Online multi-terminal interconnected production and education fusion management system

Abstract

The invention discloses an online multi-terminal interconnected production and education fusion management system, and relates to the technical field of data analysis, and the system comprises the steps: carrying out the comprehensive analysis of the development trend of a target career based on the post career directions of all cooperative enterprises, and evaluating the state index of the target career; the matching module is used for obtaining target preference data of the trainees and performing fitting matching screening on the target preference data and state indexes of post occupations to obtain a plurality of post occupations meeting target preferences of the trainees; the database server is used for acquiring post occupational demand data of all cooperative enterprises, establishing an occupational standardized learning database of the cooperative enterprises, and generating post occupational knowledge maps to be learned of all enterprises; and the task planning module is used for creating a learning task plan of the student based on the plurality of post occupations meeting the target preference of the student and the post occupation to-be-learned knowledge maps of all enterprises. The system has the advantages that the trainees have personalized occupational planning ability, the employment level of the trainees is improved, and the recruitment cost of enterprises is reduced.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to an online multi-terminal interconnected production-education integration management system. Background Art

[0002] Industry-education integration refers to vocational schools or colleges actively cooperating with industries based on their established majors, closely integrating industry with teaching, and forming a mutually reinforcing and mutually supportive school-running model, which aims to promote the development of education through industry needs and promote interaction and win-win results between education and industry.

[0003] Due to the deviations in the implementation of the integration of industry and education at the current stage, which is mainly manifested in the disconnection between education and the actual needs of the industry, the students trained have theoretical knowledge but relatively weak practical operation ability and employment adaptability, making it difficult for them to meet the rapidly changing market demands, which in turn affects their employability and competitiveness. Summary of the invention

[0004] In order to solve the above technical problems, an online multi-terminal interconnected industry-education integration management system is provided. This technical solution solves the above-mentioned problem that due to the deviations in the implementation of industry-education integration at the current stage, the main manifestation is the disconnection between education and the actual needs of the industry, resulting in the trained students having theoretical knowledge but relatively weak practical operation ability and employment adaptability, which makes it difficult to meet the rapidly changing market demands, thus affecting the students' employability and competitiveness.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An online multi-terminal interconnected industry-education integration management system, including:

[0007] Position analysis module: The position analysis module is used to comprehensively analyze the development trend of the target occupation based on the job career direction of all cooperating enterprises and evaluate the status indicators of the target occupation;

[0008] A preference analysis module, which is electrically connected to the position analysis module, is used to obtain the trainee's target preference data and the status indicators of the position occupation for fitting, matching and screening, and obtain several positions and occupations that meet the trainee's target preference;

[0009] Job skills map: The job skills map is used to obtain job demand data of all partner companies, establish a standardized learning database for the jobs of partner companies, and generate job knowledge maps to be learned for all companies;

[0010] A learning route generation module is electrically connected to the preference analysis module and the job skill map. The learning route generation module is used to create a learning task plan for students based on a number of job skills that meet the students' target preferences and the job skills map of all companies.

[0011] Preferably, the position analysis module includes:

[0012] The data division unit divides the positions and occupations of all the cooperating enterprises according to the types of industries they belong to, and obtains the industry classification data of the positions and occupations of all the cooperating enterprises;

[0013] The data collection unit obtains big data of job positions in the corresponding industry classification based on the industry classification data of job positions of all cooperating enterprises; the big data of job positions include: the number of job positions, job responsibilities, job salary levels, and job development paths;

[0014] The job occupation matrix unit performs data standardization based on the job occupation big data classified by the corresponding industry, and converts the job occupation big data classified by the corresponding industry into numerical data through unique hot encoding to form a job occupation characteristic data matrix classified by industry;

[0015] The vector unit calculates the covariance matrix of the industry-classified job occupation characteristic data matrix based on the industry-classified job occupation characteristic data matrix, and performs characteristic decomposition on the covariance matrix to obtain the industry-classified job occupation characteristic vector data matrix A=[a 11 ,…,a ij ,…,a nm ]; where a ij is the jth characteristic vector parameter of the i-th job classified by industry, n is the total number of job positions, and m is the total number of characteristic vector parameters of job positions;

[0016] The dimension reduction unit performs data dimension reduction on the data matrix of the position and occupation characteristic vectors classified by the industry through linear transformation, and obtains the dimension reduction data matrix B of the position and occupation characteristic vectors classified by the industry = [b ′ 11 ,…,b i ′ j ,…,b ′ nm ]; among them, b i ′ j The dimension reduction parameter of the jth eigenvector of the i-th job classified by industry;

[0017] The trend model unit builds a prediction model for the development trend of industry-classified job occupations based on the dimension-reduced data matrix of the job occupation feature vectors classified by industry;

[0018] The status evaluation unit, based on the vector dimension reduction data matrix of the job characteristics of the industry classification, substitutes the vector dimension reduction data of the job characteristics of the industry classification into the industry classification job development trend prediction model, and outputs the status index of the job classification of the industry classification;

[0019] Among them, the data matrix of the job occupation characteristic vectors classified by the industry is specifically:

[0020]

[0021] Where B is the dimensionality reduction data matrix of the occupational feature vector classified by industry, μ ij is the mean value of the jth characteristic vector parameter of the i-th job classified by industry, σ is the standard deviation of the job characteristic data matrix classified by industry, X norm It is the data matrix of job characteristics of standardized industry classification. is the transpose of the job occupation characteristic data matrix classified by industry, A is the job occupation characteristic vector data matrix classified by industry, V is the eigenvector column matrix of B, and Λ is the eigenvalue diagonal matrix of B;

[0022] The specific prediction model of career development trend of industry classification positions is as follows:

[0023] G ij =α0+α1a ′ 11 +α2a ′ 22 +α i a ′ ij +…+α n a ′ nm +ε

[0024] In the formula, G ij is the status indicator of the jth job classified in the i-th industry, a ′ ij is the dimension reduction parameter of the characteristic vector of the jth job classified by the i-th industry, α0 is the intercept, α1, α2, α i , α n are linear regression coefficients, and ε is the error term.

[0025] Preferably, the preference analysis module includes:

[0026] A preference unit obtains the target preference data of the trainee and performs matching and screening with the status indicators of the job occupation to obtain a number of job occupations that meet the target preference of the trainee; the target preference data of the trainee includes: career interest, skill preference, salary expectation, and career development path expectation;

[0027] The preference matrix unit performs data standardization based on the target preference data of the students, converts the preference data into numerical data through unique hot encoding, and converts the target preference numerical data of the students into the characteristic vector data matrix C of the students' target preference through linear mapping. 11 ,…,c kj ,…,c lm ]; where c kj is the jth feature vector data of the kth student’s target preference, l is the total number of students’ target preferences, and m is the total number of feature vector parameters of students’ target preferences;

[0028] The matching unit is based on fitting and matching the target preference feature vector data matrix of the trainees with the dimensionality reduction data matrix of the job feature vectors classified by the industry, and obtains the job matching index of each trainee;

[0029] The screening unit screens out positions and occupations of several industries that meet the students' preferences according to the maximum value of the job matching index of each student, and records them as the students' optional positions and occupations;

[0030] Among them, the optional positions and occupations of the students are as follows:

[0031]

[0032] Where P ki is the occupation matching index of the i-th job preferred by the k-th student, β j is the weight coefficient of the jth eigenvector, arg min Pki f(P ki ) is the job-occupation matching index function for selecting students with the minimum distance.

[0033] Preferably, the job occupation requirement module includes:

[0034] The skill requirement unit obtains the skill knowledge information corresponding to the job requirement data based on the job requirement data of all the cooperating enterprises; the job requirement data includes: skill requirements;

[0035] Knowledge database, which will correspond to the skill knowledge information of the job requirements data to form a database of skills knowledge information to be learned;

[0036] The network graph unit, based on the database of skills and knowledge to be learned, creates a knowledge graph for all enterprise positions and occupations according to the learning difficulty of the knowledge information to be learned.

[0037] Preferably, the learning route generation module includes:

[0038] The verification question unit, based on the difficulty network map of the learning knowledge, selects the initial knowledge information to be learned corresponding to each optional job occupation according to the trainees' optional job occupations, and generates verification exercises for the optional job occupation knowledge to be learned;

[0039] The learning speed unit obtains the mastery of the optional job occupation knowledge verification exercises to be learned by each student per unit time based on the optional job occupation knowledge verification exercises to be learned, and calculates the learning speed index of the student's initial learning knowledge information;

[0040] The understanding depth unit calculates the understanding depth index of the student's initial learning knowledge information based on the correct rate of the initial learning knowledge information verification exercises under the learning speed index of the student's initial learning knowledge information;

[0041] The ability assessment unit calculates the learning ability index of each student through the average weighted method based on the learning speed index of the student's initial learning knowledge information and the understanding depth index of the student's initial learning knowledge information;

[0042] The task adjustment unit adjusts the learning task plan of the corresponding student based on the learning ability index of each student and the knowledge graph to be learned for all the positions and occupations of all enterprises; the adjustment of the learning task plan of the corresponding student includes: accelerating the learning speed and increasing the difficulty of the knowledge information to be learned;

[0043] The calculation of each student's learning ability index is specifically as follows:

[0044]

[0045] In the formula, H k is the learning ability index of the kth student, R is the learning speed index of the student's initial learning knowledge information, Q is the understanding depth index of the student's initial learning knowledge information, is the mastery of the zth initial knowledge information verification exercise to be learned by the kth student in the tth unit time, d z is the correct rate of the zth initialization to be learned knowledge information verification exercise, W z is the difficulty weight of the zth initialized knowledge information verification exercise to be learned, and U is the total number of initial knowledge information verification exercises to be learned.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention proposes an online multi-terminal interconnected industry-education integration management plan, which analyzes the actual social status of the open positions of cooperative enterprises and the preferences of trainees to select the open positions of enterprises that meet the preferences of trainees; secondly, according to the needs of the open positions of enterprises, the knowledge map of the positions to be learned is constructed, and the learning task plan of the open positions of enterprises that meet the preferences of trainees is made. The advantages of the present invention are: improving the personalized career planning ability of trainees, improving the employment level of trainees, and reducing the recruitment costs of enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a framework diagram of an online multi-terminal interconnected industry-education integration management system;

[0049] Figure 2 This is the internal framework diagram of the position analysis module;

[0050] Figure 3 This is the internal framework diagram of the preference analysis module;

[0051] Figure 4 It is the internal framework diagram of the job skill map;

[0052] Figure 5 Generate module internal framework diagram for learning route. DETAILED DESCRIPTION

[0053] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0054] Reference Figure 1 As shown, an online multi-terminal interconnected industry-education integration management system includes:

[0055] Position analysis module: The position analysis module is used to comprehensively analyze the development trend of the target occupation based on the job career direction of all cooperating enterprises and evaluate the status indicators of the target occupation;

[0056] A preference analysis module, which is electrically connected to the position analysis module, is used to obtain the trainee's target preference data and the status indicators of the position occupation for fitting, matching and screening, and obtain several positions and occupations that meet the trainee's target preference;

[0057] Job skills map: The job skills map is used to obtain job demand data of all partner companies, establish a standardized learning database for the jobs of partner companies, and generate job knowledge maps to be learned for all companies;

[0058] A learning route generation module is electrically connected to the preference analysis module and the job skill map. The learning route generation module is used to create a learning task plan for students based on a number of job skills that meet the students' target preferences and the job skills map of all companies.

[0059] This solution analyzes the actual social status of the open positions of the cooperating enterprises and the preferences of the trainees to select the open positions of the enterprises that meet the preferences of the trainees; secondly, according to the needs of the open positions of the enterprises, the knowledge map of the positions to be learned is constructed, and the learning task plan of the open positions of the enterprises that meet the preferences of the trainees is made. The advantages of the present invention are: improving the students' personalized career planning ability, improving the employment level of the students, and reducing the recruitment costs of the enterprises.

[0060] Reference Figure 2 As shown, the job analysis module includes:

[0061] The data division unit divides the positions and occupations of all the cooperating enterprises according to the types of industries they belong to, and obtains the industry classification data of the positions and occupations of all the cooperating enterprises;

[0062] The data collection unit obtains big data of job positions in the corresponding industry classification based on the industry classification data of job positions of all cooperating enterprises; the big data of job positions include: the number of job positions, job responsibilities, job salary levels, and job development paths;

[0063] The job occupation matrix unit performs data standardization based on the job occupation big data classified by the corresponding industry, and converts the job occupation big data classified by the corresponding industry into numerical data through unique hot encoding to form a job occupation characteristic data matrix classified by industry;

[0064] The vector unit calculates the covariance matrix of the industry-classified job occupation characteristic data matrix based on the industry-classified job occupation characteristic data matrix, and performs characteristic decomposition on the covariance matrix to obtain the industry-classified job occupation characteristic vector data matrix A=[a 11 ,…,a ij ,…,a nm ]; where a ij is the jth characteristic vector parameter of the i-th job classified by industry, n is the total number of job positions, and m is the total number of characteristic vector parameters of job positions;

[0065] The dimension reduction unit performs data dimension reduction on the data matrix of the position and occupation characteristic vectors classified by the industry through linear transformation, and obtains the dimension reduction data matrix B of the position and occupation characteristic vectors classified by the industry = [b ′11 ,…,b i ′ j ,…,b ′ nm ]; among them, b i ′ j The dimension reduction parameter of the jth eigenvector of the i-th job classified by industry;

[0066] The trend model unit builds a prediction model for the development trend of industry-classified job occupations based on the dimension-reduced data matrix of the job occupation feature vectors classified by industry;

[0067] The status evaluation unit, based on the vector dimension reduction data matrix of the job characteristics of the industry classification, substitutes the vector dimension reduction data of the job characteristics of the industry classification into the industry classification job development trend prediction model, and outputs the status index of the job classification of the industry classification;

[0068] Among them, the data matrix of the job occupation characteristic vectors classified by the industry is specifically:

[0069]

[0070] Where B is the dimensionality reduction data matrix of the occupational feature vector classified by industry, μ ij is the mean value of the jth characteristic vector parameter of the i-th job classified by industry, σ is the standard deviation of the job characteristic data matrix classified by industry, X norm It is the data matrix of job characteristics of standardized industry classification. is the transpose of the job occupation characteristic data matrix classified by industry, A is the job occupation characteristic vector data matrix classified by industry, V is the eigenvector column matrix of B, and Λ is the eigenvalue diagonal matrix of B;

[0071] The specific prediction model of career development trend of industry classification positions is as follows:

[0072] G ij =α0+α1a ′ 11 +α2a ′ 22 +α i a ′ ij +…+α n a ′ nm +ε

[0073] In the formula, G ij is the status indicator of the jth job classified in the i-th industry, a ′ ijis the dimension reduction parameter of the characteristic vector of the jth job classified by the i-th industry, α0 is the intercept, α1, α2, α i , α n are linear regression coefficients, and ε is the error term.

[0074] It should be noted that the industry classification job career development trend prediction model is a linear regression model.

[0075] It should be noted that the job occupation big data in this plan is obtained by screening the job occupation big data of new employees in market research reports. The purpose is to increase the observable granularity of the data to ensure the reliability of the quantitative indicators obtained from the analyzed job occupation big data.

[0076] Reference Figure 3 As shown, the preference analysis module includes:

[0077] A preference unit obtains the target preference data of the trainee and performs matching and screening with the status indicators of the job occupation to obtain a number of job occupations that meet the target preference of the trainee; the target preference data of the trainee includes: career interest, skill preference, salary expectation, and career development path expectation;

[0078] The preference matrix unit performs data standardization based on the target preference data of the students, converts the preference data into numerical data through unique hot encoding, and converts the target preference numerical data of the students into the characteristic vector data matrix C of the students' target preference through linear mapping. 11 ,…,c kj ,…,c lm ]; where c kj is the jth feature vector data of the kth student’s target preference, l is the total number of students’ target preferences, and m is the total number of feature vector parameters of students’ target preferences;

[0079] The matching unit is based on fitting and matching the target preference feature vector data matrix of the trainees with the dimensionality reduction data matrix of the job feature vectors classified by the industry, and obtains the job matching index of each trainee;

[0080] The screening unit screens out positions and occupations of several industries that meet the students' preferences according to the maximum value of the job matching index of each student, and records them as the students' optional positions and occupations;

[0081] Among them, the optional positions and occupations of the students are as follows:

[0082]

[0083] Where P ki is the occupation matching index of the i-th job preferred by the k-th student, β jis the weight coefficient of the jth eigenvector, It is a job-occupation matching index function for selecting students with the minimum distance.

[0084] This solution collects and analyzes students' career interests, skill preferences, salary expectations, career development paths and other target preference data, standardizes them and converts them into numerical feature vectors, and then accurately matches them with the feature vector dimension reduction data of job positions under industry classification to calculate the matching degree between each student and different job positions. Based on the principle of the highest matching degree, multiple job options that best meet the students' preferences are selected to ensure the rationality and accuracy of the learning direction of industry-education integration.

[0085] Reference Figure 4 As shown in the figure, the job occupation requirement module includes:

[0086] The skill requirement unit obtains the skill knowledge information corresponding to the job requirement data based on the job requirement data of all the cooperating enterprises; the job requirement data includes: skill requirements;

[0087] Knowledge database, which will correspond to the skill knowledge information of the job requirements data to form a database of skills knowledge information to be learned;

[0088] The network graph unit, based on the database of skills and knowledge to be learned, creates a knowledge graph for all enterprise positions and occupations according to the learning difficulty of the knowledge information to be learned.

[0089] It is understandable that since different job positions have different requirements for skills to be learned, and since there are differences in difficulty of the knowledge information to be learned, a network map of the difficulty of learning knowledge is created according to the difficulty differences of the knowledge information to be learned for different job positions to provide students with learning direction; for example: a job position classified by the IT industry is: front-end engineer, and the corresponding knowledge information to be learned for the front-end engineer is: simple basic content of JavaScript, css, and HTML, and difficult advanced content of vue and React. Secondly, due to the weak correlation between job positions, the initial learning content of the back-end engineer can be adjusted to common knowledge information to be learned, such as common knowledge such as C# and Java.

[0090] Reference Figure 5 As shown, the learning route generation module includes:

[0091] The verification question unit, based on the difficulty network map of the learning knowledge, selects the initial knowledge information to be learned corresponding to each optional job occupation according to the trainees' optional job occupations, and generates verification exercises for the optional job occupation knowledge to be learned;

[0092] The learning speed unit obtains the mastery of the optional job occupation knowledge verification exercises to be learned by each student per unit time based on the optional job occupation knowledge verification exercises to be learned, and calculates the learning speed index of the student's initial learning knowledge information;

[0093] The understanding depth unit calculates the understanding depth index of the student's initial learning knowledge information based on the correct rate of the initial learning knowledge information verification exercises under the learning speed index of the student's initial learning knowledge information;

[0094] The ability assessment unit calculates the learning ability index of each student through the average weighted method based on the learning speed index of the student's initial learning knowledge information and the understanding depth index of the student's initial learning knowledge information;

[0095] The task adjustment unit adjusts the learning task plan of the corresponding student based on the learning ability index of each student and the knowledge graph to be learned for all the positions and occupations of all enterprises; the adjustment of the learning task plan of the corresponding student includes: accelerating the learning speed and increasing the difficulty of the knowledge information to be learned;

[0096] The calculation of each student's learning ability index is specifically as follows:

[0097]

[0098] In the formula, H k is the learning ability index of the kth student, R is the learning speed index of the student's initial learning knowledge information, Q is the understanding depth index of the student's initial learning knowledge information, is the mastery of the zth initial knowledge information verification exercise to be learned by the kth student in the tth unit time, d z is the correct rate of the zth initialization to be learned knowledge information verification exercise, W z is the difficulty weight of the zth initialized knowledge information verification exercise to be learned, and U is the total number of initial knowledge information verification exercises to be learned.

[0099] This solution aims to achieve deep integration of industry and education by constructing a network map of knowledge difficulty based on job positions, customizing students' learning paths, evaluating learning speed and depth of understanding in real time through verification exercises, accurately calculating learning ability indicators, and dynamically adjusting learning task plans accordingly. The principle is to accurately match job requirements with student capabilities, accelerate knowledge absorption and skill improvement, ensure seamless connection between educational content and industrial practice, and effectively improve students' professional competitiveness and corporate employment efficiency.

[0100] The use process of an online multi-terminal interconnected industry-education integration management system is as follows:

[0101] Step 1: Based on the job orientation of all partner companies, classify the job positions according to the industry type to obtain the industry classification data of the job positions of all partner companies;

[0102] Step 2: Based on the industry classification data of the positions and occupations of all cooperating enterprises, obtain the big data of positions and occupations under the corresponding industry classification;

[0103] Step 3: Perform data standardization based on the big data of job positions classified in the corresponding industry, and convert the big data of job positions classified in the corresponding industry into numerical data through unique hot encoding to form a data matrix of job characteristics classified in the industry;

[0104] Step 4: Based on the job occupation characteristic data matrix classified by industry, calculate the covariance matrix of the job occupation characteristic data matrix classified by industry, and perform characteristic decomposition on the covariance matrix to obtain the job occupation characteristic vector data matrix classified by industry;

[0105] Step 5: Perform data dimensionality reduction on the job occupation characteristic vector data matrix classified by industry through linear transformation to obtain the reduced dimensionality data matrix of the job occupation characteristic vector classified by industry;

[0106] Step 6: Based on the dimensionality reduction data matrix of the job characteristic vectors classified by industry, a prediction model for the development trend of job classification by industry is constructed;

[0107] Step 7: Based on the dimensionality reduction data matrix of the industry-classified job occupation feature vectors, substitute the dimensionality reduction data of the industry-classified job occupation feature vectors into the industry-classified job occupation development trend prediction model, and output the predicted state indicators of the industry-classified job occupations;

[0108] Step 8: Obtain the students' target preference data and the job status indicators for fitting and matching screening to obtain several job positions that meet the students' target preferences;

[0109] Step 9: Perform data standardization based on the students' target preference data, convert the preference data into numerical data through one-hot encoding, and convert the students' target preference numerical data into the feature vector data matrix of the students' target preference through linear mapping;

[0110] Step 10: Fit and match the target preference feature vector data matrix of the trainees with the dimensionality reduction data matrix of the job feature vectors classified by the industry to obtain the job matching index of each trainee;

[0111] Step 11: According to the maximum value of each student's job matching index, select several job positions classified by industry that meet the student's preferences and record them as the student's optional job positions;

[0112] Step 12: Based on the job demand data of all cooperating enterprises, obtain the skill and knowledge information of the corresponding job demand data;

[0113] Step 13: Use the skill knowledge information corresponding to the job requirements to build a database of skills knowledge information to be learned;

[0114] Step 14: Based on the database of skills and knowledge to be learned, create a knowledge graph of all the companies' job positions and occupations according to the learning difficulty of the knowledge to be learned;

[0115] Step 15: Based on the network map of the difficulty of learning knowledge, according to the optional positions and occupations of the trainees, the initial knowledge information to be learned corresponding to each optional position and occupation is screened out, and verification exercises for the knowledge to be learned for the optional position and occupation are generated;

[0116] Step 16: Based on the optional job occupation knowledge verification exercises to be learned, obtain the mastery of the optional job occupation knowledge information verification exercises to be learned by each student per unit time, and calculate the learning speed index of the student's initial learning knowledge information;

[0117] Step 17: Based on the correct rate of the verification exercises of the initialized knowledge information to be learned under the learning speed index of the trainee's initialized learning knowledge information, calculate the understanding depth index of the trainee's initialized learning knowledge information;

[0118] Step 18: Based on the learning speed index of the trainee's initial learning knowledge information and the understanding depth index of the trainee's initial learning knowledge information, calculate the learning ability index of each trainee by using the average weighted method;

[0119] Step 19: Based on each student’s learning ability indicator, adjust the corresponding student’s learning task plan for all the company’s job occupations and knowledge graphs to be learned.

[0120] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An online multi-terminal interconnected industry-education integration management system, characterized in that: include: Position analysis module: The position analysis module is used to comprehensively analyze the development trend of the target occupation based on the job career direction of all cooperating enterprises and evaluate the status indicators of the target occupation; A preference analysis module, which is electrically connected to the position analysis module, is used to obtain the trainee's target preference data and the status indicators of the position occupation for fitting, matching and screening, and obtain several positions and occupations that meet the trainee's target preference; Job skills map: The job skills map is used to obtain job demand data of all partner companies, establish a standardized learning database for the jobs of partner companies, and generate job knowledge maps to be learned for all companies; A learning route generation module is electrically connected to the preference analysis module and the job skill map. The learning route generation module is used to create a learning task plan for students based on a number of job skills that meet the students' target preferences and the job skills map of all companies.

2. According to claim 1, an online multi-terminal interconnected industry-education integration management system is characterized in that: The job analysis module includes: The data division unit divides the positions and occupations of all the cooperating enterprises according to the types of industries they belong to, and obtains the industry classification data of the positions and occupations of all the cooperating enterprises; The data collection unit obtains big data of job positions in the corresponding industry classification based on the industry classification data of job positions of all cooperating enterprises; the big data of job positions include: the number of job positions, job responsibilities, job salary levels, and job development paths; The job occupation matrix unit performs data standardization based on the job occupation big data classified by the corresponding industry, and converts the job occupation big data classified by the corresponding industry into numerical data through unique hot encoding to form a job occupation characteristic data matrix classified by industry; The vector unit calculates the covariance matrix of the industry-classified job occupation characteristic data matrix based on the industry-classified job occupation characteristic data matrix, and performs characteristic decomposition on the covariance matrix to obtain the industry-classified job occupation characteristic vector data matrix A=[a 11 ,…,a ij ,…,a nm ]; where a ij is the jth characteristic vector parameter of the i-th job classified by industry, n is the total number of job positions, and m is the total number of characteristic vector parameters of job positions; The dimension reduction unit performs data dimension reduction on the data matrix of the position and occupation characteristic vectors classified by the industry through linear transformation, and obtains the dimension reduction data matrix B of the position and occupation characteristic vectors classified by the industry = [b ′ 11 ,…,b i ′ j ,…,b ′ nm ]; among them, b i ′ j The dimension reduction parameter of the jth eigenvector of the i-th job classified by industry; The trend model unit builds a prediction model for the development trend of industry-classified job occupations based on the dimension-reduced data matrix of the job occupation feature vectors classified by industry; The status evaluation unit, based on the vector dimension reduction data matrix of the industry-classified job occupation characteristics, substitutes the vector dimension reduction data of the industry-classified job occupation characteristics into the industry-classified job occupation development trend prediction model, and outputs the predicted status index of the industry-classified job occupation.

3. According to claim 2, an online multi-terminal interconnected industry-education integration management system is characterized in that: The data matrix of the job occupation characteristic vectors classified by the industry is specifically as follows: Where B is the dimensionality reduction data matrix of the occupational feature vector classified by industry, μ ij is the mean value of the jth characteristic vector parameter of the i-th job classified by industry, σ is the standard deviation of the job characteristic data matrix classified by industry, X norm It is the data matrix of job characteristics classified by standardized industries. is the transpose of the job occupation characteristic data matrix classified by industry, A is the job occupation characteristic vector data matrix classified by industry, V is the eigenvector column matrix of B, and Λ is the eigenvalue diagonal matrix of B.

4. According to claim 3, an online multi-terminal interconnected industry-education integration management system is characterized in that: The specific prediction model for career development trends of industry classification positions is as follows: G ij =α0+α1a ′ 11 +α2a ′ 22 +a i a ′ ij +…+a n a ′ nm +e In the formula, G ij is the status indicator of the jth job classified in the i-th industry, a ′ ij is the dimension reduction parameter of the characteristic vector of the jth job classified by the i-th industry, α0 is the intercept, α1, α2, α i , α n are linear regression coefficients, and ε is the error term.

5. According to claim 4, an online multi-terminal interconnected industry-education integration management system is characterized in that: The preference analysis module includes: A preference unit obtains the target preference data of the trainee and performs matching and screening with the status indicators of the job occupation to obtain a number of job occupations that meet the target preference of the trainee; the target preference data of the trainee includes: career interest, skill preference, salary expectation, and career development path expectation; The preference matrix unit performs data standardization based on the target preference data of the students, converts the preference data into numerical data through unique hot encoding, and converts the target preference numerical data of the students into the characteristic vector data matrix C of the students' target preference through linear mapping. 11 ,…,c kj ,…,c lm ]; where c kj is the jth feature vector data of the kth student’s target preference, l is the total number of students’ target preferences, and m is the total number of feature vector parameters of students’ target preferences; The matching unit is based on fitting and matching the target preference feature vector data matrix of the trainees with the dimensionality reduction data matrix of the job feature vectors classified by the industry, and obtains the job matching index of each trainee; The screening unit selects jobs and occupations classified in several industries that meet the students' preferences according to the maximum value of each student's job matching index, and records them as the students' optional jobs and occupations.

6. The online multi-terminal interconnected industry-education integration management system according to claim 5 is characterized in that: The optional positions for the trainees are: Where P ki is the occupation matching index of the i-th job preferred by the k-th student, β j is the weight coefficient of the jth eigenvector, It is a job-occupation matching index function for selecting students with the minimum distance.

7. The online multi-terminal interconnected industry-education integration management system according to claim 6 is characterized in that: The job requirements module includes: The skill requirement unit obtains the skill knowledge information corresponding to the job requirement data based on the job requirement data of all the cooperating enterprises; the job requirement data includes: skill requirements; Knowledge database, which will correspond to the skill knowledge information of the job requirements data to form a database of skills knowledge information to be learned; The network graph unit, based on the database of skills and knowledge to be learned, creates a knowledge graph for all enterprise positions and occupations according to the learning difficulty of the knowledge information to be learned.

8. The online multi-terminal interconnected industry-education integration management system according to claim 7 is characterized in that: The learning route generation module includes: The verification question unit, based on the difficulty network map of the learning knowledge, selects the initial knowledge information to be learned corresponding to each optional job occupation according to the trainees' optional job occupations, and generates verification exercises for the optional job occupation knowledge to be learned; The learning speed unit obtains the mastery of the optional job occupation knowledge verification exercises to be learned by each student per unit time based on the optional job occupation knowledge verification exercises to be learned, and calculates the learning speed index of the student's initial learning knowledge information; The understanding depth unit calculates the understanding depth index of the student's initial learning knowledge information based on the correct rate of the initial learning knowledge information verification exercises under the learning speed index of the student's initial learning knowledge information; The ability assessment unit calculates the learning ability index of each student through the average weighted method based on the learning speed index of the student's initial learning knowledge information and the understanding depth index of the student's initial learning knowledge information; The task adjustment unit adjusts the learning task plan of the corresponding student based on the learning ability index of each student and the knowledge graph to be learned for all the job positions of all enterprises; the adjustment of the learning task plan of the corresponding student includes: accelerating the learning speed and increasing the difficulty of the knowledge information to be learned.

9. The online multi-terminal interconnected industry-education integration management system according to claim 8, characterized in that: The specific calculation of the learning ability index of each student is: In the formula, H k is the learning ability index of the kth student, R is the learning speed index of the student's initial learning knowledge information, Q is the understanding depth index of the student's initial learning knowledge information, is the mastery of the zth initial knowledge information verification exercise to be learned by the kth student in the tth unit time, d z is the correct rate of the zth initialization to be learned knowledge information verification exercise, W z is the difficulty weight of the zth initialized knowledge information verification exercise to be learned, and U is the total number of initial knowledge information verification exercises to be learned.

Images