Smart art education and teaching resource system construction method, storage medium and equipment

Abstract

The invention discloses a smart art education teaching resource system construction method, a storage medium and equipment, and belongs to the field of artificial intelligence and art education cross technologies, and the method comprises the steps: obtaining online art education professional teaching resources and online art education associated teaching resources through structuralization and knowledge processing, and carrying out the multi-modal knowledge graph fusion, thereby achieving the intelligent art education teaching resource system construction. The knowledge fusion of the online art education major teaching resources and the online art education associated teaching resources is realized, and an online art education major course system is constructed. And fusing an online art education major teacher resource library, an online art education major course resource library, an online art education major practice resource library and the online art education major course system to obtain an intelligent art education teaching resource system. The teaching efficiency and the teaching effect of online art education professional courses can be improved, and the method is of great significance to improvement and enhancement of existing online art education.

Description

Technical Field

[0001] The present invention belongs to the field of intersection of artificial intelligence and art education, and in particular relates to a method, storage medium and device for constructing an intelligent art education and teaching resource system. Background Art

[0002] Currently, most professional art schools and mainstream online art education platforms, both domestically and internationally, offer so-called "online art education," which merely translates offline courses online. This approach lacks maturity, standardization, and systematicity, remaining at a multi-source, heterogeneous, and cross-platform stage. A "professional online art education curriculum system" has yet to emerge, making it unable to support the sustainable development of online art education. Current mainstream online art education platforms still utilize the traditional "video course + online live broadcast" teaching model, with a single, single-track teaching system. Courses displayed are fixed schedules, lacking customized teaching plans tailored to individual students. This results in low teaching efficiency and is unable to meet the requirements for sustainable development of "online art education."

[0003] Furthermore, mainstream online art education platforms have yet to develop a mature, standardized, and systematic online art professional curriculum system. Existing professional curriculum systems have not undergone structured and knowledge-based processing to form an online art education knowledge base system. Multi-source, heterogeneous, and cross-platform characteristics have become common characteristics of online art education. Furthermore, the massive, decentralized, and fragmented art education big data from the internet has not undergone structured and knowledge-based processing to form professional art knowledge. This makes it impossible to form a mature, standardized, and systematic online art education professional curriculum system, nor to achieve the sharing of high-quality teaching content and advanced teaching technologies. Furthermore, development bottlenecks such as irrational matching of art education resources and uneven ecological development persist, making it difficult to meet the personalized professional course learning needs of online learners. Therefore, developing and constructing a smart art education teaching resource system that supports multimodal blended teaching and achieves a deep integration of high-quality teaching content and advanced teaching technologies is of great significance for improving the level of online art education and promoting its sustainable development. Summary of the Invention

[0004] In view of this, the present invention provides a method, storage medium and device for constructing a smart art education and teaching resource system.

[0005] The present invention adopts the following technical solutions:

[0006] A method for constructing a smart art education and teaching resource system, wherein the system is used for full-scenario teaching, the method comprising the following steps:

[0007] S1. Structuring and knowledge-based processing of multi-source, heterogeneous, and cross-platform professional curriculum systems of art colleges and universities to obtain professional teaching resources for online art education; structuring and knowledge-based processing of massive, decentralized, and fragmented art education big data on the Internet to obtain relevant teaching resources for online art education;

[0008] S2. Based on the online art education professional teaching resources and online art education related teaching resources, realize the knowledge fusion of the online art education professional teaching resources and online art education related teaching resources through multimodal knowledge graph fusion, and construct an online art education professional course system;

[0009] S3. Integrate the online art education professional teacher resource library, the online art education professional course resource library, the online art education professional practice resource library and the online art education professional course system to obtain the smart art education teaching resource system.

[0010] Furthermore, the structuring and knowledge-based processing of the multi-source, heterogeneous, cross-platform professional course system of art schools described in step S1 includes: storing online art education professional teaching resource entries expressed in natural language into an online art education professional teaching resource library; the online art education professional teaching resource entries include: structured information expressed in natural language according to course ID, course name, course category, course level, course introduction, course key points, technical difficulties or lecturers.

[0011] Furthermore, the structuring and knowledge-based processing of the multi-source, heterogeneous, cross-platform professional course system of art schools described in step S1 includes: structured information expressed in natural language according to resource ID, resource name, resource category, resource introduction or author introduction; subject integration and professional classification processing of the online art education professional teaching resources to form online art education professional knowledge, and store it in the online art education professional teaching resource library.

[0012] Furthermore, the structured and knowledge-based processing of the massive, decentralized and fragmented art education big data on the Internet as described in step S1 includes: using a combination of "semantic-based knowledge extraction" and "semantic-based machine learning" to conduct subject integration and professional classification processing on the massive, decentralized and fragmented art education big data on the Internet to form online art education-related knowledge, and storing the online art education-related knowledge in an online art education-related teaching resource library.

[0013] Furthermore, the multimodal knowledge graph described in step S2 includes: using a hybrid reasoning method of online art education multimodal knowledge graph based on reinforcement learning to achieve multimodal knowledge graph fusion.

[0014] Furthermore, the construction of the online art education professional course system described in step S2 includes: multimodal emotion recognition, multimodal knowledge fusion or multimodal resource reorganization.

[0015] Furthermore, step S2 includes: multimodal art emotion cognitive processing of professional teaching resources based on the Naive Bayes algorithm, and establishing a growth model for online art education professional courses.

[0016] Furthermore, step S2 includes: the online art education professional course system is automatically updated through multimodal resource reorganization.

[0017] Furthermore, the application of the smart art education and teaching resource system described in step S3 includes: continuously optimizing online art education professional courses based on an entity unification method based on pattern matching and the professional foundation, emotional level, personality characteristics or course teaching needs of online art education learners.

[0018] Furthermore, the application of the smart art education and teaching resource system in step S3 includes: providing personalized professional training programs and smart professional course services.

[0019] A computer storage medium stores a computer program, and the computer program is executed by a processor to implement the above method.

[0020] An electronic device, comprising:

[0021] a memory storing executable instructions;

[0022] A processor runs the executable instructions in the memory to implement the above method.

[0023] The present invention realizes the structuralization and knowledge processing of multi-source, heterogeneous, and cross-platform art professional course systems, forming online art education professional teaching resources; at the same time, it realizes the structuralization and knowledge processing of massive, decentralized, and fragmented art education big data on the Internet, forming online art education related teaching resources; the teaching resources come from a wider range of sources, and the processed teaching resources are more conducive to knowledge fusion; the present invention realizes the knowledge fusion of online art education professional teaching resources and related teaching resources by constructing a multimodal knowledge graph for online art education and fusion of multimodal knowledge graphs;

[0024] This invention is based on the multimodal art emotion cognitive processing of professional teaching resources using the Naive Bayes algorithm, establishes an online art education professional course growth model, obtains the precise positioning and influencing factors of online art education professional teaching resources, realizes multimodal resource reorganization and automatically updates the online art education professional course system, and thus enables the online art education professional course system to be continuously improved.

[0025] Aiming at the teaching needs of online art education professional courses, the present invention adopts the "entity unification method based on pattern matching" to realize the integration of online art education professional teacher resource library, professional course resource library, and professional practice resource library, and constructs an intelligent art education teaching resource system for full-scene teaching applications according to professional foundation, emotional level or personality characteristics. It is more conducive to providing online art education learners with personalized and intelligent customization services of online art education professional teaching resources, guiding learners to learn online art education professional course knowledge in a standardized, systematic and efficient manner, improve professional cognition and artistic creation ability, and improve the teaching efficiency and teaching effect of online art education professional courses, which is of great significance to improving and enhancing existing online art education.

[0026] The disclosed "Smart Art Education Teaching Resource System Construction Method" develops personalized professional course training plans based on the "professional foundation, emotional level, or personality characteristics" of online art education learners, achieving the optimal allocation of professional (course / teaching / practice) resources. During the professional course teaching process, learners determine the next stage of professional course configuration based on the professional courses they have already learned, thus providing learners with more accurate and humane "personalized" professional training and "smart" professional course services. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 This is a flow chart of a method for constructing a smart art education and teaching resource system according to the present invention;

[0029] Figure 2 This is a schematic diagram of a multimodal knowledge graph for online art education in a method for constructing a smart art education teaching resource system according to the present invention;

[0030] Figure 3 This is a schematic diagram of a course growth model (CGM) for online art education in a method for constructing a smart art education teaching resource system according to the present invention;

[0031] Figure 4 This is a schematic diagram of the process of implementing the big data knowledge fusion technology for art education in a method for constructing a smart art education teaching resource system of the present invention;

[0032] Figure 5 This is a schematic diagram of the knowledge structure of the online art education professional course system in the method for constructing a smart art education teaching resource system of the present invention;

[0033] Figure 6 It is a schematic diagram of the knowledge map of the online art education professional course system in the method for constructing the intelligent art education teaching resource system of the present invention. DETAILED DESCRIPTION

[0034] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0035] It should be understood that the embodiments described are only a portion of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative work are within the scope of protection of the present invention.

[0036] Example 1:

[0037] like Figure 1 As shown, a method for constructing a smart art education teaching resource system, the system is used for full-scenario teaching, and the method includes the following steps:

[0038] S1. Structuring and knowledge-based processing of multi-source, heterogeneous, and cross-platform professional curriculum systems of art colleges and universities to obtain professional teaching resources for online art education; structuring and knowledge-based processing of massive, decentralized, and fragmented art education big data on the Internet to obtain relevant teaching resources for online art education;

[0039] S2. Based on the online art education professional teaching resources and online art education related teaching resources, realize the knowledge fusion of the online art education professional teaching resources and online art education related teaching resources through multimodal knowledge graph fusion, and construct an online art education professional course system;

[0040] S3. Integrate the online art education professional teacher resource library, the online art education professional course resource library, the online art education professional practice resource library and the online art education professional course system to obtain the smart art education teaching resource system.

[0041] Furthermore, the structuring and knowledge-based processing of the multi-source, heterogeneous, cross-platform professional course system of art schools described in step S1 includes: storing online art education professional teaching resource entries expressed in natural language into an online art education professional teaching resource library; the online art education professional teaching resource entries include: structured information expressed in natural language according to course ID, course name, course category, course level, course introduction, course key points, technical difficulties or lecturers.

[0042] Furthermore, the structuring and knowledge-based processing of the multi-source, heterogeneous, cross-platform professional course system of art schools described in step S1 includes: structured information expressed in natural language according to resource ID, resource name, resource category, resource introduction or author introduction; subject integration and professional classification processing of the online art education professional teaching resources to form online art education professional knowledge, and store it in the online art education professional teaching resource library.

[0043] Furthermore, the structured and knowledge-based processing of the massive, decentralized and fragmented art education big data on the Internet as described in step S1 includes: using a combination of "semantic-based knowledge extraction" and "semantic-based machine learning" to conduct subject integration and professional classification processing on the massive, decentralized and fragmented art education big data on the Internet to form online art education-related knowledge, and storing the online art education-related knowledge in an online art education-related teaching resource library.

[0044] Furthermore, the multimodal knowledge graph described in step S2 includes: using a hybrid reasoning method of online art education multimodal knowledge graph based on reinforcement learning to achieve multimodal knowledge graph fusion.

[0045] Furthermore, the construction of the online art education professional course system described in step S2 includes: multimodal emotion recognition, multimodal knowledge fusion or multimodal resource reorganization.

[0046] Furthermore, step S2 includes: multimodal art emotion cognitive processing of professional teaching resources based on the Naive Bayes algorithm, and establishing a growth model for online art education professional courses.

[0047] Furthermore, step S2 includes: the online art education professional course system is automatically updated through multimodal resource reorganization.

[0048] Furthermore, the application of the smart art education and teaching resource system described in step S3 includes: continuously optimizing online art education professional courses based on an entity unification method based on pattern matching and the professional foundation, emotional level, personality characteristics or course teaching needs of online art education learners.

[0049] Furthermore, the application of the smart art education and teaching resource system in step S3 includes: providing personalized professional training programs and smart professional course services.

[0050] A computer storage medium stores a computer program, and the computer program is executed by a processor to implement the above method.

[0051] An electronic device, comprising:

[0052] a memory storing executable instructions;

[0053] A processor runs the executable instructions in the memory to implement the above method.

[0054] Example 2

[0055] like Figure 1 As shown in the figure, a method for constructing an intelligent art education and teaching resource system is proposed. First, for the multi-source, heterogeneous, and cross-platform art professional course system (covering music, dance, drama, visual arts, film production or design production disciplines) of (professional art colleges), a "non-automatic knowledge acquisition" method is used to structure the art professional course systems of different (professional art colleges) to form structured information such as course ID, course name, course category, course level, course introduction, course key points, technical difficulties, and lecturers (expressed in natural language) and store it in the online art education professional teaching resource library, and then carry out subject integration and professional classification processing to form online art education professional knowledge.

[0056] like Figure 1 As shown in the figure, for the massive, decentralized and fragmented art education big data (pictures, texts, audio or video) on the Internet (mobile Internet), a combination of "semantic-based knowledge extraction" and "semantic-based machine learning" is adopted to identify, understand, filter, merge and other structured processing for related teaching resources, and form structured information according to resource ID, resource name, resource category, resource introduction, author introduction, etc. (expressed in natural language) and store it in the online art education related teaching resource library, and then carry out subject integration and professional classification processing to form online art education related knowledge.

[0057] The implementation process of the big data knowledge fusion technology for art education disclosed in the present invention is as follows: Figure 4 shown.

[0058] (1) Data preprocessing

[0059] During the preprocessing phase of online art education data, the quality of the original data (art education big data) directly affects the final record linkage results. Different datasets often describe the same entity in different ways. Normalizing this knowledge is an important step in improving the accuracy of subsequent online art education record linkage. The data preprocessing methods used in this paper mainly include: grammatical normalization: grammatical matching (such as the representation of contact numbers) and comprehensive attributes (such as the expression of home addresses); data normalization: removing spaces, symbols such as "", "", and "-"; topological errors of input errors; and replacing nicknames and abbreviations with formal names.

[0060] (2) Data Blocking

[0061] Data blocking is to select potential matching record pairs from all entity pairs in a given knowledge base as candidates and narrow the candidate list as much as possible. The blocking methods adopted in the present invention include hash function-based blocking, proximity blocking, etc.

[0062] Hash function-based chunking: For a record x, if hash(x) = hi or hash(x) = hi, then x is mapped to the chunk CiCi bound to the keyword hihi. Common hash functions include: the first n characters of a string; n-grams; and combining multiple simple hash functions.

[0063] Neighborhood block algorithms include Canopy clustering, sorted neighbor algorithm, Red-Blue Set Cover, etc.

[0064] (3) Record Link

[0065] Assume there are two entity records x and y, and the values ​​of x and y on the i-th attribute are xi and yi, respectively. The records are linked in the following two steps:

[0066] Attribute similarity: The attribute similarity vector is obtained by combining the similarities of individual attributes:

[0067] [sim(x1, y1), sim(x2, y2),...sim(xN, yN)]

[0068] Entity similarity: Get an entity similarity based on the attribute similarity vector.

[0069] The attribute similarity calculation methods used in this method include edit distance, set similarity calculation, vector-based similarity calculation, etc.

[0070] (4) Load balancing

[0071] Load balancing is used to ensure that the number of entities in all online art education data blocks is equal, thereby ensuring the degree of performance improvement of knowledge data blocks. The load balancing method adopted by the present invention is multiple Map-Reduce operations.

[0072] For the multi-source, heterogeneous, and cross-platform art professional course system (of professional art colleges), structured and knowledge-based processing is carried out to form structured information and store it in the online art education professional teaching resource (professional knowledge) library; at the same time, for the massive, decentralized, and fragmented art education big data (pictures, text, audio or video) on the Internet (mobile Internet), structured and knowledge-based processing is carried out to form structured information and store it in the online art education related teaching resource (related knowledge) library.

[0073] like Figure 2As shown in the figure, by constructing a hybrid knowledge graph for online art education (using a hybrid reasoning method for online art education multimodal knowledge graph based on reinforcement learning to achieve multimodal knowledge graph fusion), the professional teaching resources and related teaching resources are integrated to form a unique "online art education professional course system (knowledge base system)"; furthermore, based on the "professional foundation, emotional level" classification criteria, an online art education professional course growth model is established (such as Figure 3 (as shown) to obtain the precise positioning and influencing factors of online art education professional teaching resources, determine the ranking of online art education professional teaching resources and related teaching resources, and continuously optimize and refine them, realize multimodal resource reorganization and automatically update the "Online Art Education Professional Course System (Knowledge Base System)";

[0074] In response to the teaching needs of online art education professional courses, we adopt the "entity unified method based on pattern matching" to target the professional foundation / emotional level / personality characteristics / course teaching needs of online art education learners, continuously optimize the "entity" relationship of online art education professional course teaching, provide "personalized" professional training programs and "intelligent" professional course services, and realize the integration of online art education professional teacher resource library, professional course resource library, and professional practice resource library, so as to construct an intelligent art education teaching resource system (intelligent knowledge base system) classified according to "professional foundation / emotional level / personality characteristics" and oriented to full-scene teaching applications.

[0075] A method for constructing a smart art education and teaching resource system, that is, a method for constructing a smart art education and teaching resource system for full-scenario teaching applications, such as Figure 1As shown in the figure, in response to the professional teaching problems existing in the traditional teaching model of current professional art colleges and universities at home and abroad (online art education platforms), especially based on the analysis and demonstration of common technical problems in online art education such as in-depth mining of Internet (mobile Internet) art education big data (related knowledge) and the application of advanced teaching technologies for full-scene (online and offline) teaching, a growth path (structuring → knowledge-based → intelligent) and construction method of the professional course system of online art education are proposed. The multi-source, heterogeneous, and cross-platform art professional curriculum system of professional art colleges is structured (standardized and systematized) and knowledge-based (disciplinary integration and professional classification) to form online art education professional teaching resources (professional knowledge); the massive, decentralized, and fragmented art education big data on the Internet is structured (standardized and systematized) and knowledge-based (disciplinary integration and professional classification) to form online art education related teaching resources (related knowledge); by constructing an online art education hybrid knowledge graph (based on the hybrid method of knowledge reasoning and curriculum reasoning to achieve multimodal knowledge graph fusion), professional knowledge and related knowledge are integrated to form an "online art education professional curriculum system (knowledge base system)"; further, in response to the teaching needs of online art education professional courses, the "entity unification method based on pattern matching" is adopted to achieve deep integration of online art education professional teacher resource library, professional course resource library, and professional practice resource library, thereby constructing an intelligent art education teaching resource system (intelligent knowledge base system) classified according to "professional foundation, emotional level or personality characteristics" and oriented to full-scene teaching applications.

[0076] As a smart art education teaching resource system (smart knowledge base system) for full-scenario teaching applications, it should not only provide mature, standardized and systematic online art education professional course resources (professional knowledge) for online art education learners, but also help learners accurately locate and provide personalized training programs (customized course plans and recommended professional teachers) according to the professional foundation and individual needs of learners, and establish accurate "teacher-student" links. This method can accurately provide online art education learners with "online art education professional course system (professional knowledge, related knowledge)" At the same time, according to the professional foundation and "personalized" teaching needs of online art education learners, it customizes and recommends online art education professional teacher resources and professional practice resources, realizes the trinity of online art education professional (courses / teachers / practice) teaching resources, and promotes the simultaneous improvement of online art education learners' professional knowledge and professional ability.

[0077] The "online art education professional course system (knowledge base system)" constructed according to the technical solution (construction method) of the present invention includes diversified professional course forms such as regular art courses, art master courses, and art observation courses (such as Figure 4Among them, regular art courses include general art courses and art professional courses. General art courses include art foundation courses and professional foundation courses. Professional art courses include professional core courses, professional development courses and cross-disciplinary courses, etc. Figure 5 shown.

[0078] The online art education professional course system includes disciplines such as music, dance, drama, visual arts, film and television production, and design production, which are divided into three professional levels: elementary, intermediate, and advanced. It is necessary to design a multimodal knowledge graph for the knowledge structure of the online art education professional course system (such as Figure 6 As shown). The "smart art education and teaching resource system (smart knowledge base system)" constructed according to the present invention integrates professional course resource library, professional teacher resource library, and professional practice resource library, wherein the professional course resource library and the professional practice resource library both contain course attribute table, course grade table, course type table, etc. The course attribute table contains attributes such as course ID, course name, course category, course grade, course introduction, course key points, technical difficulties, main lecturer, and course URL; the course grade table contains ID and course grade; the course table contains six attributes, namely ID, course name, course introduction, course chapter, course price, and URL; the course type table contains course ID number and course type. The professional teacher resource library contains a teacher table (containing three attributes): ID, teacher name, and teacher introduction.

[0079] The embodiments of the present invention are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A method for constructing a smart art education and teaching resource system, wherein the system is used for full-scenario teaching, and is characterized by: The method comprises the following steps: S1. Structuring and knowledge-based processing of multi-source, heterogeneous, and cross-platform professional curriculum systems of art colleges and universities to obtain professional teaching resources for online art education; structuring and knowledge-based processing of massive, decentralized, and fragmented art education big data on the Internet to obtain relevant teaching resources for online art education; S2. Based on the online art education professional teaching resources and online art education related teaching resources, realize the knowledge fusion of the online art education professional teaching resources and online art education related teaching resources through multimodal knowledge graph fusion, and construct an online art education professional course system; S3. Integrate the online art education professional teacher resource library, the online art education professional course resource library, the online art education professional practice resource library and the online art education professional course system to obtain the smart art education teaching resource system.

2. The construction method according to claim 1, characterized in that: The structured and knowledge-based processing of the multi-source, heterogeneous, and cross-platform professional course system of art schools described in step S1 includes: storing online art education professional teaching resource entries expressed in natural language into an online art education professional teaching resource library; the online art education professional teaching resource entries include: structured information expressed in natural language according to course ID, course name, course category, course level, course introduction, course key points, technical difficulties or lecturers.

3. The construction method according to claim 1, characterized in that: The structured and knowledge-based processing of the multi-source, heterogeneous, and cross-platform professional course system of art schools described in step S1 includes: structured information expressed in natural language according to resource ID, resource name, resource category, resource introduction or author introduction; subject integration and professional classification processing of the online art education professional teaching resources to form online art education professional knowledge, and store it in the online art education professional teaching resource library.

4. The construction method according to claim 1, characterized in that: The structured and knowledge-based processing of the massive, decentralized and fragmented art education big data on the Internet described in step S1 includes: using a combination of "semantic-based knowledge extraction" and "semantic-based machine learning" to conduct subject integration and professional classification processing on the massive, decentralized and fragmented art education big data on the Internet to form online art education-related knowledge, and storing the online art education-related knowledge in an online art education-related teaching resource library.

5. The construction method according to claim 1, characterized in that: The multimodal knowledge graph described in step S2 includes: using a hybrid reasoning method of online art education multimodal knowledge graph based on reinforcement learning to achieve multimodal knowledge graph fusion.

6. The construction method according to claim 1, characterized in that: The construction of the online art education professional course system described in step S2 includes: multimodal emotion recognition, multimodal knowledge fusion or multimodal resource reorganization.

7. The construction method according to claim 1, characterized in that: Step S2 includes: multimodal art emotion cognitive processing of professional teaching resources based on the Naive Bayes algorithm, establishing an online art education professional course growth model; the online art education professional course system is automatically updated through multimodal resource reorganization.

8. The construction method according to claim 1, characterized in that: The application of the smart art education and teaching resource system described in step S3 includes: continuously optimizing online art education professional courses based on the entity unification method of pattern matching and the professional foundation, emotional level, personality characteristics or course teaching needs of online art education learners; providing personalized professional training programs and smart professional course services.

9. A computer storage medium, wherein a computer program is stored on the medium, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 8.

10. An electronic device, comprising: a memory storing executable instructions; A processor, wherein the processor runs the executable instructions in the memory to implement the method according to any one of claims 1 to 8.

Images