Generation method and generation system for curriculum labels of online education resources

Abstract

The invention provides an online education resource course label generation method and system, and the method comprises the steps: carrying out the label extraction of the text data of a to-be-generated online education resource, and obtaining a label set; labels in the label set are converted into high-dimensional vectors through a preset word vector model, and first similarity information between the high-dimensional vectors is obtained; constructing a binary balance tree of the high-dimensional vector according to the first similarity information through a preset binary K-means clustering algorithm; extracting subject terms from the text data of the curriculum brief introduction of the to-be-generated online education resources; converting the subject term into a subject term vector, and obtaining second similarity information of the subject term vector and the high-dimensional vector; and determining the subject term vector and the high-dimensional vector corresponding to the third similarity information as the course tag of the to-be-generated online education resource.

Description

Technical Field

[0001] This application belongs to the field of machine learning, and in particular relates to methods and systems for generating course tags for online educational resources. Background Technology

[0002] In recent years, with the rapid advancements in internet technology, big data analytics, artificial intelligence, and natural language processing (NLP), the intelligent management and application of online educational resources have seen significant development. Intelligent course tag generation technology has demonstrated enormous potential and value in optimizing educational resource retrieval, enhancing the learning experience, and enabling personalized recommendations. This technology primarily relies on advanced technologies such as natural language processing, machine learning, and deep learning. Through in-depth analysis and understanding of course content, it automatically extracts keywords, phrases, or concepts closely related to the course content as tags, thereby enabling rapid classification and retrieval of course content. The application of this technology can not only significantly improve the efficiency of educational resource management but also recommend the most suitable learning content based on learners' interests and learning history, thus enhancing the effectiveness and efficiency of online learning. While online educational resources are abundant, their effective organization and utilization still face many challenges. On the one hand, the sheer volume and diversity of educational resources require efficient technical means for rapid and accurate tag generation and resource retrieval; on the other hand, the complexity of educational content and the diversity of language also place higher demands on the accuracy and adaptability of automatic tag generation systems. Summary of the Invention

[0003] The main objective of this invention is to provide a method and system for generating course tags for online educational resources. By comparing two vectors based on different data sources, tags with the highest possible similarity can be obtained. The higher the similarity, the higher the accuracy of the tags, thereby ensuring the accuracy of the generated tags for educational resources.

[0004] Firstly, a method for generating course tags for online educational resources is provided, the method comprising:

[0005] Tag extraction is performed on the text data of the online educational resources to be generated to obtain a tag set;

[0006] The tags in the tag set are converted into high-dimensional vectors using a preset word vector model, and the first similarity information between the high-dimensional vectors is obtained.

[0007] A binary balanced tree of the high-dimensional vector is constructed using a preset binary K-means clustering algorithm based on the first similarity information;

[0008] Extract keywords from the text data of the course description of the online educational resources to be generated;

[0009] The topic words are converted into topic word vectors, and the second similarity information between the topic word vectors and the high-dimensional vectors is obtained;

[0010] The second similarity information is sorted, and a third similarity information higher than a preset similarity information threshold is obtained from the sorted information using a preset Top-N algorithm. The topic word vector and high-dimensional vector corresponding to the third similarity information are determined as the course tags of the online education resource to be generated.

[0011] In one possible implementation, the first similarity information is expressed by a formula. The similarity is obtained as follows: similarity(u,v) is the first similarity information between high-dimensional vector u and high-dimensional vector v, u·v is the dot product between high-dimensional vector u and high-dimensional vector v, and ||u||·||v|| is the norm between high-dimensional vector u and high-dimensional vector v.

[0012] In another possible implementation, extracting keywords from the text data of the course description of the online educational resource to be generated includes:

[0013] Keywords are extracted from the text data of the course description of the online educational resources to be generated using a preset LDA model.

[0014] In another possible implementation, the Top-N algorithm is the formula u is a high-dimensional vector, t is the average value of the topic word labels, and N is the amount of the third similarity information.

[0015] In another possible implementation, the step of constructing a binary balanced tree of the high-dimensional vector based on the first similarity information using a preset binary K-means clustering algorithm includes:

[0016] The first similarity information is used as input data to the binary K-means clustering algorithm, and the high-dimensional vector is divided into two different categories according to the calculation result of the binary K-means clustering algorithm.

[0017] The high-dimensional vector with the smallest first similarity information with other labels in a single category is obtained as the cluster center word of the category, and the cluster center word is used as the node of the binary balanced tree and the starting point of the next binary K-means clustering.

[0018] Repeat the aforementioned steps until all of the high-dimensional vectors are called nodes of the binary balanced tree.

[0019] In another possible implementation, the step of converting the tags in the tag set into high-dimensional vectors using a preset word vector model and obtaining the first similarity information between the high-dimensional vectors includes:

[0020] The labels are converted into primary high-dimensional vectors using the word2vec model;

[0021] The initial high-dimensional vector is denoised to obtain a denoised high-dimensional vector;

[0022] The word2vec model is trained using the denoised high-dimensional vector to obtain a trained word2vec model;

[0023] The labels are converted into high-dimensional vectors using the trained word2vec model.

[0024] Secondly, a system for generating course tags for online educational resources is provided, the system comprising:

[0025] The tag set acquisition module is used to extract tags from the text data of the online educational resources to be generated and obtain a tag set;

[0026] The first similarity information acquisition module is used to convert the tags in the tag set into high-dimensional vectors through a preset word vector model, and to acquire the first similarity information between the high-dimensional vectors.

[0027] The binary balanced tree construction module is used to construct a binary balanced tree of the high-dimensional vector based on the first similarity information using a preset binary K-means clustering algorithm.

[0028] The keyword extraction module is used to extract keywords from the text data of the course description of the online educational resources to be generated;

[0029] The second similarity information acquisition module is used to convert the topic words into topic word vectors and acquire the second similarity information between the topic word vectors and the high-dimensional vectors;

[0030] The course tag generation module is used to sort the second similarity information, obtain third similarity information that is higher than a preset similarity information threshold from the sorted information using a preset Top-N algorithm, and determine the topic word vector and high-dimensional vector corresponding to the third similarity information as the course tags of the online education resource to be generated.

[0031] In one possible implementation, the first similarity information is expressed by a formula. The similarity is obtained as follows: similarity(u,v) is the first similarity information between high-dimensional vector u and high-dimensional vector v, u·v is the dot product between high-dimensional vector u and high-dimensional vector v, and ||u||·||v|| is the norm between high-dimensional vector u and high-dimensional vector v.

[0032] Thirdly, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for generating course tags for online educational resources as provided in the first aspect.

[0033] Fourthly, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements a method for generating course tags for online educational resources as provided in the first aspect.

[0034] In this application, by comparing two vectors based on different data sources, labels with the highest possible similarity can be obtained. The higher the similarity, the higher the accuracy of the labels, thus ensuring the accuracy of the labels generated for educational resources. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0036] Figure 1 A flowchart illustrating a method for generating course tags for online educational resources according to an embodiment of the present invention;

[0037] Figure 2 A flowchart illustrating a method for generating course tags for online educational resources, as provided in another embodiment of the present invention;

[0038] Figure 3 A flowchart illustrating a method for generating course tags for online educational resources, as provided in another embodiment of the present invention.

[0039] Figure 4 A structural diagram of a course tag generation system for online educational resources provided in one embodiment of the present invention;

[0040] Figure 5 This is a schematic diagram of the process for detecting defects based on dual light, as provided by the present invention.

[0041] Specific implementation method

[0042] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar modules or modules having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting the invention.

[0043] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, modules, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, modules, components, and / or groups thereof. It should be understood that when we say a module is “connected” or “coupled” to another module, it can be directly connected or coupled to the other module, or there may be an intermediate module. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein includes all or any of the modules and all combinations thereof of one or more associated listed items.

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the implementation of this application will be described in further detail below with reference to the accompanying drawings.

[0045] The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0046] like Figure 1 The diagram shows a flowchart of a method for generating course tags for online educational resources according to an embodiment of the present invention. The method includes:

[0047] Step S101: Extract tags from the text data of the online educational resources to be generated and obtain a tag set;

[0048] Step S102: Convert the tags in the tag set into high-dimensional vectors using a preset word vector model, and obtain the first similarity information between the high-dimensional vectors;

[0049] Step S103: Construct a binary balanced tree of the high-dimensional vector based on the first similarity information using a preset binary K-means clustering algorithm;

[0050] Step S104: Extract keywords from the text data of the course description of the online educational resource to be generated;

[0051] Step S105: Convert the topic words into topic word vectors, and obtain the second similarity information between the topic word vectors and the high-dimensional vectors;

[0052] Step S106: Sort the second similarity information, and obtain the third similarity information that is higher than the preset similarity information threshold from the sorted information using a preset Top-N algorithm. Then, determine the topic word vector and high-dimensional vector corresponding to the third similarity information as the course tags of the online education resource to be generated.

[0053] In this embodiment of the invention, tags are first extracted from the text data of the online educational resources to be generated. This step extracts multiple different tags, which are then used to generate a tag set. The tags in the tag set are converted into high-dimensional vectors using a preset word vector model, and the similarity information between these high-dimensional vectors is obtained; this is the first similarity information.

[0054] The first similarity information is used as input data to a preset binary K-means clustering algorithm model. The binary balanced tree of high-dimensional vectors is obtained through the classification of the binary K-means clustering algorithm model.

[0055] Meanwhile, multiple different topic words are obtained from the course descriptions of the educational resources to be generated. The topic words are converted into topic word vectors through a preset word vector model, and the similarity information between the topic word vectors and the high-dimensional vectors is obtained, which is the second similarity information.

[0056] The second similarity information is compared with a preset similarity information threshold. Second similarity information that is higher than the threshold is obtained. The topic word vector and high-dimensional vector corresponding to the second similarity information are obtained and the topic word vector and high-dimensional vector are determined as the course tags of the online education resources to be generated.

[0057] The first similarity information is obtained through the formula The similarity is obtained as follows: similarity(u,v) is the first similarity information between high-dimensional vector u and high-dimensional vector v, u·v is the dot product between high-dimensional vector u and high-dimensional vector v, and ||u||·||v|| is the norm between high-dimensional vector u and high-dimensional vector v.

[0058] The step of extracting keywords from the text data of the course description of the online educational resource to be generated includes:

[0059] Keywords are extracted from the text data of the course description of the online educational resources to be generated using a preset LDA model.

[0060] The Top-N algorithm is defined by the formula... u is a high-dimensional vector, t is the average value of the topic word labels, and N is the amount of the third similarity information.

[0061] In this embodiment of the invention, tags are extracted from the text data of the online educational resources to be generated, obtaining a tag set; the tags in the tag set are converted into high-dimensional vectors using a preset word vector model, and first similarity information between the high-dimensional vectors is obtained; a binary balanced tree of the high-dimensional vectors is constructed based on the first similarity information using a preset binary K-means clustering algorithm; topic words are extracted from the text data of the course description of the online educational resources to be generated; the topic words are converted into topic word vectors, and second similarity information between the topic word vectors and the high-dimensional vectors is obtained; the second similarity information is sorted, and a third similarity information higher than a preset similarity information threshold is obtained from the sorted list using a preset Top-N algorithm; the topic word vectors and high-dimensional vectors corresponding to the third similarity information are determined as the course tags of the online educational resources to be generated. By comparing two vectors based on different data sources, tags with the highest possible similarity can be obtained. The higher the similarity, the higher the accuracy of the tags, thus ensuring the accuracy of the generated tags for the educational resources.

[0062] like Figure 2 The diagram shows a flowchart of a method for generating course tags for online educational resources according to another embodiment of the present invention. The step of constructing a binary balanced tree of the high-dimensional vector based on the first similarity information using a preset binary K-means clustering algorithm includes:

[0063] Step S201: Using the first similarity information as input data, input the binary K-means clustering algorithm, and divide the high-dimensional vector into two different categories according to the calculation result of the binary K-means clustering algorithm;

[0064] Step S202: Obtain the high-dimensional vector with the smallest first similarity information with other labels in a single category as the cluster center word of the category, and use the cluster center word as the node of the binary balanced tree and the starting point of the next binary K-means clustering.

[0065] Step S203: Repeat steps S201-S202 until all the high-dimensional vectors are called nodes of the binary balanced tree.

[0066] like Figure 3 The diagram illustrates another embodiment of the present invention, a method for generating course tags for online educational resources. The method involves converting tags from the tag set into high-dimensional vectors using a preset word vector model and obtaining first similarity information between the high-dimensional vectors, including:

[0067] Step S301: Convert the labels into primary high-dimensional vectors using the word2vec model;

[0068] Step S302: Denoise the initial high-dimensional vector to obtain a denoised high-dimensional vector;

[0069] Step S303: Train the word2vec model using the denoised high-dimensional vector to obtain the trained word2vec model;

[0070] Step S304: Convert the label into the high-dimensional vector using the trained word2vec model.

[0071] like Figure 4 The diagram shown is a structural diagram of a course tag generation system for online educational resources according to an embodiment of the present invention. The generation system includes:

[0072] The tag set acquisition module 401 is used to extract tags from the text data of the online education resources to be generated and acquire a tag set.

[0073] The first similarity information acquisition module 402 is used to convert the tags in the tag set into high-dimensional vectors through a preset word vector model, and to acquire the first similarity information between the high-dimensional vectors.

[0074] Binary balanced tree construction module 403 is used to construct a binary balanced tree of the high-dimensional vector based on the first similarity information using a preset binary K-means clustering algorithm;

[0075] The keyword extraction module 404 is used to extract keywords from the text data of the course description of the online educational resource to be generated;

[0076] The second similarity information acquisition module 405 is used to convert the topic words into topic word vectors and acquire the second similarity information between the topic word vectors and the high-dimensional vectors;

[0077] The course tag generation module 406 is used to sort the second similarity information, obtain third similarity information that is higher than the preset similarity information threshold from the sorted information using a preset Top-N algorithm, and determine the topic word vector and high-dimensional vector corresponding to the third similarity information as the course tags of the online education resource to be generated.

[0078] In this embodiment of the invention, tags are first extracted from the text data of the online educational resources to be generated. This step extracts multiple different tags, which are then used to generate a tag set. The tags in the tag set are converted into high-dimensional vectors using a preset word vector model, and the similarity information between these high-dimensional vectors is obtained; this is the first similarity information.

[0079] The first similarity information is used as input data to a preset binary K-means clustering algorithm model. The binary balanced tree of high-dimensional vectors is obtained through the classification of the binary K-means clustering algorithm model.

[0080] Meanwhile, multiple different topic words are obtained from the course descriptions of the educational resources to be generated. The topic words are converted into topic word vectors through a preset word vector model, and the similarity information between the topic word vectors and the high-dimensional vectors is obtained, which is the second similarity information.

[0081] The second similarity information is compared with a preset similarity information threshold. Second similarity information that is higher than the threshold is obtained. The topic word vector and high-dimensional vector corresponding to the second similarity information are obtained and the topic word vector and high-dimensional vector are determined as the course tags of the online education resources to be generated.

[0082] The first similarity information is obtained through the formula The similarity is obtained as follows: similarity(u,v) is the first similarity information between high-dimensional vector u and high-dimensional vector v, u·v is the dot product between high-dimensional vector u and high-dimensional vector v, and ||u||·||v|| is the norm between high-dimensional vector u and high-dimensional vector v.

[0083] The step of extracting keywords from the text data of the course description of the online educational resource to be generated includes:

[0084] Keywords are extracted from the text data of the course description of the online educational resources to be generated using a preset LDA model.

[0085] The Top-N algorithm is defined by the formula... u is a high-dimensional vector, t is the average value of the topic word labels, and N is the amount of the third similarity information.

[0086] In this embodiment of the invention, tags are extracted from the text data of the online educational resources to be generated, obtaining a tag set; the tags in the tag set are converted into high-dimensional vectors using a preset word vector model, and first similarity information between the high-dimensional vectors is obtained; a binary balanced tree of the high-dimensional vectors is constructed based on the first similarity information using a preset binary K-means clustering algorithm; topic words are extracted from the text data of the course description of the online educational resources to be generated; the topic words are converted into topic word vectors, and second similarity information between the topic word vectors and the high-dimensional vectors is obtained; the second similarity information is sorted, and a third similarity information higher than a preset similarity information threshold is obtained from the sorted data using a preset Top-N algorithm; the topic word vectors and high-dimensional vectors corresponding to the third similarity information are determined as the course tags of the online educational resources to be generated. By comparing two vectors based on different data sources, tags with the highest possible similarity can be obtained. The higher the similarity, the higher the accuracy of the tags, thus ensuring the accuracy of the generated tags for the educational resources.

[0087] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include: a processor 501, a communication interface 502, a memory 503, and a communication bus 504, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor can invoke logical instructions in memory to execute a method for generating course tags for online educational resources. This method includes: extracting tags from the text data of the online educational resources to be generated, obtaining a tag set; converting the tags in the tag set into high-dimensional vectors using a preset word vector model, and obtaining first similarity information between the high-dimensional vectors; constructing a binary balanced tree of the high-dimensional vectors based on the first similarity information using a preset binary K-means clustering algorithm; extracting topic words from the text data of the course description of the online educational resources to be generated; converting the topic words into topic word vectors, and obtaining second similarity information between the topic word vectors and the high-dimensional vectors; sorting the second similarity information, and obtaining third similarity information higher than a preset similarity information threshold from the sorted data using a preset Top-N algorithm; and determining the topic word vectors and high-dimensional vectors corresponding to the third similarity information as the course tags for the online educational resources to be generated.

[0088] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0089] On the other hand, embodiments of the present invention also provide a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer is able to execute the method for generating course tags for online educational resources provided in the above-described method embodiments, the method including: extracting tags from text data of online educational resources to be generated, obtaining a tag set; converting the tags in the tag set into high-dimensional vectors through a preset word vector model, and obtaining first similarity information between the high-dimensional vectors; constructing a binary balanced tree of the high-dimensional vectors based on the first similarity information using a preset binary K-means clustering algorithm; extracting topic words from the text data of the course description of the online educational resources to be generated; converting the topic words into topic word vectors, and obtaining second similarity information between the topic word vectors and the high-dimensional vectors; sorting the second similarity information, obtaining third similarity information higher than a preset similarity information threshold from the sorted data using a preset Top-N algorithm, and determining the topic word vectors and high-dimensional vectors corresponding to the third similarity information as course tags for the online educational resources to be generated.

[0090] In another aspect, embodiments of the present invention also provide a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a method for generating course tags for online educational resources provided in the above embodiments. The method includes: extracting tags from text data of the online educational resources to be generated to obtain a tag set; converting the tags in the tag set into high-dimensional vectors using a preset word vector model, and obtaining first similarity information between the high-dimensional vectors; constructing a binary balanced tree of the high-dimensional vectors based on the first similarity information using a preset binary K-means clustering algorithm; extracting topic words from the text data of the course description of the online educational resources to be generated; converting the topic words into topic word vectors, and obtaining second similarity information between the topic word vectors and the high-dimensional vectors; sorting the second similarity information, obtaining third similarity information higher than a preset similarity information threshold from the sorted data using a preset Top-N algorithm, and determining the topic word vectors and high-dimensional vectors corresponding to the third similarity information as course tags for the online educational resources to be generated.

[0091] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0092] The above description is only a partial implementation of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for generating course tags for online educational resources, characterized in that, The generation method includes: Tag extraction is performed on the text data of the online educational resources to be generated to obtain a tag set; The tags in the tag set are converted into high-dimensional vectors using a preset word vector model, and the first similarity information between the high-dimensional vectors is obtained. A binary balanced tree of the high-dimensional vector is constructed using a preset binary K-means clustering algorithm based on the first similarity information. Extract keywords from the text data of the course description of the online educational resources to be generated; The topic words are converted into topic word vectors, and the second similarity information between the topic word vectors and the high-dimensional vectors is obtained; The second similarity information is sorted, and a third similarity information higher than a preset similarity information threshold is obtained from the sorted information using a preset Top-N algorithm. The topic word vector and high-dimensional vector corresponding to the third similarity information are determined as the course tags of the online education resource to be generated.

2. The generation method as described in claim 1, characterized in that, The first similarity information is obtained through the formula The similarity is obtained as follows: similarity(u,v) is the first similarity information between high-dimensional vector u and high-dimensional vector v, u·v is the dot product between high-dimensional vector u and high-dimensional vector v, and ||u||·||v|| is the norm between high-dimensional vector u and high-dimensional vector v.

3. The generation method as described in claim 1, characterized in that, The extraction of keywords from the text data of the course description of the online educational resource to be generated includes: Keywords are extracted from the text data of the course description of the online educational resources to be generated using a preset LDA model.

4. The generation method as described in claim 1, characterized in that, The Top-N algorithm is the formula. u is a high-dimensional vector, t is the average value of the topic word labels, and N is the amount of the third similarity information.

5. The generation method as described in claim 1, characterized in that, The step of constructing a binary balanced tree of the high-dimensional vector based on the first similarity information using a preset binary K-means clustering algorithm includes: The first similarity information is used as input data to the binary K-means clustering algorithm, and the high-dimensional vector is divided into two different categories according to the calculation result of the binary K-means clustering algorithm. The high-dimensional vector with the smallest first similarity information with other labels in a single category is obtained as the cluster center word of the category, and the cluster center word is used as the node of the binary balanced tree and the starting point of the next binary K-means clustering. Repeat the aforementioned steps until all of the high-dimensional vectors are called nodes of the binary balanced tree.

6. The generation method as described in claim 1, characterized in that, The step of converting the tags in the tag set into high-dimensional vectors using a preset word vector model and obtaining the first similarity information between the high-dimensional vectors includes: The labels are converted into primary high-dimensional vectors using the word2vec model; The initial high-dimensional vector is denoised to obtain a denoised high-dimensional vector; The word2vec model is trained using the denoised high-dimensional vector to obtain a trained word2vec model; The labels are converted into high-dimensional vectors using the trained word2vec model.

7. A system for generating course tags for online educational resources, characterized in that, The generation system includes: The tag set acquisition module is used to extract tags from the text data of the online educational resources to be generated and obtain a tag set; The first similarity information acquisition module is used to convert the tags in the tag set into high-dimensional vectors through a preset word vector model, and to acquire the first similarity information between the high-dimensional vectors. The binary balanced tree construction module is used to construct a binary balanced tree of the high-dimensional vector based on the first similarity information using a preset binary K-means clustering algorithm. The keyword extraction module is used to extract keywords from the text data of the course description of the online educational resources to be generated; The second similarity information acquisition module is used to convert the topic words into topic word vectors and acquire the second similarity information between the topic word vectors and the high-dimensional vectors; The course tag generation module is used to sort the second similarity information, obtain third similarity information that is higher than a preset similarity information threshold from the sorted information using a preset Top-N algorithm, and determine the topic word vector and high-dimensional vector corresponding to the third similarity information as the course tags of the online education resource to be generated.

8. The generation system as described in claim 7, characterized in that, The first similarity information is obtained through the formula The similarity is obtained as follows: similarity(u,v) is the first similarity information between high-dimensional vector u and high-dimensional vector v, u·v is the dot product between high-dimensional vector u and high-dimensional vector v, and ||u||·||v|| is the norm between high-dimensional vector u and high-dimensional vector v.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for generating course tags for online educational resources as described in any one of claims 1-6.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method for generating course tags for online educational resources as described in any one of claims 1-6.

Images