Position resume intelligent matching method and system based on multi-dimensional analysis

Abstract

The invention relates to the technical field of human resource information processing, in particular to a position resume intelligent matching method and system based on multi-dimensional analysis, and the system comprises a data collection module, a data processing module and a data matching module, and the data collection module is used for obtaining resume information data of job seekers and recruitment information data of enterprises; and the data processing module is used for extracting information dimensions in the resume information data and the recruitment information data. According to the method, all the information dimension scores in the hard information data and the soft information data are quantitatively calculated, and the matching score is calculated after the scores are combined, so that the matching degree of the job seekers and the positions can be more comprehensively evaluated, the demand difference of the job seekers is automatically identified according to the attention degree of the job seekers on the information dimensions, and the job seekers can be more accurately evaluated. And the weight coefficient is updated, so that the personalized demand of the job seeker is accurately met, the accurate matching rigidity requirement is provided for the job seeker and the enterprise, and a flexible secondary selection scheme can also be provided for the job seeker and the enterprise.

Description

Technical Field

[0001] The present invention relates to the technical field of human resource information processing, and in particular to a method and system for intelligently matching job resumes based on multi-dimensional analysis. Background Art

[0002] With the rapid development of global technology and the growing demand for human resource management, the traditional recruitment model can no longer meet the requirements of modern enterprises for efficiency and accuracy. The massive amount of corporate job requirements and job seekers' resume data makes the tasks of human resources departments in the recruitment process arduous and inefficient, and simply relying on manual matching of positions and resumes can no longer meet the timeliness and scientific needs of modern enterprises. In this context, the intelligent job resume matching system based on multi-dimensional analysis came into being. This system uses technical means to build an intelligent and automated talent screening and matching process, becoming an important tool for improving recruitment efficiency in the information age.

[0003] After searching, Chinese patent number CN201610784547.4 discloses a resume and position matching method, which includes: obtaining the job seeker's behavioral attribute information and the recruiter's behavioral attribute information based on the job seeker's and the recruiter's access records on the recruitment platform; determining a first matching score between the job seeker's resume and the recruiter's position based on the job seeker's resume and the recruiter's position; determining a second matching score between the job seeker's resume and the recruiter's position based on the job seeker's and the recruiter's behavioral attribute information; determining a total matching score between the job seeker's resume and the recruiter's position based on the first matching score and the second matching score.

[0004] The above scheme matches and analyzes the resumes of job seekers and the positions of recruiters, and also matches and analyzes the desire of both parties based on the behavioral attribute information of both parties. Based on multiple matching degree analyses between resumes and positions, comprehensive sorting is performed considering multiple factors, and the optimal matching set of resumes and positions is automatically generated, achieving optimal matching and accurate delivery, which can greatly improve the interview conversion rate of recruitment platforms, allowing job seekers to find the job interview opportunities they want faster and more accurately, and also allowing recruiting companies to find ideal talents more timely and accurately, and accordingly, the revenue of recruitment platforms can be increased.

[0005] However, most of the current job resume matching systems rely on keyword template matching or shallow text similarity calculations, with a single analysis method that easily ignores contextual semantics and detailed information, resulting in inaccurate matching. For example, most job resume matching systems only focus on basic hard condition matching, such as work experience, education, skill list and other data, and ignore soft conditions, such as work preferences, career interests, cultural values ​​and other data; in addition, dimensional data such as soft conditions are relatively subjective, and existing job resume matching systems find it difficult to accurately extract their quantitative data, which in turn makes it difficult for job resume matching systems to fully support the needs of job seekers and recruiting companies.

[0006] Therefore, a method and system for intelligent job resume matching based on multi-dimensional analysis is proposed to solve the above problems. Summary of the invention

[0007] Technical issues solved In view of the above-mentioned shortcomings of the prior art, the present invention provides a method and system for intelligent matching of job resumes based on multi-dimensional analysis, which can effectively solve the problem that most of the job resume matching systems in the prior art rely on basic hard condition data for matching while ignoring the consideration of soft conditions, and at the same time cannot accurately extract the subjective data in the soft conditions and perform quantification processing.

[0008] Technical Solution To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention provides a job resume intelligent matching system based on multi-dimensional analysis, including a data acquisition module, a data processing module and a data matching module. The data acquisition module is used to obtain the resume information data of job seekers and the recruitment information data of enterprises. The data processing module is used to extract the information dimensions in the resume information data and the recruitment information data, and calculate the job seeker's suitability score based on the information dimensions. And enterprise adaptability And output, the data matching module is based on the job seeker's suitability score And enterprise adaptability Calculate the matching score between job seekers and companies , using matching score Determine whether the resume information data of job seekers matches the recruitment information data of the company; build an optimization model based on the information dimension to obtain the optimized matching score ; The data matching module is based on the optimized matching score Construct a matching matrix M, input the matching matrix M into the matching model, and obtain the global optimal matching result.

[0009] Furthermore, the resume information data and recruitment information data both include hard information data and soft information data; wherein, the information dimensions of the hard information data include: educational information, work information, skill information and demand information; the information dimensions of the soft information data include: career interests, career direction, cultural fit and career stability.

[0010] Furthermore, the calculation of the job seeker's suitability score And enterprise adaptability The methods include: defining information dimension scores in hard information data and soft information data; calculating the hard scores of job seekers based on the information dimension scores , Soft Rating of Job Applicants , Enterprise hard scoring and enterprise soft rating , the calculation formula is: ; In the formula, Score the job applicant's academic qualifications. Rating job seekers jobs, Score job applicant skills, Score job seekers' needs. is the influence coefficient of the corresponding information dimension; ; In the formula, Score job applicant interest, Score the job seeker's orientation, Score the culture of job seekers. Score the stability of job seekers. is the influence coefficient of the corresponding information dimension; ; In the formula, Score the company's academic qualifications. Rate the company's work. Score the skills of your business, Score the needs of the business; ; In the formula, Score the interest of the business, Score the direction of the business, Rate your company culture. Score the stability of the business; ; ; In the formula, and are the weight coefficients of hard information data and soft information data respectively.

[0011] Furthermore, the calculation of the matching score between the job seeker and the enterprise The formula is: ; In the formula, and The job seeker suitability scores are And enterprise adaptability Weight coefficient, matching score Used to compare with pre-set thresholds for comparison.

[0012] Furthermore, the method of constructing the optimization model includes: constructing a feature vector according to the information dimension score, normalizing the information dimension score, mapping all feature values ​​to the [0,1] interval, and obtaining a hard information feature vector and soft information feature vector ; Using hard information feature vector and soft information feature vector Constructing a comprehensive feature vector ; Calculate the mathematical distance between the job applicant feature vector and the position feature vector. The calculation formula is: distance ; In the formula, represents the job seeker feature vector, ; represents the position feature vector, ; n is the number of features in the vector; , is the value of the i-th eigenvalue, belonging to the job seeker eigenvector and the position feature vector The i-th dimension of Calculate each sample and its target sample Distance , and record the distances in order And the corresponding sample index i; according to the calculated distance d value, all samples are sorted in ascending order to obtain a sorted list ; In the formula, is the sorted distance; is the minimum distance after sorting, the corresponding sample is the target sample The closest sample; is the maximum distance after sorting, the corresponding sample is the target sample The farthest sample; select the first K samples with the shortest distance from the sorted list List to construct the nearest neighbor set ; Assign weights to each nearest neighbor sample , the calculation formula is: ; In the formula, is the distance to the ith neighbor; Optimize the job seeker's suitability score And enterprise adaptability , the calculation formula is: ; In the formula, To optimize the suitability score of job seekers; represents the job seeker fitness score of the i-th neighbor; ; In the formula, The adaptability score for the optimized enterprise; represents the enterprise fitness score of the i-th neighbor; Using the optimized job seeker suitability score And the optimized enterprise adaptability score Calculate optimized match scores between job seekers and companies .

[0013] Furthermore, the matching model is constructed in the following manner: Define the format of the matching matrix M: The rows of the matching matrix M represent each job applicant ; The columns of the matching matrix M represent each position ; Matching matrix M elements Representing job seekers With position Optimized match score of ; Based on the elements of each row in the matching matrix M size, determine each job seeker Priority list of positions ; Based on the elements of each column in the matching matrix M The size of each position Priority list of job seekers ; Set input as a priority list of positions and a priority list of job seekers ; Set the output to the best matching result; Initialize the matching state and perform step-by-step matching, repeating the step-by-step matching operation until all job seekers are matched. All matched or all positions are occupied, and all job seekers and Position Until there are no more better options; output the optimal matching result without any obstruction pairs.

[0014] Furthermore, the data matching module constructs a feedback model based on the job seekers' dynamic behaviors and selection preferences, and generates feedback information for updating the weight coefficients of the hard information data. and the weight coefficient of soft information data , get the updated hard information data weight coefficient that meets the constraint conditions and updated soft information data weight coefficient ; Based on the updated hard information data weight coefficient and updated soft information data weight coefficient Calculate the updated job seeker suitability score and updated enterprise suitability scores , calculate the updated matching score , used to return to the matching model to obtain a new optimal matching result; The feedback information includes: the job seeker's score in the information dimension of the positions that were not successfully matched in the first round, the automatically assigned secondary positions, and the newly selected positions; the constraints are .

[0015] Furthermore, the weight coefficient of the updated hard information data and the weight coefficient of soft information data The methods include: ; In the formula, is the learning rate; k is the index of the information dimension; It represents the sum of the absolute values ​​of the difference values ​​of the information dimension scores in the hard information data; n is the total number of information dimensions in the hard information data; is the difference value of the information dimension, and the calculation formula is: ; In the formula, Score the information dimension of the secondary position, Score the dimensions of the new position; ; In the formula, It represents the sum of the absolute values ​​of the difference values ​​of the information dimension scores in the soft information data; m is the total number of information dimensions in the soft information data.

[0016] Furthermore, the data matching module Input into the weight dynamic adjustment model and compare with the preset threshold T; if , then increase the weight of the information dimension with index k; if , the adjustment of the weight by the information dimension with index k is ignored.

[0017] A method for intelligently matching job resumes based on multi-dimensional analysis, comprising the following steps: Step 1: Collect the resume information data of job seekers and the recruitment information data of enterprises, and extract the information dimensions; Step 2: Calculate the applicant's suitability score and the company's suitability score based on the information dimension; Step 3: Calculate the matching score between job seekers and companies based on the job seeker suitability score and the company suitability score, compare the matching score with the preset threshold score, and give priority to matching job seekers and companies with matching scores greater than or equal to the threshold score.

[0018] Beneficial Effects Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects: This solution quantifies the scores of all information dimensions in the hard information data and soft information data, and combines them to form a job seeker suitability score. And enterprise adaptability , can more comprehensively evaluate the matching degree between job seekers and positions; hard information data can evaluate the basic qualifications of job seekers, and soft information data can evaluate the potential fit of job seekers. When evaluating job seekers, if the hard information data of job seekers fully meets the job requirements, but the soft information data score is low, the final comprehensive score will be appropriately reduced, thereby avoiding the risk of recruitment failure. On the contrary, if the hard information data of job seekers is slightly lower than the job requirements, but the soft information score is high, the comprehensive score will be appropriately increased, thereby providing opportunities for job seekers; This solution can more accurately meet the two-way matching needs of job seekers and companies through the setting of feedback model and weight dynamic adjustment model; in the matching process, according to the importance of job seekers to hard information data and soft information data, the differences in job seekers' needs are automatically identified, and the weight coefficient of hard information data is adjusted accordingly. and the weight coefficient of soft information data It can be updated to accurately meet the personalized needs of job seekers, which can provide job seekers and companies with both rigid requirements for precise matching and flexible alternative plans. At the same time, it will provide feedback on each failed match between job seekers and companies, record job seekers' behavioral data, and then capture job seekers' demand preferences, improve the adaptability of the matching model, and gradually optimize the matching effect, making the matching logic more flexible and adaptable, thereby greatly improving the matching success rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 The figure is a schematic diagram of the composition of the job resume intelligent matching system in the first embodiment of the present invention.

[0021] Figure 2 The figure is a flow chart of the method for intelligently matching job resumes in the second embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] The present invention will be further described below in conjunction with the embodiments.

[0024] Embodiment 1: See attached Figure 1 This case proposes a job resume intelligent matching system based on multi-dimensional analysis, including a data collection module, a data processing module and a data matching module; the data collection module is used to obtain the resume information data of job seekers and the recruitment information data of enterprises; the data processing module is used to extract the information dimensions in the resume information data and the recruitment information data, and calculate their respective fitness scores (respectively, the job seeker fitness score and the enterprise fitness score). And enterprise adaptability ) and then output; the data matching module is used to receive the fitness score output by the data processing module and calculate the matching score between the job seeker and the enterprise , and is divided into Compare and determine whether the resume information data of job seekers and the recruitment information data of enterprises match each other, so as to provide the best two-way choice for job seekers and enterprises.

[0025] Specifically, resume information data and recruitment information data both include hard information data and soft information data; among them, the information dimensions of hard information data include: educational information (i.e. the applicant's own alma mater, degree, major, graduation time and other data and the company's educational and professional requirements for applicants), work information (i.e. the applicant's years of work, relevant industry experience and achievements obtained during work, and the company's work requirements for applicants), skill information (i.e. the applicant's professional skills, professional qualification certificates obtained, and the company's skill requirements for whether the applicant has the job qualifications), demand information (i.e. the applicant's salary expectations and target work location, and the information on the job form provided by the company); the information dimensions of soft information data include: career interests (i.e. the applicant's own interest in the position and the attractiveness of the recruitment industry and position to the applicant), career direction (i.e. the applicant's plan for his or her own career development and the company's development concept for the position), cultural fit (i.e. whether the applicant can adapt to and integrate into the company's work culture), and career stability (i.e. whether the company's job position has long-term development, or whether the applicant has long-term job stability).

[0026] Furthermore, in this solution, the job seeker suitability score is calculated based on the information dimensions in the resume information data and the recruitment information data. And enterprise adaptability The methods include: Define the information dimension scores in the hard information data, namely, academic degree score (including applicants’ academic qualifications rating and enterprise academic rating ), work rating (including job applicant job ratings and enterprise work rating ), skill rating (including job seeker skill ratings and enterprise skills rating ) and demand score (including job seeker needs score and Enterprise Needs Rating ); Define the information dimension scores in the soft information data, namely interest scores (including job seeker interest rating and business interest score ), direction score (Including job seeker orientation score and enterprise direction score ), cultural score (Including job seeker culture score and corporate culture rating ) and stability score (Including applicant stability score and enterprise stability score ); Calculate the hard score of job applicants based on information dimension scores and soft ratings of job applicants , the calculation formula is: ; In the formula, is the influence coefficient of the corresponding information dimension, reflecting the impact of each information dimension on the overall matching score the relative importance of ; In the formula, is the influence coefficient of the corresponding information dimension, reflecting the impact of each information dimension on the overall matching score the relative importance of Based on hard scoring of job applicants and soft ratings of job applicants Calculate the candidate's suitability score , the calculation formula is: ; In the formula, and They are the weight coefficients of hard information data and soft information data, respectively, reflecting the overall matching score of each information dimension the relative importance of .

[0027] Calculate the enterprise hard score based on the information dimension score and enterprise soft rating , the calculation formula is: ; ; Based on the company's hard score and enterprise soft rating Calculate the enterprise fit score , the calculation formula is ; Based on the above content, this solution provides an operational basis for the accurate matching of job seekers and enterprises by mechanically quantifying and calculating the information dimensions in resume information data and recruitment information data.

[0028] It is worth noting that job applicants are hard-scored. and corporate hard ratings It is usually quantified and regularized, and can be calculated by explicit quantification or assignment based on the degree of matching, specifically: Education score The calculation method is: The education requirements are set to several levels, such as: if the education of the job seeker is higher than the minimum requirement of the position, the value is 1; if the education of the job seeker is equal to the minimum requirement of the position, the value is 0.8; if the education requirement of the job seeker is lower than the position requirement but close to the position requirement, the negative value is 0.4; if the education requirement of the job seeker does not match the position requirement at all, the negative value is 0; The matching degree of professionalism is set to several levels, such as: if the applicant's major and the job requirements are completely matched, the value is assigned to 1; if the applicant's major and the job requirements are partially matched (such as belonging to the same subject category, such as computer technology and software engineering), the value is assigned to 0.8; if the applicant's major and the job requirements are not matched but related (belonging to adjacent subject areas or have a certain intersection, such as computer technology and mathematics), the value is assigned to 0.4; if the applicant's major and the job requirements do not match at all, the value is assigned to 0; The scoring values ​​for colleges and universities are also set to several levels, such as: top colleges and universities, assigned a value of 1; key undergraduate colleges, assigned a value of 0.7; ordinary undergraduate colleges, assigned a value of 0.5; and technical colleges, assigned a value of 0.1.

[0029] .

[0030] Work Rating The calculation method is: ; In the formula, Score industry relevance to measure whether the applicant's work experience is relevant to the industry of the target position; Scoring job achievement to measure whether the applicant has significant actual performance during work; , , is the weight coefficient of the corresponding parameter; industry relevance score and job achievement ratings The values ​​are assigned according to the degree of matching.

[0031] Skill Rating The calculation method is: ; Demand Rating The calculation method is: ; In the formula, is the salary score, and its calculation formula is , by calculating the ratio between the salary provided by the enterprise and the expected salary of the job seeker and Quantitative calculations are performed. If the ratio is greater than 1, it means that the company's salary level fully meets the job seeker's target expectations and even provides additional attraction. If the ratio is less than 1 and the smaller the ratio, the greater the gap between the company's salary level and the job seeker's. Score the workplace using the formula , where d is the actual distance between the job seeker's address and the company's office. The maximum acceptable distance threshold set for job seekers, To ensure that the calculation result is not negative and avoid unreasonable negative scores; Scoring the work form is used to match whether the job seeker accepts the work model provided by the company, and the value is also assigned based on the degree of match; , , is the weight coefficient of the corresponding parameter.

[0032] Soft Scoring of Job Applicants and enterprise soft rating It is calculated based on the information dimensions in the soft information data. The information dimensions in the soft information data are related to the information dimensions in the hard information data. Usually, they cannot be directly quantified. However, by analyzing the user's resume content, behavioral data or feedback, quantitative modeling is built based on the analyzed data to capture these information dimensions, map them to the standardized framework of the system, and then quantify them. Specifically: They are: Interest score The calculation method is: ; In the formula, is a similarity function used to calculate the semantic similarity between job search keywords in resume information data and job position keywords in recruitment information data (for example, by converting job search keywords and job position keywords into word vectors and using cosine similarity to calculate the semantic similarity between job search keywords and job position keywords). The score range is [0, 1]. , indicating that the job search keywords and the job position keywords completely match (i.e., they have the same semantics). , indicating that the job search keywords and the job position keywords partially match (i.e., contain synonymous relationships and correlations), if , indicating that the job search keywords and job position keywords do not match at all; n is the number of matching job search keywords and job position keywords; and then quantified to obtain the interest score ; Direction Rating The calculation method is: ; By extracting the description of career goals from the resume information data of job seekers and extracting the position development path from the recruitment information data, and then using the similarity function to calculate the similarity between the career goals of job seekers and the position development path of the recruitment occupation; and then quantifying the direction score ; Cultural Rating Calculation method: ; By extracting descriptions of personality keywords from the resume information data of job seekers, and extracting descriptions of corporate culture keywords from recruitment information data, and then using a similarity function to calculate the similarity between the personality keywords of job seekers and the cultural keywords of the company; and then quantifying the cultural score ; Stability score The calculation method is: ; In the formula, The average duration of each job held by job seekers; is a scoring function that converts the average duration Mapping to stability score , in this case, the scoring function can be set as a piecewise function, such as: , by taking the average duration Set it to three intervals, and map different intervals to different values ​​to quantify the stability score .

[0033] In summary, by calculating the scores of all information dimensions in the hard information data and the soft information data, and combining them to form the job seeker suitability score And enterprise adaptability , can more comprehensively evaluate the degree of match between job seekers and positions; hard information data can evaluate the basic qualifications of job seekers, and soft information data can evaluate the potential fit of job seekers. When evaluating job seekers, if the hard information data of job seekers fully meets the job requirements, but the soft information data score is low, the final comprehensive score will be appropriately lowered to avoid the risk of recruitment failure. Conversely, if the job seeker's hard information data is slightly lower than the job requirements, but the soft information score is high, the comprehensive score will be appropriately increased, thereby providing opportunities for job seekers.

[0034] The data matching module calculates the matching score between job seekers and companies The method is: ; and The job seeker suitability scores are And enterprise adaptability The weight coefficient of .

[0035] Define the threshold score High matching and low matching , the matching score and threshold For comparison: like , indicating that the job seeker and the company's position are highly matched in both hard and soft information data, and are suitable for priority recommendation; like , indicating that there is a certain degree of match between the job seeker and the company's position, but some dimensions do not reach the optimal standard. It is suitable for recommending job seekers or company positions in specific scenarios, and further communication and confirmation is required between the job seeker and the company; like , indicating that the job seeker and the company's position are seriously inconsistent in terms of hard information data and soft information data, and no recommendation is recommended. It is suitable for excluding inappropriate job seekers or positions to improve screening efficiency; Finally, Job seekers and companies can recommend each other, providing the best two-way choice for job seekers and companies.

[0036] The data processing module is used to score the match between job seekers and companies. When performing calculations, define the KNN algorithm to optimize the matching score The optimization model constructs a feature vector based on the information dimension scores of job seekers and companies, normalizes the information dimension scores, maps all eigenvalues ​​to the [0,1] interval, and obtains the hard information feature vector and soft information feature vector ; Then use the hard information feature vector and soft information feature vector Constructing a comprehensive feature vector ; Define Euclidean distance as a measurement method for job seekers and companies, and calculate the mathematical distance between the job seeker feature vector and the position feature vector (that is, the degree of proximity between the job seeker and the company in the feature space). The smaller the distance between the two, the closer they are; the larger the distance, the greater the difference in their features, that is, the lower the matching degree. The calculation formula is: distance ; In the formula, represents the job seeker feature vector, ; represents the position feature vector, ; n is the number of features in the vector, that is, the dimension of the feature vector, which indicates the number of elements involved in the similarity calculation; , is the value of the i-th eigenvalue, belonging to the job seeker eigenvector and the position feature vector The i-th dimension of To all job seekers and Position , calculate each sample and its target sample Distance , and record the distances in order And the corresponding sample index i; according to the distance d value calculated above, all samples are sorted in ascending order to obtain a sorted list ; In the formula, is the sorted distance; is the minimum distance after sorting, the corresponding sample is the target sample The closest sample; is the maximum distance after sorting, the corresponding sample is the target sample The farthest sample; by sorting, the sample with the shortest distance is placed at the top of the sorted list List, and the sample with the longest distance is placed at the end; select the first K samples (neighbors) with the shortest distance from the sorted list List to construct the nearest neighbor set ; Assign weights to each nearest neighbor sample , reflecting the distance and matching score The correlation is calculated as follows: ; In the formula, is the distance to the i-th neighbor; from the above formula, we can see that the samples with smaller distances have higher weights because they are closer and have greater reference value; Use the scores of the K neighbors found by the optimization model to optimize the job seeker's suitability score And enterprise adaptability , the calculation formula is: ; In the formula, The optimized job seeker's fitness score indicates that a more reasonable comprehensive score is obtained after combining the K neighbors' rating information; represents the job seeker fitness score of the i-th neighbor; ; In the formula, is the optimized enterprise fitness score, which means that after combining the K neighbor scoring information, a more reasonable comprehensive score is obtained; represents the enterprise fitness score of the i-th neighbor; Using the optimized job seeker suitability score And the optimized enterprise adaptability score Calculate optimized match scores between job seekers and companies .

[0037] Furthermore, in this case, it is necessary not only to calculate the optimized matching score between a single job seeker and a single corporate position We also need to consider that a job seeker may be suitable for different positions in multiple companies, and a company's position may be suitable for multiple different job seekers. Therefore, it is necessary to find the most suitable combination among all job seekers and company positions to meet the needs of both parties as much as possible. The data matching module is based on the optimized matching score of each job seeker and each position. Construct a matching matrix M, where each row of the matching matrix M represents each job seeker (like There are n job seekers in total), the columns of the matching matrix M represent each position (like There are m positions in total), matching the elements of the matrix M Representing job seekers With position Optimized match score of , the range is [0, 1], the higher the value, the higher the matching degree.

[0038] Based on the elements of each row in the matching matrix M size, determine each job seeker Priority list of positions ; Based on the elements of each column in the matching matrix M The size of each position Priority list of job seekers ; Input the matching matrix M into the pre-built matching model to obtain the global optimal matching result; The matching model is constructed as follows: Set input (i.e., priority list of positions and a priority list of job seekers ) and output (optimal matching result); then initialize the matching state, that is, all job seekers All positions are unmatched. are all vacant; then they are matched step by step, that is, each job seeker Priority list of positions Jobs in Apply in order, if the position is prioritized Jobs in If there is no match, accept the current application, i.e. job seeker Matching positions If the position There are already matching job seekers (denoted as ), but new applicants (job seekers ) have a higher priority, i.e. job seekers Optimized match score of Bigger than job seekers Optimized match score of , then the position Change to a new job seeker, i.e. position Matching job seekers At the same time, reject the original matching object and return it to a free state, that is, job seekers Change to unmatched state; repeat the above steps to make the rejected job seekers Continue to submit to their job priority list Next job in Submit an application and continue until all job seekers are All matched or all positions are occupied, and all job seekers and Position Until there are no more better options; the optimal matching result finally output meets the stability (that is, there is no blocking pair).

[0039] Example: Assume there are three job seekers and three positions: job seeker Priority list of positions ; job seeker Priority list of positions ; job seeker Priority list of positions ; Position Priority list of job seekers ; Position Priority list of job seekers ; Position Priority list of job seekers ; Initialize the matching state, that is, job seekers , , All are free status, positions , , All are vacant; start matching gradually, round 1: job seeker To the position Apply for a job Accepting job applicants ; job seeker Also to the position Apply for a job Compare Job Applicants and job seekers Priority, still choose job seekers , reject job seekers ; job seeker Again to the position Apply for a job Accepting job applicants ; job seeker To the position Apply for a job Compare Job Applicants and job seekers Priority for selecting job seekers , reject job seekers ; The matching status at this time is: Job seeker Matching positions ,job seeker Matching positions ,job seeker It is in free state; start round 2: job seeker Also to the position Apply for a job Accepting job applicants ; The matching status at this time is: Job seeker Matching positions ,job seeker Matching positions ,job seeker Matching positions ; The matching is completed, all job seekers have been matched, and the results are stable.

[0040] By setting up the matching model, job seekers can actively initiate matching and positions respond in an interactive mode, which is iterated repeatedly until the matching is stable. This can ensure the stability of the two-way matching between job seekers and corporate positions. At the same time, the priority ranking of job seekers and corporate positions is taken into consideration, and the fairest possible distribution is achieved in the process of two-way matching.

[0041] It is worth mentioning that after the matching model completes the job matching between job seekers and companies, although it can solve the basic stability problem, in the multi-round matching process, some job seekers may still encounter incomplete matching problems due to missing information or weight offset during matching; for example, job seekers did not enter the highest matching position in the first round of matching, and after matching with the secondary matching position, the reverse position is not suitable and needs to reapply for the primary position; in this process, the data matching module builds a feedback model based on the dynamic behavior and selection preferences of job seekers, and generates feedback information to optimize the weight coefficient of the hard information data. and the weight coefficient of soft information data , in order to improve the success rate and accuracy of subsequent matching between job seekers and positions.

[0042] The feedback model is constructed as follows: Collect job seekers' behavior records, including: the primary positions (i.e. the positions with the highest matching degree) that job seekers failed to match in the first round, the secondary positions (i.e. the positions with lower matching degree) that job seekers were assigned in the second round of matching, and the new positions that job seekers reapplied for; collect the information dimension scores of primary positions and secondary positions; and collect the difference value DV between the information dimension scores, and weight the hard information data based on the difference value DV and the weight coefficient of soft information data Update to get the updated hard information data weight coefficient and updated soft information data weight coefficient , and then calculate the updated job seeker suitability score and updated enterprise suitability scores , and then use the updated job seeker suitability score and updated enterprise suitability scores Calculate updated matching score , and the updated matching score Return to the matching model, and then update the matching between job seekers and corporate positions to obtain a new optimal matching result.

[0043] Weight coefficient for hard information data and the weight coefficient of soft information data The update is done by: Difference ; In the formula, Score the information dimension of the secondary position, Score the dimensions of the new position; ; In the formula, is the weight coefficient of the updated hard information data; is the learning rate; k is the index of the information dimension, representing the specific information dimension; It represents the sum of the absolute values ​​of the difference values ​​of the information dimension scores in the hard information data, reflecting the overall matching deviation of the hard information data; n is the total number of information dimensions in the hard information data, which is used for normalization calculation; ; In the formula, is the weight coefficient of the updated soft information data; It represents the sum of the absolute values ​​of the difference values ​​of the information dimension scores in the soft information data, reflecting the overall matching deviation of the soft information data; m is the total number of information dimensions in the soft information data; At the same time, add constraints, .

[0044] In calculating the difference values ​​of different information dimensions Then, the difference Input into the pre-built dynamic weight adjustment model and convert the difference Compare with the preset threshold T; if , it means that when the matching model matches job seekers and companies, the actual needs of job seekers are greatly deviated, so the weight of the information dimension with index k needs to be increased; for example , then it is necessary to increase the weight coefficient of the updated hard information data , in order to improve the updated job seeker suitability score Scoring updated matches influence; if , indicating that the matching module's matching on the information dimension with index k is accurate enough without obvious deviation, so the weight adjustment can be turned to other dimensional information to optimize the overall matching.

[0045] In summary, this solution can more accurately meet the two-way matching needs of job seekers and companies through the setting of feedback model and dynamic weight adjustment model; in the matching process, according to the importance of job seekers to hard information data and soft information data, the differences in job seekers' needs are automatically identified, and then the weight coefficient of hard information data is adjusted. and the weight coefficient of soft information data It can be updated to accurately meet the personalized needs of job seekers, which can provide job seekers and companies with both rigid requirements for precise matching and flexible alternative plans. At the same time, it will provide feedback on each failed match between job seekers and companies, record job seekers' behavioral data, and then capture job seekers' demand preferences, improve the adaptability of the matching model, and gradually optimize the matching effect, making the matching logic more flexible and adaptable, thereby greatly improving the matching success rate.

[0046] Embodiment 2: See attached Figure 2 Based on the first embodiment, this case proposes a method for intelligent matching of job resumes based on multi-dimensional analysis, including the following steps: Step 1: Collect the resume information data of job seekers and the recruitment information data of enterprises, and extract the information dimensions; Step 2: Calculate the applicant's suitability score and the company's suitability score based on the information dimension; Step 3: Calculate the matching score between job seekers and companies based on the job seeker suitability score and the company suitability score, compare the matching score with the preset threshold score, and give priority to matching job seekers and companies with matching scores greater than or equal to the threshold score.

[0047] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. A job resume intelligent matching system based on multi-dimensional analysis, including a data collection module, a data processing module and a data matching module. The data collection module is used to obtain the resume information data of job seekers and the recruitment information data of enterprises, and is characterized in that: The data processing module is used to extract information dimensions from resume information data and recruitment information data, and calculate the job seeker's suitability score based on the information dimensions. And enterprise adaptability And output, the data matching module is based on the job seeker's suitability score And enterprise adaptability Calculate the matching score between job seekers and companies , using matching score Determine whether to match the resume information data of the job seeker with the recruitment information data of the enterprise; Build an optimization model based on information dimensions to obtain optimized matching scores ; The data matching module is based on the optimized matching score Construct a matching matrix M, input the matching matrix M into the matching model, and obtain the global optimal matching result.

2. According to claim 1, a job resume intelligent matching system based on multi-dimensional analysis is characterized in that: The resume information data and recruitment information data both include hard information data and soft information data; wherein, the information dimensions of the hard information data include: educational information, work information, skill information and demand information; the information dimensions of the soft information data include: career interests, career direction, cultural fit and career stability.

3. According to claim 2, a job resume intelligent matching system based on multi-dimensional analysis is characterized in that: The calculation of the job applicant's suitability score And enterprise adaptability The methods include: defining information dimension scores in hard information data and soft information data; calculating the hard scores of job seekers based on the information dimension scores , Soft Rating of Job Applicants , Enterprise hard scoring and enterprise soft rating , the calculation formula is: ； In the formula, Score the job applicant's academic qualifications. Rating job seekers jobs, Score job applicant skills, Score job seekers' needs. is the influence coefficient of the corresponding information dimension; ； In the formula, Score job applicant interest, Score the job seeker's orientation, Score the culture of job seekers. Score the stability of job seekers. is the influence coefficient of the corresponding information dimension; ； In the formula, Score the company's academic qualifications. Rate the company's work. Score the skills of your business. Score business needs; ； In the formula, Score the interest of the business, Score the direction of the business, Rate your company culture. Score the stability of the business; ； ； In the formula, and are the weight coefficients of hard information data and soft information data respectively.

4. According to claim 3, a job resume intelligent matching system based on multi-dimensional analysis is characterized in that: Calculate the matching score between job seekers and enterprises The formula is: ; In the formula, and The job seeker suitability scores are And enterprise adaptability Weight coefficient, matching score Used to compare with pre-set thresholds for comparison.

5. According to claim 4, a job resume intelligent matching system based on multi-dimensional analysis is characterized in that: The method of constructing the optimization model includes: constructing a feature vector according to the information dimension score, normalizing the information dimension score, mapping all feature values ​​to the [0,1] interval, and obtaining a hard information feature vector and soft information feature vector ; Using hard information feature vector and soft information feature vector Constructing a comprehensive feature vector ; Calculate the mathematical distance between the job applicant feature vector and the position feature vector. The calculation formula is: distance ; In the formula, represents the job applicant feature vector, ; represents the position feature vector, ; n is the number of features in the vector; , is the value of the i-th eigenvalue, belonging to the job seeker eigenvector and the position feature vector The i-th dimension of Calculate each sample and its target sample Distance , and record the distances in order And the corresponding sample index i; according to the calculated distance d value, all samples are sorted in ascending order to obtain a sorted list ; In the formula, is the sorted distance; is the minimum distance after sorting, the corresponding sample is the target sample The closest sample; is the maximum distance after sorting, the corresponding sample is the target sample The farthest sample; select the first K samples with the shortest distance from the sorted list List to construct the nearest neighbor set ; Assign weights to each nearest neighbor sample , the calculation formula is: ; In the formula, is the distance to the ith neighbor; Optimize the job seeker's suitability score And enterprise adaptability , the calculation formula is: ; In the formula, To optimize the suitability score of job seekers; represents the job seeker fitness score of the i-th neighbor; ; In the formula, The adaptability score for the optimized enterprise; represents the enterprise fitness score of the i-th neighbor; Using the optimized job seeker suitability score And the optimized enterprise adaptability score Calculate optimized match scores between job seekers and companies .

6. The intelligent job resume matching system based on multi-dimensional analysis according to claim 5 is characterized in that: The matching model is constructed in the following manner: Define the format of the matching matrix M: The rows of the matching matrix M represent each job applicant ; The columns of the matching matrix M represent each position ; Matching matrix M elements Representing job seekers With position Optimized match score of ; Based on the elements of each row in the matching matrix M size, determine each job seeker Priority list of positions ; Based on the elements of each column in the matching matrix M The size of each position Priority list of job seekers ; Set input as a priority list of positions and a priority list of job seekers ; Set the output to the optimal matching result; Initialize the matching state and perform step-by-step matching, repeating the step-by-step matching operation until all job seekers are matched. All matched or all positions are occupied, and all job seekers and Position Until there are no more better options; output the optimal matching result without any obstruction pairs.

7. The intelligent job resume matching system based on multi-dimensional analysis according to claim 6 is characterized in that: The data matching module builds a feedback model based on the dynamic behavior and selection preferences of job seekers, and generates feedback information for updating the weight coefficient of hard information data. and the weight coefficient of soft information data , get the updated hard information data weight coefficient that meets the constraint conditions and updated soft information data weight coefficient ; Based on the updated hard information data weight coefficient and updated soft information data weight coefficient Calculate the updated job seeker suitability score and updated enterprise suitability scores , calculate the updated matching score , used to return to the matching model to obtain a new optimal matching result; The feedback information includes: the job seeker's score in the information dimension of the positions that were not successfully matched in the first round, the automatically assigned secondary positions, and the newly selected positions; the constraints are .

8. The intelligent job resume matching system based on multi-dimensional analysis according to claim 7 is characterized in that: The weight coefficient of updating the hard information data and the weight coefficient of soft information data The methods include: ; In the formula, is the learning rate; k is the index of the information dimension; It represents the sum of the absolute values ​​of the difference values ​​of the information dimension scores in the hard information data; n is the total number of information dimensions in the hard information data; is the difference value of the information dimension, and the calculation formula is: ; In the formula, Score the information dimension of the secondary position, Score the dimensions of the new position; ; In the formula, It represents the sum of the absolute values ​​of the difference values ​​of the information dimension scores in the soft information data; m is the total number of information dimensions in the soft information data.

9. The intelligent job resume matching system based on multi-dimensional analysis according to claim 8 is characterized in that: The data matching module will Input into the weight dynamic adjustment model and compare with the preset threshold T; if , then increase the weight of the information dimension with index k; if , the adjustment of the weight by the information dimension with index k is ignored.

10. A matching method performed by a job resume intelligent matching system based on multi-dimensional analysis according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Collect the resume information data of job seekers and the recruitment information data of enterprises, and extract the information dimensions; Step 2: Calculate the applicant's suitability score and the company's suitability score based on the information dimension; Step 3: Calculate the matching score between job seekers and companies based on the job seeker suitability score and the company suitability score, compare the matching score with the preset threshold score, and give priority to matching job seekers and companies with matching scores greater than or equal to the threshold score.

Images