A professional ability assessment system and method based on big data analysis
Through big data analysis and multi-category differentiated assessment, the problem of inconsistent professional ability assessment standards is solved, comprehensive and objective evaluation of professional ability is achieved, the accuracy and reliability of the evaluation is improved, and good system updates are provided Application effect.
Patent Information
- Application Number
- CN202410261032.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-07
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-03-07
AI Technical Summary
The existing professional ability assessment system lacks unified standards, resulting in inconsistent standards and the inability to objectively and comprehensively evaluate professional ability, and the differentiation of various institutions is large.
A professional ability assessment system based on big data analysis is adopted to obtain, process and integrate the assessment data, build a professional ability model, conduct multiple categories and levels of differentiated assessments, optimize the generation of assessment and integration data, and ensure the accuracy and reliability of the assessment.
It has achieved a comprehensive and objective assessment of professional abilities, improved the pertinence and reliability of assessment, improved the data processing and scoring stages of multi-institutions, and brought good application effects to system updates.
Smart Images

Figure CN118115035B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of assessment data processing, and in particular to a system and method for assessing professional competence based on big data analysis. Background Art
[0002] At this stage, with the development of digital society, professional ability assessment has also become more intelligent with the development of the Internet. Professional ability assessment refers to understanding an individual's professional traits and level by evaluating the professional skills, knowledge and abilities demonstrated by the individual in the work process. Professional ability assessment can be carried out through online tests, mock interviews, case analysis and other methods.
[0003] In the assessment process, the relevant assessment and appraisal institutions play an important role. The relevant institutions usually include vocational skill appraisal centers, industry associations, enterprises, and educational institutions. These institutions are responsible for organizing the assessment work. At the same time, there is no unified and standardized assessment model for professional ability assessment. Each professional department writes ability assessment papers according to its own needs through assessors from relevant institutions to conduct professional ability assessment of personnel. Due to the large differences in the existing assessment and appraisal institutions and the lack of a unified and standardized assessment model in each professional profession, it is easy to lead to inconsistent standards and it is impossible to objectively and comprehensively evaluate professional ability. To this end, we propose a professional ability assessment system and method based on big data analysis. Summary of the invention
[0004] In view of the above problems existing in the existing assessment data processing system, the present invention is proposed.
[0005] Therefore, the present invention provides a professional ability assessment system and method based on big data analysis, which utilizes assessment data analysis to obtain relevant multi-category-level assessment data and assessor's ability data, optimizes and generates assessment integration data after fusion analysis, and conducts differentiated assessments at different category levels. It has strong pertinence and reliability, and makes the assessment content more accurate, which is conducive to objective and comprehensive assessment of professional ability, and improves the data processing of assessment data from multiple assessment agencies and the subsequent scoring stage, which can bring good application effects for subsequent system updates.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a professional ability assessment system based on big data analysis, comprising:
[0007] An acquisition module is used to acquire professional competence assessment data, wherein the professional competence assessment data includes assessment answer data of the assessed personnel, professional assessment test data of the assessment institution, and professional test paper question and answer data;
[0008] A processing module is used for data processing of the occupational competency assessment data, wherein the data processing includes data integration, data standardization and data fusion processing of the occupational assessment test data of different assessment institutions, and after completion, unified assessment data of the corresponding occupational category is formed and imported into the database;
[0009] The professional competence estimation module is used to construct a professional competence assessment model for the assessed personnel, and calculate the corresponding professional competence of the assessed personnel through the professional competence assessment model of the assessed personnel according to the assessment answer data of the assessed personnel, as shown in formula (1):
[0010]
[0011] in, is the professional ability coefficient of the i-th person being assessed; W 1.a ,W 1.b ,W 1.c Respectively represent the weight coefficients of the three aspects of the occupational evaluation criteria layer; W 2.k , W 3.l , W 4.j They represent the weight coefficients of k, l and j indicators corresponding to the three criteria of qualification standard, skill standard and quality standard respectively; U(x) represents the utility value of the indicator parameter;
[0012] The fusion analysis module is used to perform a fusion analysis of the effectiveness and availability of the assessment event based on the professional ability coefficient of the assessed person and the unified assessment data of the occupational category matching the assessed person in the database to form optimized assessment integration data, which is specifically calculated by formula (3). Formula (3) is as follows:
[0013]
[0014] Among them, G(U,E) represents the optimization of assessment integration data, U represents the collection of unified assessment data of occupational categories; E represents the occupational ability assessment event; U i Indicates the unified data of occupational category assessment; U j Indicates the professional ability coefficient data of the person being assessed; w(U i ,E) represents the unified data of occupational category assessment U i Support for the professional competence assessment event E; corr(U j ,U i ) represents the unified data of occupational category assessment U i To the professional ability coefficient data U of the person being assessed j relevance;
[0015] An assessment information collection and processing module is used to obtain optimized assessment integration data and combine it with the matching occupational category assessment unified data in the database to perform corresponding collection processing and generate on-site assessment data;
[0016] The output module is used to process the generated on-site assessment data and output it to the assessment visualization system for visualization and for assessment test operations;
[0017] The equivalent scoring module is used to obtain the professional test question and answer data after the on-site assessment test is performed by the assessee, and to give an equivalent score to the on-site assessment data;
[0018] The updating unit is used to obtain equivalent scoring data and update the optimized evaluation integration data of the fusion analysis module according to the equivalent scoring.
[0019] Preferably, when constructing the professional ability assessment model of the examinee, the professional ability estimation module adopts a multi-task learning method to model and evaluate the professional ability coefficients in multiple professional ability assessment learning tasks of the examinee. Preferably, the professional ability estimation module is based on the above-mentioned professional ability assessment model of the examinee, and after performing a correlation analysis based on the target occupational category of the examinee, the assessment qualification standards, skill standards and quality standard characteristic data associated with the target occupational category of the examinee are obtained, and then a separate analysis is performed based on the difference characteristics, and the corresponding professional ability coefficient of the examinee is calculated based on the fuzzy hierarchical analysis method FAHP and the criterion layer weights.
[0020] Preferably, the correlation analysis is performed according to the target occupational category of the person being assessed, wherein the occupational ability estimation module classifies the assessment qualification standards, skill standards and quality standard feature data associated with the target occupational category using an SVM support vector machine for data classification, i.e., data labeling and grouping, constructing an SVM classifier, training a classification model and applying the model to predict results; the data is classified and labeled by the SVM support vector machine, and the optimal hyperplane w is obtained by the following formula (2). φt φ(x)+b=0 classifies the data, and formula (2) is as follows:
[0021]
[0022] Among them, w is the weight vector, a and b are the vectors to be solved, and y i is the true label, x i and x are input samples, K(x i , x) is used to replace x i The kernel function of the inner product operation with x, a i≥0 is the Lagrange multiplier; the data are labeled one by one according to the classification results of the SVM support vector machine.
[0023] Preferably, the assessment qualification criteria include characteristic data of general education level, characteristic data of skill level application conditions and characteristic data of basic knowledge requirements;
[0024] The skill standards include characteristic data of job skill requirements, characteristic data of relevant professional knowledge requirements and characteristic data of performance;
[0025] The quality standards include craftsman spirit characteristic data, professional ethics characteristic data, professional behavior characteristic data, and social responsibility characteristic data.
[0026] Preferably, it also includes a client mounting terminal for the assessed person and the assessment institution to log in and connect to the acquisition module, the client mounting terminal is used to obtain the professional assessment test question data of different assessment institutions, and input the name information, work number information, quality standard information, assessment qualification standard information, department information, skill standard information and position information of the assessed person, and after determining the specific information of the assessed person, generate the on-site assessment data in the assessment visualization system of the client mounting terminal. Preferably, the processing module includes a clustering unit, the clustering unit performs cluster analysis based on the professional assessment test question data of the assessment institution, based on the knowledge point data of the occupational category or the assessment difficulty data, and performs hierarchical clustering processing of the professional ability assessment test questions to form unified assessment data of multi-level assessment difficulty of the corresponding occupational category;
[0027] The assessment information collection and processing module includes a calibration matching unit, which is used to establish a unified assessment database table of multi-level assessment difficulty levels for corresponding occupational categories and an optimized assessment integration database table, and match and calibrate the two.
[0028] Preferably, the equivalent scoring module includes an equivalent analysis unit, the equivalent analysis unit obtains the occupational question and answer data, the occupational question and answer data includes the on-site occupational ability coefficient data of the assessed person filled in by the assessed person, and the equivalent analysis unit is used to perform an assessment equivalent score of the same occupational category level on the occupational ability coefficient of the assessed person and the corresponding on-site occupational ability coefficient data of the assessed person filled in by the assessed person, as shown in formula (4):
[0029]
[0030] Wherein, N(i) represents the professional ability coefficient data of the i-th examinee at the same occupational category level; N(m) represents the professional ability coefficient data of the on-site examinee filled in by the m-th examinee at the same occupational category level; n is the sequence number; P is the probability of scoring; Q iThe equivalent score of the assessment of the same occupational category level is calculated by the weight formula. i The updating unit obtains the weight data Q i , responding to the weight data Q through the professional ability estimation module i After updating the weight coefficients of the k, l and j indicators corresponding to the three criteria of the qualification standards, skill standards and quality standards of the assessed personnel, the assessment integration data is updated and optimized through the fusion analysis module.
[0031] Preferably, the data standardization processing in the processing module includes deleting noise data, completing missing items and eliminating sparse data.
[0032] The present invention also provides a method for a professional competency assessment system based on big data analysis, comprising:
[0033] Step 1: Obtaining professional competency assessment data, including assessment answer data of the assessed personnel, professional assessment test data of the assessment institution, and professional test paper question and answer data;
[0034] Step 2: Data processing of the professional competency assessment data, including data integration, data standardization and data fusion of the professional assessment test data of different assessment institutions, after which unified assessment data of the corresponding professional category is formed and imported into the database;
[0035] Step 3: construct a professional competence assessment model for the assessed personnel, and calculate the corresponding professional competence coefficient of the assessed personnel through the professional competence assessment model of the assessed personnel according to the assessment answer data of the assessed personnel;
[0036] Step 4: Based on the professional competence coefficient of the person being assessed, combined with the unified assessment data of the professional category matching the person being assessed in the database, a fusion analysis of the effectiveness and availability of the assessment event is performed to form optimized assessment integration data;
[0037] Step 5: Obtain optimized assessment integration data and combine it with the matching unified assessment data of occupational categories in the database to perform corresponding collection processing and generate on-site assessment data;
[0038] Step 6: Output application processing of the generated on-site assessment data, and output to the assessment visualization system for visualization presentation for assessment test operation;
[0039] Step seven, after the person being assessed has completed the on-site assessment test, the professional adjustment question and answer data is obtained, and the equivalent score of the on-site assessment data is calculated, and the assessment integration data is updated and optimized according to the equivalent score.
[0040] Beneficial effects of the invention: The occupational competency assessment system and method of the invention based on big data analysis utilizes assessment data analysis to obtain relevant multi-category-level assessment data and assessor competency data, optimizes and generates assessment integration data after fusion analysis, and conducts differentiated assessments at different category levels, which is highly targeted and reliable, and makes the assessment content more accurate, which is conducive to objective and comprehensive assessment of occupational competency, and improves the data processing of assessment data from multiple assessment agencies and the subsequent scoring stage, which can bring good application effects for subsequent system updates. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:
[0042] Figure 1 Schematic diagram of the modular structure of a professional competency assessment system based on big data analysis in an embodiment of the present invention;
[0043] Figure 2 It is a schematic diagram of data processing modularization of a professional competency assessment system based on big data analysis in an embodiment of the present invention;
[0044] Figure 3 A tree diagram of features required for professional competence assessment in a professional competence assessment system based on big data analysis in an embodiment of the present invention;
[0045] Figure 4 The present invention is a flowchart of a method for evaluating professional competence based on big data analysis in an embodiment of the present invention.
[0046] Numbers in the figure: 10, acquisition module; 20, processing module; 30, professional ability estimation module; 40, fusion analysis module; 50, assessment information collection and processing module; 60, output module; 70, equivalent scoring module; 80, update unit. DETAILED DESCRIPTION
[0047] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.
[0048] Reference Figure 1-Figure 4, is an embodiment of the present invention, which provides a system and method for evaluating professional competence based on big data analysis. Figure 1-Figure 3 , the professional competency assessment system includes:
[0049] The acquisition module 10 is used to obtain professional ability assessment data, which includes the assessment answer data of the assessed person, the professional assessment test data of the assessment organization, and the professional paper adjustment question and answer data. Among them, the assessment answer data of the assessor, the professional assessment test data of the assessment organization, and the professional paper adjustment question and answer data are all obtained through the assessed user's answers or assessment information on the client mounting end.
[0050] It is further explained that it also includes a client mounting terminal for the person being assessed and the assessment organization to log in and connected to the acquisition module 10. The client mounting terminal is used to obtain the professional assessment test question data of different assessment organizations, and input the name information, work number information, quality standard information, assessment qualification standard information, department information, skill standard information and position information of the person being assessed. After determining the specific information of the person being assessed, the on-site assessment data is generated in the assessment visualization system of the client mounting terminal. It should be emphasized that the acquisition module 10 of this embodiment can obtain the identity information and related information of the person being assessed, including the assessment qualification standard, skill standard and quality standard information of the person being assessed, when the user being assessed logs in on the client mounting terminal, wherein the assessment qualification standard, skill standard and quality standard information can be obtained from the name information, work number information or the questionnaire survey information of the assessment organization or the person being assessed in the call history. Refer to Figure 3 Specifically, the assessment qualification standards include the characteristic data of general education level, the characteristic data of skill level application conditions and the characteristic data of basic knowledge requirements; the skill standards include the characteristic data of work skill requirements, the characteristic data of relevant professional knowledge requirements and the characteristic data of performance; the quality standards include the characteristic data of craftsman spirit, the characteristic data of professional ethics, the characteristic data of professional behavior and the characteristic data of social responsibility. Through the above-mentioned characteristic information, the professional ability of the person being assessed can be estimated, that is, a professional ability assessment model for the person being assessed can be provided and applied to the assessment of the corresponding subject category, which can match the assessment content of the corresponding level category according to the current ability coefficient of the person being assessed.
[0051] Processing module 20 is used for data processing of occupational competency assessment data. Data processing includes data integration, data standardization and data fusion processing of occupational assessment test data from different assessment institutions. After completion, unified assessment data for the corresponding occupational category is formed and imported into the database. In addition, data standardization processing in processing module 20 includes deletion of noise data, completion of missing items and elimination of sparse data.
[0052] To further illustrate, the processing module 20 of this embodiment includes a clustering unit, which performs cluster analysis based on the professional assessment test data of the assessment organization and the knowledge point data or assessment difficulty data of the occupational category, and performs hierarchical clustering processing of the professional ability assessment test questions to form unified assessment data of multi-level assessment difficulty levels for the corresponding occupational category; the assessment information collection and processing module 50 includes a calibration and matching unit, which is used to establish a unified assessment database table of multi-level assessment difficulty levels for the corresponding occupational category and an optimized assessment integration database table, and match and calibrate the two.
[0053] The professional ability estimation module 30 is used to construct a professional ability assessment model for the assessed person, and calculate the corresponding professional ability coefficient of the assessed person through the professional ability assessment model of the assessed person based on the assessment answer data of the assessed person.
[0054] Specifically, this embodiment models and evaluates the professional ability level of the person being assessed on multiple professional ability assessment learning tasks based on multi-task learning, namely, the professional ability estimation module 30.
[0055] It is used to construct the professional competence assessment model of the assessed personnel, and calculate the corresponding professional competence of the assessed personnel through the professional competence assessment model of the assessed personnel according to the assessment answer data of the assessed personnel, as shown in formula (1):
[0056]
[0057] in, is the professional ability coefficient of the i-th person being assessed; W 1.a ,W 1.b ,W 1.c Respectively represent the weight coefficients of the three aspects of the occupational evaluation criteria layer; W 2.k , W 3.l , W 4.j They represent the weight coefficients of k, l and j indicators corresponding to the three criteria of qualification standard, skill standard and quality standard respectively; U(x) represents the utility value of the indicator parameter. For the convenience of calculation, U(x)=exp(-x).
[0058] Preferably, based on the above-mentioned professional ability assessment model of the assessee, and after conducting a correlation analysis according to the target occupational category of the assessee, the assessment qualification standards, skill standards and quality standard characteristic data associated with the target occupational category of the assessee are obtained, and then a separate analysis is conducted based on the difference characteristics, and the corresponding professional ability coefficient of the assessee is calculated based on the fuzzy hierarchical analysis method FAHP and the criterion layer weights.
[0059] Specifically, a correlation analysis is performed based on the target occupational category of the person being assessed, wherein the occupational ability estimation module 30 classifies the assessment qualification standards, skill standards, and quality standard feature data associated with the target occupational category using an SVM support vector machine for data classification, i.e., data labeling and grouping, constructing an SVM classifier, training a classification model, and applying the model to predict results; the data is classified and labeled using the SVM support vector machine, and the optimal hyperplane w is obtained by the following formula (2): φt φ(x)+b=0 classifies the data, and formula (2) is as follows:
[0060]
[0061] Among them, w is the weight vector, a and b are the vectors to be solved, and y i is the true label, x i and x are input samples, K(x i , x) is used to replace x i The kernel function of the inner product operation with x, a i ≥0 is the Lagrange multiplier; the data are labeled one by one according to the classification results of the SVM support vector machine.
[0062] Through the above-mentioned data classification, the classification operation of similar data among multiple assessment institutions can be realized, which increases the diversity of data and makes the data from different data sources have different coverage, granularity, perspective, etc. Data fusion can expand the diversity of data and increase the redundancy and comprehensiveness of data.
[0063] The fusion analysis module 40 is used to perform fusion analysis of the effectiveness and availability of the assessment event based on the professional ability coefficient of the assessed person and the unified assessment data of the professional category matching the assessed person in the database to form optimized assessment integration data;
[0064] It should be emphasized that the fusion analysis module 40 performs fusion analysis of the effectiveness and availability of the evaluation event to form evaluation integration data, which is specifically calculated by formula (3). Formula (3) is as follows:
[0065]
[0066] Among them, G(U, E) represents the optimization of assessment integration data, U represents the collection of unified assessment data of occupational categories; E represents the occupational ability assessment event; U i Indicates the unified data of occupational category assessment; U j Indicates the professional ability coefficient data of the person being assessed; w(U i , E) represents the unified data of occupational category assessment U i Support for the professional competence assessment event E; corr(U j, U i ) represents the unified data of occupational category assessment U i To the professional ability coefficient data U of the person being assessed j of relevance.
[0067] Through modeling assessment of professional ability levels and fusion analysis, it is possible to evaluate the multi-dimensional information of the evaluated persons, obtain comprehensive data information, and expand data diversity, which will be conducive to the accurate delivery of subsequent evaluation content and enhance the reliability of the data.
[0068] The assessment information collection and processing module 50 is used to obtain the optimized assessment integration data and combine it with the matching occupational category assessment unified data in the database to perform corresponding collection processing and generate on-site assessment data;
[0069] Output module 60, used to perform output application processing on the generated on-site assessment data, and output it to the assessment visualization system for visualization presentation for assessment test operation;
[0070] The equivalent scoring module 70 is used to obtain the professional test question and answer data after the on-site assessment test is performed by the assessee, and to give an equivalent score to the on-site assessment data;
[0071] It should be emphasized that the equivalent scoring module 70 includes an equivalent analysis unit, which obtains the occupational questionnaire data, the occupational questionnaire data includes the on-site occupational competence coefficient data of the assessed person filled in by the assessed person, and the equivalent analysis unit is used to perform an equivalent scoring of the assessment of the same occupational category level on the occupational competence coefficient of the assessed person and the corresponding on-site occupational competence coefficient data of the assessed person filled in by the assessed person, as shown in formula (4):
[0072]
[0073] Wherein, N(i) represents the professional ability coefficient data of the i-th examinee at the same occupational category level; N(m) represents the professional ability coefficient data of the on-site examinee filled in by the m-th examinee at the same occupational category level; n is the sequence number; P is the probability of scoring; Q i The equivalent score of the assessment of the same occupational category level is calculated by the weight formula. i The updating unit 80 obtains the weight data Q i , through the professional ability estimation module 30 responding to the weight data Q i After updating the weight coefficients of the k, l and j indicators corresponding to the three criteria of the assessment qualification standard, skill standard and quality standard of the assessed personnel, the assessment integrated data is updated and optimized through the fusion analysis module 40.
[0074] The updating unit 80 is used to obtain equivalent scoring data and update the optimized evaluation integration data of the fusion analysis module 40 according to the equivalent scoring.
[0075] Based on the scoring of the pushed test questions after the assessment, the equivalent scoring module 70 and the acquisition of professional test question and answer data of multiple assessed persons in the same category can perform equivalent scoring on the currently pushed assessment content, analyze the weights based on the equivalent scoring, and update and optimize the assessment integration data based on the weights. This not only improves the accuracy of the subsequent assessment content push data, reduces errors and deviations, but also meets the public's demand for updated assessment content, promotes communication between assessment agencies and assessors, and is beneficial to the setting of questions by assessment agencies.
[0076] refer to Figure 4 Based on the above-mentioned embodiment of a professional ability assessment system based on big data analysis, the present invention also provides a method of a professional ability assessment system based on big data analysis, including:
[0077] Step 1: Obtaining professional competency assessment data, including assessment answer data of the assessed personnel, professional assessment test data of the assessment institution, and professional test paper question and answer data;
[0078] Step 2: Data processing of professional competency assessment data, including data integration, data standardization and data fusion of professional assessment test data from different assessment institutions. After completion, unified assessment data for the corresponding professional category is formed and imported into the database;
[0079] Step 3: construct a professional competence assessment model for the assessed personnel, and calculate the corresponding professional competence coefficient of the assessed personnel through the professional competence assessment model of the assessed personnel according to the assessment answer data of the assessed personnel;
[0080] Step 4: Based on the professional competence coefficient of the person being assessed, combined with the unified assessment data of the occupational category matching the person being assessed in the database, a fusion analysis of the effectiveness and availability of the assessment event is conducted to form optimized assessment integration data;
[0081] Step 5: Obtain optimized assessment integration data and combine it with the matching occupational category assessment unified data in the database to perform corresponding collection processing and generate on-site assessment data;
[0082] Step 6: Output application processing of the generated on-site assessment data, and output to the assessment visualization system for visualization presentation for assessment test operation;
[0083] Step seven, after the person being assessed has completed the on-site assessment test, obtain the professional adjustment question and answer data, and make an equivalent score for the on-site assessment data, and update and optimize the assessment integration data based on the equivalent score.
[0084] In summary, the present invention is a professional competency assessment system and method based on big data analysis. It utilizes assessment data analysis to obtain relevant multi-category-level assessment data and assessor competency data. After fusion analysis, it optimizes and generates assessment integration data to conduct differentiated assessments at different category levels. It has strong pertinence and reliability, and makes the assessment content more accurate, which is conducive to an objective and comprehensive assessment of professional competence. It also improves the data processing of assessment data from multiple assessment agencies and the subsequent scoring stage, which can bring good application effects for subsequent system updates.
[0085] It should be noted that 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A professional competence assessment system based on big data analysis, characterized in that: include: An acquisition module (10) is used to acquire professional competence assessment data, wherein the professional competence assessment data includes assessment answer data of the assessed person, professional assessment test data of the assessment institution, and professional test paper question and answer data; A processing module (20) is used for data processing of the occupational competency assessment data, wherein the data processing includes data integration, data standardization and data fusion processing of the occupational assessment test data of different assessment institutions, and after completion, unified assessment data of the corresponding occupational category is formed and imported into the database; The professional ability estimation module (30) is used to construct a professional ability assessment model for the assessed person, and calculate the corresponding professional ability of the assessed person through the professional ability assessment model of the assessed person according to the assessment answer data of the assessed person, as shown in formula (1): (1); in, For the i The professional competence coefficient of the person being assessed; , , They represent the weight coefficients of the three aspects of the occupational evaluation criteria layer; , , They represent the qualifications, skills and quality standards of the three criteria. k , l and j The weight coefficient of the indicator; Indicates that the i The utility value of the parameters of the assessed personnel, Indicates that under the skill standard indicator i The utility value of the parameters of the assessed personnel, Indicates that the quality standard indicators i The utility value of the parameters of the person being assessed; The fusion analysis module (40) is used to perform a fusion analysis of the effectiveness and availability of the assessment event based on the professional ability coefficient of the assessed person and the unified assessment data of the professional category matching the assessed person in the database to form optimized assessment integration data, wherein the fusion analysis module (40) performs a fusion analysis of the effectiveness and availability of the assessment event to form the assessment integration data, which is specifically calculated by formula (3), and formula (3) is as follows: (3); in, represents optimized assessment integration data, U represents the collection of unified assessment data of occupational categories; E represents occupational competency assessment events; It indicates the unified data of occupational category assessment; Indicates the professional ability coefficient data of the person being assessed; Indicates unified data of occupational category assessment Support for the professional competence assessment event E; Indicates unified data of occupational category assessment To the professional ability coefficient data of the assessed personnel relevance; An assessment information collection and processing module (50) is used to obtain optimized assessment integration data and combine it with the matching occupational category assessment unified data in the database to perform corresponding collection processing and generate on-site assessment data; An output module (60) is used to perform output application processing on the generated on-site assessment data and output it to the assessment visualization system for visualization presentation for assessment test operations; An equivalent scoring module (70) is used to obtain the professional test question and answer data after the examinee has completed the on-site assessment test, and to give an equivalent score to the on-site assessment data; An updating unit (80) is used to obtain equivalent scoring data and update the optimized evaluation integration data of the fusion analysis module (40) according to the equivalent scoring; The equivalent scoring module (70) includes an equivalent analysis unit, the equivalent analysis unit obtains the occupational questionnaire data, the occupational questionnaire data includes the on-site occupational competence coefficient data of the examinee filled in by the examinee, and the equivalent analysis unit is used to perform an assessment equivalent score of the same occupational category level on the occupational competence coefficient of the examinee and the corresponding on-site occupational competence coefficient data of the examinee filled in by the examinee, as shown in formula (4): (4); in, Indicates the first i The professional competence coefficient data of the persons being assessed; Indicates the first m The professional competence coefficient data of the on-site personnel being assessed filled in by the personnel being assessed; n is the serial number; The probability of scoring the person being assessed; The equivalent score for the same occupational category level is calculated using the weight formula. The updating unit (80) obtains the weight data , responding to the weight data through the professional ability estimation module (30) , the three criteria of qualification, skill and quality standards for the persons being assessed correspond to k , l and j After the weight coefficient of the indicator is updated, the evaluation integration data is updated and optimized through the fusion analysis module (40).
2. A professional ability assessment system based on big data analysis as claimed in claim 1, characterized in that: When constructing the professional ability assessment model of the assessed person, the professional ability estimation module (30) uses a multi-task learning method to model and evaluate the professional ability coefficients in multiple professional ability assessment learning tasks of the assessed person.
3. A professional ability assessment system based on big data analysis as claimed in claim 2, characterized in that: The occupational competence estimation module (30) is based on the occupational competence assessment model of the person being assessed, and after performing a correlation analysis according to the target occupational category of the person being assessed, obtains the characteristic data of the assessment qualification standard, skill standard and quality standard associated with the target occupational category of the person being assessed, and then performs a separate analysis according to the difference characteristics, and calculates the corresponding occupational competence coefficient of the person being assessed according to the fuzzy hierarchical analysis method FAHP and the criterion layer weight.
4. A professional ability assessment system based on big data analysis as claimed in claim 3, characterized in that: The correlation analysis is performed based on the target occupational category of the person being assessed, wherein the occupational ability estimation module (30) classifies the assessment qualification standards, skill standards and quality standard feature data associated with the target occupational category using an SVM support vector machine for data classification, i.e., data labeling and grouping, constructing an SVM classifier, training a classification model and applying the model to predict results; the data is classified and labeled by the SVM support vector machine, and the optimal hyperplane is obtained by the following formula (2) Classify the data, formula (2) is as follows: (2); in, is the weight vector, a, b is the vector to be solved, is the true label, and is the input sample, As a replacement and The kernel function of the inner product operation, is the Lagrange multiplier; the data are labeled one by one according to the classification results of the SVM support vector machine.
5. A professional competency assessment system based on big data analysis as claimed in claim 1, characterized in that: The assessment qualification standards include characteristic data of general education level, characteristic data of skill level application conditions and characteristic data of basic knowledge requirements; The skill standards include characteristic data of job skill requirements, characteristic data of relevant professional knowledge requirements and characteristic data of performance; The quality standards include craftsman spirit characteristic data, professional ethics characteristic data, professional behavior characteristic data, and social responsibility characteristic data.
6. A professional ability assessment system based on big data analysis as claimed in claim 1, characterized in that: It also includes a client mounting terminal for the person being assessed and the assessment institution to log in and connected to the acquisition module (10), the client mounting terminal is used to obtain the professional assessment test question data of different assessment institutions, and input the name information, work number information, quality standard information, assessment qualification standard information, department information, skill standard information and position information of the person being assessed. After determining the specific information of the person being assessed, the on-site assessment data is generated in the assessment visualization system of the client mounting terminal.
7. A professional ability assessment system based on big data analysis as claimed in claim 1, characterized in that: The processing module (20) comprises a clustering unit, which performs cluster analysis based on the professional assessment test question data of the assessment institution and the knowledge point data or assessment difficulty data of the occupational category, and performs hierarchical clustering processing on the professional ability assessment test questions to form unified assessment data of multi-level assessment difficulty of the corresponding occupational category; The assessment information collection and processing module (50) comprises a calibration matching unit, which is used to establish a unified assessment database table of multi-level assessment difficulty levels for corresponding occupational categories and an optimized assessment integration database table, and to match and calibrate the two.
8. A professional competency assessment system based on big data analysis as claimed in claim 1, characterized in that: The data standardization processing in the processing module (20) includes the deletion of noise data, the completion of missing items and the elimination of sparse data.
9. A method applied to the occupational competency assessment system based on big data analysis as claimed in claim 1, characterized in that: include: Step 1: Obtaining professional competency assessment data, including assessment answer data of the assessed personnel, professional assessment test data of the assessment institution, and professional test paper question and answer data; Step 2: Data processing of the professional competency assessment data, including data integration, data standardization and data fusion of the professional assessment test data of different assessment institutions, after which unified assessment data of the corresponding professional category is formed and imported into the database; Step 3: construct a professional competence assessment model for the assessed personnel, and calculate the corresponding professional competence coefficient of the assessed personnel through the professional competence assessment model of the assessed personnel according to the assessment answer data of the assessed personnel; Step 4: Based on the professional competence coefficient of the person being assessed, combined with the unified assessment data of the professional category matching the person being assessed in the database, a fusion analysis of the effectiveness and availability of the assessment event is performed to form optimized assessment integration data; Step 5: Obtain optimized assessment integration data and combine it with the matching unified assessment data of occupational categories in the database to perform corresponding collection processing and generate on-site assessment data; Step 6: Output application processing of the generated on-site assessment data, and output to the assessment visualization system for visualization presentation for assessment test operation; Step seven, after the person being assessed has completed the on-site assessment test, the professional adjustment question and answer data is obtained, and the equivalent score of the on-site assessment data is calculated, and the assessment integration data is updated and optimized according to the equivalent score.
