Production and learning fusion comprehensive platform based on big data analysis

Abstract

The invention discloses a production and study integration comprehensive platform based on big data analysis, and relates to the technical field of production and study integration, and the platform comprises the following components: a data collection module, a big data analysis module, a practice mode and management module, and an enterprise cooperation module. The data acquisition module is used for acquiring basic information, internship demand information and internship feedback information of college students, a large amount of data about student and enterprise demands are acquired and analyzed, the students and internship posts can be matched more accurately, the internship pertinence and effectiveness of the students are improved, and the internship experience of the students is improved. And the students can better exert professional advantages in practice, the practical ability and occupational literacy are improved, and meanwhile, the platform continuously optimizes the practice mode according to the data analysis result, so that the practice content is closer to the actual demand of the enterprise, the practice effect is remarkably improved, and a solid foundation is laid for the future occupational development of the students.

Description

Technical Field

[0001] The present invention relates to the technical field of industry-university integration, and specifically to a comprehensive industry-university integration platform based on big data analysis. Background Art

[0002] With the continuous deepening of education reform, the integration of industry and education has become an important way to improve the quality of higher education and promote the innovative development of enterprises. The integration of industry and education aims to achieve the effective connection between the education chain, talent chain, industrial chain and innovation chain through in-depth cooperation between universities and enterprises, so as to cultivate more high-quality talents that meet market demand. Against this background, a comprehensive platform for industry-university integration based on big data analysis came into being, aiming to utilize the advantages of big data technology, optimize the industry-university cooperation process and improve the quality of talent training.

[0003] However, the traditional industry-university cooperation model has exposed a series of problems in practice. First, the internship model is single and mainly aimed at students who are about to graduate, while ignoring the practical needs of non-graduating students, resulting in their lack of sufficient practical opportunities to consolidate the theoretical knowledge they have learned. Secondly, the internship guidance system is imperfect, the composition of the instructors is simple and the guidance method is too formal, making it difficult to provide targeted guidance and help. In addition, the matching rate between internship positions and majors is low, making it difficult for students to give full play to their professional advantages during the internship, affecting the internship effect. At the same time, the fixed internship positions also restrict students' career exploration and interest development. Finally, due to the lack of effective management and evaluation mechanisms in the internship process, the quality of internships varies, making it difficult to achieve the expected educational results.

[0004] In view of the above problems, it is necessary to optimize the existing comprehensive platform for industry-university integration based on big data analysis. By collecting and analyzing multi-dimensional data such as basic information of college students, internship demand information, internship feedback information, basic information of enterprises and evaluation information of interns, accurate matching of students and internship positions is achieved. Therefore, it is of great significance to develop a comprehensive platform for industry-university integration based on big data analysis that can comprehensively realize the above characteristics. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a comprehensive platform for industry-university integration based on big data analysis. It can collect and analyze multi-dimensional data such as basic information of college students, internship demand information, internship feedback information, basic information of enterprises and evaluation information of interns, so as to achieve accurate matching of students and internship positions. At the same time, according to the results of big data analysis, a variety of internship models are designed and optimized, and the internship process is comprehensively managed, including internship position allocation, internship process tracking and internship evaluation management. In addition, the platform also promotes in-depth cooperation between colleges and universities and enterprises, enables enterprises to publish recruitment information and internship position information, and promotes enterprise mentors to participate in college course design and practical teaching guidance, providing strong support for the in-depth development of industry-education integration.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a comprehensive platform for industry-university integration based on big data analysis, the platform includes the following components: a data collection module, a big data analysis module, an internship model and management module, and an enterprise cooperation module;

[0007] The data collection module is used to collect basic information of college students, internship demand information, internship feedback information, basic information of enterprises and evaluation information of interns;

[0008] The big data analysis module is used to analyze and process the collected data, including internship matching analysis, internship model effect analysis and potential demand mining;

[0009] The internship mode and management module includes an internship mode design submodule and an internship management submodule. The internship mode design submodule uses the formula T for the "1+3+2" internship mode according to the big data analysis results. p Determine the pre-internship time for non-graduating students, including T pre Pre-internship time for non-graduate students, T total is the total internship time, N is the student's current grade, N m ax is the maximum number of grades, λ is the adjustment parameter, N midThe number of middle grades is set up, and rotation positions are set up, covering the core business departments and auxiliary business departments of the enterprise. The proportion of the internship team is determined to be one on-campus instructor, three enterprise-designated specialists, two graduating class interns and non-graduating class pre-interns. An internship task list is formulated. For other internship modes, project-based internships and remote internship modes are designed according to different majors and enterprise needs. The internship management submodule optimizes job allocation based on the student-job matching score, comprehensively considers enterprise needs and student wishes, and connects the platform with the enterprise internship management system to obtain real-time student internship progress and evaluate the internship process tracking effect. At the same time, a combination of quantitative scoring and qualitative evaluation is adopted to calculate the comprehensive score of the internship evaluation through a formula;

[0010] The enterprise cooperation module is used to promote in-depth cooperation between universities and enterprises, including enterprises publishing recruitment information, internship position information and enterprises participating in the teaching process of universities.

[0011] Furthermore, the data collection module collects basic information, academic performance, internship demand information, and internship feedback information of college students by connecting with the college student management system and teaching system and setting up a questionnaire module. It also collects basic information, job demand information, and evaluation information of interns by connecting with the enterprise human resource management system, and uses the formula Measures the quality of collected data, where CI is the data integrity index, n is the number of collected data samples, and x i is the quality assessment value of the ith data sample, and M is the theoretical maximum quality assessment value of the data sample.

[0012] Furthermore, the big data analysis module analyzes and processes the collected data, including internship matching analysis, internship model effect analysis and potential demand mining. The internship matching analysis extracts and quantifies the characteristics of students and enterprise positions after preprocessing the collected data, and uses the formula Calculate the matching score, where MS is the internship matching score, m is the number of feature dimensions, and w is the i is the weight of the i-th feature dimension, K(x i ,y i ) is the kernel function.

[0013] Furthermore, the big data analysis module analyzes and processes the collected data, including internship matching analysis, internship model effect analysis and potential demand mining. The internship model effect analysis collects relevant indicator data of different internship models, uses variance analysis and regression analysis, and uses the formula Comprehensive evaluation effect, where E is the comprehensive evaluation value of the internship model effect, p is the number of factors related to the internship model, ω jis the weight of the jth internship mode related factor, n is the number of samples, α i is the learning rate parameter, g ij It is the grey correlation.

[0014] Furthermore, the big data analysis module analyzes and processes the collected data, including internship matching analysis, internship model effect analysis and potential demand mining. The potential demand mining is performed by pre-processing the student internship feedback information and the company's evaluation information on interns, applying the word vector model and the topic model, and using the formula Mining potential demand, where ND is the potential demand score vector, q is the number of potential demand categories, β k is the weight of the kth potential demand category, s k is the semantic understanding score, r is the number of input feature dimensions, and w kl is the weight coefficient, x kl is the value of the lth input feature.

[0015] Furthermore, in the internship model and management module, the internship management submodule uses the formula based on the student-job matching score, taking into account the needs of the enterprise and the willingness of the students. Optimize job allocation, where P opt is the optimization index for job assignment, MS is the student’s internship matching score, and E pri is the priority of the enterprise for the position, S is the student’s willingness for the position, and S max is the maximum value of the student's willingness for the position, α, β, and μ are the adjustment parameters of the matching score, enterprise priority, and student willingness, respectively. cos To allocate the cost of this position.

[0016] Furthermore, in the internship mode and management module, the internship management submodule connects with the enterprise internship management system through the platform to obtain the student internship progress in real time, using the formula Evaluate the internship process tracking effect, where TE is the internship process tracking effect indicator, CA is the number of key information of student internships accurately obtained, TA is the number of all key information of student internships that should be obtained in theory, and γ and k are adjustment parameters.

[0017] Furthermore, in the internship mode and management module, the internship management submodule adopts a combination of quantitative scoring and qualitative evaluation, through the formula Calculate the comprehensive score of internship evaluation, where ES is the comprehensive score of internship evaluation, w i is the weight of the i-th evaluation dimension, E i is the score of the i-th evaluation dimension, θ iis the nonlinear adjustment coefficient of the i-th evaluation dimension.

[0018] Furthermore, the enterprise cooperation module includes enterprise recruitment information release, enterprise internship position release and enterprise participation in teaching. Enterprise recruitment information release enterprises fill in recruitment information in the prescribed format, including job title, responsibilities, skill requirements, recruitment conditions and salary and benefits. The platform reviews the information and uses the formula Measures the matching degree between enterprise recruitment information and students, where RM is the matching score between enterprise recruitment information and students, m is the number of key requirements in the recruitment information, and r i is the weight of the i-th key requirement in the job posting, s i is the actual value of the student on the i-th key requirement, t i is the threshold of the i-th key requirement, σ i For the adjustment parameters of the i-th key requirement, the company's internship position publishing company clearly specifies the internship position name, time and content information and publishes it. The platform matches and pushes information based on students' internship needs. The company participates in teaching. The company mentors provide actual cases for classroom teaching through the platform and discuss the course teaching objectives, content and methods with university teachers. In the practical teaching session, the company mentors guide students' experimental operations on site and answer questions.

[0019] Compared with the existing technology, this comprehensive industry-university integration platform based on big data analysis has the following beneficial effects:

[0020] 1. By collecting and analyzing a large amount of data on students and corporate needs, the present invention can more accurately match students with internship positions, which not only improves the pertinence and effectiveness of students' internships, but also enables them to better play their professional advantages in internships, improve their practical ability and professional qualities. At the same time, the platform continuously optimizes the internship model based on the results of data analysis, making the internship content closer to the actual needs of the enterprise, thereby significantly improving the internship effect and laying a solid foundation for students' future career development.

[0021] 2. The present invention strengthens the communication and cooperation between universities and enterprises by constructing a comprehensive platform for industry-university integration. It not only provides enterprises with a convenient channel to publish recruitment information and internship position information, but also promotes the participation of enterprise mentors in university course design and practical teaching guidance, thereby realizing the deep integration of industry-university-research. At the same time, through interaction and communication on the platform, universities and enterprises can jointly explore new cooperation models, promote scientific and technological innovation and industrial upgrading, and achieve mutual benefit and win-win results.

[0022] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a schematic diagram of the structure of the comprehensive platform for industry-university integration based on big data analysis;

[0025] Figure 2 This is a schematic diagram of the internship model of the comprehensive platform for industry-university integration based on big data analysis. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Example

[0028] This embodiment describes in detail the specific application of the industry-university integration comprehensive platform based on big data analysis in the internship of computer science major.

[0029] In terms of college student data collection, the data collection module is connected to the student management system of the computer science major in colleges and universities, and a standardized RESTful API interface is used to obtain student-related information, including the student's name, student number, grade, major (clearly computer science) and academic performance data. At the same time, it is connected to the teaching system to obtain relevant information such as course practical operation scores. The internship demand questionnaire and internship feedback questionnaire are issued through a specially designed questionnaire module. The internship demand questionnaire is used to collect information such as students' expected internship position type (such as software development, etc.), internship time preference (such as winter and summer vacations, semesters, long-term internships, etc.), internship location requirements (local, other places, etc.) and expectations for internship remuneration. The internship feedback questionnaire is used to understand students' satisfaction with the previous internship model (using the corresponding evaluation scale), actual The system collects data from the internship and collects information about the interns’ learning gains (such as the skills and knowledge acquired) and the problems encountered during the internship. In terms of enterprise data collection, it connects with the human resources management system of a software company and uses SSL / TLS encrypted RESTful API to ensure data transmission security. It obtains the company’s basic information, including the company name (set as XX Software Company), company size (such as medium-sized), industry type (clearly information technology), and other information. At the same time, it obtains job demand information. For example, for software development positions, detailed requirements include proficiency in specific programming languages ​​(such as Java, Python, etc.), good teamwork and problem-solving skills, and job quantity requirements (set to a certain number). In addition, it also obtains the company’s evaluation information on interns, covering aspects such as professional skills scores, work attitude scores, and teamwork ability scores.

[0030] The big data analysis module performs preprocessing operations on the data collected from college students and enterprises, including removing duplicate data, erroneous data, and incomplete data, and standardizing numerical data (such as grades), for example, normalizing them to between 0 and 1 to facilitate comparison and analysis between different indicators, extracting key features from student data and quantifying them, quantifying professional knowledge levels based on course grades and relevant certificates (set to corresponding values), and skill levels through practical course grades and project experience assessment quantification (set to corresponding values). General abilities (such as teamwork ability obtained through questionnaires and related evaluations) are quantified (set to corresponding values). The characteristics of enterprise job demand data are also quantified, for example, the requirements for programming languages ​​for positions are quantified (set to corresponding values), and the requirements for teamwork ability are quantified (set to corresponding values). The formula is used. Calculate the internship matching score, where m represents the number of feature dimensions (such as professional knowledge, skill level, and general ability, set to m = 3), and w iis the weight of the i-th feature dimension (determined by cross-validation and genetic algorithm optimization, set to corresponding values such as w1, w2, w3, etc.), and the kernel function K(x i , y i ) adopts the Gaussian kernel function where σ is the kernel width parameter (set to the corresponding value), calculates the matching degree score MS (set to the corresponding value) between the student and the software development position, and collects relevant index data of different internship modes of computer science majors from the data collection module, including the professional matching rate (i.e., the proportion of students actually engaged in professional matching work), the employment rate (the proportion of students employed within a certain period after the internship ends), the internship satisfaction (the average satisfaction score obtained through the internship feedback questionnaire), etc. Use the analysis of variance method to compare the differences of each index under different internship modes, and judge whether the influence of different internship modes on the index is significant. At the same time, use the regression analysis method to establish a regression model between the relevant factors of the internship mode (such as internship time, position setting, instructor configuration, etc.) and the index (such as professional matching rate, employment rate, etc.), and analyze the influence degree of each factor on the index. Through the formula Comprehensively evaluate the effect of the internship mode, where p represents the number of relevant factors of the internship mode (set to p = 3, that is, three relevant factors: internship time, position setting, and instructor configuration), ω j is the weight of the j-th relevant factor of the internship mode (determined by the analytic hierarchy process, set to corresponding values such as ω1, ω2, ω3, etc.), n represents the sample size (set to the corresponding value), α i is the neural network learning rate parameter (set to the corresponding value), g ij is the grey relational degree (calculated by grey relational analysis), calculates the comprehensive evaluation value E of different internship modes and compares them. In addition, preprocess text data such as students' internship feedback information and enterprises' evaluations of interns, including removing stop words (such as common words like "of", "is", "in", etc.), stemming (restoring words to their root forms), and part-of-speech tagging. Apply the word vector model to convert the text data into vector representations for computer processing and analysis, and use the topic model to mine the potential topics in the text data. Through the formula Mine the potential demand score vector, where q represents the number of potential demand categories (such as three categories: practical operation guidance demand, theoretical deepening demand, career planning guidance demand, set to q = 3), β k is the weight of the k-th potential demand category (determined according to enterprise and student feedback, set to corresponding values such as β1, β2, β3, etc.), s k is the semantic understanding score (obtained by semantic analysis of the text through a deep learning model), and r represents the number of input feature dimensions (such as the word vector dimension, set to the corresponding value), wkl is the weight coefficient, x kl is the value of the lth input feature. By mining, we can obtain the score vector of students’ potential needs in different aspects and understand their potential demand tendencies.

[0031] For the “1+3+2” internship model, according to the formula Determine the pre-internship time for non-graduating students, including T total represents the total internship duration expected by the enterprise (set to a corresponding value), N max Indicates the maximum undergraduate grade (set to N max =4), λ is the adjustment parameter (set to the corresponding value), N mid is the number of intermediate grades (set as N mid =2.5), N is the student's current grade (set to a corresponding value), and T is calculated by substituting the corresponding value. pre , determine the pre-internship time for non-graduate students, and the rotation positions cover the core business departments and auxiliary business departments of the enterprise. For companies related to computer science majors, such as R&D departments and testing departments, they can be used as core business departments, and technical support departments can be used as auxiliary business departments. The composition ratio of the internship team is determined to be 1 on-campus instructor, 3 enterprise-designated specialists, 2 graduate interns and several non-graduate pre-interns, and a detailed internship task list is formulated. For example, internship tasks in the R&D department include participating in a module of project development, code writing and testing, etc., and internship tasks in the testing department include formulating test plans, executing test cases, etc. The internship management submodule is based on the student-position matching score (set as MS) and comprehensively considers enterprise needs (set as software development position priority E). pri ) and student willingness (set as the student's willingness for software development positions S, S max The maximum value of the student's willingness to take the position is set as S max =5), using the formula Optimize job allocation, where α, k, and μ are adjustment parameters (set to corresponding values) for matching score, enterprise priority, and student willingness, respectively. cos To allocate the cost of the position (taking into account the training cost, time cost, etc., and setting it to a corresponding value), the optimization index P of the position allocation is calculated by substituting the corresponding value. opt , according to P optThe platform is connected with the enterprise internship management system to obtain the progress of students' internships in real time, such as the completion percentage of students' internship tasks in the R&D department (set to the corresponding value), whether some codes and test reports are submitted on time, etc. At the same time, a tutor communication module is set up (using instant messaging tools such as WeChat for enterprises, etc.) to realize real-time communication between on-campus instructors and enterprise tutors and students. Formula The effect of internship process tracking is evaluated, where CA represents the number of key internship information of students accurately obtained (set to the corresponding value), TA represents the number of all key internship information of students that should be obtained in theory (set to the corresponding value), γ and k are adjustment parameters (set to the corresponding values), and the internship process tracking effect index TE is calculated by substituting the corresponding values. The effectiveness of internship process tracking is judged according to the value of TE. In addition, the enterprise evaluation adopts a combination of quantitative scoring and qualitative evaluation to conduct quantitative scoring on interns' professional skills (set to the corresponding score), work attitude (set to the corresponding score), teamwork ability (set to the corresponding score), etc., and qualitatively describe the advantages and disadvantages (such as "solid professional skills, positive work attitude, strong teamwork ability", etc.). Students' self-evaluation focuses on internship gains (such as mastering more software development skills and project management experience, etc.), satisfaction with the internship model (such as satisfaction, dissatisfaction, etc.), etc., and uses the formula Calculate the comprehensive score of the internship evaluation, where w i is the weight of the i-th evaluation dimension (professional skills, work attitude, teamwork ability) (determined by the hierarchical analysis method, set to corresponding values ​​such as w1, w2, w3, etc.), E i is the score of the i-th evaluation dimension (set to the corresponding score), θ i is the nonlinear adjustment coefficient of the ith evaluation dimension (determined by analyzing a large amount of internship evaluation data and set to the corresponding value). The comprehensive internship evaluation score ES is calculated by substituting the corresponding value. The value of ES objectively reflects the overall performance of students during the internship.

[0032] The enterprise cooperation module is used to promote in-depth cooperation between universities and enterprises, including the release of recruitment information, internship information and the participation of enterprises in the teaching process of universities. For enterprises to release recruitment information, enterprises fill in the recruitment information in the format specified by the platform, including software development positions, detailed responsibilities (such as participation in project development and maintenance, etc.), skill requirements (such as proficiency in programming languages ​​such as Java and Python), recruitment conditions (such as bachelor's degree or above, computer-related majors, project experience is preferred), salary and benefits (such as a certain amount per month), etc. The platform reviews the information and uses the formula Measures the matching degree between enterprise recruitment information and students, where m represents the number of key requirements in the recruitment information (set as m=3, such as academic qualifications, majors, and skills), r i is the weight of the ith key requirement in the recruitment information (determined according to the importance of different requirements by the enterprise, set to corresponding values ​​such as r1, r2, r3, etc.), s i is the actual value of the student on the i-th key requirement (after standardization, set to the corresponding value), t i is the threshold of the i-th key requirement (determined according to the enterprise recruitment standards and set to the corresponding value), σ i is the adjustment parameter of the ith key requirement (determined according to the strictness of the recruitment requirements and set to the corresponding value). The matching score RM between the enterprise recruitment information and the student is calculated. For the software development internship information released by the enterprise, including the internship position name (set to software development internship), internship time (such as winter and summer vacations, the start time is the beginning of winter vacation, and the end time is the end of summer vacation), internship content (such as participating in some modules of project development, learning software development processes and specifications, etc.), etc., the platform matches and pushes information based on the student internship demand information. When there is a position that meets the student's needs, the relevant students are notified in time. For the participation of enterprises in the university teaching process, the enterprise tutors cooperate with the computer science teachers of the university through the platform. The enterprise tutors provide actual cases such as the development process and technical difficulties of a large project based on their actual experience in the software development industry. These cases cover the complete software development cycle from project demand analysis, system design, coding implementation to testing and deployment. University teachers and enterprise tutors discuss the course teaching objectives together and integrate theoretical knowledge with In combination with actual project needs, the core knowledge and skills that students should master are determined, such as cultivating students' problem-solving ability, teamwork ability and ability to apply new technologies in the software development process. In terms of teaching content, corporate mentors assist university teachers in adjusting course content and adding knowledge points and practical links related to actual projects. For example, they introduce the industry's latest software development tools and technical frameworks, explain how to apply design patterns in actual projects, and how to effectively manage and version control codes. In the practical teaching link, corporate mentors go deep into university laboratories or corporate internship bases to guide students in experimental operations on site. For example, in the software development practice course, corporate mentors guide students on how to effectively debug codes, how to use testing tools to perform unit and integration tests on codes, and how to optimize code performance. Corporate mentors provide timely answers and guidance to students' problems encountered in the practical operation process. For some common problems, corporate mentors will focus on explaining to ensure that all students can understand and master the correct operation methods and technical points.

[0033] To sum up, by introducing the present invention, in the internship application of computer science major, the data acquisition module comprehensively and accurately obtains student and enterprise information, the big data analysis module realizes the precise matching of students and positions, as well as the scientific evaluation of internship models and the mining of potential needs, the internship model and management module optimizes the internship model design and management process, improves the internship quality and student satisfaction, and the enterprise cooperation module strengthens the integration of industry and academia, selects suitable talents for enterprises and provides students with a better internship and learning environment, effectively solving the problems existing in the existing internship model and improving the overall effect and efficiency of the industry-university integration internship.

[0034] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A comprehensive platform for industry-university integration based on big data analysis, characterized by: The platform includes the following components: data collection module, big data analysis module, internship model and management module and enterprise cooperation module; The data collection module is used to collect basic information of college students, internship demand information, internship feedback information, basic information of enterprises and evaluation information of interns; The big data analysis module is used to analyze and process the collected data, including internship matching analysis, internship model effect analysis and potential demand mining; The internship mode and management module includes an internship mode design submodule and an internship management submodule. The internship mode design submodule uses the formula T for the "1+3+2" internship mode according to the big data analysis results. p Determine the pre-internship time for non-graduating students, including T pre Pre-internship time for non-graduate students, T total is the total internship time, N is the student's current grade, N m ax is the maximum number of grades, λ is the adjustment parameter, N mid The number of middle grades is set up, and rotation positions are set up, covering the core business departments and auxiliary business departments of the enterprise. The proportion of the internship team is determined to be one on-campus instructor, three enterprise-designated specialists, two graduating class interns and non-graduating class pre-interns. An internship task list is formulated. For other internship modes, project-based internships and remote internship modes are designed according to different majors and enterprise needs. The internship management submodule optimizes job allocation based on the student-job matching score, comprehensively considers enterprise needs and student wishes, and connects the platform with the enterprise internship management system to obtain real-time student internship progress and evaluate the internship process tracking effect. At the same time, a combination of quantitative scoring and qualitative evaluation is adopted to calculate the comprehensive score of the internship evaluation through a formula; The enterprise cooperation module is used to promote in-depth cooperation between universities and enterprises, including enterprises publishing recruitment information, internship position information and enterprises participating in the teaching process of universities.

2. The comprehensive platform for industry-university integration based on big data analysis according to claim 1 is characterized in that: The data collection module collects basic information, academic performance, internship demand information, and internship feedback information of college students by connecting with the college student management system and teaching system and setting up a questionnaire module. It also collects basic information, job demand information, and evaluation information of interns by connecting with the enterprise human resource management system, and uses the formula Measures the quality of collected data, where CI is the data integrity index, n is the number of collected data samples, and x i is the quality assessment value of the ith data sample, and M is the theoretical maximum quality assessment value of the data sample.

3. The comprehensive platform for industry-university integration based on big data analysis according to claim 1 is characterized in that: The big data analysis module analyzes and processes the collected data, including internship matching analysis, internship model effect analysis and potential demand mining. The internship matching analysis extracts and quantifies the characteristics of students and enterprise positions after preprocessing the collected data, and uses the formula Calculate the matching score, where MS is the internship matching score, m is the number of feature dimensions, and w is the number of feature dimensions. i is the weight of the i-th feature dimension, K(x i ,y i ) is the kernel function.

4. The comprehensive platform for industry-university integration based on big data analysis according to claim 1 is characterized in that: The big data analysis module analyzes and processes the collected data, including internship matching analysis, internship model effect analysis and potential demand mining. The internship model effect analysis collects relevant indicator data of different internship models, uses variance analysis and regression analysis, and uses the formula Comprehensive evaluation effect, where E is the comprehensive evaluation value of the internship model effect, p is the number of factors related to the internship model, ω j is the weight of the jth internship mode related factor, n is the number of samples, α i is the learning rate parameter, g ij It is the grey correlation.

5. The comprehensive platform for industry-university integration based on big data analysis according to claim 1 is characterized in that: The big data analysis module analyzes and processes the collected data, including internship matching analysis, internship model effect analysis and potential demand mining. The potential demand mining is carried out by pre-processing the student internship feedback information and the enterprise's evaluation information on interns, applying the word vector model and the topic model, and using the formula Mining potential demand, where ND is the potential demand score vector, q is the number of potential demand categories, β k is the weight of the kth potential demand category, s k is the semantic understanding score, r is the number of input feature dimensions, and w kl is the weight coefficient, x kl is the value of the lth input feature.

6. The comprehensive platform for industry-university integration based on big data analysis according to claim 1 is characterized in that: In the internship model and management module, the internship management submodule uses the formula based on the student-job matching score, taking into account the needs of the enterprise and the willingness of the students. Optimize job allocation, where P opt is the optimization index for job assignment, MS is the student’s internship matching score, and E pri is the priority of the enterprise for the position, S is the student’s willingness for the position, and S max is the maximum value of the student's willingness for the position, α, β, and μ are the adjustment parameters of the matching score, enterprise priority, and student willingness, respectively. cos To allocate the cost of this position.

7. The comprehensive platform for industry-university integration based on big data analysis according to claim 1 is characterized in that: In the internship mode and management module, the internship management submodule connects with the enterprise internship management system through the platform to obtain the student internship progress in real time, using the formula Evaluate the internship process tracking effect, where TE is the internship process tracking effect indicator, CA is the number of key information of student internships accurately obtained, TA is the number of all key information of student internships that should be obtained in theory, and γ and k are adjustment parameters.

8. The comprehensive platform for industry-university integration based on big data analysis according to claim 1 is characterized in that: In the internship model and management module, the internship management submodule adopts a combination of quantitative scoring and qualitative evaluation, through the formula Calculate the comprehensive score of internship evaluation, where ES is the comprehensive score of internship evaluation, w i is the weight of the i-th evaluation dimension, E i is the score of the i-th evaluation dimension, θ i is the nonlinear adjustment coefficient of the i-th evaluation dimension.

9. The comprehensive platform for industry-university integration based on big data analysis according to claim 1 is characterized in that: The enterprise cooperation module includes enterprise recruitment information release, enterprise internship position release and enterprise participation in teaching. Enterprise recruitment information release enterprises fill in recruitment information in the prescribed format, including job title, responsibilities, skill requirements, recruitment conditions and salary and benefits. The platform reviews the information and uses the formula Measures the matching degree between enterprise recruitment information and students, where RM is the matching score between enterprise recruitment information and students, m is the number of key requirements in the recruitment information, and r i is the weight of the i-th key requirement in the job posting, s i is the actual value of the student on the i-th key requirement, t i is the threshold of the i-th key requirement, σ i For the adjustment parameters of the i-th key requirement, the company's internship position publishing company clearly specifies the internship position name, time and content information and publishes it. The platform matches and pushes information based on students' internship needs. The company participates in teaching. The company mentors provide actual cases for classroom teaching through the platform and discuss the course teaching objectives, content and methods with university teachers. In the practical teaching session, the company mentors guide students' experimental operations on site and answer questions.

Images