Method for constructing course ideological and political material library

Abstract

The invention discloses a method for constructing a course ideological and political material library, and the method comprises the steps: obtaining data related to course ideological and political, and carrying out the preprocessing of the data, and obtaining a data set; performing entity extraction on the unlabeled data by using the fine-tuned UIE model, and identifying and extracting knowledge points and ideological and political elements in the unlabeled data; the extracted triple information is stored in a graph database Neo4j, knowledge points and ideological and political elements are associated through relation edges, and a course ideological and political knowledge graph is formed; displaying a course ideological and political material library on the basis of the course ideological and political knowledge graph, checking the association between knowledge points and ideological and political elements, and performing detailed display of specific cases; and providing extended case resources related to the knowledge points and the ideological and political elements according to a preset intelligent retrieval system. According to the invention, the problem of insufficient fusion degree of professional knowledge and ideological and political education can be effectively solved, and systematicness and effectiveness of course ideological and political construction are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of educational resource integration, and specifically relates to a method for constructing a curriculum ideological and political material library. Background Art

[0002] The Guiding Outline for the Construction of Ideological and Political Courses in Higher Education Institutions clearly states that ideological and political education should be integrated into the entire talent training system of higher education and play its role in educating people in every course. In order to ensure the effective integration of professional courses and ideological and political elements, teachers not only need to have a deep understanding of professional knowledge points, but also need to skillfully integrate ideological and political education content into professional teaching content to achieve seamless connection between the two. However, in current educational practice, we find that there are some challenges: on the one hand, a systematic and structured ideological and political course material library has not yet been established to support the realization of this goal; on the other hand, there is a lack of an efficient technical solution to accurately extract and establish the correspondence between course knowledge points and ideological and political elements.

[0003] Therefore, there is an urgent need to develop and apply an innovative technical method that can effectively integrate ideological and political resources from different disciplines, and at the same time has strong data analysis capabilities to accurately identify and match course knowledge points with corresponding ideological and political elements. This method should also support dynamic updates to adapt to changing social values ​​and educational needs. Through such technological innovation, not only can teachers' teaching effectiveness be improved, but students' acceptance and recognition of ideological and political education can also be enhanced, ultimately achieving the goal of comprehensively improving the quality of talent training. Summary of the invention

[0004] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art and provide a method for constructing a course ideological and political material library. Through the present invention, an efficient, flexible and expandable course ideological and political material library can be constructed for teachers to naturally integrate ideological and political elements into the teaching process, thereby realizing the deep integration of professional knowledge and ideological and political education.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In the first aspect, the present invention proposes a method for constructing a course ideological and political material library, comprising the following steps:

[0007] Acquire data related to ideological and political education in courses, and preprocess the data to obtain a data set;

[0008] Constructing the course ideological and political knowledge graph, specifically: constructing the ontology structure of the course ideological and political field based on domain knowledge, the ontology structure is based on the course knowledge points, ideological and political elements and their mutual relationships as a structured framework; using text annotation tools to manually annotate part of the data in the data set, the annotation content includes course knowledge points and ideological and political elements, and then based on the annotated data, using the fine-tuned UIE model to perform entity extraction on the unlabeled data, identify and extract knowledge points and ideological and political elements in the unlabeled data; storing the extracted triple information in the graph database Neo4j, and associating knowledge points and ideological and political elements through relationship edges to form a course ideological and political knowledge graph; the UIE model uses a pre-trained Transformer model to encode the input text, convert the input text into a context-related embedding representation, and extract the required information by generating a target sequence;

[0009] Based on the course ideological and political knowledge map, the course ideological and political material library is displayed. Users can intuitively view the relationship between knowledge points and ideological and political elements, as well as the detailed display of specific cases through a graphical interface;

[0010] According to the preset intelligent retrieval system, users query by entering specific knowledge points, and the system returns relevant graph nodes and their associated information. It also provides extended case resources related to knowledge points and ideological and political elements by integrating external search engines.

[0011] As a preferred technical solution, the data related to ideological and political education in the course is obtained, and the data is preprocessed to obtain a data set, specifically:

[0012] Obtain data related to ideological and political education in courses from multiple channels, including at least literature, web pages, and public accounts;

[0013] Clean the acquired data to remove redundant and invalid information;

[0014] The data is formatted and unified into a structured format to obtain a data set.

[0015] As a preferred technical solution, the ontology structure of the course ideological and political field is constructed, including:

[0016] Define entities: including knowledge points, ideological and political elements, and case descriptions;

[0017] Define the relationship between entities: the relationship between knowledge points, ideological and political elements and case descriptions is belonging to; the relationship between knowledge points and ideological and political elements is association.

[0018] As a preferred technical solution, the fine-tuned UIE model is used to extract entities from unlabeled data, specifically:

[0019] The input text sequence is The structure model SSI is First, the UIE model will Input to Encoder to get the hidden layer representation of each token as Then use the pre-trained Transformer model to get the output, which is expressed as follows: in,

[0020]

[0021] Next, in the nth step of decoding, the hidden layer is used to represent the y in the nth token in the Decoder to generate the SEL sequence. n and decoder status It is expressed as follows:

[0022] As an optimal technical solution, the knowledge graph construction is to store the entities extracted from the data set into the graph database Neo4j. The data stored in the graph database includes entities and relationships between entities. The entities include: knowledge points, ideological and political elements, and case descriptions. The relationships include: the relationship between knowledge points, ideological and political elements and case descriptions is belonging, and the relationship between knowledge points and ideological and political elements is associated.

[0023] As an optimal technical solution, the course ideological and political material library can display the knowledge graph view, local node view and specific cases.

[0024] As a preferred technical solution, the intelligent retrieval system is specifically:

[0025] The intelligent retrieval system design is a retrieval system developed by implementing the front end with vue3 and the back end with python. The system includes realizing the query of knowledge points in the search box. The query of knowledge points will call the graph database Neo4j, and display the nodes and relationships of the knowledge points in the retrieval system. Click any node in the knowledge graph display area, the system will call the Bing search engine to search for the node and display the search results in the pop-up window on the right. The pop-up window supports secondary search, thereby helping users find suitable ideological and political resources.

[0026] In a second aspect, the present invention provides a system for constructing a course ideological and political material library, which applies the method for constructing a course ideological and political material library, including a data acquisition module, a knowledge graph construction module, a visualization module, and an intelligent retrieval module;

[0027] The data acquisition module is used to acquire data related to ideological and political education in the course, and preprocess the data to obtain a data set;

[0028] The knowledge graph construction module is used to construct a course ideological and political knowledge graph, specifically: construct an ontology structure of the course ideological and political field based on domain knowledge, and the ontology structure is a structured framework based on course knowledge points, ideological and political elements and their mutual relationships; use a text annotation tool to manually annotate part of the data in the data set, and the annotation content includes course knowledge points and ideological and political elements, and then based on the annotated data, use the fine-tuned UIE model to perform entity extraction on the unlabeled data, identify and extract knowledge points and ideological and political elements in the unlabeled data; store the extracted triple information in the graph database Neo4j, associate knowledge points and ideological and political elements through relationship edges, and form a course ideological and political knowledge graph; the UIE model uses a pre-trained Transformer model to encode the input text, convert the input text into a context-related embedding representation, and extract the required information by generating a target sequence;

[0029] The visualization module is used to display the course ideological and political material library based on the course ideological and political knowledge map. Users can intuitively view the relationship between knowledge points and ideological and political elements, as well as the detailed display of specific cases through a graphical interface;

[0030] The intelligent retrieval module is used to query according to the preset intelligent retrieval system. Users enter specific knowledge points, and the system returns relevant graph nodes and their associated information. It also provides extended case resources related to knowledge points and ideological and political elements by integrating external search engines.

[0031] In a third aspect, the present invention provides an electronic device, the electronic device comprising:

[0032] at least one processor; and,

[0033] a memory communicatively connected to the at least one processor; wherein,

[0034] The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the method for constructing a course ideological and political material library.

[0035] In a fourth aspect, the present invention provides a computer-readable storage medium storing a program, which, when executed by a processor, implements the method of constructing a course ideological and political material library.

[0036] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0037] The method for constructing a course ideological and political material library of the present invention innovatively solves the problems of the lack of existing course ideological and political resources and the insufficient integration of professional education and ideological and political education, and greatly improves the construction speed through the UIE deep learning model, reducing manpower and material resources. By constructing a course ideological and political material library, teachers can quickly query the relationship between course content and ideological and political elements, and flexibly integrate ideological and political education into classroom teaching.

[0038] The present invention also designs an intelligent retrieval system to support teachers to quickly obtain relevant ideological and political materials during teaching design and teaching, and further improve the implementation effect of ideological and political education in courses. The method has high scalability and is suitable for the ideological and political construction of various disciplines and professional courses, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 The present invention is a flowchart of a method for constructing a course ideological and political material library according to an embodiment of the present invention.

[0041] Figure 2 This is a working example diagram of the UIE model in an embodiment of the present invention.

[0042] Figure 3 Schematic diagram of displaying the course ideological and political material library in an embodiment of the present invention.

[0043] Figure 4 The figure is a schematic diagram showing a retrieval system in an embodiment of the present invention.

[0044] Figure 5 A system block diagram for constructing a course ideological and political material library for an embodiment of the present invention.

[0045] Figure 6 4 is a structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0047] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0048] See also Figure 1 In this embodiment, a method for constructing a professional course ideological and political knowledge graph is provided, including the following steps:

[0049] S1. Obtain data related to ideological and political education in courses from multiple data sources.

[0050] Furthermore, data acquisition includes collecting text content related to course knowledge points and ideological and political elements from academic literature, educational websites, public account tweets and other channels. These data may contain a lot of noise information, so they need to be preprocessed. The preprocessing steps include data cleaning, deduplication, standardization and format conversion to ensure the quality of data for subsequent processing.

[0051] S2. After data preprocessing, the ontology structure of the ideological and political education field of the course is constructed based on the acquired domain knowledge. Ontology construction can provide a structured framework for the knowledge graph and clarify the relationship between knowledge points and ideological and political elements. Ontology construction includes defining the core knowledge points, ideological and political elements and their attributes in the course, and clarifying the relationship between them to form a logically clear knowledge system.

[0052] Furthermore, the ontology structure of the field of ideological and political education in courses includes:

[0053] Define entities: including knowledge points, ideological and political elements, and case descriptions;

[0054] Define the relationship between entities: the relationship between knowledge points, ideological and political elements and case descriptions is belonging to; the relationship between knowledge points and ideological and political elements is association.

[0055] S3. After the ontology is constructed, the knowledge points and ideological and political elements are identified by combining manual annotation and automatic entity extraction technology. First, use the Doccano text annotation tool to manually annotate some of the data to determine the key knowledge points and ideological and political elements. Next, based on these annotated data, train and use the UIE (Unified Information Extraction) model to automatically extract entities from unlabeled data. The UIE model is a general information extraction framework proposed in 2022. Based on this framework, PaddleNLP combines ERNIE 3.0 to enhance knowledge learning capabilities and achieve efficient extraction in zero-sample and few-sample scenarios. It significantly reduces dependence on labeled data, thereby reducing manual annotation costs. The core of the UIE model's work is to transform the traditional multi-task information extraction problem into a sequence generation problem, using a unified framework to solve a variety of information extraction tasks. The model uses a specific prompt or task description to guide the model to generate a target sequence, thereby completing a specific extraction task. Examples of UIE model work are as follows: Figure 2 Specifically, the input text sequence is The structure model SSI is First, the UIE model will Input to Encoder to get the hidden layer representation of each token as Then use the pre-trained Transformer model to get the output, which is expressed as follows:

[0056] in,

[0057]

[0058] Next, in the nth step of decoding, the hidden layer is used to represent the y in the nth token in the Decoder to generate the SEL sequence. n and decoder status It is expressed as follows:

[0059] The UIE model can effectively identify relevant entities in unlabeled data through a small amount of labeled data, reducing the workload of manual labeling while also improving the efficiency and accuracy of entity extraction.

[0060] S4. Store the extracted knowledge points and ideological and political elements and their associations in a graph database. Graph databases can efficiently manage and store complex knowledge networks and support query, update, and expansion of knowledge graphs. Graph databases use a node- and edge-based storage structure to efficiently manage and query complex knowledge networks. Knowledge storage includes entity nodes (e.g., knowledge points and ideological and political elements) and their interrelated relationships.

[0061] Furthermore, the knowledge graph construction is to store the entities extracted from the data set into the graph database Neo4j. The data stored in the graph database includes entities and relationships between entities. The entities include: knowledge points, ideological and political elements, and case descriptions. The relationships include: the relationship between knowledge points, ideological and political elements and case descriptions is belonging, and the relationship between knowledge points and ideological and political elements is associated.

[0062] S5. Based on the constructed knowledge graph, the course ideological and political material library is displayed. Through the graphical interface, users can intuitively view the relationship between knowledge points and ideological and political elements, as well as the detailed display of specific cases. Multi-level visualization helps users better understand the relationship between nodes and provides strong support for teaching design.

[0063] Furthermore, the system provides multi-level visual displays to help teachers intuitively understand the relationship between various knowledge points and ideological and political elements, and enhance the operability and flexibility of ideological and political elements in the teaching process.

[0064] S6. Based on the construction and visualization of the knowledge graph, an intelligent retrieval system is designed. Users can query by entering specific knowledge points, and the system will return relevant graph nodes and their associated information. In addition, the system supports searching for additional material resources by integrating external search engines to expand the application scenarios of curriculum ideological and political education and help teachers flexibly use curriculum ideological and political education resources in course design and teaching.

[0065] Furthermore, the retrieval system design is a retrieval system developed by implementing the front end with vue3 and the back end with python. The system includes realizing the query of knowledge points in the search box. The query of knowledge points will call the graph database Neo4j, and display the nodes and relationships of the knowledge points in the retrieval system. Click any node in the knowledge graph display area, the system will call the Bing search engine to search for the node and display the search results in the pop-up window on the right. The pop-up window supports secondary search, thereby helping users find suitable ideological and political resources.

[0066] In order to better illustrate the scheme and effect of the present invention, the present invention provides another more specific embodiment, comprising the following steps:

[0067] Step 1: Data acquisition and preprocessing. Search "data structure + course ideological and political education" as the subject search terms in CNKI, the national college course ideological and political education teaching resource service platform, and the public ideological and political education platforms of various colleges and universities, and collect the course ideological and political education texts related to the course in the results. The data preprocessing steps include data cleaning, deduplication, standardization, and format conversion. To ensure the scientificity and reliability of the data, this paper uses the academic papers published by college teachers included in "CNKI" as the data source, and searches with "data structure" and "course ideological and political education" as the subject words to screen out articles containing sentences related to knowledge points and ideological and political elements, and obtains a total of 472 valid sentences. However, considering that relying solely on CNKI data may lead to insufficient data volume, this paper further expands the data source by searching for keywords such as "course ideological and political education in data structure" on Baidu. To ensure the practicality and representativeness of the data, this paper screens out relevant content published on the official website of colleges and universities and the national college course ideological and political education teaching resource service platform from the search results, and finally supplements 99 valid sentences, totaling 571 sentences and 51,833 characters. The data example is "Introducing artificial intelligence applications such as express sorting systems in graph traversal to establish a scientific spirit and professional identity."

[0068] Step 2: Ontology construction. For the course "Data Structure", determine the ontology for the ideological and political knowledge graph of the course. An example is shown in Table 1.

[0069] Table 1

[0070]

[0071] Step 3: Manual labeling and automatic entity extraction. The Doccano text labeling tool was used to manually label 300 data items, and finally 1238 entities were labeled. The specific distribution of each entity is shown in Table 2. Then, the 300 data items were divided into training set, validation set and test set according to 8:1:1, and the UIE model was trained. The trained UIE model was used to extract entities from the remaining unlabeled data in the data set. Therefore, the introduction of the UIE model for entity extraction can automatically extract key entities with less labeled data, which not only effectively reduces the cost of data labeling, but also helps to build a structured and rich knowledge graph, thereby providing support for the in-depth implementation of ideological and political education in courses.

[0072] Table 2

[0073]

[0074] Step 4: Build the knowledge graph and store the entities and relationships between them into the graph database Neo4j, resulting in a knowledge graph with 1,795 nodes and 1,784 relationships in total.

[0075] Step 5: Display the course ideological and political material library. Use the following Cypher statement to query nodes in the graph database Neo4j: MATCH(k: knowledge point {name: "string"})

[0076] OPTIONAL MATCH(k)-[:Relationship]-(p:Ideological and political elements)

[0077] OPTIONAL MATCH(k)-[:`Knowledge point_belongs to`]-(c:Case)

[0078] RETURN k,p,c

[0079] See also Figure 3 , Figure 3 The material display returned by the query "string" node is centered on the queried knowledge point, and the specific case description is shown in Table 3. When querying a certain knowledge point in the graph database, the system will display the ideological and political elements associated with the knowledge point, and simultaneously display the corresponding specific case description. Taking the "string" knowledge point in the figure as an example, after retrieving the knowledge point, the system displays the following related content: "Design a nucleic acid detection program to determine whether the virus is infected by comparing whether the viral nucleic acid DNA appears in the human DNA string, and stimulate students to use professional knowledge to solve practical problems." In addition, the system also displays another case: "When explaining the string, take poetry as an example", by showing the unique style and charm of Chinese language and characters. In this way, teachers can combine knowledge points with rich ideological and political elements when teaching, which not only makes the teaching content more vivid, but also effectively integrates ideological and political education while imparting knowledge, achieving the effect of educating people silently.

[0080] Table 3

[0081]

[0082] Step 6: Retrieval system design, use vue3 on the front end and python on the back end to build a retrieval system for the material library, please refer to Figure 4 When the user enters the knowledge point (graph) to be searched in the search box of the retrieval system, the nodes related to the knowledge point stored in the graph database Neo4j will be returned to the knowledge graph display area. In the displayed knowledge graph, ideological and political elements and specific case descriptions will be displayed. When the user is interested in any of the nodes, click on the node, and the Bing search engine will be called on the right to search for the node. Secondary search is also supported in this window. Figure 4, when the user inputs a knowledge point of "graph", the graph display area on the left will first return the entity nodes related to the knowledge point in the graph database. At this time, the user clicks the "craftsman spirit" node, and the Bing search module on the right will return the material content related to "craftsman spirit". The user can select the material content of interest in this interface and click to view it. At the same time, a secondary search can be performed in the Bing search box, which is convenient for users to quickly find the required materials. The retrieval system provides users with more optional resources, improves the flexibility and richness of integrating ideological and political elements into teaching, and helps to achieve more attractive ideological and political education.

[0083] It should be noted that, for the sake of convenience, the aforementioned method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited to the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously.

[0084] Based on the same idea as the method for constructing a course ideological and political material library in the above embodiment, the present invention also provides a system for constructing a course ideological and political material library, which can be used to execute the above method for constructing a course ideological and political material library. For ease of explanation, in the structural schematic diagram of an embodiment of a system for constructing a course ideological and political material library, only the parts related to the embodiment of the present invention are shown. Those skilled in the art can understand that the illustrated structure does not constitute a limitation on the device, and may include more or fewer components than shown in the diagram, or combine certain components, or arrange the components differently.

[0085] See also Figure 5 In another embodiment of the present application, a system 100 for constructing a course ideological and political material library is provided, the system comprising a data acquisition module 101, a knowledge graph construction module 102, a visualization module 103 and an intelligent retrieval module 104;

[0086] The data acquisition module 101 is used to acquire data related to ideological and political education in courses and pre-process the data to obtain a data set;

[0087] The knowledge graph construction module 102 is used to construct a course ideological and political knowledge graph, specifically: construct an ontology structure of the course ideological and political field based on domain knowledge, the ontology structure is a structured framework based on course knowledge points, ideological and political elements and their mutual relationships; use a text annotation tool to manually annotate part of the data in the data set, the annotation content includes course knowledge points and ideological and political elements, and then based on the annotated data, use the fine-tuned UIE model to perform entity extraction on the unlabeled data, identify and extract knowledge points and ideological and political elements in the unlabeled data; store the extracted triple information in the graph database Neo4j, associate knowledge points and ideological and political elements through relationship edges, and form a course ideological and political knowledge graph; the UIE model uses a pre-trained Transformer model to encode the input text, convert the input text into a context-related embedding representation, and extract the required information by generating a target sequence;

[0088] The visualization module 103 is used to display the course ideological and political material library based on the course ideological and political knowledge map, so that users can intuitively view the relationship between knowledge points and ideological and political elements, as well as the detailed display of specific cases through a graphical interface;

[0089] The intelligent retrieval module 104 is used to query by users by inputting specific knowledge points according to a preset intelligent retrieval system. The system returns relevant graph nodes and their associated information, and provides extended case resources related to knowledge points and ideological and political elements by integrating external search engines.

[0090] It should be noted that a system for constructing a course ideological and political material library of the present invention corresponds one to one with a method for constructing a course ideological and political material library of the present invention. The technical features and beneficial effects described in the embodiment of the method for constructing a course ideological and political material library are applicable to an embodiment of a system for constructing a course ideological and political material library. For specific contents, please refer to the description in the embodiment of the method of the present invention. No further details will be given here. This is hereby declared.

[0091] In addition, in the implementation of a system for constructing a course ideological and political material library in the above-mentioned embodiment, the logical division of each program module is only an example. In actual applications, the above-mentioned functions can be assigned to different program modules as needed, for example, for the convenience of corresponding hardware configuration requirements or software implementation. That is, the internal structure of the system for constructing a course ideological and political material library is divided into different program modules to complete all or part of the functions described above.

[0092] See also Figure 6In one embodiment, an electronic device for implementing a method for constructing a course ideological and political material library is provided. The electronic device 200 may include a first processor 201, a first memory 202 and a bus, and may also include a computer program stored in the first memory 202 and executable on the first processor 201, such as a program 203 for constructing a course ideological and political material library.

[0093] Among them, the first memory 202 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the first memory 202 can be an internal storage unit of the electronic device 200, such as a mobile hard disk of the electronic device 200. In other embodiments, the first memory 202 can also be an external storage device of the electronic device 200, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 200. Further, the first memory 202 can also include both an internal storage unit of the electronic device 200 and an external storage device. The first memory 202 can not only be used to store application software and various types of data installed in the electronic device 200, such as a code of a program 203 for building a course ideological and political material library, but also can be used to temporarily store data that has been output or is to be output.

[0094] In some embodiments, the first processor 201 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The first processor 201 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions and processes data of the electronic device 200 by running or executing programs or modules stored in the first memory 202, and calling data stored in the first memory 202.

[0095] Figure 6 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the electronic device 200 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0096] The program 203 for constructing a course ideological and political material library stored in the first memory 202 of the electronic device 200 is a combination of multiple instructions. When running in the first processor 201, it can achieve:

[0097] Acquire data related to ideological and political education in courses, and preprocess the data to obtain a data set;

[0098] Constructing the course ideological and political knowledge graph, specifically: constructing the ontology structure of the course ideological and political field based on domain knowledge, the ontology structure is based on the course knowledge points, ideological and political elements and their mutual relationships as a structured framework; using text annotation tools to manually annotate part of the data in the data set, the annotation content includes course knowledge points and ideological and political elements, and then based on the annotated data, using the fine-tuned UIE model to perform entity extraction on the unlabeled data, identify and extract knowledge points and ideological and political elements in the unlabeled data; storing the extracted triple information in the graph database Neo4j, and associating knowledge points and ideological and political elements through relationship edges to form a course ideological and political knowledge graph; the UIE model uses a pre-trained Transformer model to encode the input text, convert the input text into a context-related embedding representation, and extract the required information by generating a target sequence;

[0099] Based on the course ideological and political knowledge map, the course ideological and political material library is displayed. Users can intuitively view the relationship between knowledge points and ideological and political elements, as well as the detailed display of specific cases through a graphical interface;

[0100] According to the preset intelligent retrieval system, users query by entering specific knowledge points, and the system returns relevant graph nodes and their associated information. It also provides extended case resources related to knowledge points and ideological and political elements by integrating external search engines.

[0101] Furthermore, if the module / unit integrated in the electronic device 200 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0102] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0103] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0104] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

Claims

1. A method for constructing a curriculum ideological and political material library, characterized in that: The steps include: Acquire data related to ideological and political education in courses, and preprocess the data to obtain a data set; Constructing the course ideological and political knowledge graph, specifically: constructing the ontology structure of the course ideological and political field based on domain knowledge, the ontology structure is based on the course knowledge points, ideological and political elements and their mutual relationships as a structured framework; using text annotation tools to manually annotate part of the data in the data set, the annotation content includes course knowledge points and ideological and political elements, and then based on the annotated data, using the fine-tuned UIE model to perform entity extraction on the unlabeled data, identify and extract the knowledge points and ideological and political elements in the unlabeled data; The extracted triple information is stored in the graph database Neo4j, and the knowledge points and ideological and political elements are associated through relationship edges to form a course ideological and political knowledge graph; the UIE model uses a pre-trained Transformer model to encode the input text, convert the input text into a context-related embedding representation, and extract the required information by generating a target sequence; Based on the course ideological and political knowledge map, the course ideological and political material library is displayed. Users can intuitively view the relationship between knowledge points and ideological and political elements, as well as the detailed display of specific cases through a graphical interface; According to the preset intelligent retrieval system, users query by entering specific knowledge points, and the system returns relevant graph nodes and their associated information. It also provides extended case resources related to knowledge points and ideological and political elements by integrating external search engines.

2. A method for constructing a course ideological and political material library according to claim 1, characterized in that: The data related to the ideological and political education of the course is obtained, and the data is preprocessed to obtain a data set, specifically: Obtain data related to ideological and political education in courses from multiple channels, including at least literature, web pages, and public accounts; Clean the acquired data to remove redundant and invalid information; The data is formatted and unified into a structured format to obtain a data set.

3. A method for constructing a course ideological and political material library according to claim 1, characterized in that: The ontology structure of constructing the ideological and political field of courses includes: Define entities: including knowledge points, ideological and political elements, and case descriptions; Define the relationship between entities: the relationship between knowledge points, ideological and political elements and case descriptions is belonging to; the relationship between knowledge points and ideological and political elements is association.

4. A method for constructing a course ideological and political material library according to claim 1, characterized in that: The fine-tuned UIE model is used to extract entities from unlabeled data, specifically: The input text sequence is The structure model SSI is First, the UIE model will Input to Encoder to get the hidden layer representation of each token as Then use the pre-trained Transformer model to get the output, which is expressed as follows: in, Next, in the nth step of decoding, the hidden layer is used to represent the y in the nth token in the Decoder to generate the SEL sequence. n and decoder status It is expressed as follows:

5. A method for constructing a course ideological and political material library according to claim 1, characterized in that: The knowledge graph construction is to store the entities extracted from the data set into the graph database Neo4j. The data stored in the graph database includes entities and relationships between entities. The entities include: knowledge points, ideological and political elements, and case descriptions. The relationships include: the relationship between knowledge points, ideological and political elements and case descriptions is belonging, and the relationship between knowledge points and ideological and political elements is associated.

6. A method for constructing a course ideological and political material library according to claim 1, characterized in that: The course ideological and political material library can display the knowledge graph view, local node view and specific cases.

7. A method for constructing a course ideological and political material library according to claim 1, characterized in that: The intelligent retrieval system is specifically: The intelligent retrieval system design is a retrieval system developed by implementing the front end with vue3 and the back end with python. The system includes realizing the query of knowledge points in the search box. The query of knowledge points will call the graph database Neo4j, and display the nodes and relationships of the knowledge points in the retrieval system. Click any node in the knowledge graph display area, the system will call the Bing search engine to search for the node and display the search results in the pop-up window on the right. The pop-up window supports secondary search, thereby helping users find suitable ideological and political resources.

8. A system for constructing a curriculum ideological and political material library, characterized in that: A method for constructing a course ideological and political material library applied to any one of claims 1-7, comprising a data acquisition module, a knowledge graph construction module, a visualization module, and an intelligent retrieval module; The data acquisition module is used to acquire data related to ideological and political education in the course, and preprocess the data to obtain a data set; The knowledge graph construction module is used to construct the course ideological and political knowledge graph, specifically: construct an ontology structure of the course ideological and political field based on domain knowledge, and the ontology structure is a structured framework based on course knowledge points, ideological and political elements and their mutual relationships; use text annotation tools to manually annotate part of the data in the data set, and the annotation content includes course knowledge points and ideological and political elements, and then based on the annotated data, use the fine-tuned UIE model to perform entity extraction on the unannotated data, identify and extract knowledge points and ideological and political elements in the unannotated data; The extracted triple information is stored in the graph database Neo4j, and the knowledge points and ideological and political elements are associated through relationship edges to form a course ideological and political knowledge graph; the UIE model uses a pre-trained Transformer model to encode the input text, convert the input text into a context-related embedding representation, and extract the required information by generating a target sequence; The visualization module is used to display the course ideological and political material library based on the course ideological and political knowledge map. Users can intuitively view the relationship between knowledge points and ideological and political elements, as well as the detailed display of specific cases through a graphical interface; The intelligent retrieval module is used to query according to the preset intelligent retrieval system. Users enter specific knowledge points, and the system returns relevant graph nodes and their associated information. It also provides extended case resources related to knowledge points and ideological and political elements by integrating external search engines.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute a method for constructing a course ideological and political material library as described in any one of claims 1-7.

10. A computer-readable storage medium storing a program, characterized in that: When the program is executed by a processor, a method for constructing a course ideological and political material library as described in any one of claims 1 to 7 is implemented.

Images