Data sharing method for network courses

Abstract

The invention discloses a data sharing method for network courses, and relates to the technical field of data sharing of network courses. According to an existing network course data sharing method, efficient distribution of resources, real-time updating of the learning progress and cross-platform resource integration are achieved through the data sharing method; a current data sharing method has the problems that learning contents are not matched with user demands, course content complexity is not matched with user capabilities, and the utilization rate of learning resources is low. According to the method, through construction of the user guide graph and generation of the content preference portrait graph, accurate personalized recommendation is realized, and specific learning requirements of the user are met; through natural language processing, formula analysis and image recognition technologies, course content complexity is subjected to quantitative analysis, optimal distribution is performed in combination with user preferences, and the problem of insufficient content adaptability is solved; and through a complexity and preference matching technology, optimal or sub-optimal recommendation of existing courses is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data sharing for online courses, and specifically to a data sharing method for online courses. Background Art

[0002] With the popularization of online education, the demand for teaching resources of online courses has been increasing continuously. To improve the learning effect, many platforms achieve efficient distribution of resources through data sharing methods, such as synchronizing course content through the cloud, updating learning progress in real time, and integrating resources across platforms. These technologies have improved the availability and coverage of teaching resources, providing a more flexible learning and teaching experience for students and teachers.

[0003] Current data sharing methods usually adopt simple tag matching or popularization recommendations, lacking a deep understanding of users' learning goals, interests, and background information, resulting in the learning content obtained by users not matching their own needs. Existing course content lacks dynamic regulation of users' learning ability and content complexity in design and presentation, and it is easy to have situations where the content is too simple or too complex. When existing platforms recommend courses, they fail to make full use of existing resources, and often waste potential resources due to the lack of completely matching courses, etc. Summary of the Invention

[0004] The purpose of the present invention is to propose a data sharing method for online courses in order to solve the above problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A data sharing method for online courses, including the following steps: Step 1: Obtain the learning goal or purpose of the user's online course, specifically: Through the data sharing platform or sharing APP of the online course, investigate the background of the user and the motivation for participating in the course, and conduct investigation questions within the platform; if the user has made an answer, organize the user's answer, classify it according to commonality and individuality, extract the core vocabulary from the user's answer, and extract the keywords of the learning goal; then count the extracted keywords to obtain the proportion of each type of user, and then make a selection to obtain the optional marked online courses; Step 2: Conduct course user habit analysis on the optional marked online courses in Step 1, specifically: Calculate for each content category to obtain the degree of detail of the user's preference for the explanation of a certain content category; calculate the corresponding degree of detail of the category preference for the concept part, formula part, practical operation part, and other parts; the habit coefficients of each content category are combined by the weighted average method to obtain the user's comprehensive habit coefficient; convert the degree of detail of the corresponding category preference explanation into the corresponding user portrait; Step 3: Differentiate the explanations of the online courses, specifically: Obtain the explanatory content in the online courses, including text, paragraphs, formulas, and charts; Analyze the text and paragraphs in the online courses to obtain passage coefficients; Analyze the formulas in the online courses to obtain formula coefficients; Analyze the charts in the online courses to obtain chart coefficients; Then comprehensively evaluate the passage coefficients, formula coefficients, and chart coefficients to obtain the complexity of the corresponding online courses; Step 4: Obtain the online course targets corresponding to the users by combining the optional marked online courses stored in the database with the corresponding user portraits; Calculate the chapter complexity coefficient through Step 3, and overlap and match it with the model shape in the user content preference portrait diagram to obtain the result courses and alternative courses.

[0006] As a preferred implementation manner of the present invention, the specific process of selecting the optional marked online courses is as follows: Make a visualization graph of the proportion of each type of user obtained by statistics to obtain a user-oriented graph, and match the shape of the user-oriented graph with the user-oriented graphs of the online courses existing in the database; If the similarity between the shape of the user-oriented graph of the corresponding customer and the shape of the preset online course visualization graph in the database reaches 95%, mark the corresponding online courses in the database as optional; Then count the optional marked online courses and store them; If there is no online course with a similarity reaching 95% in the database, obtain the online courses with the same content, and perform content splitting; Combine the learning content corresponding to the shape of the user-oriented graph of the customer to obtain a combined online course with the same shape as the user-oriented graph of the visualization chart corresponding to the customer, and store it.

[0007] As a preferred implementation manner of the present invention, the specific process of calculating the degree of detail explanation preference of the user for a certain content category for each content category is as follows: Extract the statistical information selected by the user from the record, and mark the number of times of selecting detailed explanation as D i , mark the number of times of selecting brief explanation as S i , mark the total number of selections as N i , and N i =D i +S i ; Calculate the detail preference coefficient of the user for each content category through the formula: Output the degree of detail explanation preference H of the user for a certain content category i .

[0008] As a preferred implementation manner of the present invention, the specific process of converting the degree of detail explanation preference of the corresponding category into a content preference to obtain the corresponding user portrait is as follows: Calculate the degree H of the detailed explanation of the corresponding category preferences for the concept part, formula part, practical operation part, and other parts i , which are H 概念 , H 公式 , H 实操 and H 其他 ; then perform content preference conversion on the obtained H concept, H formula, H practical operation, and H other; substitute H 概念 , H 公式 , H 实操 and H 其他 into the bar chart to obtain the user content preference portrait diagram; use the model shape in the user content preference portrait diagram as the corresponding user portrait.

[0009] As a preferred embodiment of the present invention, the specific process of analyzing the text and paragraphs in the online course to obtain the text passage coefficient: Through the formula: Output the text passage coefficient Cw, where m is the number of paragraphs, L j is the number of words in the j-th paragraph, S j is the number of sentences in the j-th paragraph, W j is the average word length of the j-th paragraph, and a1, a2, and a3 are all corresponding preset weight coefficients.

[0010] As a preferred embodiment of the present invention, the specific process of analyzing the formulas in the online course to obtain the formula coefficient: Through the formula: Output the formula coefficient Cg, where f is the total number of formulas, C k is the complexity of the k-th formula, b1 is the preset weight factor corresponding to the number of formulas, b2 is the preset weight factor for the formula complexity; C k is the complexity of each formula, and is obtained, where x is the number of terms in the formula, q is the nesting level of the formula, z is the number of different symbols in the formula, and b3, b4, and b5 are all preset weight factors.

[0011] As a preferred embodiment of the present invention, the specific process of analyzing the charts in the online course to obtain the chart coefficient: Through the formula: Output the chart coefficient Ct, where g is the total number of charts, C o is the complexity of the o-th chart, d1 is the preset weight factor for the number of charts, d2 is the preset weight factor for the chart complexity; where C o is obtained through the formula: where y is the number of main elements in the chart, b is the number of annotations of the chart, r is the annotation density of the chart area, and d3, d4, and d5 are all preset weight factors.

[0012] As a preferred embodiment of the present invention, the specific process of overlapping and matching the chapter complexity coefficient with the model shape in the user content preference portrait diagram is as follows: The complexity of the content within the course chapter is calculated through Step 3 to obtain the chapter concept complexity coefficient C 概念 , the chapter formula complexity coefficient C 公式 , the chapter practical operation complexity coefficient C 实操 and the chapter other complexity coefficient C 其他 , and the value ranges are all [0, 1]; then substitute the calculated chapter other complexity coefficient into the user content preference portrait diagram, and overlap and match the model shape in the content preference portrait diagram with the model shape corresponding to the chapter complexity coefficient. If the coincidence rate reaches 80%, it is marked as the result course. Among the optional marked online courses, count the optional marked online courses with a coincidence rate reaching 80%, screen out the optional marked online course with the largest coincidence rate as the preferred course, and mark the other optional marked online courses with a coincidence rate reaching 80% as the secondary courses.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. The present invention forms a user-oriented diagram by investigating the learning goals, interests, and background information of users, and matches it with the online courses in the database. This process can accurately recommend course content that meets the user's needs, and generate a user content preference portrait diagram through the analysis of the data selected by the user, further optimizing the presentation method of the courses. This personalized and targeted recommendation mechanism can significantly improve the user's learning efficiency and satisfaction, and let the user feel the customized learning service.

[0014] 2. The present invention conducts a detailed analysis of the course chapter content, including dimensions such as text, formulas, and charts, and uses natural language processing, formula parsing, and image recognition technologies to quantify the complexity of the course content, and optimizes the allocation in combination with the user's content preference analysis. This data-driven design method helps to refine the course content, making the content presentation more in line with the actual needs of users, avoiding information overload while also taking into account the possibility of in-depth learning.

[0015] 3. The present invention matches the user's needs and the course content in terms of complexity and preference, can preferentially select existing courses that meet the user's needs, and at the same time provides sub-optimal choices to ensure the maximization of the utilization of learning resources. In addition, when there is a lack of directly matching courses, splitting and reorganizing the content to meet the user's needs not only enriches the course resources in the database, but also promotes the innovative application of resource integration, improving the quality and utilization efficiency of the overall platform's learning resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings.

[0017] Figure 1 It is the method step diagram of the present invention; Figure 2 It is the user orientation diagram of the present invention; Figure 3 It is the user content preference portrait diagram of the present invention. Specific embodiments

[0018] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0019] It should be understood that the terms "including" and "comprising" used in the specification and claims of this disclosure indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0020] It should also be understood that the terms used in this disclosure specification are only for the purpose of describing specific embodiments and are not intended to limit this disclosure. As used in this disclosure specification and claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms. It should be further understood that the term "and / or" used in this disclosure specification and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0021] Please refer to Figure 1 As shown, a data sharing method for online courses, the specific steps are as follows: Step 1: Obtain the learning goal or purpose of the user's online course, specifically: Through the data sharing platform or sharing APP of the online course, investigate the background of users (occupation, interests, skill level, etc.) and their motivation for participating in the course, and conduct investigation questions within the platform, such as: "What is your current occupation or field of study?" "What problems do you hope to solve through this course?" etc.; then design guiding questions to guide users to clearly express their needs, expectations, and learning goals, such as example questions: "Do you hope to obtain a specific skill or qualification through this course?" "Which part of the course content are you most concerned about?" "How do you plan to apply what you have learned in the course to practice?"; if the user has answered, organize the user's answers, classify them according to commonalities and individualities, extract core words from the user's answers, extract keywords of learning goals, etc., such as occupation-oriented related keywords ("career development", "qualification certificate", "skill improvement", etc.), interest-oriented related keywords ("hobbies", "curiosity", "knowledge expansion", etc.), and practical-oriented related keywords ("problem-solving", "practical application", "project requirements", etc.); count the extracted keywords to obtain the proportion of each type of user, such as for a certain user, occupation-oriented: 60%, interest-oriented: 25%, practical-oriented: 15%, others: 10%; Please refer to Figure 2 As shown, count the proportion of each type of user, create a visual chart to obtain the user orientation map; and obtain the shape of the user orientation map, and perform shape matching with the user orientation maps of the online courses existing in the database; if the shape of the user orientation map of the corresponding customer is 95% similar to the shape of the preset online course visualization map in the database, make an optional mark for the corresponding online course in the database; then count the optionally marked online courses and store them; if there is no online course in the database with a similarity of 95%, obtain the online courses with the same content, split them, and then combine them according to the learning content corresponding to the shape of the customer's user orientation map to obtain a combined online course with the same shape as the user orientation map of the visual chart corresponding to the customer, and store it; Step 2: Conduct a course user habit analysis on the optionally marked online courses in Step 1, specifically as follows: The selected online courses for the user are displayed by chapter, and there are two options for each chapter, namely: detailed explanation (suitable for users who need to deeply understand the knowledge points) and brief explanation (suitable for users who hope to quickly obtain the core information). In each chapter, the content is divided into concepts (the basic theory or definition part of the chapter), formulas (the mathematical expressions or derivation parts involved in the chapter), and practical operations (the actual applications, case analyses, or hands-on exercises of the chapter), etc.; then the user makes a choice. After each choice, the user's choice is stored, and the data format includes: user ID, selected chapter number, content category (concepts, formulas, practical operations, etc.), corresponding explanation type (detailed or brief); for example: the user selects a brief explanation in the "Chapter 1 - Concepts" section, and the user selects a detailed explanation in the "Chapter 1 - Formulas" section, and accumulates the user's selection data, and sets a threshold (such as accumulating 10 selections). When the recorded number of selections reaches the threshold, trigger user habit analysis to evaluate the user's preferences; otherwise, if the recorded number of selections does not reach the threshold, then distinguish the course explanations according to the user's selections. Analysis of user habits: Extract the statistical information of the user's selections from the records, including: the number of times of selecting detailed explanations, marked as D i (the number of times the user selects a detailed explanation in a certain content category), the number of times of selecting brief explanations, marked as S i (the number of times the user selects a brief explanation in a certain content category), the total number of selections, marked as N i (the total number of selections in a certain content category), and N i = D i + S i ; Calculate the user's detailed preference coefficient for each content category. The process is as follows: Through the formula: Output the degree H of the user's preference for detailed explanations in a certain content category i , and the value range is [0, 1]; The closer H i is to 1, the more the user tends to choose detailed explanations; the closer it is to 0, the more the user prefers brief explanations; then calculate the corresponding degree H of the category's preference for detailed explanations for the concept part, formula part, practical operation part, and other parts i , which are H 概念 , H 公式 , H 实操 , and H 其他 ; To reflect the user's overall preference, combine the habit coefficients of each content category by the weighted average method to calculate the user's comprehensive habit coefficient H 综合 . The process is as follows: Output the user's comprehensive habit coefficient H 综合 , Is the preset weight for this content category, usually set according to the frequency of user selection or the importance of chapter content; for example: the preset weight is ω 概念 = 2, ω 公式 = 4, ω 实操 = 3, ω 其他 = 1; The comprehensive habit coefficient H 综合 is compared with the preset value range of [0, 1]. The closer the comprehensive habit coefficient H 综合 is to 1, the more inclined the user is to choose the detailed explanation; the closer the comprehensive habit coefficient H 综合 is to 0, the more the user prefers the brief explanation; if the user is more inclined to choose the detailed explanation, then choose the detailed online course; if the user prefers the brief explanation, then choose the brief online course; Please refer to Figure 3 as shown, and then the obtained H 概念 、H 公式 、H 实操 and H 其他 ; Perform content preference conversion, and substitute H 概念 、H 公式 、H 实操 and H 其他 into the bar chart to obtain the user content preference portrait diagram; Use the model shape in the user content preference portrait diagram as the corresponding user portrait; It should be noted that: The H 概念 、H 公式 、H 实操 and H 其他 ; corresponding to the bar chart have equal bases; Step 3: Differentiate the explanations of the online courses, specifically: Obtain the explanatory content in the online course. Then, perform paragraph recognition by using natural language processing (NLP) tools (such as spaCy, NLTK), and extract paragraphs according to the chapter logical structure; Identify and count the formulas in the course, use formula parsing tools (such as SymPy) to decompose the formulas, and count the number of terms, nested levels (bracket levels), and symbol quantities of the formulas; Identify the charts in the course, and use image recognition technology (such as OpenCV) to extract the annotation elements and text information of the charts; Analyze the text and paragraphs in the online course. The process is as follows: Through the formula: Output the text paragraph coefficient Cw, where m is the number of paragraphs, L j is the number of words in the j-th paragraph, S j is the number of sentences in the j-th paragraph, W j is the average word length of the j-th paragraph (in characters), and a1, a2, and a3 are all corresponding preset weight coefficients; is the average number of words per paragraph, obtained by counting the total number of characters in each paragraph and taking the average; is the average number of sentences per paragraph, obtained by splitting the paragraph text by full stops, question marks, exclamation marks, etc., counting the total number of sentences, then calculating the number of sentences per paragraph and taking the average; is the average word length per paragraph, obtained by splitting the words in the paragraph (by spaces or punctuation marks), counting the character length of each word, calculating the average word length of the paragraph, and taking the average of all paragraphs; Analyze the formulas in the online course. The process is as follows: Through the formula: Output the formula coefficient Cg, where f is the total number of formulas, C k is the complexity of the k-th formula, b1 is the preset weight factor corresponding to the number of formulas, b2 is the preset weight factor for formula complexity; C k is the complexity of each formula, and is obtained, where x is the number of terms in the formula (e.g., "x + y = z" has 3 terms, has 5 terms), q is the nesting level of the formula (such as fraction, integral, matrix nesting, etc., for example: has a nesting level of 1, has a nesting level of 2), z is the number of different symbol types in the formula (such as +, −, ∫, ∑; for example, the symbol type of y = mx + b is 3, has a symbol type of 4), and b3, b4, and b5 are all preset weight factors, respectively reflecting the contribution degrees of the number of terms, nesting level, and symbol type to the complexity; Analyze the charts in the online course. The process is as follows: Through the formula: Output the chart coefficient Ct, where g is the total number of charts, C o is the complexity of the o-th chart, d1 is the preset weight factor for the number of charts, d2 is the preset weight factor for chart complexity; where C o , through the formula: Obtained, where y is the number of main elements (such as points, lines, columns, etc.) in the chart, b is the number of annotations in the chart (such as coordinate axes, labels, legends, etc.), r is the annotation density of the chart area (number of annotations / unified area value of the chart), and d3, d4, and d5 are all preset weight factors, respectively reflecting the contribution degrees of the main elements, the number of annotations, and the annotation density to the complexity; it should be noted that: the number of main elements y is obtained by detecting the main drawing elements in the chart through an image analysis tool (such as OpenCV), extracting columns, lines, points, or other visual elements and counting the total number; the number of annotations b is obtained by using OCR technology (such as Tesseract) to extract the text and digital annotations in the chart and counting different types of annotations according to specific classifications; the annotation density r is calculated through the formula: r = b / unified area value of the chart, and the unified area value of the chart is obtained by uniformly scaling different chart sizes to the same size; Then, comprehensively evaluate the text coefficient Cw, the formula coefficient Cg, and the chart coefficient Ct to obtain the complexity of the corresponding online course. The process is as follows: Through the formula: Output the course complexity coefficient C 综 , where βw, βg, and βt are all preset weight factors, respectively representing the influence degrees of the text, the formula, and the chart on the course complexity (satisfying βw + βg + βt = 1); the value range of the course complexity coefficient C 综 is set to [0, 1]; the closer C 综 is to 1, the more complex the course content; the closer it is to 0, the simpler the course content; Step Four: Obtain the online course with optional tags stored in the database and combine it with the corresponding user portrait to obtain the online course target of the corresponding user; Please refer to Figure 3 shown. Similarly, calculate the complexity of the content within the course chapter through Step Three to obtain the chapter concept complexity coefficient C 概念 , the chapter formula complexity coefficient C 公式 , the chapter practical operation complexity coefficient C 实操 , and the chapter other complexity coefficient C 其他 (the chapter other complexity coefficient C 其他 is the general term for other chapter contents in the corresponding course chapter except for concepts, formulas, and practical operations; analyze the text and paragraphs of other chapter contents in the online course except for concepts, formulas, and practical operations. The process is as follows: Through the formula: Output the chapter other text coefficient Cw 其他 , where m 其他 is the number of other paragraphs in the chapter, L 其他j其他 is the number of words in the j 其他 th paragraph, S 其他j is the number of sentences in the j 其他 th paragraph, W其他j其他 is the average word length of the j-th 其他 segment; Analyze the charts in other chapters of the online course except for concepts, formulas, and practical operations. The process is as follows: Through the formula: Output the coefficient Ct of other charts in the chapter 其他 , where g 其他 is the total number of other charts in the chapter, and C o其他 is the complexity of the o-th 其他 other chart in the chapter, d1 其他 is the preset weight factor for the number of other charts in the chapter, and d2 其他 is the preset weight factor for the complexity of other charts in the chapter; where C o其他 , through the formula: is obtained, where y 其他 is the number of main elements in other charts of the chapter, and b 其他 is the number of annotations of other charts in the chapter; r 其他 is the annotation density of the area of other charts in the chapter (number of annotations / unified chart area value). Then, comprehensively evaluate the coefficient Cw 其他 of other paragraphs in the chapter and the coefficient Ct 其他 of other charts in the chapter to obtain the complexity of the corresponding online course. The process is as follows: Through the formula: Output the coefficient C of other complexity in the chapter 其他 , where βw 其他 and βt 其他 are both preset weight factors); It should be noted that: the complexity coefficient C 概念 of chapter concepts, the complexity coefficient C 公式 of corresponding chapter formulas, the complexity coefficient C 实操 of corresponding chapter practical operations, and the complexity coefficient C 其他 of corresponding chapter other complexity all have a value range of [0, 1], and are collectively referred to as chapter complexity coefficients; Then substitute the calculated chapter complexity coefficients into the user content preference portrait diagram, and overlap and match the model shape in the content preference portrait diagram with the model shape corresponding to the chapter complexity coefficients. If the coincidence rate reaches 80%, it is marked as the result course. Among the selectable marked online courses, count the selectable marked online courses with a coincidence rate of 80%, screen out the selectable marked online course with the largest coincidence rate as the preferred course, and mark the other selectable marked online courses with a coincidence rate of 80% as secondary courses.

[0022] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments only. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A data sharing method for online courses, characterized in that: The following steps are involved: Step 1: Obtain the learning goals or objectives of the user's online course, specifically: Through the online course data sharing platform or sharing APP, investigate the user's background and motivation for participating in the course, and conduct research questions on the platform; if the user has answered, organize the user's answer and classify it according to commonality and individuality, extract core vocabulary from the user's answer, and extract the keywords of the learning goal; then count the extracted keywords to obtain the proportion of each type of user, and then select to obtain the optional marked online course; Step 2: Analyze the user habits of the online courses that can be marked in step 1, specifically: Calculate each content category to obtain the degree of explanation of the user's preference details for a certain content category; calculate the concept part, formula part, practical part and other parts to obtain the degree of explanation of the corresponding category preference details; The habit coefficients of each content category are combined by weighted average method to obtain the user's comprehensive habit coefficient; the degree of detail explanation of the corresponding category preference is converted into content preference to obtain the corresponding user portrait; Step 3: Differentiate the explanations of online courses, specifically: obtain the explanation content in the online courses, including text, paragraphs, formulas and charts; analyze the text and paragraphs in the online courses to obtain the text coefficient; analyze the formulas in the online courses to obtain the formula coefficient; analyze the charts in the online courses to obtain the chart coefficient; and then comprehensively evaluate the text coefficient, formula coefficient and chart coefficient to obtain the complexity of the corresponding online courses; Step 4: Obtain the optional marked online courses stored in the database and combine them with the corresponding user portrait to obtain the online course goals of the corresponding user; The chapter complexity coefficient is calculated through step three, and the chapter complexity coefficient is overlapped and matched with the model shape in the user content preference portrait to obtain the result course and the second choice course.

2. A method for sharing data of online courses according to claim 1, characterized in that: The specific process of making a selection to get the optional mark online course is: The statistically obtained proportion of each type of user is visualized to obtain a user-oriented map, and the corresponding shape of the user-oriented map is obtained, and the shape of the online course user-oriented map in the database is matched; if the shape of the user-oriented map of the corresponding customer is 95% similar to the shape of the preset online course visualization map in the database, the corresponding online course in the database is marked as optional; Then count the optional marked online courses and store them; If there is no online course with a similarity of 95% in the database, then obtain the online courses with the same subject content and split the content; combine the learning content corresponding to the shape of the customer's user-oriented graph, and obtain a combined online course with a user-oriented graph of the same shape as the user-oriented graph of the visual chart corresponding to the customer, and store it.

3. A method for sharing data of online courses according to claim 1, characterized in that: The specific process of calculating the degree of explanation of the user's preference details for a certain content category for each content category is as follows: Extract the statistics of user selections from the records and mark the number of selections for the detailed explanation as D i , the number of choices briefly explained is marked as S i , the total number of selections is marked as N i , and N i =D i +S i ; Calculate the user's detail preference coefficient for each content category using the formula: Output the degree of detail of the user's preference for a certain content category H i .

4. A method for sharing data of online courses according to claim 3, characterized in that: The specific process of converting the degree of detail explanation of the corresponding category preference into content preference to obtain the corresponding user portrait is as follows: Calculate the concept part, formula part, practical part and other parts to get the corresponding category preference detail explanation degree H i , respectively H 概念 , H 公式 , H 实操 and H 其他 ; Then convert the obtained H concepts, H formulas, H operations and H others; to content preference, and convert H 概念 , H 公式 , H 实操 and H 其他 Substitute into the bar chart to get the user content preference portrait; The model shape in the user content preference portrait diagram is used as the corresponding user portrait.

5. The data sharing method of a network course according to claim 1 is characterized in that: The specific process of analyzing the text and paragraphs in the online course to obtain the paragraph coefficient is as follows: By formula: Output paragraph coefficient Cw, m is the number of paragraphs, L j is the number of words in the jth paragraph, S j is the number of sentences in the jth paragraph, W j is the average vocabulary length of the jth segment, and a1, a2, and a3 are their respective corresponding preset weight coefficients.

6. A method for sharing data of online courses according to claim 5, characterized in that: The specific process of analyzing the formula in the online course to obtain the formula coefficient is as follows: By formula: Output formula coefficient Cg, f is the total number of formulas, C k is the complexity of the kth formula, b1 is the preset weight factor corresponding to the number of formulas, and b2 is the preset weight factor for the complexity of the formula; C k is the complexity of each formula, and We obtain: where x is the number of terms in the formula, q is the nesting level of the formula, z is the number of different symbols in the formula, and b3, b4, and b5 are all preset weight factors.

7. A method for sharing data of online courses according to claim 6, characterized in that: The specific process of analyzing the charts in the online course to obtain the chart coefficients is as follows: By formula: Output chart coefficient Ct, g is the total number of charts, C o is the complexity of the oth chart, d1 is the preset weight factor of the number of charts, and d2 is the preset weight factor of the complexity of the chart; where C o By formula: It is obtained that y is the number of main elements in the chart, b is the number of annotations in the chart, r is the annotation density of the chart area, and d3, d4 and d5 are all preset weight factors.

8. The method for sharing data of an online course according to claim 1, characterized in that: The specific process of matching the chapter complexity coefficient with the model shape in the user content preference portrait is as follows: Through step 3, the complexity of the content in the course chapter is calculated to obtain the chapter concept complexity coefficient C 概念 , Chapter formula complexity coefficient C 公式 , Chapter practical complexity coefficient C 实操 and other complexity coefficients C of the chapter 其他 , and the value range is [0,1]; Then substitute the calculated other complexity coefficients of the chapter into the user content preference portrait, and overlap and match the model shape in the content preference portrait with the model shape corresponding to the chapter complexity coefficient. If the overlap rate reaches 80%, it will be marked as the result course. Among the optional marked online courses, the optional marked online courses with an overlap rate of 80% are counted, and the optional marked online courses with the largest overlap rate are selected as the priority courses, and other optional marked online courses with an overlap rate of 80% are marked as secondary courses.

Images