School course design quality evaluation method and system and medium
By processing course review data using data mining algorithms and sentiment analysis models, a scientific set of quality indicators is generated, which solves the problems of systematic feature description and objectivity in course design evaluation, and achieves efficient evaluation and optimization guidance.
Patent Information
- Application Number
- CN202411996840.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-11-07
AI Technical Summary
The lack of scientific and reasonable system feature descriptions and insufficient objectivity in the evaluation process in existing technologies leads to a lack of accuracy in course design evaluation.
Data mining algorithms are used to preprocess comment data, extract comment phrases, generate comment targets through semantic role labeling and dependency analysis, classify quality indicators using the TF-IDF algorithm, and calculate evaluation scores and indicator scores by combining sentiment analysis models to generate evaluation results.
It improves the objectivity and accuracy of course design evaluation, enabling precise identification of user opinions and providing accurate evaluation results and optimization guidance.
Smart Images
Figure CN120912017A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of course evaluation, and particularly relates to a school course design quality evaluation method and system. BACKGROUND
[0002] Course design is the core link of education and teaching, and the quality of course design is evaluated to ensure the scientificity, systematicness and advancement of teaching content, so as to improve the overall education quality. Through the evaluation of the quality of course design, the deficiencies and problems of the existing course can be found, the basis for course reform can be provided, the updating of course content and the innovation of teaching method can be promoted, the allocation of teaching resources can be optimized, the limited resources can be used in the most needed place, the resource use efficiency can be improved, the actual needs of students can be better understood, the course design can be closer to the interests, abilities and career development needs of students, and the all-round development of students can be promoted.
[0003] The traditional course design evaluation at least has the following problems:
[0004] 1. The attribute of the school course system is not described, so that there is no scientific and reasonable system characteristic description that can be used as a basis for school course design evaluation;
[0005] 2. The evaluation process relies on traditional experience, and the objectivity is insufficient, so that an accurate optimization scheme cannot be provided for course design. SUMMARY
[0006] The application aims to provide a school course design quality evaluation method, system and medium, so as to solve the problems of lack of scientific and reasonable system characteristic description and insufficient objectivity in the prior art.
[0007] In order to achieve the above-mentioned purpose, the application adopts the following technical scheme:
[0008] In a first aspect, the application provides a school course design quality evaluation method, which comprises:
[0009] Obtaining comment data of a target course, and preprocessing the comment data to obtain preprocessed comment data;
[0010] Performing object extraction on the preprocessed comment data based on a data mining algorithm to obtain a plurality of comment word groups, each comment word group comprising a comment target and a comment word;
[0011] Classifying the comment targets in the plurality of comment word groups to obtain a quality index set of the school course, the quality index set comprising a plurality of quality indexes;
[0012] counting an evaluation score of the comment phrase corresponding to each quality indicator, the evaluation score being used to represent a text sentiment tendency of a comment word in the comment phrase;
[0013] calculating an indicator score of each quality indicator according to the evaluation score of the comment phrase corresponding to each quality indicator;
[0014] determining an evaluation result of the target course according to the indicator scores of the quality indicators.
[0015] Preferably, the data mining algorithm comprises a semantic role labeling algorithm and a dependency analysis algorithm, and based on object extraction on the preprocessed comment data, a plurality of comment phrases are obtained, comprising:
[0016] identifying an argument and a predicate in the preprocessed comment data based on the semantic role labeling algorithm;
[0017] identifying a dependency relationship between words in the preprocessed comment data based on the dependency analysis algorithm;
[0018] generating a comment phrase according to the argument and the predicate in the preprocessed comment data and the dependency relationship between the words in the preprocessed comment data.
[0019] Preferably, the algorithm for classifying the comment targets in the plurality of comment phrases is a TF-IDF algorithm, and the comment targets in the plurality of comment phrases are classified to obtain a quality indicator set of the school course, comprising:
[0020] calculating a TF frequency and an IDF frequency of each comment target in the comment data;
[0021] calculating a TF-IDF value of each comment target according to the TF frequency and the IDF frequency of each comment target in the comment data;
[0022] sorting the TF-IDF values of the comment targets to obtain a comment sequence;
[0023] determining k comment targets from the comment sequence, taking the comment targets as quality indicators, and the quality indicator set of the school course comprises k quality indicators; wherein k is a positive integer.
[0024] Preferably, the evaluation score of the comment phrase corresponding to each quality indicator is calculated, comprising:
[0025] classifying each comment phrase based on a sentiment analysis model to obtain a sentiment polarity category of each comment phrase;
[0026] determining a category score of each comment phrase according to the sentiment polarity category of each comment phrase;
[0027] determine the number of the comment phrases corresponding to each quality indicator;
[0028] determine an evaluation score of the comment phrases corresponding to each quality indicator according to the number of the comment phrases corresponding to each quality indicator and the category score of each comment phrase.
[0029] Preferably, the sentiment polarity category of the comment phrase includes negative, neutral or positive, and the category score of the comment phrase ranges from 0 to 1.
[0030] Preferably, the indicator score of each quality indicator is calculated according to the evaluation score of the comment phrases corresponding to each quality indicator, including:
[0031] obtain the total number of the comment data of the target course and the course number of the target course;
[0032] determine the influence proportion of each quality indicator according to the total number of the comment data and the evaluation score of the comment phrases corresponding to each quality indicator;
[0033] generate the proportion threshold of each quality indicator according to the influence proportion of each quality indicator and the course number;
[0034] generate the influence score of each quality indicator according to the proportion threshold of each quality indicator and the influence proportion of each quality indicator;
[0035] generate the indicator score of each quality indicator according to the influence score of each quality indicator and the course number.
[0036] Preferably, the influence score of each quality indicator is generated according to the proportion threshold of each quality indicator and the influence proportion of each quality indicator, including:
[0037] For the influence proportion of any one quality indicator, it is determined whether the influence proportion of the quality indicator is greater than the proportion threshold of the quality indicator. If yes, a first score is generated, and the first score is taken as the influence score of the quality indicator. If no, a second score is generated, and the second score is taken as the influence score of the quality indicator.
[0038] Preferably, the evaluation result of the target course is determined according to the indicator scores of the quality indicators, including:
[0039] filter out the quality indicators with an indicator score lower than a preset score from all the quality indicators, and mark the quality indicators with an indicator score lower than the preset score to obtain a plurality of substandard indicators;
[0040] Based on the evaluation score of the comment phrase corresponding to each quality indicator, the correlation degree value between any two quality indicators is calculated, and when the correlation degree value between any two quality indicators reaches a preset correlation degree value, it is indicated that the two quality indicators are correlated quality indicators.
[0041] Based on the correlation degree value between any two quality indicators, the correlated quality indicators corresponding to each unmet indicator are screened, and the plurality of unmet indicators and the correlated quality indicators corresponding to each unmet indicator are used as the evaluation result of the target course.
[0042] In a second aspect, the present application provides a school course design quality evaluation system, which is used to implement the school course design quality evaluation method described above, and the system comprises:
[0043] A data acquisition module is configured to acquire comment data of a target course, and preprocess the comment data to obtain preprocessed comment data.
[0044] A data extraction module is configured to extract objects from the preprocessed comment data based on a data mining algorithm to obtain a plurality of comment phrases, each comment phrase comprising a comment target and a comment word.
[0045] A data classification module is configured to classify the comment targets in the plurality of comment phrases to obtain a quality indicator set of a school course, the quality indicator set comprising a plurality of quality indicators.
[0046] A first calculation module is configured to count the comment phrases corresponding to each quality indicator, and calculate an evaluation score of the comment phrases corresponding to each quality indicator, the evaluation score being used to represent the text sentiment tendency of the comment words in the comment phrases.
[0047] A second calculation module is configured to calculate an indicator score of each quality indicator according to the evaluation score of the comment phrases corresponding to each quality indicator.
[0048] An evaluation generation module is configured to determine an evaluation result of a target course according to the indicator scores of the quality indicators.
[0049] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the school course design quality evaluation method described above when executing the computer program.
[0050] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the program is executable by a processor to implement the school course design quality evaluation method described above.
[0051] Advantages:
[0052] 1、The application utilizes a data mining algorithm to extract features such as comment targets and comment words of comment data, can accurately extract important features affecting the quality of course design, and classifies comment targets in multiple comment word groups to establish a quality index set of school courses, so that multiple quality indexes can evaluate course design from multiple aspects, and the objectivity of evaluation is improved.
[0053] 2、In the evaluation process, the evaluation score is calculated, which can be used to describe the text emotional tendency of the comment words in the comment word group, and the user opinion tendency and the user's evaluation preference on the course attributes or functions can be accurately mined; and the evaluation score is used to calculate the index score of each quality index, the evaluation result is quantified through the index score, the accuracy of evaluation is improved, and accurate guidance direction can be provided for course design. BRIEF DESCRIPTION OF DRAWINGS
[0054] The accompanying drawings are used to provide a further understanding of the embodiments of the application, and constitute a part of the specification, and are used to explain the embodiments of the application together with the following specific embodiments, but do not constitute a limitation to the embodiments of the application. In the drawings:
[0055] Figure 1 is a flowchart of a school course design quality evaluation method provided by an embodiment of the application;
[0056] Figure 2 is a block diagram of a school course design quality evaluation system provided by an embodiment of the application. DETAILED DESCRIPTION
[0057] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the application will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the drawings is only some embodiments of the application, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of these drawings. It should be noted that the description of these embodiments is used to help understand the application, but does not constitute a limitation to the application.
[0058] Embodiment one
[0059] Figure 1 is a flowchart of a school course design quality evaluation method provided by an embodiment of the application. As shown in Figure 1 , the embodiment provides a school course design quality evaluation method, which comprises:
[0060] Step S10: Obtain the comment data of the target course, and pre-process the comment data to obtain the pre-processed comment data.
[0061] In this embodiment, the target course can be one course or multiple courses. This embodiment preferably selects multiple courses to simultaneously evaluate the design quality of multiple courses and judge the rationality and scientificity of the school's overall course design. Among them, the review data can be obtained through relevant data such as course questionnaires, school forums, and on-site interviews.
[0062] In this embodiment, the preprocessing of the review data includes: data cleaning, word segmentation, and noise removal, etc.
[0063] Among them, data cleaning is mainly used to: delete non-text elements such as special characters, punctuation marks, and numbers in the text, and delete common and non-discriminative stop words in the text, such as "de", "he", "shi", etc.
[0064] Among them, word segmentation is mainly used to: split the text into words or vocabulary, and split Chinese sentences into words.
[0065] Among them, noise removal is mainly used to: fill or delete missing values in the text data, etc.
[0066] Step S20: Extract objects from the preprocessed review data based on a data mining algorithm to obtain multiple review phrases. Each review phrase includes: a review target and review words.
[0067] In this embodiment, the data mining algorithm includes: a semantic role labeling algorithm and a dependency parsing algorithm. Then, extracting objects from the preprocessed review data based on the data mining algorithm to obtain multiple review phrases includes:
[0068] Step S201: Identify the arguments and predicates in the preprocessed review data based on the semantic role labeling algorithm. Among them, the semantic role labeling algorithm (Semantic Role Labeling, abbreviated as SRL) can identify the predicates and their related arguments (subjects, objects, etc.) in a sentence. For example, in the sentence "The teacher lectures seriously", "lectures" is the predicate, "The teacher" is the subject, and "lectures" is the object.
[0069] Step S202: Identify the dependency relationships between words in the preprocessed review data based on the dependency parsing algorithm. Among them, dependency parsing represents how the words in a sentence are related and organized by constructing a dependency tree. Each word is a node in the tree, and the dependency relationship between words is an edge in the tree. The root node is usually the core word in the sentence, such as the predicate verb or the subject, and other words are connected to the core word through dependency relationships. Dependency relationship labels describe the specific syntactic relationships between dependent words and core words, such as "subject-predicate relationship", "modifier-head relationship", "verb-object relationship", etc.
[0070] Step S203: generating a comment phrase according to the arguments and predicates in the preprocessed comment data and the dependency relationship between the words in the preprocessed comment data.
[0071] Through steps S201-S203, a plurality of comment phrases can be generated. For example, the sentence of the comment is: "The teaching content of a course is novel, and the course explanation is clear". At this time, "teaching content" is the subject, and "novel" is the predicate. The generated comment phrase is "teaching content-novel", and "teaching content" is the comment target of the comment phrase, and "novel" is the comment word of the comment phrase.
[0072] Step S30: classifying the comment targets in the plurality of comment phrases to obtain a quality indicator set of school courses, the quality indicator set including a plurality of quality indicators.
[0073] In this embodiment, the algorithm for classifying the comment targets in the plurality of comment phrases is the TF-IDF algorithm. The TF-IDF (Term Frequency-Inverse Document Frequency) algorithm is a commonly used technique for information retrieval and text mining, which can measure the importance of a word in a specific document.
[0074] Therefore, classifying the comment targets in the plurality of comment phrases to obtain the quality indicator set of school courses includes:
[0075] Step S301: calculating the TF frequency and the IDF frequency of each comment target appearing in the comment data; wherein the TF frequency is the frequency of a word appearing in a document, and the IDF frequency is the inverse document frequency of a word appearing in all documents;
[0076] Step S302: calculating the TF-IDF value of each comment target according to the TF frequency and the IDF frequency of each comment target appearing in the comment data; wherein the TF-IDF value of each comment target is the product of the TF frequency and the IDF frequency of each comment target appearing in the comment data;
[0077] Step S303: sorting the TF-IDF values of each comment target to obtain a comment sequence;
[0078] Step S304: Determine k review targets from the review sequence, use the review targets as quality indicators, and the quality indicators of the school course include k quality indicators; wherein k is a positive integer; wherein the TF-IDF values in the review sequence are sorted from large to small, and the first k review targets in the review sequence have larger TF-IDF values, the review targets are high-frequency objects, and the first k review targets are used as quality indicators, for example: quality indicators include teaching content, course teacher, learning task, course textbook, and learning experience, and there are 5 quality indicators, k = 5.
[0079] Step S40: Count the review phrases corresponding to each quality indicator, and calculate the evaluation score of the review phrases corresponding to each quality indicator, wherein the evaluation score is used to represent the text emotional tendency of the review words in the review phrases.
[0080] In this embodiment, one review target corresponds to multiple review words, and one quality indicator corresponds to multiple review phrases, and the review targets in the multiple review phrases are the same, but the review words are different; therefore, all review phrases corresponding to each quality indicator are counted.
[0081] In this embodiment, the evaluation score of the review phrases corresponding to each quality indicator is calculated, including:
[0082] Step S401: Classify each review phrase based on the sentiment analysis model to obtain the sentiment polarity category of each review phrase; wherein the sentiment analysis model can use the following models:
[0083] Convolutional Neural Network (CNN): through convolutional layers and pooling layers to extract text features, suitable for local feature extraction of text;
[0084] Recurrent Neural Network (RNN): especially its variants LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit), which can capture sequence dependencies in text;
[0085] Transformer and BERT: Transformer model captures long-distance dependencies in text through self-attention mechanism. BERT (Bidirectional Encoder Representations from Transformers) is a pre-trained model based on Transformer, which performs well in sentiment analysis tasks;
[0086] Emotion-enhanced word embedding: use pre-trained word embedding such as GloVe or Word2Vec, and combine sentiment information to improve the accuracy of sentiment analysis.
[0087] Step S402: determining a category score of each comment phrase according to the sentiment polarity category of each comment phrase;
[0088] In the embodiment, the sentiment polarity category of the comment phrase includes negative, neutral or positive, the category score of the comment phrase ranges from 0 to 1, the category score closer to 1 represents that the sentiment polarity category of the comment phrase is positive, indicating higher positivity, the category score closer to 0 represents that the sentiment polarity category of the comment phrase is negative, indicating lower positivity, and when the category score ranges from 0.4 to 0.6, the sentiment polarity category of the comment phrase is neutral.
[0089] Step S403: determining the number of comment phrases corresponding to each quality indicator; wherein the number of comment phrases corresponding to each quality indicator is the number of comment expressions corresponding to one comment target.
[0090] Step S404: determining the evaluation score of the comment phrases corresponding to each quality indicator according to the number of comment phrases corresponding to each quality indicator and the category score of each comment phrase.
[0091] wherein the calculation expression of the evaluation score of the comment phrases corresponding to the quality indicator is:
[0092]
[0093] In the formula, S i is the evaluation score of the comment phrases corresponding to the i-th quality indicator, i=1, 2,..., k, N is the number of comment phrases corresponding to the i-th quality indicator, n is the n-th comment phrase corresponding to the i-th quality indicator, n=1, 2,..., N, and S i，n is the category score of the n-th comment phrase corresponding to the i-th quality indicator.
[0094] Step S50: calculating the indicator score of each quality indicator according to the evaluation score of the comment phrases corresponding to each quality indicator.
[0095] In the embodiment, the calculation of the indicator score of each quality indicator according to the evaluation score of the comment phrases corresponding to each quality indicator includes:
[0096] Step S501: obtaining the total number of comment data of the target course and the number of courses of the target course.
[0097] Step S502: determining the influence proportion of each quality indicator according to the total number of comment data and the evaluation score of the comment phrases corresponding to each quality indicator; wherein the calculation formula of the influence proportion of each quality indicator is:
[0098] Step S503: generating a proportion threshold of each quality indicator according to the influence proportion of each quality indicator and the number of courses;
[0099] Step S504: generating an influence score of each quality indicator according to the proportion threshold of each quality indicator and the influence proportion of each quality indicator; wherein, generating the influence score of each quality indicator according to the proportion threshold of each quality indicator and the influence proportion of each quality indicator comprises:
[0100] For the influence proportion of any one quality indicator, it is judged whether the influence proportion of the quality indicator is greater than the proportion threshold of the quality indicator, if yes, a first score is generated, and the first score is taken as the influence score of the quality indicator; if no, a second score is generated, and the second score is taken as the influence score of the quality indicator.
[0101] Step S505: generating an indicator score of each quality indicator according to the influence score of each quality indicator and the number of courses.
[0102] Step S60: determining the evaluation result of the target course according to the indicator scores of the quality indicators.
[0103] In the embodiment, determining the evaluation result of the target course according to the indicator scores of the quality indicators comprises:
[0104] Step S601: selecting a quality indicator with an indicator score lower than a preset score from the indicator scores of all quality indicators, marking the quality indicator with the indicator score lower than the preset score, and obtaining a plurality of unqualified indicators;
[0105] Step S602: calculating an association degree value between any two quality indicators based on the evaluation scores of the comment word groups corresponding to each quality indicator, when the association degree value between any two quality indicators reaches a preset association degree value, the two quality indicators are associated with each other, in the embodiment, when the two quality indicators have a high association, the two quality indicators change synchronously with the optimization of the course, when the course design is unreasonable, the indicator scores of the two quality indicators are both low, and when the course design is reasonable, the indicator scores of the two quality indicators are both high;
[0106] Step S603: selecting an associated quality indicator corresponding to each unqualified indicator based on the association degree value between any two quality indicators, and taking the plurality of unqualified indicators and the associated quality indicators corresponding to the unqualified indicators as the evaluation result of the target course.
[0107] Therefore, after obtaining the evaluation result of the target course, the evaluation result of the target course contains a plurality of unqualified indicators and the associated quality indicators corresponding to each unqualified indicator, the quality indicators corresponding to the unqualified indicators need to be referred to in the design optimization of the target course, and it can be judged which quality indicators have correlations in the adjustment process; therefore, the plurality of unqualified indicators and the associated quality indicators corresponding to each unqualified indicator can guide the optimization of the course design, and improve the optimization efficiency and optimization quality of the course.
[0108] The application uses a data mining algorithm to extract features such as comment targets and comment words of comment data, can accurately extract important features affecting the quality of course design, and classifies comment targets in a plurality of comment word groups to establish a quality indicator set of school courses, so that the plurality of quality indicators can evaluate the course design from multiple aspects and improve the objectivity of the evaluation; secondly, in the evaluation process, the evaluation score is calculated, the evaluation score can be used to describe the text emotional tendency of the comment words in the comment word group, and the user opinion tendency and the user evaluation preference on the course attributes or functions can be accurately mined; and the evaluation score is used to calculate the indicator score of each quality indicator, the evaluation result is quantified through the indicator score, the accuracy of the evaluation is improved, and accurate guidance direction can be provided for the course design.
[0109] Embodiment two
[0110] Figure 2 is a block diagram of a school course design quality evaluation system provided by an embodiment of the application. As shown in Figure 2 The embodiment provides a school course design quality evaluation system, which is used to implement the school course design quality evaluation method in embodiment one, and includes:
[0111] A data acquisition module is configured to acquire comment data of a target course, and pre-process the comment data to obtain pre-processed comment data.
[0112] A data extraction module is configured to extract objects from the pre-processed comment data based on a data mining algorithm to obtain a plurality of comment word groups, each comment word group including a comment target and a comment word.
[0113] A data classification module is configured to classify the comment targets in the plurality of comment word groups to obtain a quality indicator set of school courses, the quality indicator set including a plurality of quality indicators.
[0114] A first calculation module is configured to count the comment word groups corresponding to each quality indicator, and calculate an evaluation score of the comment word groups corresponding to each quality indicator, the evaluation score being used to represent the text emotional tendency of the comment words in the comment word group.
[0115] The second calculation module is configured to calculate an index score of each quality indicator according to the evaluation score of the comment phrase corresponding to each quality indicator.
[0116] The evaluation generation module is configured to determine an evaluation result of the target course according to the index scores of the quality indicators.
[0117] The embodiment further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the school course design quality evaluation method in the embodiment one when executing the computer program.
[0118] The embodiment further provides a computer readable storage medium, which stores a computer program, and the program is executable on a processor to implement the school course design quality evaluation method in the embodiment one.
[0119] The application extracts the features such as comment targets and comment words of the comment data by using a data mining algorithm, can accurately extract important features affecting the course design quality, classifies the comment targets in multiple comment phrases to establish a quality indicator set of the school course, and multiple quality indicators can evaluate the course design from multiple aspects, thereby improving the objectivity of the evaluation.
[0120] Those skilled in the art should understand that the embodiments of the application can be provided as a method, a system, or a computer program product. Therefore, the application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the application can adopt a computer program product in the form of one or more computer usable storage media containing computer usable program codes (including but not limited to disk storage, CD-ROM, optical storage, etc.).
[0121] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other processing device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other processing device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions specified in the flowchart block or blocks. Figure 1 The flowchart and / or block diagram in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments. In this regard, each flowchart block and / or combination of flowchart blocks can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, implement the functions specified in the flowchart block or blocks. Figure 1 These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks.
[0122] The embodiments of the present application can be implemented in various ways. The above embodiments are only used to illustrate the present application, and not intended to limit the present application. The present application can be modified and changed by those skilled in the art without departing from the spirit and principle of the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A method of evaluating the quality of a school curriculum design, characterized by, The method comprises: obtaining comment data of a target course, and preprocessing the comment data to obtain preprocessed comment data; extracting objects from the preprocessed comment data based on a data mining algorithm to obtain a plurality of comment phrases, each comment phrase comprising a comment target and a comment word; classifying the comment targets in the plurality of comment phrases to obtain a quality indicator set of the school course, the quality indicator set comprising a plurality of quality indicators; counting the comment phrases corresponding to each quality indicator, and calculating an evaluation score of the comment phrases corresponding to each quality indicator, the evaluation score being used to represent the text emotional tendency of the comment words in the comment phrases; calculating an indicator score of each quality indicator according to the evaluation score of the comment phrases corresponding to each quality indicator; determining an evaluation result of the target course according to the indicator scores of the quality indicators.
2. The method of evaluating the quality of a school curriculum design according to claim 1, wherein, The data mining algorithm comprises a semantic role labeling algorithm and a dependency analysis algorithm, and the plurality of comment phrases are obtained by extracting objects from the preprocessed comment data, comprising: identifying arguments and predicates in the preprocessed comment data based on the semantic role labeling algorithm; identifying the dependency relationship between words in the preprocessed comment data based on the dependency analysis algorithm; generating a comment phrase according to the arguments and predicates in the preprocessed comment data and the dependency relationship between words in the preprocessed comment data.
3. The method of claim 1, wherein, The algorithm for classifying the comment targets in the plurality of comment phrases is a TF-IDF algorithm, and the quality indicator set of the school course is obtained by classifying the comment targets in the plurality of comment phrases, comprising: calculating the TF frequency and IDF frequency of each comment target in the comment data; calculating the TF-IDF value of each comment target according to the TF frequency and IDF frequency of each comment target in the comment data; sorting the TF-IDF values of each comment target to obtain a comment sequence; determining k comment targets from the comment sequence, taking the comment targets as quality indicators, and the quality indicator set of the school course contains k quality indicators; wherein k is a positive integer.
4. The method of claim 1, wherein, The evaluation score of the comment phrases corresponding to each quality indicator is calculated, comprising: classifying each comment phrase based on a sentiment analysis model to obtain the sentiment polarity category of each comment phrase; determining the category score of each comment phrase according to the sentiment polarity category of each comment phrase; determining the number of comment phrases corresponding to each quality indicator; determining the evaluation score of the comment phrases corresponding to each quality indicator according to the number of comment phrases corresponding to each quality indicator and the category score of each comment phrase.
5. The method of claim 4, wherein, The sentiment polarity category of the comment phrase comprises negative, neutral or positive, and the category score of the comment phrase has a value range of [0, 1].
6. The method of claim 4, wherein, The indicator score of each quality indicator is calculated according to the evaluation score of the comment phrases corresponding to each quality indicator, comprising: obtaining the total number of comment data of the target course and the number of courses of the target course; determining the influence proportion of each quality indicator according to the total number of comment data and the evaluation score of the comment phrases corresponding to each quality indicator; generating a proportion threshold of each quality indicator according to the influence proportion of each quality indicator and the number of courses; According to the proportion threshold of each quality indicator and the influence proportion of each quality indicator, an influence score of each quality indicator is generated; According to the influence score of each quality indicator and the number of courses, an indicator score of each quality indicator is generated.
7. The method of evaluating the quality of a school curriculum design according to claim 6, wherein, According to the proportion threshold of each quality indicator and the influence proportion of each quality indicator, an influence score of each quality indicator is generated, including: For the influence proportion of any one quality indicator, it is judged whether the influence proportion of the quality indicator is greater than the proportion threshold of the quality indicator, if yes, a first score is generated, and the first score is taken as the influence score of the quality indicator; if not, a second score is generated, and the second score is taken as the influence score of the quality indicator.
8. The method of claim 6, wherein, According to the indicator scores of the quality indicators, an evaluation result of the target course is determined, including: From the indicator scores of all quality indicators, a quality indicator with an indicator score lower than a preset score is selected, and the quality indicator with the indicator score lower than the preset score is marked to obtain a plurality of substandard indicators; Based on the evaluation score of the comment phrase corresponding to each quality indicator, an association degree value between any two quality indicators is calculated, and when the association degree value between any two quality indicators reaches a preset association degree value, it is represented that the two quality indicators are associated quality indicators; Based on the association degree value between any two quality indicators, an associated quality indicator corresponding to each substandard indicator is selected, and the plurality of substandard indicators and the associated quality indicators corresponding to each substandard indicator are taken as the evaluation result of the target course.
9. A school curriculum design quality evaluation system for implementing the school curriculum design quality evaluation method according to any one of claims 1 to 8, characterized by The system comprises: A data acquisition module is configured to acquire comment data of a target course and pre-process the comment data to obtain pre-processed comment data; A data extraction module is configured to extract objects from the pre-processed comment data based on a data mining algorithm to obtain a plurality of comment phrases, each comment phrase comprising a comment target and a comment word; A data classification module is configured to classify the comment targets in the plurality of comment phrases to obtain a quality indicator set of a school course, the quality indicator set comprising a plurality of quality indicators; A first calculation module is configured to count the comment phrases corresponding to each quality indicator and calculate an evaluation score of the comment phrases corresponding to each quality indicator, the evaluation score being used to represent a text sentiment tendency of the comment words in the comment phrases; A second calculation module is configured to calculate an indicator score of each quality indicator based on the evaluation score of the comment phrases corresponding to each quality indicator; An evaluation generation module is configured to determine an evaluation result of the target course based on the indicator scores of the quality indicators.
10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the school course design quality evaluation method of any one of claims 1-8.