An enterprise recruitment management system based on talent portraits

Abstract

The present invention provides an enterprise recruitment management system based on talent portraits, including a portrait construction module, a job matching module, an interview generation module, and a result management module; the portrait construction module is used to obtain the talent characteristic data of candidates and construct the talent portraits of candidates; the job matching module is used to obtain the released job requirement characteristics, obtain the job requirement items and the corresponding job requirement feature vectors; and extract the talent feature vectors according to the talent portraits; perform matching analysis based on the obtained job requirement feature vectors and talent feature vectors to obtain the candidate job matching analysis results; the interview generation module is used to match corresponding interview questions from the question bank according to the obtained candidate job matching analysis results and generate an interview question list; the result management module is used to obtain the interview information of candidates for the interview questions and generate the candidate job interview evaluation results. The present invention helps to improve the objectivity and intelligent level of enterprise job recruitment.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise recruitment management, and particularly to an enterprise recruitment management system based on talent portraits. Background Art

[0002] The sound development of an enterprise depends on the support of outstanding talents. At present, enterprises have an increasing demand for and attach more importance to talents. In the traditional enterprise recruitment process, it usually relies on a third-party talent platform or talent pool as a medium, and selects suitable talents for the positions posted by the enterprise through resume keyword matching or manual screening. However, the above methods have problems such as low efficiency, strong subjectivity, and low suitability of the selected talents for the positions. As a result, enterprises cannot effectively identify talents quickly, truly, and effectively. Summary of the Invention

[0003] In view of the above problems, the present invention aims to provide an enterprise recruitment management system based on talent portraits.

[0004] The object of the present invention is achieved by the following technical solutions:

[0005] The present invention proposes an enterprise recruitment management system based on talent portraits, including a portrait construction module, a position matching module, an interview generation module, and a result management module; wherein,

[0006] The portrait construction module is used to obtain the talent characteristic data of candidates, and construct the talent portraits of candidates according to the obtained talent characteristic data; wherein the talent portraits include the characteristic quantities of various talent characteristics of candidates and the corresponding evaluation factors;

[0007] The position matching module is used to obtain the posted position requirement characteristics, obtain the position requirement items and the corresponding position requirement feature vectors; and extract the talent feature vectors corresponding to the position requirement items according to the talent portraits; perform matching analysis according to the obtained position requirement feature vectors and talent feature vectors to obtain the candidate position matching analysis result;

[0008] Among them, performing matching analysis according to the obtained position requirement feature vectors and talent feature vectors specifically includes:

[0009] For each position requirement item, respectively obtain the matching degree of the candidate to each position requirement item P(i) = sim (VC i , VJ i ) , where VC i represents the talent feature vector of the candidate under the talent feature item i , VJ iIndicates the job requirements for the recruitment position for the job requirement project i of the job requirement feature vector sim(VC i , VJ i ) Indicates VC i and VJ i similarity, calculated using the cosine function;

[0010] Further analyze the matching degree between the candidate and the recruitment position, and the matching analysis function used is: ；

[0011] In the formula, MatchP Indicates the candidate's job matching degree factor, where the larger the matching degree factor, the higher the matching degree between the candidate and the current recruitment position; P(i) Indicates the matching degree of the candidate for the job requirement project i ; N Indicates the total number of projects; S i Indicates the attention factor of the job requirement project i , obtained by counting the frequency of occurrence of this job requirement project i in the recruitment position feature data; j Indicates a variable S j Indicates the attention factor of the job requirement project j ; λ i Indicates the preset time adjustment factor of the job requirement project i ; tC i Indicates the experience time difference of the candidate for the talent feature project i , obtained by counting the time difference between the latest experience time node of the candidate for the talent feature project i and the current time node, with the unit of month; α and β respectively indicate the set weight adjustment factors δ Indicates the set conditional influence factor Num(c) Indicates the number of items where the candidate does not meet the minimum standard, obtained by counting the candidate's condition comparison analysis results; NumT Indicates the set number of standard conditions;

[0012] Output the matching degree of the candidate for each job requirement project and the candidate's job matching degree factor MatchP as the candidate's job matching analysis result;

[0013] The interview generation module is used to match corresponding interview questions from the question bank according to the obtained candidate position matching analysis results, and generate an interview question list.

[0014] The result management module is used to obtain the interview information of the candidate for the interview questions and generate the interview evaluation result of the candidate position.

[0015] Preferably, the portrait construction module includes a resume data acquisition unit, a project data acquisition unit, a test data acquisition unit, and a talent portrait construction unit; among them,

[0016] The resume data acquisition unit is used to obtain the resume data of the candidate, and extract the corresponding skill feature data according to the resume data, where the skill feature data includes the mastered skill items, the mastery level and experience corresponding to the skill items, and the obtained qualification certificates;

[0017] The project data acquisition unit is used to obtain the project feature data corresponding to the candidate from the project release source, where the project feature data includes the number of projects, the project occurrence time, and the skill features associated with the project, etc.; the test data acquisition unit is used to obtain the test feature data of the candidate, where the test feature data includes the logical test result, the personality test result, etc.;

[0018] The talent portrait construction unit is used to construct the talent portrait of the candidate according to the candidate's skill feature data, project feature data, and test feature data.

[0019] Preferably, the resume data acquisition unit includes:

[0020] Obtain the resume text of the candidate;

[0021] Perform text vectorization processing on the obtained resume text, extract the text feature vector of the resume data, and perform key feature word extraction according to the text feature vector to obtain the corresponding skill feature text;

[0022] Further perform text mapping processing on the obtained skill feature text to obtain the skill feature text and the mapping text as the skill feature data.

[0023] Preferably, the system further includes a job requirement extraction module;

[0024] The job requirement extraction module is used to obtain the recruitment job feature data released, and extract the job requirement features according to the obtained recruitment job feature data; among them, the job requirement features also include the minimum standard requirement features.

[0025] Preferably, the position matching module includes a feature integration unit, a condition analysis unit, and a matching analysis unit; among them,

[0026] The feature integration unit is used to integrate the job requirement features under the same job requirement item according to the obtained job requirement features, so as to obtain the job requirement feature vectors of each job requirement item; and according to the talent portrait of the candidate, integrate the talent feature data under the talent feature item corresponding to the job requirement item, so as to obtain the talent feature vectors under the corresponding talent feature item; wherein, the job requirement feature vectors and the talent feature vectors include the feature quantities or evaluation factors of the corresponding items.

[0027] The condition analysis unit is used to perform condition comparison and analysis on the minimum standard items set in the job requirement features and the corresponding talent feature items in the candidate's talent portrait, so as to obtain the condition comparison and analysis results of the candidate corresponding to each minimum standard feature.

[0028] The matching analysis unit is used to perform matching analysis according to the obtained job requirement features and talent portrait, so as to obtain the candidate job matching analysis result.

[0029] Preferably, the interview generation module includes a question bank unit, a question recommendation unit and a generation unit; wherein,

[0030] The question bank unit is used to store and manage the interview questions for the recruitment position, and each interview question includes the corresponding question feature item label and the corresponding question feature vector label.

[0031] The question recommendation unit is used to calculate the priority of each interview question in the question bank unit according to the candidate job matching analysis result.

[0032] The generation unit is used to select appropriate interview questions from the question bank unit based on the preset question selection rules according to the priority of each interview question, and generate the corresponding interview question list.

[0033] Preferably, the result management module further includes: obtaining the corresponding interview questions according to the generated interview question list and pushing them to the candidate, obtaining the interview results of the candidate for the interview questions, and displaying the interview results.

[0034] The beneficial effects of the present invention are as follows: The present invention proposes an enterprise recruitment management system based on talent portraits. According to the obtained talent characteristic data of candidates, the talent characteristics of candidates are extracted, and a talent portrait for candidates is constructed. Based on the constructed talent portrait, it can intuitively and accurately reflect the capabilities and levels of candidates for different talent characteristic items, and accurately provide precise feedback and evaluation on the situation of candidates. When performing job matching, it can adaptively extract the characteristic items and feature vectors corresponding to the recruitment position based on the talent portrait of the candidate, and complete the matching analysis of the candidate's fitness for the position based on the talent feature vectors. Through the matching analysis based on the talent feature vectors, it can accurately provide feedback on the fitness of the candidate and the recruitment position; objectively and comprehensively evaluate the fitness degree of the candidate and the recruitment position. At the same time, based on the matching analysis results of the candidate and the recruitment position, interview questions suitable for the current situation of the candidate are further matched to assist the manager in further interviewing or conducting a written test on the candidate. Through the suitable interview questions, it helps to further assess and test the true situation of the candidate, thereby improving the objectivity and authenticity of enterprise job recruitment. At the same time, with the assistance of this system to complete enterprise recruitment management, it can greatly save the time and manpower for data integration, matching, and targeted data matching and screening, and further improve the efficiency of enterprise recruitment management. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the following drawings.

[0036] Figure 1 It is a framework structure diagram of an enterprise recruitment management system based on talent portraits shown in an embodiment of the present invention;

[0037] Figure 2 is Figure 1 a schematic diagram of the module structure in the embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The present invention is further described in combination with the following application scenarios.

[0039] Refer to Figure 1 the embodiment shown, which shows an enterprise recruitment management system based on talent portraits, including a portrait construction module, a job matching module, an interview generation module, and a result management module; among them,

[0040] The portrait construction module is used to obtain the talent characteristic data of candidates and construct a talent portrait of candidates according to the obtained talent characteristic data; among them, the talent portrait includes the feature quantities of various talent characteristics of candidates and the corresponding evaluation factors;

[0041] The job matching module is used to obtain the job requirement characteristics published, obtain the job requirement items and the corresponding job requirement feature vectors; and extract the talent feature vectors corresponding to the job requirement items according to the talent portrait; perform matching analysis based on the obtained job requirement feature vectors and talent feature vectors to obtain the candidate job matching analysis results; the interview generation module is used to match corresponding interview questions from the question bank according to the obtained candidate job matching analysis results and generate an interview question list.

[0042] The result management module is used to obtain the interview information of the candidate for the interview questions and generate the candidate job interview evaluation results.

[0043] In the above embodiments of the present invention, an enterprise recruitment management system based on a talent portrait is proposed. According to the obtained talent feature data of the candidate, the talent features of the candidate are extracted, and a talent portrait for the candidate is constructed. Based on the constructed talent portrait, it can intuitively and accurately reflect the candidate's abilities and levels for different talent feature items, and accurately provide precise feedback and evaluation on the candidate's situation. When performing job matching, it can adaptively extract the corresponding feature items and feature vectors corresponding to the recruitment position based on the candidate's talent portrait, and complete the matching analysis of the candidate's suitability for the position based on the talent feature vectors. Through the matching analysis based on the talent feature vectors, it can accurately provide feedback on the suitability of the candidate and the recruitment position; objectively and comprehensively evaluate the suitability degree of the candidate and the recruitment position. At the same time, based on the matching analysis results of the candidate and the recruitment position, it further matches interview questions suitable for the candidate's current situation to assist the manager in further conducting further interviews or written tests on the candidate. Through the suitable interview questions, it helps to further assess and test the true situation of the candidate, thereby improving the objectivity and authenticity of enterprise job recruitment. At the same time, with the assistance of this system to complete enterprise recruitment management, it can greatly save the time and manpower for data integration, matching, and targeted data matching and screening, and further improve the efficiency of enterprise recruitment management.

[0044] In one scenario, the system proposed by the present invention can be built based on a cloud server, a local server, etc., and corresponding data is input or transmitted through intelligent terminals and other means.

[0045] Preferably, referring to Figure 2 , the portrait construction module includes a resume data acquisition unit, a project data acquisition unit, a test data acquisition unit, and a talent portrait construction unit; wherein,

[0046] The resume data acquisition unit is used to obtain the resume data of the candidate and extract the corresponding skill feature data according to the resume data, where the skill feature data includes the mastered skill items, the mastery degree and experience corresponding to the skill items, and the obtained qualification certificates.

[0047] The project data acquisition unit is used to acquire the project feature data corresponding to the candidate from the project release source, where the project feature data includes the number of projects, the project occurrence time, and the skill features associated with the project, etc.;

[0048] The test data acquisition unit is used to acquire the test feature data of the candidate, where the test feature data includes the logical test result, the personality test result, etc.;

[0049] The talent portrait construction unit is used to construct the talent portrait of the candidate according to the candidate's skill feature data, project feature data, and test feature data.

[0050] Among them, for the extraction of the candidate's talent feature data, it is usually completed based on three aspects: resume data, project data, and test data. Therefore, in the above embodiments of the present invention, corresponding data acquisition units are specifically set up, which can extract the required candidate talent feature data based on different data sources, laying a foundation for building the candidate's talent portrait later. Preferably, the resume data acquisition unit includes:

[0051] Obtain the resume text of the candidate;

[0052] Perform text vectorization processing on the obtained resume text, extract the text feature vector of the resume data, and perform key feature word extraction according to the text feature vector to obtain the corresponding skill feature text;

[0053] Perform further text mapping processing on the obtained skill feature text to obtain the skill feature text and the mapping text as the skill feature data.

[0054] In one scenario, for the skill feature text, a text classification model implemented based on the BERT model can be used. By converting the resume text into a 768-dimensional feature vector and performing text classification processing according to the feature vector and the trained classifier, the corresponding skill feature text can be obtained, such as "proficient in Linux", "skilled in Python", etc.

[0055] For the acquired resume data, skill feature data extraction is performed. First, it is extracted according to the text describing the skills on the resume, and data cleaning and text mapping processing are performed according to the extracted text. On the one hand, the description of the skill features can be accurately extracted from the resume text, and on the other hand, further adaptive mapping processing is performed on the text of the skill features, which can further perform standardized mapping on the extracted skill text features and adaptively extract the candidate's skill features.

[0056] In one scenario, for the skill feature text "proficient in Linux" recorded in the candidate's resume, after standardization mapping, mapping features such as "proficient in script writing", "proficient in permission management", and "proficient in log troubleshooting" related to Linux can be further extracted according to the preset mapping rules; in another scenario, for the skill feature text "IELTS 7.5", after standardization mapping, the mapping feature of the ability of "skilled English listening, speaking, reading, and writing" can be further obtained according to the mapping rules; thus, the skill feature data of the candidate is further adaptively expanded to make the skill feature data extracted from the resume text more comprehensive.

[0057] Preferably, the way for the project data acquisition unit to acquire project feature data is similar to that of the resume data acquisition unit. By acquiring the project description text of the candidate or the works associated with the project, the corresponding project feature data is extracted. For example, text vectorization processing and key feature word extraction are performed on the acquired project description text to obtain the project feature data text as the project feature data.

[0058] Among them, for the acquisition of the candidate's project feature data, if there is no corresponding project release source, the corresponding project description text can also be obtained from the project experience column of the candidate's resume, etc.

[0059] In one scenario, according to the project experience description in the candidate's resume, the candidate's project feature data is extracted as "2 years of AI algorithm development experience", "2 years of Python experience", "5 GitHub works" and the corresponding release time, "1 SCI paper corresponding to NLP natural language processing" and the corresponding release time, etc.

[0060] For the extraction of test data, it is possible to obtain the corresponding test results in the form of a questionnaire based on the enterprise-customized test questionnaire or the authoritative questionnaire in the industry. The candidate's corresponding test data is entered or automatically obtained through the test data acquisition unit, which helps to improve the convenience of test data acquisition.

[0061] In one scenario, the test data takes the direct test result as the corresponding test feature data.

[0062] Preferably, the talent portrait construction unit specifically includes:

[0063] Perform feature quantization processing on the obtained candidate talent feature data to extract the feature quantities of the candidate feature data; among them, the candidate talent feature data includes the candidate's skill feature data, project feature data, and test feature data;

[0064] Calculate the evaluation factors of the corresponding talent feature items according to the obtained feature quantities, and the evaluation factor calculation function adopted is:

[0065] ;

[0066] wherein, Mark(i) represents the evaluation factor corresponding to the talent characteristic item i ; x(i) represents the characteristic quantity of the candidate corresponding to the talent characteristic item i ; μ(i) and σ(i) respectively represent the average characteristic quantity and the standard deviation of the characteristic quantity in the talent pool for the talent characteristic item i ; represents a preset non - zero adjustment term, wherein ;

[0067] According to the obtained talent characteristic items and corresponding evaluation factors of the candidate, a talent portrait of the candidate is constructed, and the talent portrait of the candidate includes the characteristic quantities of each talent characteristic of the candidate and the corresponding evaluation factors.

[0068] In one scenario, when performing quantization processing on talent characteristic data, the characteristic data corresponding to the talent characteristic items is quantized. For example, "skilled" and "mastered" are quantized to "4 points" and "3 points" respectively; for characteristic quantities represented by numerical values, such as "5 published works" and "3 years of experience", the corresponding numbers "5" and "3" are directly used as the characteristic quantities of the corresponding talent characteristic items "number of works" and "experience".

[0069] When constructing a talent portrait for an individual candidate, first, through the method of characteristic quantization processing, the talent characteristic data of the candidate is numerically represented. Among them, an evaluation factor calculation function is proposed, which can be based on the same - type talent characteristic data in the talent pool as a benchmark, so as to accurately quantify the talent characteristic data of the candidate after horizontal comparison, objectively and accurately represent the level of a certain talent characteristic of the candidate, and at the same time, based on the same quantization standard, it can lay a foundation for subsequent further characteristic matching and analysis.

[0070] Preferably, the system further includes a job requirement extraction module;

[0071] The job requirement extraction module is used to obtain the characteristic data of the published recruitment job and extract the job requirement characteristics according to the obtained characteristic data of the recruitment job; the job requirement characteristics also include the minimum standard requirement characteristics.

[0072] In a scenario, the job requirement extraction module obtains the description text of the recruitment position and extracts key features based on the obtained description text to obtain the job requirement features corresponding to the recruitment position, such as "proficient in Java", "5 years of Java experience", "3 years of Python", "e-commerce operation experience", "idle time less than 6 months", etc. At the same time, according to the actual situation, the minimum standard requirement features can also be set to stipulate the minimum standard situation, such as setting the minimum standard requirement feature "Java not less than 1 year", etc.

[0073] The method for obtaining the enterprise recruitment position requirement data is usually to extract based on the recruitment position information text released by the enterprise as the basis; at the same time, it is also possible to directly input the enterprise position requirement features into the system based on a dedicated feature input framework.

[0074] In a scenario, the method for extracting job requirement features from the enterprise position information text can be implemented by using a text feature extraction model that has been trained in the prior art, such as an enterprise recruitment feature extraction model built based on TF-IDF or other artificial intelligence models. The present invention does not make specific limitations here.

[0075] Preferably, the job matching module includes a feature integration unit, a condition analysis unit, and a matching analysis unit; among them,

[0076] The feature integration unit is used to integrate the job requirement features under the same job requirement item according to the obtained job requirement features to obtain the job requirement feature vectors of each job requirement item VJ i ; and according to the talent portrait of the candidate, integrate the talent feature data under the talent feature item corresponding to the job requirement item to obtain the talent feature vectors under the corresponding talent feature item VC i ; among them, the job requirement feature vectors and talent feature vectors include the feature quantities or evaluation factors of the corresponding items;

[0077] The condition analysis unit is used to perform condition comparison and analysis on the minimum standard items set in the job requirement features and the corresponding talent feature items in the candidate's talent portrait to obtain the condition comparison and analysis results of the candidate corresponding to each minimum standard feature;

[0078] The matching analysis unit is used to perform matching analysis based on the obtained job requirement feature vectors and talent feature vectors to obtain the candidate job matching analysis results.

[0079] Preferably, the matching analysis unit specifically includes:

[0080] For each job requirement item, obtain the matching degree of the candidate to each job requirement item P(i) = sim(VC i , VJ i ) , where VC i represents the talent feature vector of the candidate under the talent feature item i ; VJ i represents the job requirement feature vector of the recruitment position for the job requirement item i ; sim(VC i , VJ i ) represents VC i and VJ i similarity, calculated using the cosine function;

[0081] Further analyze the matching degree between the candidate and the recruitment position. The matching analysis function used is:

[0082] ；

[0083] In the formula, MatchP represents the candidate job matching degree factor. The larger the matching degree factor, the higher the matching degree between the candidate and the current recruitment position; P(i) represents the matching degree of the candidate for the job requirement item i ; N represents the total number of items; S i represents the attention factor of the job requirement item i , obtained by counting the occurrence frequency of this job requirement item i in the recruitment position feature data; j represents a variable, S j represents the attention factor of the job requirement item j ; λ i represents the time adjustment factor of the preset job requirement item i ; tC i represents the experience time difference of the candidate for the talent feature item i , obtained by counting the time difference between the latest experience time node of the candidate for the talent feature item i and the current time node, in months; α and β respectively represent the set weight adjustment factors, δ represents the set condition influence factor,Num(c) Indicates the number of candidates who do not meet the minimum standard items, which is statistically obtained based on the comparison and analysis results of the candidates' conditions; NumT Indicates the number of set standard conditions;

[0084] Output the matching degree of the candidate for each job requirement item and the candidate job matching degree factor MatchP As the candidate job matching analysis result.

[0085] In one scenario, in order to improve the calculation accuracy, when performing VC i and VJ i similarity calculation, first correct the features of each dimension in the talent feature vector. When the feature quantity of a certain dimension is greater than the corresponding dimension's feature quantity in the job requirement feature vector, then correct the value of the feature quantity to the same value as the corresponding dimension in the job requirement feature vector. Or when using the cos function for cosine similarity calculation, by setting the local maximum value, limit the similarity range between the two to avoid the situation of result callback caused by exceeding the maximum value during the similarity calculation process.

[0086] In one scenario, for example, the job requirement vector for the job requirement item "Logical test score" is "120+", and the candidate's logical test result is 130. When performing the similarity calculation between the job requirement vector and the talent feature vector, then correct the talent feature item vector so that the similarity (matching degree) result between the two is 1.

[0087] In one scenario, in the feature integration unit, for job requirement features such as "Master Java", "Java experience over 5 years", "Java project experience as the main developer", "Proficient in BUG troubleshooting", etc., they can be integrated into the job requirement feature vector under the unified job requirement item "Java" VJ java = {2 + ab, 5 + yrs, 0.8 + mmb, 2.2 + abb} where 4+ and 1+ are the evaluation factor standards corresponding to the Java ability item and the Java experience item respectively. Similarly, based on the candidate's talent portrait, by integrating the feature quantities or evaluation factors related to the candidate and the talent feature item "Java", such as "Java ability evaluation factor 2.3", "Java experience 4 years", "Java experience evaluation factor 2.5", and the mapped ability feature "bug troubleshooting evaluation factor 2.2" obtained according to their "Proficient in Python", into the talent feature vector VC java = {2.3ab, 4yrs, 2.5mmb, 2.2abb} .

[0088] In another scenario, in the feature integration unit, for items related to testing, the feature quantities or evaluation factors corresponding to the results of each test (such as personality tests, logic tests, etc.) can be integrated into a feature vector under the unified "test"; or the results of each test can be subdivided, with different "personality tests" or "logic tests", etc. as separate items, and feature vectors corresponding to each item (which may be one-dimensional or multi-dimensional feature vectors) can be obtained based on the feature quantities or evaluation factors under each item.

[0089] It should be noted that the above-mentioned job requirement items and talent feature items can be collectively referred to as items. The only difference is that when the item appears in the relevant content of the recruitment position, it is called a job requirement item; when the item appears in the relevant content of the candidate, it is called a talent feature item. Therefore, in the actual data processing and operation process, the job requirement feature vectors and talent feature vectors for the same item can be processed correspondingly.

[0090] In the above embodiments of the present invention, considering that in the actual recruitment scenario, the feature quantities for the same item are usually one or more, therefore, first, based on the job requirement features and talent feature data, feature vector extraction under the item is performed, and one-dimensional or multi-dimensional feature vectors can be constructed for different items, which is convenient for subsequent further data matching or analysis processing.

[0091] Among them, when performing condition analysis, first, based on the minimum standard in the job requirements, the talent features of the candidate are compared and analyzed for the minimum conditions. Based on the minimum standard principle, each talent feature item of the candidate can be verified to ensure that the candidate can meet the minimum standard of the recruitment position (the minimum standard can have a direct impact on the subsequent matching analysis results);

[0092] When performing matching analysis, based on the ideas of single-item analysis and comprehensive analysis, first, based on the proposed matching degree calculation function P(i) , based on the job requirement feature vector and the talent feature vector, the talent feature items corresponding to the candidate can be matched and analyzed item by item for the job requirement items; based on the obtained item matching degree, further based on the proposed matching analysis function MatchP, to comprehensively statistically analyze the matching degree of each item. Meanwhile, during the comprehensive statistical process, a special attention factor S is added to objectively adjust the requirements (importance) and attention of the recruitment position for different projects, so as to improve the accuracy of the comprehensive statistics. At the same time, the timeliness of talent capabilities is further considered in the comprehensive statistics part. Therefore, when conducting comprehensive analysis, a time adjustment item is specially added to correct the timeliness of the candidate's talent capabilities. Compared with the traditional method based on a single evaluation criterion, it can better fit the changing characteristics of talent characteristics. Meanwhile, the matching analysis function further makes a final correction to the matching degree of the candidate for the position recruitment based on the conditional comparison analysis results, enabling the obtained candidate position matching degree factor to accurately and objectively quantify the matching degree of the candidate for the recruitment position, and improving the intelligent level of the matching degree analysis of the candidate for the recruitment position.

[0093] In one scenario, according to the obtained candidate position matching degree factor, a corresponding standard threshold can be set to preliminarily screen the candidates, so as to achieve the result of accurate screening based on the objective conditions of the candidates.

[0094] Considering that only through the candidate position matching degree factor or other comprehensive evaluation results, usually only the candidate's situation can be reflected from the perspective of hardware conditions, but it cannot fully reflect the true situation of the candidate (such as subjective evaluation, false reporting of situations (overstated or understated), etc.). Therefore, usually further interview questions need to be combined to consider the candidates. However, in the current interview question selection method, one is to use fixed interview questions to test the candidates. This method usually can only consider whether the interviewee meets a certain condition (such as whether they are qualified), but cannot further consider outstanding talents, and the gradient level is insufficient; the other is to propose interview questions based on the subjective thinking of the interviewer. This method is prone to strong subjectivity or bias, and cannot further consider the comprehensive situation of the candidates.

[0095] Therefore, the present invention further proposes a matching and generating method for interview questions, which is based on the characteristics of the recruitment position and the candidate as a basis to match suitable questions to assist in further considering the candidates, so as to truly reflect the true situation of the candidates.

[0096] Preferably, the interview generation module includes a question bank unit, a question recommendation unit, and a generation unit; among them,

[0097] The question bank unit is used to store and manage interview questions for the recruitment position, and each interview question contains corresponding question feature item labels i and corresponding question feature vector labels VTi ;

[0098] The question recommendation unit is used to calculate the priority of each interview question in the question bank unit according to the candidate position matching analysis result. The priority calculation function used is:

[0099] ;

[0100] In the formula, PR t (i, VT i ) Table indicates the priority of the interview question t , where the question feature item corresponding to the interview question t is i , and the corresponding stylistic feature vector is VT i , P(i) represents the matching degree of the candidate to the position requirement item i , where P(i) = sim (VC i , VJ i ) , VC i represents the talent feature vector of the candidate under the talent feature item i , VJ i represents the position requirement feature vector of the recruitment position for the position requirement item i , sim(VC i , VJ i ) represents VC i and VJ i 's similarity, calculated using the cosine function; MatchP represents the candidate position matching degree factor, θP represents the preset standard matching degree factor threshold, and k represents the set sensitivity factor, where k∈[0.1,1000] , sim(VT i , VC i ) represents VT i and VC i 's similarity,

[0101] sim(VT i , VJ i) representation VT i and VJ i similarity;

[0102] The generation unit is used to select appropriate interview questions from the question bank unit based on the priorities of each interview question and generate a corresponding interview question list according to a preset topic selection rule.

[0103] Among them, the question bank unit stores interview questions for different ability items (such as for Java, logical ability, Python, etc.), each of which carries a corresponding question feature item label and a corresponding question feature vector label. The above-mentioned question feature items correspond to the job requirement items of the above-mentioned recruitment position and the talent feature items of the candidate. That is, for example, the question feature item labels carried in the interview questions are "Java", "project management", etc.; and based on the same idea, the question feature vector labels also correspond to the job requirement feature vectors of the job requirement items and the talent feature vectors of the talent feature items. That is, for example, the feature vector labels carried in the interview questions are VT java = {3ab, 2abb} etc.

[0104] In one scenario, the generation unit selects appropriate interview questions from the question bank unit based on a preset topic selection rule. The preset topic selection rule can be to select the N interview questions with the highest priorities from them to generate an interview question list. In another scenario, as an optimization, when selecting interview questions according to the priorities of the interview questions, more conditions can be added. For example, for each recruitment requirement item, obtain the top n interview questions with corresponding priorities to generate an interview question list to ensure that the questions can comprehensively cover the job requirements.

[0105] According to the generated interview question list, the interviewer / manager can obtain the corresponding interview questions to conduct personalized and targeted further assessment of the candidate, and then further evaluate whether to hire the candidate or explore the candidate's talent ability based on the candidate's answers to the interview questions.

[0106] In the above embodiments of the present invention, based on the established question bank, corresponding assessment items (projects) and difficulty levels (reflected in the form of eigenvectors) are set for the interview questions in the question bank; when matching interview questions for a specified recruitment position and candidates, based on the proposed priority calculation function, the similarity between the eigenvectors of the interview questions and the position requirements vector of the recruitment position and the talent eigenvector of the candidates can be used as a benchmark to match the priority of the interview questions. Among them, a judgment factor based on the candidate's position matching degree factor is particularly added to adaptively adjust and match appropriate interview questions according to the candidate's situation, so that the finally matched interview questions can meet the position requirements while their difficulty level can most closely approximate the true level of the candidates, thereby reflecting the ability gradient among the candidates and helping to improve the intelligent level of interview question matching.

[0107] Among them, for the setting of the above priority calculation function, when the candidate's ability is slightly lower than the position requirement standard, the focus of the interview is more on whether the candidate can meet the position requirements. Therefore, through the calculation of the priority, the difficulty and conditions of the interview questions can be made closer to the level corresponding to the position requirements, so as to further consider the candidate's situation based on the interview questions, which helps to further discover and explore potential candidates or candidates with falsely low conditions and avoid talent waste. When the candidate's ability is significantly higher than the position requirements, the focus of the interview is to accurately locate the candidate's ability. Therefore, matching corresponding interview questions based on the candidate's characteristics as a benchmark can help to reflect the true situation of the candidate, screen candidates with falsely high conditions and explore the true ability of the candidates, improving the intelligent level and accuracy of the evaluation of the candidate's true level.

[0108] Preferably, the result management module further includes:

[0109] Obtain the corresponding interview questions according to the generated interview question list and push them to the candidates, obtain the interview results of the candidates for the interview questions, and display the interview results.

[0110] Among them, after generating the interview question list, according to the actual situation, the written test or interview method can be selected to test the candidates based on the interview questions, and the corresponding recruitment results can be obtained based on the candidates' answers to the interview questions. The result management module is used to overall manage the recruitment results of the candidates.

[0111] It should be noted that in each embodiment of the present invention, each functional unit / module can be integrated into a processing unit / module, or each unit / module can exist physically alone, or two or more units / module can be integrated into one unit / module. The above integrated unit / module can be implemented in the form of hardware or in the form of a software functional unit / module.

[0112] From the description of the above embodiments, those skilled in the art can clearly understand that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, or other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiments can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. The computer-readable medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transfer of a computer program from one place to another. The storage media can be any available medium that can be accessed by a computer. The computer-readable medium can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM, or other optical disc storage, magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the protection scope of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the essence and scope of the technical solutions of the present invention.

Claims

1. An enterprise recruitment management system based on talent portrait, characterized in that: It includes portrait construction module, job matching module, interview generation module and result management module; among them, The portrait construction module is used to obtain the talent characteristic data of the candidate and construct the talent portrait of the candidate based on the obtained talent characteristic data; wherein the talent portrait includes the characteristic quantity of each talent characteristic of the candidate and the corresponding evaluation factor; The job matching module is used to obtain the characteristics of the published job requirements, obtain the job requirement items and the corresponding job requirement feature vectors; and extract the talent feature vectors corresponding to the job requirement items according to the talent portrait; perform matching analysis based on the obtained job requirement feature vectors and talent feature vectors to obtain the candidate job matching analysis results; Among them, matching analysis is performed based on the obtained job requirement feature vector and talent feature vector, specifically including: Get the matching degree of candidates for each job requirement item separately P(i)=sim(VC i ,VJ i ) ,in VC i Indicates that the candidate has a high level of talent i The talent feature vector under VJ i Indicates that the recruitment position is targeted at the job demand project i The job requirement feature vector, sim(VC i ,VJ i ) express VC i and VJ i The similarity is calculated using the cosine function; The matching degree between the candidates and the recruitment positions is further analyzed, and the matching analysis function used is: ； In the formula, MatchP Indicates the candidate's job matching factor, where the larger the matching factor, the higher the matching degree between the candidate and the current recruitment position; P(i) Indicates the candidate's requirements for the position i The matching degree, N Indicates the total number of items; S i Indicates job requirements i The attention factor of the position is calculated by counting the project requirements of the position. i Obtained from the frequency of occurrence in the recruitment position characteristic data; j Represents a variable, S j Indicates job requirements j The attention factor λ i Indicates the preset job requirements i The time adjustment factor, tC i Indicates the candidate's talent characteristics project i Experience time difference, based on candidates' talent characteristics i The time difference between the latest experience time node and the current time node is obtained by statistics; α and β Respectively represent the set weight adjustment factors, δ represents the influence factor of the set condition, Num(c) Indicates the number of candidates that do not meet the minimum standard, calculated based on the results of the candidate condition comparison analysis; NumT Indicates the number of standard conditions set; Output the candidate's matching degree for each job requirement and the candidate's job matching factor MatchP As the result of candidate job matching analysis; The interview generation module is used to match the corresponding interview questions from the question library according to the obtained candidate job matching analysis results, and generate an interview question list; The result management module is used to obtain the interview information of the candidate in response to the interview questions and generate the candidate's job interview evaluation results.

2. According to claim 1, the enterprise recruitment management system based on talent portrait is characterized in that: The portrait construction module includes a resume data acquisition unit, a project data acquisition unit, a test data acquisition unit and a talent portrait construction unit; among which, The resume data acquisition unit is used to acquire the resume data of the candidate and extract the corresponding skill feature data according to the resume data, wherein the skill feature data includes the skill items mastered, the mastery degree and experience corresponding to the skill items, and the qualification certificates obtained; The project data acquisition unit is used to acquire project feature data corresponding to the candidate from the project publishing source, wherein the project feature data includes the number of projects, the time of project occurrence and the skill features associated with the project; The test data acquisition unit is used to acquire the test feature data of the candidate, wherein the test feature data includes a logic test result and a personality test result; The talent profile building unit is used to build a talent profile of a candidate based on the candidate's skill feature data, project feature data and test feature data.

3. According to claim 2, the enterprise recruitment management system based on talent portrait is characterized in that: The resume data acquisition unit includes: Get the candidate's resume text; Perform text vectorization processing on the acquired resume text, extract the text feature vector of the resume data, and extract key feature words based on the text feature vector to obtain the corresponding skill feature text; The acquired skill feature text is further subjected to text mapping processing to obtain the skill feature text and the mapping text as skill feature data.

4. According to claim 2, the enterprise recruitment management system based on talent portrait is characterized in that: The talent portrait construction unit specifically includes: performing feature quantification processing according to the obtained candidate talent feature data, and extracting feature quantities of the candidate feature data; wherein the candidate talent feature data includes the candidate's skill feature data, project feature data and test feature data; The evaluation factor of the corresponding talent characteristic item is calculated based on the obtained characteristic quantity, and the evaluation factor calculation function used is: ； in, Mark(i) Indicates the corresponding talent characteristics i The evaluation factor, x(i) Indicates the talent characteristics of the candidate i The characteristic quantity of μ(i) and σ(i) Respectively represent the talent characteristics items in the talent pool i The average feature quantity and standard deviation of the feature quantity; represents the preset non-zero adjustment item, where ; Based on the obtained talent characteristic items and corresponding evaluation factors of the candidate, a talent profile of the candidate is constructed, wherein the talent profile of the candidate includes the characteristic quantities of various talent characteristics of the candidate and the corresponding evaluation factors.

5. According to claim 1, the enterprise recruitment management system based on talent portrait is characterized in that: It also includes a job requirements extraction module; The job requirement extraction module is used to obtain the published recruitment job feature data and extract job requirement features based on the obtained recruitment job feature data; The job requirement characteristics also include minimum standard requirement characteristics.

6. The enterprise recruitment management system based on talent portrait according to claim 1 is characterized in that: The job matching module includes a feature integration unit, a condition analysis unit and a matching analysis unit; among them, The feature integration unit is used to integrate the job demand features under the same job demand project according to the acquired job demand features, and obtain the job demand feature vector of each job demand project. VJ i ; and according to the candidate's talent portrait, the talent feature data under the talent feature project corresponding to the job requirement project is integrated to obtain the talent feature vector under the corresponding talent feature project VC i ; Among them, the job requirement feature vector and the talent feature vector include the feature quantity or evaluation factor of the corresponding project; The condition analysis unit is used to perform condition comparison analysis based on the minimum standard items set in the job requirement characteristics and the corresponding talent characteristic items in the candidate talent profile, and obtain the condition comparison analysis results of the candidate corresponding to each minimum standard characteristic; The matching analysis unit is used to perform matching analysis based on the acquired job requirement characteristics and talent portraits to obtain candidate job matching analysis results.

7. The enterprise recruitment management system based on talent portrait according to claim 1 is characterized in that: The interview generation module includes a question library unit, a question recommendation unit and a generation unit; among them, The question library unit is used to store and manage interview questions for recruitment positions, where each interview question contains the corresponding question feature item label i and the corresponding problem feature vector label VT i ; The question recommendation unit is used to calculate the priority of each interview question in the question library unit according to the candidate job matching analysis results. The priority calculation function used is: ； In the formula, PR t (i,VT i )surface Interview Questions t Priority of interview questions t The corresponding problem feature items are i , the corresponding style feature vector is VT i , P(i) Indicates the candidate's requirements for the position i The matching degree of P(i)=sim(VC i , VJ i ) , VC i Indicates that the candidate has a high level of talent i The talent feature vector under VJ i Indicates that the recruitment position is targeted at the job demand project i The job requirement feature vector, sim(VC i ,VJ i ) express VC i and VJ i The similarity is calculated using the cosine function; MatchP represents the candidate's job matching factor, θP represents the preset standard matching factor threshold, k represents the set sensitivity factor, where k∈[0.1,1000] , sim(VT i ,VC i ) express VT i and VC i The similarity of sim(VT i ,VJ i ) express VT i and VJ i similarity; the generating unit is used to select appropriate interview questions from the question library unit according to the priority of each interview question and based on the preset topic selection rules, and generate a corresponding interview question list.

8. The enterprise recruitment management system based on talent portrait according to claim 1 is characterized in that: The result management module further includes: According to the generated interview question list, the corresponding interview questions are obtained and pushed to the candidates, and the interview results of the candidates for the interview questions are obtained and displayed.

Images