includes the following steps: 1) Resume parsing: Automatically parse the resume of job seekers and extract key information; 2) Job description parsing: Automatically parse the job description of the recruiting company and extract key requirements; 3) Feature matching: Through deep learning algorithms, feature extraction and matching of key information of job seekers and positions are performed; 4) Similarity assessment: Based on the feature matching results, the matching degree between the job seeker and the position is evaluated and a matching score is given; 5) User interaction: Job seekers and recruiting companies query matching results and related information through the user interface.

2. The employment personnel matching method based on artificial intelligence according to claim 1, characterized in that: The resume parsing, through a fixed-mode electronic resume template, collects personal resume information in sections. The resume includes personal basic information, education background, work experience, skills and expertise, and award certificate modules. After personal information is entered, the basic information is extracted and stored through the transmitted fixed fields. The background of other information compares the basic description of the information with the set initial field tag library, and selects the affiliated colleges, majors studied and corresponding academic qualifications from the information, and judges the quality of educational background according to the fixed college and subject dictionary in the database, and comprehensively evaluates the educational background score according to the colleges and universities at all levels of academic qualifications and the highest academic qualifications. The higher the highest academic qualification, the better the graduating colleges of each level of academic qualifications, and the higher the score; otherwise, the lower the score; and the relevant information and scores are associated and stored; Work experience is obtained by matching the transmitted field information and the work experience keywords initially set in the background, and the relevant work experience information is obtained. The experience score is calculated based on the company name and the number of years of work in the job position, including the ranking of the company where the person works, the major category of the position, and the number of years of work. The better the company and the longer the years of work, the higher the work experience score in the industry, and it is stored in association with the basic information of the person. Skills and expertise: Specialties are extracted based on set keywords. Different keywords have different set directional scores. Based on the keywords, a multilateral personal ability framework is formed, which includes leadership, execution, communication, planning, and stress resistance. This item is stored in association and serves as the basis for subsequent person-job matching. For awards, corresponding certificate pictures must be provided. Awards only record information and store associated personal information.

3. The employment personnel matching method based on artificial intelligence according to claim 1 is characterized in that: The job description is parsed, and the company fills in the recruitment position, and the information filled in includes salary, position, position label, required years of work experience, school level, and required academic qualifications. The background extracts data through this part of the label field and stores it in the database. Each label corresponds to a library table field. The data is bound to the company's social credit code and position code to ensure the accuracy of the data.

4. The employment personnel matching method based on artificial intelligence according to claim 1, characterized in that: The feature matching is based on the personal information features and scores obtained from the resume analysis, and is compared with the company position label information obtained from the job description analysis. The information items of each person's information stored in the database will have a one-to-one correspondence with the field items in the database after the company fills in the information. The data under the corresponding relationship are compared, and the results are judged according to the set evaluation criteria.

5. The employment personnel matching method based on artificial intelligence according to claim 1, characterized in that: For the similarity assessment, each field has a fixed matching score. If they are exactly the same, it is 3 points; if they are higher than the requirement, it is 2 points; if they are lower than the requirement, it is 1 point. For salary, if the company provides a salary range of 6k-8k, and the employee requires a salary lower than the standard, it is 2 points; if it is exactly the standard, it is 3 points; and if it is higher than the standard, it is 1 point. The standards for people looking for jobs and jobs looking for people are the opposite. Finally, a total matching score can be obtained, which is the matching similarity.

6. The employment personnel matching method based on artificial intelligence according to claim 1, characterized in that: In the user interaction, individual users can view the final matching position information, and corporate users can see the matching personnel for each position. The matching degree is displayed in order from high to low. Users can evaluate the matching results. If the evaluation is high, the background will add similar tag matches to the initial tag library. If the evaluation is low, some similar tag matches will be removed.

7. An employment matching system based on artificial intelligence, characterized in that: include: Resume parsing module, used to automatically parse job seekers' resumes and extract key information; Job description parsing module, used to automatically parse job descriptions of recruiting companies and extract key requirements; Feature matching module, used to extract and match key information of job seekers and positions through deep learning algorithms; The similarity assessment module is used to evaluate the matching degree between job seekers and positions based on the feature matching results and give a matching score; User interaction interface, which provides a user interface for job seekers and recruiting companies to query information, view matching results and interact; The system achieves employment matching through the method described in any one of claims 1 to 6.

8. The artificial intelligence-based employment matching system according to claim 7, characterized in that: The system achieves employment matching in the following ways: The resume parsing module first collects information about employed people and analyzes their skills, preferences and needs; The job description parsing module collects job information and analyzes job requirements; The feature matching module extracts and matches the key information of job seekers and positions; and through the similarity evaluation module, it calculates the matching degree between personnel and positions, recommends them to positions or employed persons based on the scores, and adjusts and optimizes through feedback information.

9. An employment personnel matching implementation device based on artificial intelligence, characterized in that: comprising at least one memory and a processor; The at least one memory is used to store a machine-readable program; The at least one processor is used to call the machine-readable program to implement the method described in any one of claims 1 to 6.

10. A computer-readable medium, characterized in that The computer readable medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images