Management method and system based on man-post intelligent matching algorithm model

Abstract

The invention relates to the technical field of data processing and analysis, in particular to a management method and system based on a man-post intelligent matching algorithm model. The method comprises the following steps: acquiring post description data; standardizing the post description data to obtain standard post description data; performing semantic feature recognition on the standard post description data to obtain post semantic feature information; performing industry term information identification on the post semantic feature information to generate post industry term information; performing post industry type division on the standard post description data according to the post industry term information to obtain post industry type data; performing post capability demand determination on the post industry type data to obtain post capability demand data; through a semantic analysis technology, a natural language processing technology and a machine learning algorithm, the talent core capability information is accurately identified, and the post demand information is deeply analyzed, so that the talent post matching accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and analysis, and in particular to a management method and system based on an intelligent person-job matching algorithm model. Background Art

[0002] Initially, talent-job matching relied primarily on manual screening and matching, with recruiters matching applicants' skills and experience based on the required competencies. This method was inefficient and susceptible to human bias. With the application of keyword-based matching methods, recruiters can extract keywords from job descriptions and resumes and screen applicants through simple text matching. As matching technology is applied to talent-job matching, it can analyze and learn from applicant and job data, and use machine learning models to match applicant information with job requirements. However, existing matching technology struggles to fully present job requirements when faced with large amounts of resume information and job requirement data. Summary of the Invention

[0003] Based on this, it is necessary to provide a management method and system based on an intelligent person-job matching algorithm model to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a management method based on an intelligent job matching algorithm model includes the following steps: Step S1: obtaining job description data; performing standardization processing on the job description data to obtain standard job description data; performing semantic feature recognition on the standard job description data to obtain job semantic feature information; Step S2: Identify industry terminology information from the job semantic feature information to generate job industry terminology information; classify the standard job description data into job industry types based on the job industry terminology information to obtain job industry type data; determine job capability requirements based on the job industry type data to obtain job capability requirement data; Step S3: Acquire talent resume data; extract educational background from talent resume data to obtain talent educational background information; classify talent resume data into professional categories based on talent educational background information to generate talent professional type data; extract work experience information from talent resume data to obtain talent work experience data; perform career experience pattern recognition on talent work experience data to generate talent career experience data; identify professional ability characteristics from talent resume data based on talent career experience data and talent professional type data to obtain talent professional ability data; integrate talent educational background information, talent career experience data, and talent professional ability data to generate talent ability status data; perform intelligent matching analysis on talent ability status data and job ability requirement data to obtain talent job matching data; Step S4: Use the talent-job matching data to construct a talent-job intelligent matching model to obtain the talent-job intelligent matching model; obtain enterprise demand change data; dynamically optimize the talent-job intelligent matching model according to the enterprise demand change data to obtain a talent-job intelligent matching optimization model; predict talent-job matching based on the talent capability data and job capability demand data based on the talent-job intelligent matching optimization model to generate talent-job matching prediction data; visualize the talent-job matching prediction data to generate a talent-job intelligent matching report.

[0005] The present invention's standardized processing and semantic feature recognition of job description data can accurately extract the semantic feature information of the job, and then identify the industry terminology information of the job; it ensures the accuracy and consistency of the job description data, and provides a data basis for the subsequent job industry type classification and ability requirement determination. Industry type classification of standard job description data based on job industry terminology information helps to classify jobs into corresponding industries, and provides industry background data for the determination of job ability requirements; at the same time, the ability requirements of job industry type data are determined, providing clear ability standards for the subsequent matching of talents and jobs. The multi-dimensional analysis of talent resume data, specifically including education background extraction, professional talent classification, and work experience information extraction, helps to fully understand the professional ability and career experience of talents, thereby obtaining talent ability status data; the talent ability status data and job ability requirement data are intelligently matched and analyzed, and the talent job matching data obtained can accurately reflect the degree of matching between talents and jobs. The intelligent matching model for people and positions constructed using talent and position matching data can achieve intelligent matching of talents and positions; using the acquired enterprise demand change data and performing dynamic optimization, a human-position intelligent matching optimization model is finally obtained, which can adapt to job-seeking changes and thus improve the timeliness and accuracy of matching; using the human-position intelligent matching optimization model to predict talent and position matching, thereby obtaining human-position matching prediction data; through data visualization technology, a human-position intelligent matching report is obtained, which will provide intuitive and accurate talent recruitment support for enterprises; and ensure that the appropriate position is pushed to the most suitable talent at the first time. Therefore, the present invention accurately identifies talent core competency information through semantic analysis technology, natural language processing technology and machine learning algorithm, and deeply analyzes job demand information, thereby improving the accuracy of talent and position matching.

[0006] Preferably, step S2 includes the following steps: Step S21: semantically mapping the job semantic feature information to generate job semantic mapping data; extracting job description text from the standard job description data based on the job semantic mapping data to obtain job description text information; identifying industry terminology features from the job description text information to obtain industry terminology feature data; extracting industry terminology information from the job description text information based on the industry terminology feature data to generate job industry terminology information; Step S22: performing term frequency statistics on the job industry term information to obtain industry term frequency data; contextualizing the job description text information using the industry term frequency data to generate job description correlation information; and performing job industry matching on the job industry term information in combination with the job description correlation information to obtain job industry matching data; Step S23: Identify the industry category of the job industry matching data to generate job industry category data; merge the standard job description data into job industry categories based on the job industry category data to obtain industry category merged data; and classify the industry category merged data into industry types to obtain job industry type data; Step S24: Perform job capability requirement analysis on the standard job description data according to the job industry type data to obtain job capability requirement data.

[0007] The present invention performs semantic mapping on job semantic feature information, which can accurately reflect the core semantics of the job description; then extracts the job description text information, and through industry terminology feature recognition, ensures that the industry relevance of the job description is accurately identified; performs terminology frequency statistics on job industry terminology information, and clarifies the frequency of industry terminology in the job description; performs context association on the job description text information, which can reveal the relationship between the terms in the job description, and then effectively associate the job with the corresponding industry; performs industry category identification on job industry matching data, which can clarify the industry classification to which the job belongs; performs job industry category merging on standard job description data, and ensures that the job description data can be systematically organized according to industry category; performs job capability requirement analysis on standard job description data based on job industry type data, and can accurately reflect the capabilities required for specific industry jobs.

[0008] Preferably, step S24 includes the following steps: Step S241: performing capability keyword feature recognition on the job description text information to obtain capability keyword features; performing capability element extraction on the job description text information based on the capability keyword features to generate job capability element information; Step S242: Mapping the job capability factor information with the job industry type data to obtain industry capability mapping data; determining the industry capability index of the job description text information using the industry capability mapping data to generate industry capability index data; Step S243: Matching the industry capability requirements with the standard job description data based on the industry capability indicator data to obtain capability requirement matching information; extracting the requirement hierarchy structure from the capability requirement matching information to generate requirement hierarchy structure information; and performing hierarchical decomposition on the requirement hierarchy structure information to obtain capability requirement segmentation data; Step S244: Determine the education background requirements of the ability requirement segmentation data based on the job industry type data to generate job education background requirement data; identify the professional skill requirements of the ability requirement segmentation data based on the job education background requirement data to generate job professional skill requirement data; extract the professional experience requirements of the ability requirement segmentation data based on the job professional skill requirement data to generate job professional experience requirement data; Step S245: Integrate the job education background requirement data, job professional skill requirement data, and job career experience requirement data to obtain job capability requirement data.

[0009] The present invention identifies the key features of ability keywords through the job description text information, and can identify the key abilities required for the job; maps the job ability element information with the job industry type data to the industry type ability element, and can clarify the specific requirements of different industries for job abilities, thereby refining the industry-specific ability requirements in the job description; matches the industry ability requirements according to the industry ability indicator data, and can reflect the corresponding relationship between the job and the industry ability requirements; extracts and decomposes the demand hierarchy structure of the matching information, and can provide structured information for the job ability requirements, and clarify the ability hierarchy required for the job; determines the education background requirements for the ability requirement segmentation data based on the job industry type data, and clarifies the specific requirements for education level for the job; identifies the professional skill requirements for the ability requirement segmentation data based on the job education background requirement data, and provides clear indicators for the professional skills and professional experience required for the job; and by integrating the job education background requirement data, the job professional skill requirement data and the job professional experience requirement data, it can comprehensively reflect the various ability requirements of the job for talents, and ensure the comprehensiveness and accuracy of the job ability requirements.

[0010] Preferably, step S3 includes the following steps: Step S31: Acquire talent resume data; perform semantic feature recognition on the talent resume data to obtain resume semantic feature data; perform resume information semantic mapping on the resume semantic feature data to generate resume semantic mapping information; extract resume description text from the talent resume data based on the resume semantic mapping information to obtain resume description text information; Step S32: extracting educational experience features from the resume description text information to generate educational experience feature information; determining the talent's academic qualifications based on the educational experience feature information to obtain talent academic qualifications information; identifying the graduation school based on the talent academic qualifications information to generate talent graduation school information; determining the talent's major based on the educational experience feature information and the talent's graduation school information to obtain talent major information; Step S33: Integrate the talent's academic information, the talent's graduating school information, and the talent's major information to obtain the talent's educational background information; mark the talent's resume data with professional information characteristics based on the talent's educational background information to obtain talent professional characteristic data; determine the professional category of the talent professional characteristic data to generate talent industry category data; classify the talent's major information based on the talent industry category data to generate talent professional type data; Step S34: extracting work experience information from the talent resume data to obtain talent work experience data; performing career experience pattern recognition on the talent work experience data to generate talent career experience data; performing professional ability feature recognition on the talent resume data based on the talent career experience data and talent professional type data to obtain talent professional ability data; integrating the talent education background information, talent career experience data, and talent professional ability data to generate talent ability status data; Step S35: Perform intelligent matching analysis on the talent capability data and the job capability requirement data to obtain talent job matching data.

[0011] By acquiring talent resume data and performing semantic feature recognition, the present invention can accurately capture key information in a resume; extracting educational experience features from resume description text information can describe the talent's educational background in detail; by determining the talent's academic qualifications, graduating colleges and majors studied, detailed data is provided for a comprehensive understanding of the talent's educational background; integrating relevant information on educational background, the generated talent education background information can comprehensively reflect the talent's educational level and professional field; further determining professional information feature markers and professional categories can classify talents into professional categories; extracting work experience information and identifying professional experience patterns from talent resume data can describe the talent's career development path in detail; identifying professional ability features in combination with the talent's professional background provides an important basis for evaluating the talent's professional ability; integrating talent ability status data can comprehensively reflect the talent's education, professional experience and professional ability; performing intelligent matching analysis between talent ability status data and job ability requirement data can accurately match talents with job requirements, thereby improving the efficiency and accuracy of recruitment and ensuring the high level of talent and job.

[0012] Preferably, step S34 includes the following steps: Step S341: performing work experience feature recognition on the resume description text information to generate work experience feature data; performing work timeline extraction on the teaching work experience feature data to obtain work timeline data; arranging the work experience feature data in work time sequence according to the work timeline data to generate work sequence arrangement data; and extracting work experience information from the talent resume data based on the work sequence arrangement data to obtain talent work experience data; Step S342: Determine the work type of the talent's work experience data to generate work experience type information; identify the work project of the work experience type information to obtain work experience project data; extract the job position of the work experience project data to obtain past job position information; Step S343: Determine the job responsibilities of the talent's work experience data based on the past job position information to obtain past job responsibilities information; extract work experience content from the work experience item data based on the past job responsibilities information to generate past work content data; perform career experience pattern recognition on the past work content data to generate talent career experience data; Step S344: Identify the professional ability characteristics of the talent resume data based on the talent's career experience data and talent professional type data to obtain the talent's professional ability data; Step S345: Integrate the talent's educational background information, talent's professional ability data, and talent's career experience data to generate talent's ability status data.

[0013] The present invention identifies the work experience characteristics of resume description text information, which can capture the work experience details of talents in detail; clearly displays the work history of talents by extracting and arranging the work timeline in sequence; determines the work type of talents' work experience data, which can classify the work experience of talents; clearly describes the roles and responsibilities of talents in various work projects by identifying work projects and extracting job positions; determines job responsibilities based on past job position information, which can clarify the scope of responsibilities of talents in previous jobs; extracts content from work experience project data, and records the work results and experience of talents in detail; career experience pattern recognition reveals the career development path of talents; professional ability characteristics recognition based on talents' career experience data and talents' professional type data reflects the professional skills and ability level of talents; and can comprehensively display the comprehensive quality of talents by integrating talents' educational background information, talents' professional ability data and talents' career experience data.

[0014] Preferably, step S344 includes the following steps: Step S3441: extracting past work achievement information from the talent's career experience data to generate past work achievement information; quantifying the work results of the past work achievement information to obtain work result quantified data; and mapping the talent's career experience data to work capability based on the work result quantified data to generate work capability mapping data. Step S3442: Identify professional ability characteristics of the resume description text information to generate professional ability characteristic information; annotate the professional ability characteristic information based on the talent professional type data to obtain professional ability annotated data; classify the professional ability characteristic information into professional type capabilities based on the professional ability annotated data to generate professional ability classification data; Step S3443: Using the professional competence classification data, the resume description text information is identified by professional competence certificates to obtain professional competence certificate information; the professional competence certificate information is classified into skill certificate grades to obtain skill certificate grade data; and work competence mapping data is matched with work competences according to the skill certificate grade data to generate work competence matching information; Step S3444: Associate the professional type data of the talent with the professional type skills according to the work skill matching information to obtain type skill association data; construct a professional skill map based on the type skill association data to generate a talent professional skill map; identify professional ability characteristics of the talent professional skill map in combination with the work ability mapping data to obtain talent professional ability data.

[0015] The present invention extracts past work achievement information from the talent's professional experience data and quantifies the work results, so as to specifically measure the talent's work performance, thereby reflecting the talent's actual work ability and providing a quantitative basis for evaluating the talent's professional ability; identifies professional ability characteristics of resume description text information, and labels professional ability characteristics based on the talent's professional type data, so as to clarify the talent's ability level in a specific professional field; further refines the talent's professional skills through professional type ability classification data; identifies professional skill certificate information through professional ability classification data, and divides skill certificate levels, so as to distinguish the talent's proficiency in professional skills; effectively connects the talent's professional skills with job requirements; associates professional type skills based on work skill matching information and talent professional type data, and constructs a talent professional skill map, which can intuitively display the talent's professional skill structure; and comprehensively reflects the talent's comprehensive quality and ability by integrating the talent's educational background information, talent professional ability data and talent career experience data.

[0016] Preferably, step S35 includes the following steps: Step S351: Classify the talent's educational background information into educational hierarchies to generate talent's educational level data; compare the talent's educational level data with the job's educational background requirement data to obtain an educational background matching index; Step S352: Perform capability dimension mapping on the talent professional capability data to generate talent capability dimension data; perform skill multi-dimensional mapping on the talent capability dimension data and the job professional skill requirement data to obtain a professional skill matching index; Step S353: mining the professional experience elements of the talent professional experience data to generate professional experience element data; matching the professional experience element data with the job professional experience requirement data to obtain a professional experience matching index; Step S354: Quantitatively score the education background matching index, professional skills matching index, and career experience matching index to obtain comprehensive person-job matching scoring data; score and sort the comprehensive person-job matching scoring data to obtain matching scoring sorting data; intelligently match the talent capability data with the job capability requirement data based on the matching scoring sorting data to generate talent-job matching data.

[0017] The present invention classifies talent education background information by educational hierarchy, thereby clarifying the talent's educational level; compares it with job education background requirement data to obtain an education background matching index, thereby quantifying the degree of fit between the talent's education background and job requirements; maps talent professional ability data to ability dimensions, thereby specifically describing the talent's professional skills; performs multi-dimensional mapping with job professional skill requirement data to obtain a professional skill matching index, thereby accurately measuring the correspondence between the talent's professional skills and job requirements; mines talent career experience data for professional experience elements, thereby recording the talent's work experience in detail; matches it with job professional experience requirement data to obtain a job experience matching index, thereby evaluating the degree of fit between the talent's professional experience and job requirements; quantitatively scores the education background matching index, professional skill matching index, and career experience matching index, thereby comprehensively reflecting the degree of fit between the talent and the job; scores and ranks the comprehensive person-job matching score data, thereby providing a basis for talent screening and ranking; and intelligent matching based on the matching score ranking data can provide enterprises with talent options that best meet job requirements, thereby improving the efficiency and accuracy of talent selection and ensuring a high degree of fit between talent and job requirements.

[0018] Preferably, step S4 includes the following steps: Step S41: constructing a person-job intelligent matching model based on the talent-job matching data to obtain a person-job intelligent matching pre-model, and training the person-job intelligent matching pre-model using the talent-job matching data to obtain a person-job intelligent matching training model; Step S42: performing a model cross-validation evaluation on the intelligent job matching training model to obtain evaluation data of the intelligent job matching training model; adjusting the model parameters of the intelligent job matching training model based on the evaluation data to obtain the intelligent job matching model; Step S43: Obtain enterprise demand change data; dynamically optimize the person-job intelligent matching model based on the enterprise demand change data to obtain a person-job intelligent matching optimization model; perform talent-job matching prediction on the talent capability data and job capability requirement data based on the person-job intelligent matching optimization model to generate person-job matching prediction data; visualize the person-job matching prediction data to generate a person-job intelligent matching report.

[0019] The present invention constructs a person-job intelligent matching pre-model based on talent-job matching data, and obtains a person-job intelligent matching training model through training, which can learn the matching relationship between talents and jobs, so as to capture the correlation between talents and job requirements; obtains person-job intelligent matching training model evaluation data through model cross-validation evaluation, so as to accurately evaluate the performance of the model; adjusts model parameters based on the evaluation data, and can further optimize the person-job intelligent matching model, thereby improving the accuracy and generalization ability of the model; the obtained enterprise demand change data provides a basis for the dynamic optimization of the person-job intelligent matching model; and dynamically optimizes the model, so that the model can adapt to changes in market and enterprise needs, thereby improving the timeliness and flexibility of matching; the talent-job matching prediction based on the person-job intelligent matching optimization model can predict the matching situation of talents and jobs; and provides an intuitive matching result display for enterprise recruiters and job seekers through data visualization person-job intelligent matching report.

[0020] Preferably, step S43 includes the following steps: Step S431: Acquire enterprise demand change data; monitor demand change trends on the enterprise demand change data to generate enterprise demand change trend information; identify employment market change characteristics on the enterprise demand change trend information to obtain employment market change characteristics; determine job demand changes on the enterprise demand change data based on the employment market change characteristics to obtain job demand change information; Step S432: extracting demand differences from the job demand change information to generate job demand difference data; determining the demand priority of the job demand change information based on the job demand difference data to obtain job demand priority information; dynamically adjusting the demand priority weights of the job-person intelligent matching model based on the job demand priority information to obtain priority weight adjustment data; dynamically optimizing the weights of the job-person intelligent matching model using the priority weight adjustment data to obtain a job-person intelligent matching optimization model; Step S433: Inputting the talent capability data and the job capability requirement data into the talent-job intelligent matching optimization model to perform talent-job matching prediction and obtain talent-job matching prediction data; Step S434: Process the person-job matching prediction data into information graphics to obtain a person-job matching prediction chart; compile a visual report for the person-job matching prediction chart to obtain a person-job intelligent matching report.

[0021] The present invention monitors the trends of enterprise demand change data and identifies the characteristics of employment market changes, which can clarify the information on job demand changes; by extracting job demand difference data and determining demand priority, the person-job intelligent matching model can be dynamically weighted optimized, thereby enhancing the model's adaptability to changes in job demand and improving the accuracy and response speed of matching; using the person-job intelligent matching optimization model to predict talent-job matching, it can predict the matching situation between talents and jobs; by graphically processing the person-job matching prediction data and compiling visual reports, complex matching results can be presented in an intuitive and easy-to-understand form, thereby providing corporate recruiters and job seekers with an intuitive display of matching results.

[0022] In this specification, a management system based on an intelligent job matching algorithm model is provided, which is used to execute the above-mentioned management method based on an intelligent job matching algorithm model. The management system based on an intelligent job matching algorithm model includes: The job semantic recognition module is used to obtain job description data; standardize the job description data to obtain standard job description data; perform semantic feature recognition on the standard job description data to obtain job semantic feature information; The job competency requirement module is used to identify industry terminology information from job semantic feature information to generate job industry terminology information; classify standard job description data into job industry types based on job industry terminology information to obtain job industry type data; and determine job competency requirements based on job industry type data to obtain job competency requirement data; The talent position intelligent matching analysis module is used to obtain talent resume data; extract the educational background of talent resume data to obtain talent educational background information; classify talent resume data into professional categories based on talent educational background information to generate talent professional type data; extract work experience information from talent resume data to obtain talent work experience data; perform career experience pattern recognition on talent work experience data to generate talent career experience data; identify professional ability characteristics of talent resume data based on talent career experience data and talent professional type data to obtain talent professional ability data; integrate talent educational background information, talent career experience data and talent professional ability data to generate talent ability status data; perform intelligent matching analysis on talent ability status data and job ability requirement data to obtain talent position matching data; The intelligent person-job matching model module is used to construct an intelligent person-job matching model using talent-job matching data to obtain an intelligent person-job matching model; obtain enterprise demand change data; dynamically optimize the intelligent person-job matching model based on enterprise demand change data to obtain an intelligent person-job matching optimization model; predict talent-job matching based on talent capability data and job capability requirement data based on the intelligent person-job matching optimization model to generate person-job matching prediction data; visualize the person-job matching prediction data to generate an intelligent person-job matching report.

[0023] The present invention uses a job semantic recognition module to perform standardized processing and semantic feature recognition of job description data, which can accurately extract the semantic feature information of the job and then identify the industry terminology information of the job; ensure the accuracy and consistency of the job description data, and provide a data basis for the subsequent job industry type classification and ability requirement determination. The present invention uses a job ability requirement module to classify the standard job description data into industry types based on job industry terminology information, which helps to classify jobs into corresponding industries and provides industry background data for the determination of job ability requirements; at the same time, the ability requirements are determined for job industry type data, providing clear ability standards for the subsequent matching of talents and jobs. The present invention uses a talent job intelligent matching analysis module to perform multi-dimensional analysis of talent resume data, specifically including education background extraction, professional talent classification, and work experience information extraction, which helps to fully understand the professional ability and career experience of talents, thereby obtaining talent ability situation data; the talent ability situation data and job ability requirement data are intelligently matched and analyzed, and the obtained talent job matching data can accurately reflect the degree of matching between talents and jobs. The present invention uses a person-post intelligent matching model module to construct a person-post intelligent matching model using talent-post matching data, which can achieve intelligent matching of talents and positions; uses the acquired enterprise demand change data and performs dynamic optimization to ultimately obtain a person-post intelligent matching optimization model, which can adapt to job-seeking changes and thus improve the timeliness and accuracy of matching; uses the person-post intelligent matching optimization model to predict talent-post matching, thereby obtaining person-post matching prediction data; uses data visualization technology to obtain a person-post intelligent matching report, which will provide intuitive and accurate talent recruitment support for enterprises; and ensures that the right position is pushed to the most suitable talent at the first time. Therefore, the present invention accurately identifies talent core competency information through semantic analysis technology, natural language processing technology, and machine learning algorithms, and deeply analyzes job demand information, thereby improving talent-post matching accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flowchart of the steps of the management method based on the intelligent person-job matching algorithm model; Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG. Figure 3 for Figure 2 Detailed implementation steps of step S24 are shown in the flowchart; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0025] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0027] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figures 1 to 3 , a management method based on an intelligent job matching algorithm model, comprising the following steps: Step S1: obtaining job description data; performing standardization processing on the job description data to obtain standard job description data; performing semantic feature recognition on the standard job description data to obtain job semantic feature information; Step S2: Identify industry terminology information from the job semantic feature information to generate job industry terminology information; classify the standard job description data into job industry types based on the job industry terminology information to obtain job industry type data; determine job capability requirements based on the job industry type data to obtain job capability requirement data; Step S3: Acquire talent resume data; extract educational background from talent resume data to obtain talent educational background information; classify talent resume data into professional categories based on talent educational background information to generate talent professional type data; extract work experience information from talent resume data to obtain talent work experience data; perform career experience pattern recognition on talent work experience data to generate talent career experience data; identify professional ability characteristics from talent resume data based on talent career experience data and talent professional type data to obtain talent professional ability data; integrate talent educational background information, talent career experience data, and talent professional ability data to generate talent ability status data; perform intelligent matching analysis on talent ability status data and job ability requirement data to obtain talent job matching data; Step S4: Use the talent-job matching data to construct a talent-job intelligent matching model to obtain the talent-job intelligent matching model; obtain enterprise demand change data; dynamically optimize the talent-job intelligent matching model according to the enterprise demand change data to obtain a talent-job intelligent matching optimization model; predict talent-job matching based on the talent capability data and job capability demand data based on the talent-job intelligent matching optimization model to generate talent-job matching prediction data; visualize the talent-job matching prediction data to generate a talent-job intelligent matching report.

[0029] The present invention's standardized processing and semantic feature recognition of job description data can accurately extract the semantic feature information of the job, and then identify the industry terminology information of the job; it ensures the accuracy and consistency of the job description data, and provides a data basis for the subsequent job industry type classification and ability requirement determination. Industry type classification of standard job description data based on job industry terminology information helps to classify jobs into corresponding industries, and provides industry background data for the determination of job ability requirements; at the same time, the ability requirements of job industry type data are determined, providing clear ability standards for the subsequent matching of talents and jobs. The multi-dimensional analysis of talent resume data, specifically including education background extraction, professional talent classification, and work experience information extraction, helps to fully understand the professional ability and career experience of talents, thereby obtaining talent ability status data; the talent ability status data and job ability requirement data are intelligently matched and analyzed, and the talent job matching data obtained can accurately reflect the degree of matching between talents and jobs. The intelligent matching model for people and positions constructed using talent and position matching data can achieve intelligent matching of talents and positions; using the acquired enterprise demand change data and performing dynamic optimization, a human-position intelligent matching optimization model is finally obtained, which can adapt to job-seeking changes and thus improve the timeliness and accuracy of matching; using the human-position intelligent matching optimization model to predict talent and position matching, thereby obtaining human-position matching prediction data; through data visualization technology, a human-position intelligent matching report is obtained, which will provide intuitive and accurate talent recruitment support for enterprises; and ensure that the appropriate position is pushed to the most suitable talent at the first time. Therefore, the present invention accurately identifies talent core competency information through semantic analysis technology, natural language processing technology and machine learning algorithm, and deeply analyzes job demand information, thereby improving the accuracy of talent and position matching.

[0030] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart of the steps of the management method based on the intelligent job matching algorithm model of the present invention. In this example, the management method based on the intelligent job matching algorithm model includes the following steps: Step S1: obtaining job description data; performing standardization processing on the job description data to obtain standard job description data; performing semantic feature recognition on the standard job description data to obtain job semantic feature information; In an embodiment of the present invention, a data call interface is used to obtain job description data from a recruitment website; the job description data includes a job title, job description, and job requirements; natural language processing (NLP) technology, such as the ICTCLAS word segmenter, is used to segment the job description and convert the text data into structured data; specifically, useless symbols, stop words are removed, and part-of-speech tags are added to obtain standard job description data; the standard job description data is converted into a numerical vector, specifically, each dimension is set to represent a word, and the numerical value represents the number of times the word appears in the document; further, the frequency of each word in the document is calculated to obtain the semantic features of the job description; the semantic features are mapped to a vector in a high-dimensional space to capture the semantic relationship between words, and finally obtain the semantic feature information of the job.

[0031] Step S2: Identify industry terminology information from the job semantic feature information to generate job industry terminology information; classify the standard job description data into job industry types based on the job industry terminology information to obtain job industry type data; determine job capability requirements based on the job industry type data to obtain job capability requirement data; In an embodiment of the present invention, NLP technology is used to segment and tag job semantic feature information, and regular expressions are used to match professional terms and industry-specific abbreviations, thereby constructing a dictionary library containing industry terms; the job semantic feature information is matched with the dictionary library to identify and extract relevant industry terms; a text similarity calculation method such as cosine similarity is used to evaluate the text similarity of the job semantic feature information, specifically identifying expressions similar to industry terms, and frequency statistics are performed based on the vocabulary in the job semantic feature information to filter out the most frequently occurring professional terms, thereby obtaining job industry terminology information; the contextual usage of terms in the job description is analyzed, and the job industry type is divided based on co-occurrence relationships and semantic relevance. Based on the job industry type data, clustering technology is used to classify the job industry terminology information into different industry types; for example, if the job industry terminology information contains a large number of terms related to construction, it is classified into the construction industry; the terminology characteristics of the job industry type data are analyzed to determine the job capability requirements. For example, for positions in the software development industry, job capability requirements such as programming language skills and project management skills are required, thereby obtaining job capability requirement data.

[0032] Step S3: Acquire talent resume data; extract educational background from talent resume data to obtain talent educational background information; classify talent resume data into professional categories based on talent educational background information to generate talent professional type data; extract work experience information from talent resume data to obtain talent work experience data; perform career experience pattern recognition on talent work experience data to generate talent career experience data; identify professional ability characteristics from talent resume data based on talent career experience data and talent professional type data to obtain talent professional ability data; integrate talent educational background information, talent career experience data, and talent professional ability data to generate talent ability status data; perform intelligent matching analysis on talent ability status data and job ability requirement data to obtain talent job matching data; In the embodiment of the present invention, a data call interface is used to obtain talent resume data from a job search website; NLP technology is used to extract educational background information in the resume; specifically, by setting keywords and phrases related to education, such as "degree", "major" and "graduation school", etc., the educational background of the talent is identified to obtain the talent's educational background information; based on the talent's educational background information, such as degree, major and graduation school, a decision tree classifier is used to classify the talent by profession; specifically, according to the type of major and in combination with the degree and graduation school, the talent resume data is divided into talent professional types; NLP technology is applied again, especially NLP information extraction technology, to identify the work experience part in the resume; through predefined work-related keywords, such as "work experience", "position" and "working hours", etc., This is used to locate and extract work experience data; pattern recognition technology is used to identify career experience patterns in talent work experience data; specific time series analysis is performed on work experience, and job roles and responsibilities are classified to generate talent career experience data; combining talent education background information and career experience data, feature engineering is used to identify talent professional capabilities, specifically including quantitative analysis of skills and achievements in education background and work experience to obtain talent professional capability data; using data fusion technology, education background information, career experience data and professional capability data are integrated to form comprehensive talent capability data; using intelligent matching algorithms, such as support vector machines (SVM) or neural networks, talent capability data is intelligently matched and analyzed with job capability requirement data to obtain talent job matching data.

[0033] Step S4: Use the talent-job matching data to construct a talent-job intelligent matching model to obtain the talent-job intelligent matching model; obtain enterprise demand change data; dynamically optimize the talent-job intelligent matching model according to the enterprise demand change data to obtain a talent-job intelligent matching optimization model; predict talent-job matching based on the talent capability data and job capability demand data based on the talent-job intelligent matching optimization model to generate talent-job matching prediction data; visualize the talent-job matching prediction data to generate a talent-job intelligent matching report.

[0034] In this embodiment of the present invention, a model for intelligent job matching is constructed using talent-job matching data. Specifically, the model employs a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) network. CNN parameters include: 32 3x3 filters in the convolutional layer, a stride of 1, padding of 1, a ReLU activation function, a max-pooling layer, and a fully connected layer. BiLSTM parameters include 128 hidden units, 128 word vectors of size 100, and a two-step attention mechanism to extract sentence-level and global representations of job requirements. The resulting intelligent job matching model is achieved. Through industry reports and recruitment platforms, the recruitment dynamics of enterprises are monitored in real time to obtain data on changes in enterprise demand. The intelligent job matching model is dynamically optimized based on the obtained data on changes in enterprise demand, including adjusting model parameters and feature weights. Talent-job matching predictions are made based on talent capability data and job capability requirement data based on the intelligent job matching optimization model. The degree of match between each job seeker and each job is clarified by calculating matching scores. The predicted data on job matching is visualized, and data visualization tools, such as Power BI, are used to generate intelligent job matching reports.

[0035] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: semantically mapping the job semantic feature information to generate job semantic mapping data; extracting job description text from the standard job description data based on the job semantic mapping data to obtain job description text information; identifying industry terminology features from the job description text information to obtain industry terminology feature data; extracting industry terminology information from the job description text information based on the industry terminology feature data to generate job industry terminology information; Step S22: performing term frequency statistics on the job industry term information to obtain industry term frequency data; contextualizing the job description text information using the industry term frequency data to generate job description correlation information; and performing job industry matching on the job industry term information in combination with the job description correlation information to obtain job industry matching data; Step S23: Identify the industry category of the job industry matching data to generate job industry category data; merge the standard job description data into job industry categories based on the job industry category data to obtain industry category merged data; and classify the industry category merged data into industry types to obtain job industry type data; Step S24: Perform job capability requirement analysis on the standard job description data according to the job industry type data to obtain job capability requirement data.

[0036] In the embodiment of the present invention, NLP technology, especially semantic analysis tools such as Word2Vec, is used to map the vocabulary in the job description into the semantic space to generate job semantic mapping data; regular expressions are used in combination with professional terms and industry-specific abbreviations such as Jieba word segmentation to extract job description text information, thereby building a dictionary library containing industry terms; industry terminology features are identified for the job description text information based on the industry terminology dictionary library to identify industry terminology features; based on the industry terminology feature data, NLP technology is used again to extract industry terminology information from the job description text to generate job industry terminology information; data mining tools such as Python's pandas library are used to perform terminology frequency statistics on job industry terminology information; based on NLP technology, especially the context embedding recognition method of BERT technology, context association is performed on the job description text information to generate job description association information; Combine job description association information and job industry terminology information, and perform job industry matching through similarity calculation methods, such as cosine similarity, to obtain job industry matching data; identify industry categories for job industry matching data, for example, if the job industry is construction engineering and civil engineering, it will be classified into the construction industry category, thereby generating job industry category data; merge standard job description data into job industry categories based on job industry category data, and use Python's pandas library to integrate and merge the same job industries; divide the industry category merged data into industry types; for example, divide it according to major industry categories, specifically into construction industry type, computer industry type, etc.; analyze job capability requirements for standard job description data based on job industry type data, specifically by extracting skill keywords from standard job description data, for example, standard job description data requires "intermediate engineer", thereby obtaining job capability requirement data.

[0037] As an example of the present invention, refer to Figure 3 As shown, in this example, step S24 includes: Step S241: performing capability keyword feature recognition on the job description text information to obtain capability keyword features; performing capability element extraction on the job description text information based on the capability keyword features to generate job capability element information; Step S242: Mapping the job capability factor information with the job industry type data to obtain industry capability mapping data; determining the industry capability index of the job description text information using the industry capability mapping data to generate industry capability index data; Step S243: Matching the industry capability requirements with the standard job description data based on the industry capability indicator data to obtain capability requirement matching information; extracting the requirement hierarchy structure from the capability requirement matching information to generate requirement hierarchy structure information; and performing hierarchical decomposition on the requirement hierarchy structure information to obtain capability requirement segmentation data; Step S244: Determine the education background requirements of the ability requirement segmentation data based on the job industry type data to generate job education background requirement data; identify the professional skill requirements of the ability requirement segmentation data based on the job education background requirement data to generate job professional skill requirement data; extract the professional experience requirements of the ability requirement segmentation data based on the job professional skill requirement data to generate job professional experience requirement data; Step S245: Integrate the job education background requirement data, job professional skill requirement data, and job career experience requirement data to obtain job capability requirement data.

[0038] In an embodiment of the present invention, a named entity recognition (NER) method in NLP technology is used to scan the job description text information to specifically identify keywords related to capabilities; for example, in the job description "Software engineers need to be proficient in Java and Python programming languages", "Java" and "Python" are extracted as capability keyword features; based on the capability keyword features, specific capability elements in the job description are extracted through text mining technology; specifically, for the term "proficient in programming languages" in the job description, capability elements related to "Java" and "Python" are further extracted to obtain job capability element information; the job capability element information is matched with the job industry type data, specifically using data merging technology, such as Python's pandas library to achieve industry type capability element mapping; the job description text information is analyzed through the industry capability mapping data, and the key capability indicators of the job are determined using frequency statistics methods; for example, if the "data analysis" capability frequently appears in multiple job descriptions, the description is determined as an industry capability indicator; based on the industry capability indicator data, pattern matching technology, such as regular expressions, is used to scan the standard job description data to match the industry Competency requirements: Analyze the competency requirements matching information and use the hierarchical analysis method to extract the hierarchical structure of requirements. For example, the "data analysis" capability required by the competency requirements matching information is further subdivided into hierarchical requirements such as "data cleaning," "data modeling," and "data reporting." Decompose the requirements hierarchy information and use principal component analysis (PCA) to decompose the requirements into more specific sub-requirements to obtain competency requirements segmentation data. Based on the job industry type data, use correlation analysis technology to determine the educational background requirements related to the job. For example, for the position of "data analyst," an educational background related to "statistics" or "machine learning" is required, thereby generating job education background requirement data. Based on the job education background requirement data, use cosine similarity calculation to identify the professional skills required for the job. For example, for a position with a "statistics" background, professional skill requirements related to "statistical analysis" and "probability theory" are identified. Combined with the job professional skill requirement data, use sequence pattern mining to extract the professional experience requirements related to the job. Use data integration technology to integrate the job education background requirement data, job professional skill requirement data, and job professional experience requirement data to obtain job competency requirement data.

[0039] Preferably, step S3 includes the following steps: Step S31: Acquire talent resume data; perform semantic feature recognition on the talent resume data to obtain resume semantic feature data; perform resume information semantic mapping on the resume semantic feature data to generate resume semantic mapping information; extract resume description text from the talent resume data based on the resume semantic mapping information to obtain resume description text information; Step S32: extracting educational experience features from the resume description text information to generate educational experience feature information; determining the talent's academic qualifications based on the educational experience feature information to obtain talent academic qualifications information; identifying the graduation school based on the talent academic qualifications information to generate talent graduation school information; determining the talent's major based on the educational experience feature information and the talent's graduation school information to obtain talent major information; Step S33: Integrate the talent's academic information, the talent's graduating school information, and the talent's major information to obtain the talent's educational background information; mark the talent's resume data with professional information characteristics based on the talent's educational background information to obtain talent professional characteristic data; determine the professional category of the talent professional characteristic data to generate talent industry category data; classify the talent's major information based on the talent industry category data to generate talent professional type data; Step S34: extracting work experience information from the talent resume data to obtain talent work experience data; performing career experience pattern recognition on the talent work experience data to generate talent career experience data; performing professional ability feature recognition on the talent resume data based on the talent career experience data and talent professional type data to obtain talent professional ability data; integrating the talent education background information, talent career experience data, and talent professional ability data to generate talent ability status data; Step S35: Perform intelligent matching analysis on the talent capability data and the job capability requirement data to obtain talent job matching data.

[0040] In the embodiment of the present invention, data collection technology is used to obtain talent resume data from a job search platform; semantic analysis tools are used to analyze the resume text and identify key ability keywords; for example, for the description "proficient in Java and Python programming languages" in the resume, "Java" and "Python" are used as ability keyword features; the identified ability keyword features are converted into vector form through semantic mapping technology, such as Word2Vec tool, to generate resume semantic mapping information; text mining technology is applied, combined with regular expressions and NLP tools, such as Jieba word segmentation, to extract resume description text information; named entity recognition (NER) technology is used to extract features of educational experience in the resume description text to generate educational experience feature information; through the educational experience feature information, a classification algorithm is used to determine the talent's academic qualifications and obtain the talent's academic information; based on the talent's academic information, entity recognition technology is used to identify the name of the graduation school in the resume; combined with the talent's academic information and the talent's graduation school information, the talent's major information is determined by matching and confirming the major name; data integration technology is used, For example, Python's pandas library integrates talent education information, talent graduation school information, and talent major information to obtain talent education background information; based on talent education background information, professional information features are marked on talent resume data to obtain talent professional feature data; talent professional feature data is classified and clustering technology, such as K-means technology, is used to obtain talent industry category data; talent major information is classified according to talent industry category data; text mining technology, such as TF-IDF-based keyword extraction, is used to extract work experience information from talent resume data; pattern recognition technology, such as sequence pattern mining, is used to extract talent work experience data; professional ability features of talent resume data are identified by combining talent career experience data and talent professional type data; data integration technology, such as Python's pandas library, is used to integrate talent education background information, talent career experience data, and talent professional ability data to generate talent ability status data; talent ability status data is matched with job ability requirement data to obtain talent job matching data.

[0041] Preferably, step S34 includes the following steps: Step S341: performing work experience feature recognition on the resume description text information to generate work experience feature data; performing work timeline extraction on the teaching work experience feature data to obtain work timeline data; arranging the work experience feature data in work time sequence according to the work timeline data to generate work sequence arrangement data; and extracting work experience information from the talent resume data based on the work sequence arrangement data to obtain talent work experience data; Step S342: Determine the work type of the talent's work experience data to generate work experience type information; identify the work project of the work experience type information to obtain work experience project data; extract the job position of the work experience project data to obtain past job position information; Step S343: Determine the job responsibilities of the talent's work experience data based on the past job position information to obtain past job responsibilities information; extract work experience content from the work experience item data based on the past job responsibilities information to generate past work content data; perform career experience pattern recognition on the past work content data to generate talent career experience data; Step S344: Identify the professional ability characteristics of the talent resume data based on the talent's career experience data and talent professional type data to obtain the talent's professional ability data; Step S345: Integrate the talent's educational background information, talent's professional ability data, and talent's career experience data to generate talent's ability status data.

[0042] In an embodiment of the present invention, named entity recognition (NER) technology is used to scan the resume description text information to specifically identify keywords and phrases related to work experience; for example, in the description of "serving as a software engineer during a certain period of time" in the resume, "software engineer" is used as a work experience feature; time extraction tools, such as the HeidelTime tool, are used to extract specific work timeline data from the resume description text; for example, from the description of "software engineer" mentioned above, the specific time information of "a certain period of time" is extracted as work timeline data; string processing and date comparison algorithms are used to sort the work experience feature data; combined with the work sequence arrangement data, NLP technology is used to extract work experience information from the talent resume data; for example, the job description and achievements of "software engineer" are extracted as work experience information; pattern matching technology, such as regular expressions, is used to analyze the talent work experience data to determine the job type; project identification is performed on the work experience type information to obtain work experience Project data; for example, identifying the software development projects participated in in the description of "software engineer"; analyzing work experience project data to extract past job position information; for example, extracting position information such as "project manager" or "team" from the project description; analyzing talent work experience data to obtain past job responsibilities information; for example, extracting specific responsibilities from the position of "software engineer", such as "responsible for software development and maintenance"; analyzing work experience project data based on past job responsibilities information; for example, extracting the technology stack tasks used by "software engineers" in projects; using pattern recognition technology to perform career experience pattern recognition on past work content data; based on talent career experience data and talent professional type data, performing professional ability characteristics recognition on talent resume data to obtain talent professional ability data; using data integration technology, such as Python's pandas library, to integrate talent education background information, talent career experience data and talent professional ability data to generate talent ability status data.

[0043] Preferably, step S344 includes the following steps: Step S3441: extracting past work achievement information from the talent's career experience data to generate past work achievement information; quantifying the work results of the past work achievement information to obtain work result quantified data; and mapping the talent's career experience data to work capability based on the work result quantified data to generate work capability mapping data. Step S3442: Identify professional ability characteristics of the resume description text information to generate professional ability characteristic information; annotate the professional ability characteristic information based on the talent professional type data to obtain professional ability annotated data; classify the professional ability characteristic information into professional type capabilities based on the professional ability annotated data to generate professional ability classification data; Step S3443: Using the professional competence classification data, the resume description text information is identified by professional competence certificates to obtain professional competence certificate information; the professional competence certificate information is classified into skill certificate grades to obtain skill certificate grade data; and work competence mapping data is matched with work competences according to the skill certificate grade data to generate work competence matching information; Step S3444: Associate the professional type data of the talent with the professional type skills according to the work skill matching information to obtain type skill association data; construct a professional skill map based on the type skill association data to generate a talent professional skill map; identify professional ability characteristics of the talent professional skill map in combination with the work ability mapping data to obtain talent professional ability data.

[0044] In an embodiment of the present invention, keyword extraction in text mining is used to analyze the resume description text information to identify features related to work achievements; for example, if the description in the resume is "responsible for designing and developing the company's core business system, and achieved good results in various indicators", then "designed and developed the company's core business system" is extracted as past work achievement information; numerical extraction technology is applied to extract specific numerical data from past work achievement information; for example, from the resume description "system performance improved by 30%", the value "30%" is extracted as work achievement quantitative data; based on the work achievement quantitative data, data analysis technology is used to map the talent's career experience and ability; professional ability features are identified for the resume description text information, specifically, "proficient in Java and Python programming languages" in the resume, "Java" and "Python" are used as professional ability keywords; professional ability feature information is annotated based on the talent's professional type data, and professional type ability classification is performed on the professional ability feature information based on the professional ability annotated data, for example For example, "Java" and "Python" are classified into the "back-end development" professional type; through professional ability classification data, text mining technology, such as TF-IDF algorithm, is used to analyze the resume description text information to identify professional skill certificate information; skill certificates are divided into levels to obtain skill certificate level data; specifically, the certificates are set to the corresponding levels, for example, "software designer certificate" is divided into "intermediate" level; according to the skill certificate level data, such as K-Means clustering, the work ability mapping data is matched; according to the work skill matching information, the association rule mining technology is used to associate the talent professional type data; based on the type skill association data, a professional skill map is constructed through graph construction technology, such as Neo4j graph database; for example, a graph is constructed to visualize the relationship between "software designer certificate", "software development" skills and "holders"; data integration technology, such as Python's pandas library, is used to integrate educational background information, career experience data and professional ability data to generate talent ability status data.

[0045] Preferably, step S35 includes the following steps: Step S351: Classify the talent's educational background information into educational hierarchies to generate talent's educational level data; compare the talent's educational level data with the job's educational background requirement data to obtain an educational background matching index; Step S352: Perform capability dimension mapping on the talent professional capability data to generate talent capability dimension data; perform skill multi-dimensional mapping on the talent capability dimension data and the job professional skill requirement data to obtain a professional skill matching index; Step S353: mining the professional experience elements of the talent professional experience data to generate professional experience element data; matching the professional experience element data with the job professional experience requirement data to obtain a professional experience matching index; Step S354: Quantitatively score the education background matching index, professional skills matching index, and career experience matching index to obtain comprehensive person-job matching scoring data; score and sort the comprehensive person-job matching scoring data to obtain matching scoring sorting data; intelligently match the talent capability data with the job capability requirement data based on the matching scoring sorting data to generate talent-job matching data.

[0046] In the embodiment of the present invention, the talent's educational background information is classified according to the educational level through data mapping technology; specifically, "master's degree", "bachelor's degree" and "junior college" are identified as different educational levels; the talent's educational level data is matched with the job education background requirement data by using data comparison technology, and through comparative analysis; if the job requires "bachelor's degree" and the talent's educational level data is "bachelor's degree", then the education background matching index is high; data analysis technology is used to map the talent's professional ability data to the ability dimension; for example, the ability of "software engineer" is subdivided into dimensions such as "programming ability" and "system design ability"; multi-dimensional mapping technology is used to compare the talent's ability dimension data with the job professional skill requirement data. If the job requirement includes "Java programming ability" and the talent's ability dimension data also includes this skill, then the matching degree is high; data mining technology is used to analyze the talent's career experience data and extract key professional experience factors, for example, extracting factors such as "project management experience" and "teamwork experience" from the work experience of talents; based on the professional experience factor data and the professional experience requirement data of the position, using the matching algorithm, if the position requires "more than three years of project management experience" and the professional experience factor data of the talent contains this item, the matching degree is higher; through quantitative analysis technology, the education background matching index, professional skills matching index and professional experience matching index are quantitatively scored to obtain the comprehensive person-job matching score data; specifically, the weighted average method is used to assign weights according to the importance of each indicator to calculate the comprehensive score; using the sorting algorithm, the comprehensive person-job matching score data is scored and sorted to obtain matching score sorting data; specifically, sorting is performed from high to low according to the comprehensive score to determine the matching order of talents and positions; based on the matching score sorting data, the talent ability situation data and the position ability requirement data are intelligently matched to generate talent-job matching data.

[0047] Preferably, step S4 includes the following steps: Step S41: constructing a person-job intelligent matching model based on the talent-job matching data to obtain a person-job intelligent matching pre-model, and training the person-job intelligent matching pre-model using the talent-job matching data to obtain a person-job intelligent matching training model; Step S42: performing a model cross-validation evaluation on the intelligent job matching training model to obtain evaluation data of the intelligent job matching training model; adjusting the model parameters of the intelligent job matching training model based on the evaluation data to obtain the intelligent job matching model; Step S43: Obtain enterprise demand change data; dynamically optimize the person-job intelligent matching model based on the enterprise demand change data to obtain a person-job intelligent matching optimization model; perform talent-job matching prediction on the talent capability data and job capability requirement data based on the person-job intelligent matching optimization model to generate person-job matching prediction data; visualize the person-job matching prediction data to generate a person-job intelligent matching report.

[0048] In this embodiment of the present invention, an intelligent job matching model is constructed based on talent-job matching data. Specifically, the model utilizes a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) network. CNN parameters include: 32 3x3 filters in the convolutional layer, a stride of 1, padding of 1, a ReLU activation function, a max-pooling layer, and a fully connected layer. BiLSTM parameters set the number of hidden units to 128, using 128 word vectors of size 100, and applying a two-step attention mechanism to extract sentence-level and global representations of job requirements. This results in a preliminary model for intelligent job matching. The cross-entropy loss function was used to calculate the difference between predictions and actual results. The Adam optimizer was employed with a learning rate of 0.001 and decay rates of 0.9 and 0.999. The pre-model for intelligent job matching was trained using the talent-job matching data. Early stopping was used during training to prevent overfitting, resulting in the intelligent job matching training model. The talent-job matching dataset was divided into a training set and a validation set, with a specific ratio of 8:2. A 5-fold cross-validation method was used to further divide the training set into five equal parts. In each round of validation, four of the parts were used as training data, and the remaining part was used as validation data. This cycle was repeated until each part had been used as validation data at least once. The Macro F1 score was selected as the primary evaluation metric. In each round of cross-validation, the model was trained using the training set and the Macro F1 score was calculated on the validation set. The evaluation results for each round were recorded, and the average Macro F1 score over five rounds was calculated to obtain the evaluation data for the intelligent job matching training model. The model parameters of the intelligent job-person matching training model are adjusted based on the evaluation data of the human-job matching training model. Specifically, the initial learning rate is set to 0.001. If the model performance is found to be slow or fluctuating during the training process, the learning rate is adjusted to 0.0005 or 0.0001; if the model performance is poor, a hidden layer is added, or more neurons are added to the existing layer to obtain the intelligent job-person matching model; through industry reports and recruitment platforms, the company's recruitment dynamics are monitored in real time to obtain data on changes in corporate demand; the intelligent job-person matching model is dynamically optimized based on the obtained data on changes in corporate demand, and the model feature weights are specifically adjusted; talent-job matching predictions are made for talent capability data and job capability requirement data based on the intelligent job-person matching optimization model; human-job matching prediction data is generated by calculating the matching degree between talent characteristics and job requirements; data visualization processing is performed on the human-job matching prediction data, and data visualization tools, such as Power BI tools, are used to convert the human-job matching prediction data into intuitive chart reports to obtain human-job matching reports.

[0049] Preferably, step S43 includes the following steps: Step S431: Acquire enterprise demand change data; monitor demand change trends on the enterprise demand change data to generate enterprise demand change trend information; identify employment market change characteristics on the enterprise demand change trend information to obtain employment market change characteristics; determine job demand changes on the enterprise demand change data based on the employment market change characteristics to obtain job demand change information; Step S432: extracting demand differences from the job demand change information to generate job demand difference data; determining the demand priority of the job demand change information based on the job demand difference data to obtain job demand priority information; dynamically adjusting the demand priority weights of the job-person intelligent matching model based on the job demand priority information to obtain priority weight adjustment data; dynamically optimizing the weights of the job-person intelligent matching model using the priority weight adjustment data to obtain a job-person intelligent matching optimization model; Step S433: Inputting the talent capability data and the job capability requirement data into the talent-job intelligent matching optimization model to perform talent-job matching prediction and obtain talent-job matching prediction data; Step S434: Process the person-job matching prediction data into information graphics to obtain a person-job matching prediction chart; compile a visual report for the person-job matching prediction chart to obtain a person-job intelligent matching report.

[0050] In an embodiment of the present invention, through industry reports and recruitment platforms, the recruitment dynamics of enterprises are monitored in real time to obtain enterprise demand change data; trend monitoring of enterprise demand change data is performed to generate enterprise demand change trend information; for example, the change in the number of job postings over time is monitored to identify the trend of demand growth or decrease; based on the changing characteristics of the employment market, a classification algorithm is used to classify enterprise demand change data to obtain job demand change information; data mining technology, such as association rule mining, is used to analyze job demand change information and extract demand differences; thereby determining the demand differences in skill combinations in different positions; based on the demand difference data, a priority sorting algorithm, such as the Analytic Hierarchy Process (AHP), is used to determine the priority of job requirements; for example, a priority is assigned to each job requirement based on the urgency and importance of the position. Priority score; based on the job requirement priority information, use online learning algorithm technology, such as online gradient descent, to dynamically adjust the demand priority weight of the person-job intelligent matching model to obtain priority weight adjustment data; use the priority weight adjustment data to dynamically optimize the weight of the person-job intelligent matching model to obtain a person-job intelligent matching optimization model; input the talent ability situation data and the job ability requirement data into the person-job intelligent matching optimization model, combine with logistic regression technology to predict talent-job matching and obtain person-job matching prediction data; use data visualization technology, such as Python's Matplotlib library, to graphically process the person-job matching prediction data to obtain a person-job matching prediction chart; use the Tableau visualization tool to integrate the person-job matching prediction chart into a visualization report to obtain a person-job intelligent matching report.

[0051] In this specification, a management system based on an intelligent job matching algorithm model is provided, which is used to execute the above-mentioned management method based on an intelligent job matching algorithm model. The management system based on an intelligent job matching algorithm model includes: The job semantic recognition module is used to obtain job description data; standardize the job description data to obtain standard job description data; perform semantic feature recognition on the standard job description data to obtain job semantic feature information; The job competency requirement module is used to identify industry terminology information from job semantic feature information to generate job industry terminology information; classify standard job description data into job industry types based on job industry terminology information to obtain job industry type data; and determine job competency requirements based on job industry type data to obtain job competency requirement data; The talent position intelligent matching analysis module is used to obtain talent resume data; extract the educational background of talent resume data to obtain talent educational background information; classify talent resume data into professional categories based on talent educational background information to generate talent professional type data; extract work experience information from talent resume data to obtain talent work experience data; perform career experience pattern recognition on talent work experience data to generate talent career experience data; identify professional ability characteristics of talent resume data based on talent career experience data and talent professional type data to obtain talent professional ability data; integrate talent educational background information, talent career experience data and talent professional ability data to generate talent ability status data; perform intelligent matching analysis on talent ability status data and job ability requirement data to obtain talent position matching data; The intelligent person-job matching model module is used to construct an intelligent person-job matching model using talent-job matching data to obtain an intelligent person-job matching model; obtain enterprise demand change data; dynamically optimize the intelligent person-job matching model based on enterprise demand change data to obtain an intelligent person-job matching optimization model; predict talent-job matching based on talent capability data and job capability requirement data based on the intelligent person-job matching optimization model to generate person-job matching prediction data; visualize the person-job matching prediction data to generate an intelligent person-job matching report.

[0052] The present invention uses a job semantic recognition module to perform standardized processing and semantic feature recognition of job description data, which can accurately extract the semantic feature information of the job and then identify the industry terminology information of the job; ensure the accuracy and consistency of the job description data, and provide a data basis for the subsequent job industry type classification and ability requirement determination. The present invention uses a job ability requirement module to classify the standard job description data into industry types based on job industry terminology information, which helps to classify jobs into corresponding industries and provides industry background data for the determination of job ability requirements; at the same time, the ability requirements are determined for job industry type data, providing clear ability standards for the subsequent matching of talents and jobs. The present invention uses a talent job intelligent matching analysis module to perform multi-dimensional analysis of talent resume data, specifically including education background extraction, professional talent classification, and work experience information extraction, which helps to fully understand the professional ability and career experience of talents, thereby obtaining talent ability situation data; the talent ability situation data and job ability requirement data are intelligently matched and analyzed, and the obtained talent job matching data can accurately reflect the degree of matching between talents and jobs. The present invention uses a person-post intelligent matching model module to construct a person-post intelligent matching model using talent-post matching data, which can achieve intelligent matching of talents and positions; uses the acquired enterprise demand change data and performs dynamic optimization to ultimately obtain a person-post intelligent matching optimization model, which can adapt to job-seeking changes and thus improve the timeliness and accuracy of matching; uses the person-post intelligent matching optimization model to predict talent-post matching, thereby obtaining person-post matching prediction data; uses data visualization technology to obtain a person-post intelligent matching report, which will provide intuitive and accurate talent recruitment support for enterprises; and ensures that the right position is pushed to the most suitable talent at the first time. Therefore, the present invention accurately identifies talent core competency information through semantic analysis technology, natural language processing technology, and machine learning algorithms, and deeply analyzes job demand information, thereby improving talent-post matching accuracy.

[0053] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0054] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A management method based on an intelligent job matching algorithm model, characterized in that: The following steps are involved: Step S1: obtaining job description data; performing standardization processing on the job description data to obtain standard job description data; performing semantic feature recognition on the standard job description data to obtain job semantic feature information; Step S2: Identify industry terminology information on job semantic feature information to generate job industry terminology information; classify standard job description data into job industry types according to the job industry terminology information to obtain job industry type data; determine job capability requirements on the job industry type data to obtain job capability requirement data; Step S3: Acquire talent resume data; extract education background from talent resume data to obtain talent education background information; classify talent resume data into professional talents according to talent education background information to generate talent professional type data; extract work experience information from talent resume data to obtain talent work experience data; perform career experience pattern recognition on talent work experience data to generate talent career experience data; perform professional ability feature recognition on talent resume data based on talent career experience data and talent professional type data to obtain talent professional ability data; integrate talent education background information, talent career experience data and talent professional ability data to generate talent ability situation data; perform intelligent matching analysis on talent ability situation data and job ability requirement data to obtain talent job matching data; Step S4: construct a person-job intelligent matching model using talent-job matching data to obtain a person-job intelligent matching model; obtain enterprise demand change data; dynamically optimize the person-job intelligent matching model according to the enterprise demand change data to obtain a person-job intelligent matching optimization model; perform talent-job matching prediction on the talent capability data and the job capability requirement data based on the person-job intelligent matching optimization model to generate person-job matching prediction data; visualize the person-job matching prediction data to generate a person-job intelligent matching report; Step S4 includes the following steps: Step S41: constructing a person-job intelligent matching model according to the talent-job matching data to obtain a person-job intelligent matching pre-model, and training the person-job intelligent matching pre-model using the talent-job matching data to obtain a person-job intelligent matching training model; Step S42: performing model cross-validation evaluation on the intelligent job matching training model to obtain evaluation data of the intelligent job matching training model; adjusting model parameters of the intelligent job matching training model based on the evaluation data of the intelligent job matching training model to obtain the intelligent job matching model; Step S43: obtaining enterprise demand change data; dynamically optimizing the person-job intelligent matching model according to the enterprise demand change data to obtain a person-job intelligent matching optimization model; predicting talent-job matching based on the talent capability data and job capability requirement data based on the person-job intelligent matching optimization model to generate person-job matching prediction data; visualizing the person-job matching prediction data to generate a person-job intelligent matching report; Step 43 includes the following steps: Step S431: Acquire enterprise demand change data; monitor demand change trends on the enterprise demand change data to generate enterprise demand change trend information; identify employment market change characteristics on the enterprise demand change trend information to obtain employment market change characteristics; determine job demand changes on the enterprise demand change data based on the employment market change characteristics to obtain job demand change information; Step S432: extracting demand differences from the job demand change information to generate job demand difference data; determining the demand priority of the job demand change information according to the job demand difference data to obtain job demand priority information; dynamically adjusting the demand priority weight of the job-person intelligent matching model based on the job demand priority information to obtain priority weight adjustment data; dynamically optimizing the weight of the job-person intelligent matching model using the priority weight adjustment data to obtain a job-person intelligent matching optimization model; Step S433: inputting the talent capability data and the job capability requirement data into the talent-job intelligent matching optimization model to perform talent-job matching prediction, and obtain talent-job matching prediction data; Step S434: Process the person-job matching prediction data into information graphs to obtain a person-job matching prediction chart; compile a visual report on the person-job matching prediction chart to obtain a person-job intelligent matching report.

2. The management method based on the intelligent matching algorithm model of people and positions according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: semantically map the job semantic feature information to generate job semantic mapping data; extract job description text from standard job description data based on the job semantic mapping data to obtain job description text information; perform industry terminology feature recognition on the job description text information to obtain industry terminology feature data; extract industry terminology information from the job description text information based on the industry terminology feature data to generate job industry terminology information; Step S22: Perform terminology frequency statistics on the job industry terminology information to obtain industry terminology frequency data; perform context association on the job description text information through the industry terminology frequency data to generate job description association information; perform job industry matching on the job industry terminology information in combination with the job description association information to obtain job industry matching data; Step S23: Identify the industry category of the job industry matching data to generate job industry category data; merge the standard job description data into job industry categories based on the job industry category data to obtain industry category merged data; divide the industry category merged data into industry types to obtain job industry type data; Step S24: Performing job capability requirement analysis on the standard job description data according to the job industry type data to obtain job capability requirement data.

3. The management method based on the intelligent matching algorithm model of people and positions according to claim 2 is characterized in that: Step S24 includes the following steps: Step S241: performing capability keyword feature recognition on the job description text information to obtain capability keyword features; performing capability element extraction on the job description text information according to the capability keyword features to generate job capability element information; Step S242: Mapping the position capability factor information with the position industry type data to obtain industry capability factor mapping data; determining the industry capability index of the position description text information through the industry capability mapping data to generate industry capability index data; Step S243: matching the industry capability requirements with the standard job description data according to the industry capability index data to obtain capability requirement matching information; extracting the requirement hierarchy structure from the capability requirement matching information to generate requirement hierarchy structure information; performing hierarchical decomposition on the requirement hierarchy structure information to obtain capability requirement segmentation data; Step S244: determining the education background requirement of the ability requirement segmentation data based on the job industry type data, and generating the job education background requirement data; identifying the professional skill requirement of the ability requirement segmentation data based on the job education background requirement data, and generating the job professional skill requirement data; extracting the professional experience requirement of the ability requirement segmentation data in combination with the job professional skill requirement data, and generating the job professional experience requirement data; Step S245: Integrate the job education background requirement data, job professional skill requirement data and job career experience requirement data to obtain job capability requirement data.

4. The management method based on the intelligent matching algorithm model of people and positions according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: Acquire talent resume data; perform semantic feature recognition on the talent resume data to obtain resume semantic feature data; perform resume information semantic mapping on the resume semantic feature data to generate resume semantic mapping information; extract resume description text from the talent resume data based on the resume semantic mapping information to obtain resume description text information; Step S32: extracting educational experience characteristics from the resume description text information to generate educational experience characteristic information; determining the talent's academic qualifications from the educational experience characteristic information to obtain the talent's academic qualifications information; identifying the graduate school from the educational experience characteristic information based on the talent's academic qualifications information to generate the talent's graduate school information; determining the talent's major from the educational experience characteristic information based on the talent's academic qualifications information and the talent's graduate school information to obtain the talent's major information; Step S33: Integrate the talent's education information, the talent's graduate school information and the talent's major information to obtain the talent's education background information; perform professional information feature marking on the talent's resume data according to the talent's education background information to obtain the talent's professional feature data; determine the professional category of the talent's professional feature data to generate talent industry category data; perform professional talent classification on the talent's major information according to the talent industry category data to generate talent professional type data; Step S34: extracting work experience information from the talent resume data to obtain talent work experience data; performing career experience pattern recognition on the talent work experience data to generate talent career experience data; performing professional ability feature recognition on the talent resume data based on the talent career experience data and talent professional type data to obtain talent professional ability data; integrating talent education background information, talent career experience data and talent professional ability data to generate talent ability status data; Step S35: Perform intelligent matching analysis on the talent capability data and the job capability requirement data to obtain talent job matching data.

5. The management method based on the intelligent matching algorithm model of people and positions according to claim 4 is characterized in that: Step S34 includes the following steps: Step S341: performing work experience feature recognition on the resume description text information to generate work experience feature data; performing work timeline extraction on the work experience feature data to obtain work timeline data; performing work time sequence arrangement on the work experience feature data according to the work timeline data to generate work sequence arrangement data; performing work experience information extraction on the talent resume data based on the work sequence arrangement data to obtain the talent work experience data; Step S342: determining the work type of the talent's work experience data to generate work experience type information; identifying the work project of the work experience type information to obtain work experience project data; extracting the job position of the work experience project data to obtain past job position information; Step S343: determining the job responsibilities of the talent's work experience data according to the past job position information to obtain the past job responsibilities information; extracting the work experience content from the work experience project data based on the past job responsibilities information to generate past work content data; performing career experience pattern recognition on the past work content data to generate the talent's career experience data; Step S344: Based on the talent's career experience data and the talent's professional type data, the talent's resume data is subjected to professional capability feature recognition to obtain the talent's professional capability data; Step S345: Integrate the talent's educational background information, talent's professional ability data and talent's career experience data to generate talent's ability status data.

6. The management method based on the intelligent matching algorithm model of people and positions according to claim 5 is characterized in that: Step S344 includes the following steps: Step S3441: extracting past work achievement information from the talent's professional experience data to generate past work achievement information; quantifying the work results of the past work achievement information to obtain work result quantified data; mapping the talent's professional experience data to work capabilities based on the work result quantified data to generate work capability mapping data; Step S3442: Identify professional ability characteristics of resume description text information to generate professional ability characteristic information; annotate professional ability characteristics of the professional ability characteristic information based on the talent professional type data to obtain professional ability annotated data; classify professional type capabilities of the professional ability characteristic information according to the professional ability annotated data to generate professional ability classification data; Step S3443: identify the professional skill certificate of the resume description text information through the professional ability classification data to obtain professional skill certificate information; classify the professional skill certificate information into skill certificate grades to obtain skill certificate grade data; match the work ability mapping data with work skills according to the skill certificate grade data to generate work skill matching information; Step S3444: Associate the professional type data of the talent with the professional type skills according to the work skill matching information to obtain type skill association data; construct a professional skill map based on the type skill association data to generate a talent professional skill map; identify professional ability characteristics of the talent professional skill map in combination with the work ability mapping data to obtain talent professional ability data.

7. The management method based on the intelligent matching algorithm model of people and positions according to claim 4 is characterized in that: Step S35 includes the following steps: Step S351: classify the talent education background information into education levels to generate talent education level data; compare the talent education level data with the job education background requirement data to obtain an education background matching index; Step S352: Mapping the talent's professional ability data to the ability dimension to generate talent's ability dimension data; mapping the talent's ability dimension data to the job's professional skill requirement data to the skill multi-dimensional data to obtain a professional skill matching index; Step S353: mining the professional experience elements of the talent professional experience data to generate professional experience element data; matching the professional experience element data with the job professional experience requirement data to obtain a professional experience matching index; Step S354: Quantitatively score the education background matching index, professional skill matching index and career experience matching index to obtain comprehensive scoring data for person-job matching; score and sort the comprehensive scoring data for person-job matching to obtain matching scoring sorting data; intelligently match the talent capability data with the job capability requirement data based on the matching scoring sorting data to generate talent-job matching data.

8. A management system based on an intelligent job matching algorithm model, characterized in that: Used to execute the management method based on the intelligent matching algorithm model of people and positions as claimed in claim 1, the management system based on the intelligent matching algorithm model of people and positions includes: The job semantic recognition module is used to obtain job description data; standardize the job description data to obtain standard job description data; perform semantic feature recognition on the standard job description data to obtain job semantic feature information; The job competency requirement module is used to identify industry terminology information of job semantic feature information and generate job industry terminology information; classify the standard job description data into job industry types according to the job industry terminology information to obtain job industry type data; determine the job competency requirements of the job industry type data to obtain job competency requirement data; The talent position intelligent matching analysis module is used to obtain talent resume data; extract the education background of talent resume data to obtain talent education background information; classify talent resume data into professional talents according to talent education background information to generate talent professional type data; extract work experience information from talent resume data to obtain talent work experience data; perform career experience pattern recognition on talent work experience data to generate talent career experience data; recognize professional ability characteristics of talent resume data based on talent career experience data and talent professional type data to obtain talent professional ability data; integrate talent education background information, talent career experience data and talent professional ability data to generate talent ability situation data; perform intelligent matching analysis on talent ability situation data and job ability requirement data to obtain talent position matching data; The people-job intelligent matching model module is used to construct a people-job intelligent matching model using talent-job matching data to obtain a people-job intelligent matching model; obtain enterprise demand change data; dynamically optimize the people-job intelligent matching model according to the enterprise demand change data to obtain a people-job intelligent matching optimization model; predict talent-job matching based on talent capability data and job capability requirement data based on the people-job intelligent matching optimization model to generate people-job matching prediction data; visualize the people-job matching prediction data to generate a people-job intelligent matching report.

Images