Vocational education system based on artificial intelligence

Abstract

The invention discloses a vocational education system based on artificial intelligence, and belongs to the technical field of vocational education, the vocational education system based on artificial intelligence comprises a data layer, an artificial intelligence layer, a business logic layer and a user interface, the data layer is responsible for storing various teaching data; the artificial intelligence layer runs various machine learning and deep learning algorithms; the business logic layer processes business processes and rules; the user interface layer provides a friendly interactive interface. By using the collaborative filtering algorithm and the content-based recommendation algorithm, proper courses are accurately pushed to the students according to the learning history, interest preference, occupational objectives and course characteristics of the students.

Description

Technical Field

[0001] The present invention belongs to the technical field of vocational education, and specifically relates to a vocational education system based on artificial intelligence. Background Art

[0002] The vocational education system is an education system dedicated to cultivating professional skills, improving work ability and preparing for employment. Its purpose is to provide students with the knowledge, skills and practical experience required for a specific industry or profession, helping them enter the labor market and obtain corresponding professional qualifications. Vocational education is usually different from general higher education, focusing on practical operation and skill training rather than just theoretical learning. The vocational education system generally includes the following levels:

[0003] Secondary vocational education: usually conducted at the middle school level, where students learn one or more professional skills so that they can find employment directly after graduation. Examples include technical schools, vocational high schools, etc.

[0004] Higher vocational education: includes higher vocational education (higher vocational colleges) and technical college-level education, where students can pursue further studies, master more complex vocational skills, and obtain relevant academic certificates.

[0005] Continuing education and adult education: These courses are usually aimed at people who are already employed, providing professional skills improvement or transformation training to help them adapt to industry changes or improve their professional level.

[0006] At present, traditional vocational education has problems such as a single teaching model and an inability to accurately meet the personalized needs of students. Summary of the invention

[0007] The technical problem to be solved by the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a vocational education system based on artificial intelligence.

[0008] The technical solution adopted to solve the above technical problems is: an artificial intelligence-based vocational education system, including a data layer, an artificial intelligence layer, a business logic layer and a user interface. The data layer is responsible for storing various teaching data; the artificial intelligence layer runs various machine learning and deep learning algorithms; the business logic layer processes business processes and rules; and the user interface layer provides a friendly interactive interface.

[0009] The artificial intelligence layer includes a course recommendation module, a tutoring module, an evaluation module and a practical training module. The course recommendation module analyzes students' learning history, interest preferences, career goals, and course difficulty and content relevance, and uses collaborative filtering algorithms and content-based recommendation algorithms to accurately recommend personalized courses to students.

[0010] Furthermore, the tutoring module is responsible for intelligent question answering based on natural language processing technology. After students ask questions, the system automatically understands the semantics of the questions, retrieves answers from the knowledge base or generates answers using deep learning models. At the same time, it provides targeted tutoring materials and practice questions for students' weak knowledge points.

[0011] Furthermore, the evaluation module uses machine learning algorithms to analyze multi-dimensional data such as students' homework, test scores, and classroom performance to evaluate students' learning progress and mastery, and uses knowledge graph technology to analyze the weak links in students' knowledge system to provide reference for subsequent teaching.

[0012] Furthermore, the training module is responsible for providing students with an immersive training environment through computer simulation, virtual reality and augmented reality technologies.

[0013] Furthermore, the collaborative filtering algorithm is based on the user-item rating matrix and uses the Pearson correlation coefficient. The specific formula is as follows:

[0014]

[0015] Among them, r ui and r vi Respectively represent the ratings of user u and user v on item i, n is the number of items, and are the average ratings of user u and user v respectively;

[0016] The content-based recommendation algorithm converts the course text into a vector and expresses it using TF-IDF (term frequency-inverse document frequency). The specific formula is as follows:

[0017] Term Frequency (TF):

[0018]

[0019] where n ij is the number of times word i appears in document j, ∑ k n kj is the number of occurrences of all words in document j;

[0020] Inverse Document Frequency (IDF):

[0021]

[0022] Where N is the total number of documents, n i is the number of documents containing word i;

[0023] Final TF-IDF value: TF-IDF ij =TF ij ×IDF i .

[0024] Through the above technical solution, appropriate courses can be accurately pushed to students based on their learning history, interest preferences, career goals and the characteristics of the course itself. The similarity between students is calculated through the Pearson correlation coefficient, and courses are recommended to target students based on the course selection and learning situation of similar students. The TF-IDF method is used to analyze the course text content and recommend courses that match students' current knowledge needs to meet students' personalized learning needs.

[0025] Furthermore, the data layer collects student learning data through system logs, learning platform interaction data, etc., and performs preprocessing operations such as cleaning, denoising, and normalization to provide high-quality data for subsequent analysis.

[0026] Furthermore, the tutoring module adopts word embedding model, Transformer architecture and its pre-training model to realize text classification, sentiment analysis, and question-answering system, and the practical training module uses convolutional neural network (CNN) for image recognition and target detection to realize practical training operation monitoring and evaluation.

[0027] The beneficial effects of the present invention are as follows: the present invention utilizes collaborative filtering algorithms and content-based recommendation algorithms to accurately push appropriate courses to students based on their learning history, interest preferences, career goals, and course characteristics. The similarity between students is calculated using the Pearson correlation coefficient, and courses are recommended to target students with reference to the course selection and learning conditions of similar students. At the same time, the TF-IDF method is used to analyze the course text content, recommend courses that match students' current knowledge needs, meet students' personalized learning needs, and improve learning enthusiasm and learning effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a system architecture diagram of the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0030] like Figure 1 As shown, an artificial intelligence-based vocational education system of this embodiment includes a data layer, an artificial intelligence layer, a business logic layer and a user interface. The data layer is responsible for storing various types of teaching data; the artificial intelligence layer runs various types of machine learning and deep learning algorithms; the business logic layer processes business processes and rules; and the user interface layer provides a friendly interactive interface;

[0031] The artificial intelligence layer includes a course recommendation module, a tutoring module, an evaluation module and a practical training module. The course recommendation module analyzes students' learning history, interest preferences, career goals, and course difficulty and content relevance, and uses collaborative filtering algorithms and content-based recommendation algorithms to accurately recommend personalized courses to students.

[0032] The tutoring module is responsible for intelligent question answering based on natural language processing technology. After students ask questions, the system automatically understands the semantics of the questions, retrieves answers from the knowledge base or generates answers using deep learning models. At the same time, it provides targeted tutoring materials and practice questions for students' weak knowledge points.

[0033] The evaluation module uses machine learning algorithms to analyze multi-dimensional data such as students' homework, test scores, and classroom performance to evaluate students' learning progress and mastery, and uses knowledge graph technology to analyze the weak links in students' knowledge system to provide reference for subsequent teaching.

[0034] The practical training module is responsible for providing students with an immersive practical training environment through computer simulation, virtual reality and augmented reality technologies.

[0035] The collaborative filtering algorithm is based on the user-item rating matrix and uses the Pearson correlation coefficient. The specific formula is as follows:

[0036]

[0037] Among them, r ui and r vi Respectively represent the ratings of user u and user v on item i, n is the number of items, and are the average ratings of user u and user v respectively;

[0038] The content-based recommendation algorithm converts the course text into a vector and expresses it using TF-IDF (term frequency-inverse document frequency). The specific formula is as follows:

[0039] Term Frequency (TF):

[0040]

[0041] where n ij is the number of times word i appears in document j, ∑ k n kj is the number of occurrences of all words in document j;

[0042] Inverse Document Frequency (IDF):

[0043]

[0044] Where N is the total number of documents, ni is the number of documents containing word i;

[0045] Final TF-IDF value: TF-IDF ij =TF ij ×IDF i .

[0046] Based on students' learning history, interest preferences, career goals and the characteristics of the course itself, we accurately push appropriate courses to students. We calculate the similarity between students through the Pearson correlation coefficient, and recommend courses to target students based on the course selection and learning situation of similar students. We use the TF-IDF method to analyze the course text content and recommend courses that match students' current knowledge needs to meet students' personalized learning needs.

[0047] The data layer collects student learning data through system logs, learning platform interaction data, etc., and performs preprocessing operations such as cleaning, denoising, and normalization to provide high-quality data for subsequent analysis.

[0048] The tutoring module adopts word embedding model, Transformer architecture and its pre-training model to realize text classification, sentiment analysis and question-answering system. The practical training module uses convolutional neural network (CNN) for image recognition and target detection to realize practical training operation monitoring and evaluation.

[0049] There are three students A, B, and C who are rating four courses m, n, o, and p. The rating range is 1-5 points. The rating matrix is ​​as follows:

[0050] student m n o p A 3 4 2 5 B 4 3 3 4 C 2 1 4 2

[0051] Calculate the Pearson correlation coefficient between Student A and Student B:

[0052] Average rating of student A

[0053] Average rating of student B

[0054]

[0055] but Based on this result, if student A has not taken a course but student B has taken it and rated it well, the system will also consider recommending it to student A.

[0056] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A vocational education system based on artificial intelligence, characterized by: It includes data layer, artificial intelligence layer, business logic layer and user interface. The data layer is responsible for storing various teaching data; the artificial intelligence layer runs various machine learning and deep learning algorithms; the business logic layer processes business processes and rules; and the user interface layer provides a friendly interactive interface. The artificial intelligence layer includes a course recommendation module, a tutoring module, an evaluation module and a practical training module. The course recommendation module analyzes students' learning history, interest preferences, career goals, and course difficulty and content relevance, and uses collaborative filtering algorithms and content-based recommendation algorithms to accurately recommend personalized courses to students.

2. The artificial intelligence-based vocational education system according to claim 1, characterized in that: The tutoring module is responsible for intelligent question answering based on natural language processing technology. After students ask questions, the system automatically understands the semantics of the questions, retrieves answers from the knowledge base or generates answers using deep learning models. At the same time, it provides targeted tutoring materials and practice questions for students' weak knowledge points.

3. The artificial intelligence-based vocational education system according to claim 2, characterized in that: The evaluation module uses machine learning algorithms to analyze multi-dimensional data such as students' homework, test scores, and classroom performance to evaluate students' learning progress and mastery, and uses knowledge graph technology to analyze the weak links in students' knowledge system to provide reference for subsequent teaching.

4. The artificial intelligence-based vocational education system according to claim 3, characterized in that: The practical training module is responsible for providing students with an immersive practical training environment through computer simulation, virtual reality and augmented reality technologies.

5. The artificial intelligence-based vocational education system according to claim 2, characterized in that: The collaborative filtering algorithm is based on the user-item rating matrix and uses the Pearson correlation coefficient. The specific formula is as follows: Among them, r ui and r vi Respectively represent the ratings of user u and user v on item i, n is the number of items, and are the average ratings of user u and user v respectively; The content-based recommendation algorithm converts the course text into a vector and expresses it using TF-IDF (term frequency-inverse document frequency). The specific formula is as follows: Term Frequency (TF): Where n ij is the number of times word i appears in document j, ∑ k n kj is the number of occurrences of all words in document j; Inverse Document Frequency (IDF): Where N is the total number of documents, n i is the number of documents containing word i; Final TF-IDF value: TF-IDF ij =TF ij ×IDF i .

6. The artificial intelligence-based vocational education system according to claim 1, characterized in that: The data layer collects student learning data through system logs, learning platform interaction data, etc., and performs preprocessing operations such as cleaning, denoising, and normalization to provide high-quality data for subsequent analysis.

7. The artificial intelligence-based vocational education system according to claim 4, characterized in that: The tutoring module adopts word embedding model, Transformer architecture and its pre-training model to realize text classification, sentiment analysis and question-answering system. The practical training module uses convolutional neural network (CNN) for image recognition and target detection to realize practical training operation monitoring and evaluation.

Images