Personalized art education customization system based on big data

Abstract

The invention discloses a personalized art education customization system based on big data, and particularly relates to the technical field of education. Comprising an art education student database, an art education customization data acquisition module, an art education customization data analysis module, a personalized art education customization module, a personalized art education customization evaluation module and a personalized art education customization man-machine interaction module. The art education customized data acquisition module is used for acquiring the art learning data of the students from the art education student database and transmitting the art learning data to the art education customized data analysis module; through a big data analysis technology, learning data of students are mined and analyzed, performances of the students on different drawing themes and styles are analyzed, learning conditions, hobbies and interests and potential demands of the students are understood, personalized learning suggestions and resource recommendation are provided for each student, configuration of educational resources is optimized, and learning efficiency is improved. The teaching efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and in particular to a personalized art education customization system based on big data. Background Art

[0002] Big data technology is used to solve the problems of collecting, storing, processing, analyzing and mining massive, diverse, fast and valuable data; art education mainly studies the basic theories related to art and masters scientific educational theories and teaching methods. With the development of information technology, based on the educational innovation needs of the big data era, the important role of art education in cultivating students' quality and the application of big data technology in art education, the application of data analysis in the field of education has gradually increased, providing data support for personalized art education.

[0003] In the field of education, the application of big data provides new opportunities for educational innovation. In traditional art education, teachers usually conduct demonstration teaching, guide students to understand and master painting skills through on-site demonstrations and explanations, focus on the study and inheritance of traditional art, and attach importance to norms and paradigms. In the learning process, students need to follow the rules of traditional art and conventional aesthetic standards, pay attention to the inheritance of traditional art forms and styles, and then gradually improve their painting skills through observation, imitation and practice.

[0004] With the changes of the times and the development of educational concepts, the shortcomings of traditional art education methods have gradually emerged in actual use. For example, traditional teaching methods are often relatively uniform and cannot meet the personalized needs of different students. Each student's art foundation, interests, painting themes, styles and development potential are different. A one-size-fits-all teaching method is difficult to fully stimulate students' creativity and potential, and it is difficult to meet the needs of the new era society for talents. The personalized art education customization system of the present invention effectively solves this problem. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a personalized art education customization system based on big data to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above purpose, the present invention provides the following technical solution: a personalized art education customization system based on big data, comprising:

[0007] Art education student database: Through big data technology, collect and store students' art learning data from student information terminals to build an art education student database;

[0008] Art education customized data collection module: collects students' art learning data from the art education student database and transmits it to the art education customized data analysis module, where the students' art learning data includes student identity data, student work data, student historical work test score data, and student work completion time data;

[0009] Art education customized data analysis module: Through big data technology, the student art learning data obtained by the data collection module is analyzed, and the analysis results are transmitted to the personalized art education customized module;

[0010] Personalized art education customization module: used to provide personalized education customization plan for each student according to the analysis results obtained by the data analysis module, obtain customized indicators, and transmit them to the personalized art education customization evaluation module;

[0011] Personalized art education customized evaluation module: used to compare the customized indicators obtained by the customization module with the threshold, evaluate the effects of the customized solutions with comparison results greater than or equal to 0, and then transmit the results of the effect evaluation to the personalized art education customized human-computer interaction module;

[0012] Personalized art education customization human-computer interaction module: used to output the personalized art education customization program effect evaluation indicators obtained by the evaluation module to the administrator information terminal.

[0013] Preferably, the data analysis in the art education customized data analysis module includes the following steps:

[0014] Step 1: Students identify the analysis unit:

[0015] Step 1.1: First, collect the student data set Sd through big data technology, Sd = [Sd1, Sd2, ..., Sd i ,...,Sd n ], where Sd i represents the i-th student, n represents the number of students; then collect the art work data set Wd of each student i , Wd i =[Wd 1 ,Wd 2 ,...,Wd l ,...,Wd m ], where Wd l represents the lth art work of the ith student, and m represents the number of the ith student’s art works;

[0016] Step 1.2: Based on the student dataset and the corresponding art dataset in step 1.1, obtain the painting theme and style dataset psd of each student's art work i ,

[0017] psd i =[(p,s) 1 ,(p,s) 2 ,...,(p,s) j ,...,(p,s) k ], where (P,S) j represents the jth painting theme and style of the i-th student.

[0018] Preferably, the data analysis in the art education customized data analysis module includes the following steps:

[0019] Step 2: Analysis unit of students’ preference for art learning:

[0020] Step 2.1: Based on step 1.2, obtain the painting theme and style dataset of each student's art works. Use big data technology to obtain the number of works of each painting theme and style for each student, and sort the painting theme and style dataset PSD according to the number from most to least. i , PSD i =[(p,s) 1 ,(p,s) 2 ,...,(p,s) J ,...,(p,s) K ],(p,s) J represents the J-th most common painting theme and style of the i-th student;

[0021] Step 2.2: Based on step 1.2, obtain the painting theme and style dataset of each student's art work. Through big data analysis technology, obtain the average value avg of the test score of each painting theme and style from the art education student database. Use the average value as the quality evaluation index of each student's painting theme and style work, and sort the painting theme and style quality dataset WQD from the work quality evaluation index from large to small i , WQD(psd i )=[avg(p,s) 1 ,avg(p,s) 2 ,...,avg(p,s) I ,...,avg(p,s) N ], where avg(p,s) I represents the score of the work of the i-th student with the i-th painting theme and style;

[0022] Step 2.3: Based on the number of works of each student for each painting theme and style obtained in step 2.1, first obtain the work completion time dataset TD (PSD) through timestamp technology i ),TD(PSDi )=[t(p,s) 1 ,t(p,s) 2 ,...,t(p,s) J ,...,t(p,s) K ], where t(p,s) J represents the cumulative completion time of the i-th student's J-th painting theme and style, and obtains the student's painting theme and style preference index PPI, Where n(p,s) J represents the number of works with the Jth most common painting theme and style, avg(p,s) I represents the score of the works of the i-th student's i-th painting theme and style, a1, a2 and a3 represent the weights of the proportion of works with a specific theme and style, the proportion of completion time and the proportion of work quality respectively; then, the painting theme and style of each student are sorted from large to small according to the preference index, and the sorted painting theme and style dataset S_PSD is obtained. i , S_PSD i =[(p,s) 1 ,(p,s) 2 ,...,(p,s) L ,...,(p,s) M ],(p,s) L The painting theme and style representing the Lth preference index.

[0023] Preferably, the unit for analyzing the number of art learning difficulties of students in the art education customized data analysis module: based on the sorted painting theme and style data set obtained in step 2.3, firstly, according to each student's preferred painting theme and style, the total number of art education knowledge points KPT is listed in the comprehensive curriculum outline and industry standards, and the knowledge points are first classified and then numbered; then, the learning management system is used to track the learning progress of the students under the preferred painting themes and styles, and the completion data of the works are obtained; finally, through the skill test results, the students' incorrect knowledge points are summarized, and the number and type of knowledge points are counted, and matched with the knowledge point list, the number DLN and classification number of the difficult knowledge points in the painting theme and style preferred by each student are obtained, and the art learning difficulty index LDI of each student is obtained. i , Among them, UNA represents the number of unfinished works, and T_A represents the total number of assignments.

[0024] Preferably, the art course customization unit in the personalized art education customization module: based on the students' preferred painting themes and styles obtained in step 2.3, personalized course content is customized for each student through the art education resource database and in combination with the educational objectives, and the course content customization index CCI is obtained, CCI = cn / sn, where cn represents the number of courses with preferred painting themes and styles, and sn represents the total number of courses based on the educational objectives.

[0025] Preferably, the art education resource customization unit in the personalized art education customization module: based on the number of learning difficulties of each student's preferred painting themes and styles obtained in step 3, customize corresponding learning resources according to the learning difficulty knowledge points and classification numbers through the art education resource database, including personalized teaching methods and training work resources for the learning difficulty knowledge points, and obtain the art resource customization index ARI, ARI = lrn / T_lrn, where lrn represents the number of customized personalized resources, and T_lrn represents the total number of resources based on educational goals

[0026] Preferably, the art project practice customization unit in the personalized art education customization module customizes the corresponding painting projects for each student based on the students' preferred painting themes and styles obtained in step 2.3 and the number of difficult knowledge points in learning the painting themes and styles preferred by each student obtained in step 3, and obtains the project practice customization index PCI, PCI=cpn / T_cpn, where cpn represents the number of customized projects, and T_cpn represents the total number of projects based on educational objectives.

[0027] Preferably, the personalized art education customization program effect evaluation index CEI in the personalized art education customization evaluation module is: Where cc represents the number of clicks on the students’ personalized recommended content, TC represents the total number of clicks by the students, nw(now) represents the number of personalized works currently created by the students, nw(bef) represents the number of personalized works at the previous evaluation time, s(now) represents the cumulative score of the current personalized works, s(bef) represents the cumulative score of the personalized works at the previous evaluation time, and c1, c2, and c3 represent the weights of the personalized content click-through rate, the personalized work creation efficiency, and the personalized work improvement rate, respectively.

[0028] Technical effects and advantages of the present invention:

[0029] 1. The present invention mines and analyzes students' learning data through big data analysis technology, analyzes students' performance on different painting themes and styles, understands students' learning status, interests and hobbies, and potential needs, and thus provides personalized learning suggestions and resource recommendations for each student, which helps to optimize the allocation of educational resources and improve teaching efficiency;

[0030] 2. The present invention uses big data analysis technology to customize a personalized art education program for each student, fully stimulate students' learning interest and creativity, and improve learning effects and efficiency; it can accurately meet students' personalized needs and maximize their artistic potential; it provides new ways and methods for the intelligent and personalized development of art education;

[0031] 3. The present invention uses big data analysis technology to evaluate personalized art education programs. According to the evaluation results, the art education program is dynamically adjusted to adapt to changes in students during the learning process, ensure the pertinence and effectiveness of education, improve teaching efficiency, and thus help promote the innovative development of art education. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the overall process of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] See also Figure 1 As shown, the present invention provides a personalized art education customization system based on big data, including an art education student database, an art education customized data acquisition module, an art education customized data analysis module, a personalized art education customization module, a personalized art education customized evaluation module and a personalized art education customized human-computer interaction module.

[0035] What needs to be specifically explained in this embodiment is that in art education, a painting usually has a theme and style, which is composed of lines, colors, composition, creativity and other aspects. The painting theme often determines the basic content and emotional tone of the work, while the style is the way of artistic processing and expression of this theme, which is a reflection of the integrity and artistry of the work.

[0036] The art education student database is connected to all modules in the system, the art education customized data analysis module is respectively connected to the art education customized data collection module and the personalized art education customized module, the personalized art education customized evaluation module is respectively connected to the personalized art education customized module and the personalized art education customized human-computer interaction module, and the personalized art education customized human-computer interaction module is connected to the personalized art education customized module.

[0037] Art education student database: Through big data technology, collect and store students' art learning data from student information terminals to build an art education student database;

[0038] What needs to be specifically explained in this embodiment is that the art education student database includes but is not limited to students' works in different painting themes (such as landscapes, figures, still lifes, etc.) and styles (such as realism, abstraction, impressionism, etc.), students' learning progress, homework completion, class participation, skill assessment test scores, student questionnaire data, etc. The art education student database is connected to all modules in the system, is used to receive and store data from each module, and updates the art education student database in real time.

[0039] Art education customized data collection module: collects students' art learning data from the art education student database and transmits it to the art education customized data analysis module, where the students' art learning data includes student identity data, student work data, student historical work test score data, and student work completion time data;

[0040] Art education customized data analysis module: Through big data technology, the student art learning data obtained by the data collection module is analyzed, and the analysis results are transmitted to the personalized art education customized module, including the student identification analysis unit, the student art learning preference analysis unit and the student art learning difficulty analysis unit. The data analysis includes the following steps:

[0041] Step 1: Students identify the analysis unit:

[0042] Step 1.1: First, collect the student data set Sd through big data technology, Sd = [Sd1, Sd2, ..., Sd i ,...,Sd n ], where Sd i represents the i-th student, n represents the number of students; then collect the art work data set Wd of each student i , Wd i =[Wd 1 ,Wd 2 ,...,Wd l ,...,Wd m ], where Wd l represents the lth art work of the ith student, and m represents the number of the ith student’s art works;

[0043] Step 1.2: Based on the student dataset and the corresponding art dataset in step 1.1, obtain the painting theme and style dataset psd of each student's art work i ,

[0044] psd i=[(p,s) 1 ,(p,s) 2 ,...,(p,s) j ,...,(p,s) k ], where (P,S) j represents the jth painting theme and style of the i-th student, such as (landscape, realistic), (figure, abstract), etc.;

[0045] Step 2: Analysis unit of students’ preference for art learning:

[0046] Step 2.1: Based on step 1.2, obtain the painting theme and style dataset of each student's art works. Use big data technology to obtain the number of works of each painting theme and style for each student, and sort the painting theme and style dataset PSD according to the number from most to least. i , PSD i =[(p,s) 1 ,(p,s) 2 ,...,(p,s) J ,...,(p,s) K ],(p,s) J represents the J-th most common painting theme and style of the i-th student;

[0047] Step 2.2: Based on step 1.2, obtain the painting theme and style dataset of each student's art work. Through big data analysis technology, obtain the average value avg of the test score of each painting theme and style from the art education student database. Use the average value as the quality evaluation index of each student's painting theme and style work, and sort the painting theme and style quality dataset WQD from the work quality evaluation index from large to small i , WQD(psd i )=[avg(p,s) 1 ,avg(p,s) 2 ,...,avg(p,s) I ,...,avg(p,s) N ], where avg(p,s) I represents the score of the work of the i-th student with the i-th painting theme and style;

[0048] What needs to be specifically explained in this embodiment is that the historical work test score is obtained by adding the line score, color score, composition score and creativity score of the painting and then taking the average value.

[0049] Step 2.3: Based on the number of works of each student for each painting theme and style obtained in step 2.1, first obtain the work completion time dataset TD (PSD) through timestamp technology i),TD(PSD i )=[t(p,s) 1 ,t(p,s) 2 ,...,t(p,s) J ,...,t(p,s) K ], where t(p,s) J It represents the cumulative completion time of the J-th painting theme and style of the i-th student. A longer completion time is usually considered to be more time invested, indicating a greater preference. The PPI index of the students' painting theme and style preference is obtained. Where n(p,s) J represents the number of works with the Jth most common painting themes and styles, avg(p,s)I represents the score of the works of the i-th student with the i-th painting theme and style, a1, a2 and a3 represent the weights of the proportion of works with a specific theme and style, the proportion of completion time and the proportion of work quality, for example, a1 = 0.4, a2 = 0.3 and a3 = 0.3; then, the painting theme and style of each student are sorted from large to small according to the preference index, and the sorted painting theme and style dataset S_PSD is obtained. i , S_PSD i =[(p,s) 1 ,(p,s) 2 ,...,(p,s) L ,...,(p,s) M ],(p,s) L The painting themes and styles representing the Lth preference index provide a basis for customized personalized art education programs;

[0050] What needs to be specifically explained in this embodiment is that big data analysis technology is used to analyze the quantity, quality, creativity and time invested in students' works under different themes and styles to determine their interests and preferences and provide students with personalized feedback and suggestions.

[0051] Step 3: Quantitative analysis unit of students’ art learning difficulties: Based on the sorted painting theme and style data set obtained in step 2.3, firstly, according to each student’s preferred painting theme and style, the total number of art education knowledge points KPT is listed in the curriculum outline and industry standards, and the knowledge points are first classified and then numbered; then, the learning management system is used to track the students’ learning progress under the painting themes and styles they prefer, and obtain the completion data of the works; finally, through the skill test results, the cosine similarity algorithm is used to traverse and analyze the similarity between the students’ incorrect text content and the knowledge point list, and the knowledge point with the largest similarity is taken, and the number and type of knowledge points are counted to obtain the number DLN and classification number of the difficult knowledge points for each student’s preferred painting theme and style, and obtain the art learning difficulty index LDI for each student. i , Among them, UNA represents the number of unfinished works, and T_A represents the total number of assignments. For example, we can analyze the course outline of art education in detail, list all the knowledge points that need to be taught, refer to the industry standards and specifications of art education, understand the core knowledge points and skills that need to be mastered in this field, and include these knowledge points in the statistical scope of the total number of knowledge points, including painting techniques, color matching, creative ideas, etc.

[0052] Personalized art education customization module: used to provide personalized education customization plan for each student according to the analysis results obtained by the data analysis module, obtain customized indicators, and transmit them to the personalized art education customization evaluation module, including art course customization unit, art education resource customization unit and art project practice customization unit. Its personalized education customization plan includes the following steps:

[0053] Step 4: Art course customization unit: Based on the students' preferred painting themes and styles obtained in step 2.3, the art education resource database is used to customize personalized course content for each student in combination with the educational goals, and the course content customization index CCI is obtained. CCI = cn / sn, where cn represents the number of courses based on the preferred painting themes and styles, and sn represents the total number of courses based on the educational goals. For example, for a student with a strong talent for realistic painting, the system may recommend more realistic skills training courses for him;

[0054] Step 5: Art education resource customization unit: Based on the number of learning difficulties of each student's preferred painting themes and styles obtained in step 3, the corresponding learning resources are customized according to the learning difficulty knowledge points and classification numbers through the art education resource database, including personalized teaching methods and training work resources for the learning difficulty knowledge points, and the art resource customization index ARI is obtained, ARI = lrn / T_lrn, where lrn represents the number of customized personalized resources, and T_lrn represents the total number of resources based on educational goals, for example, teaching methods include teaching methods, such as online teaching, offline tutoring, group cooperation, etc.;

[0055] Step 6: Art project practice customization unit: Based on the students' preferred painting themes and styles obtained in step 2.3 and the number of difficult knowledge points in each student's preferred painting themes and styles obtained in step 3, customize corresponding painting projects for each student. Painting projects include competitions and exhibitions on specific themes to improve students' painting skills. The project practice customization index PCI is obtained. PCI = cpn / T_cpn, where cpn represents the number of customized projects and T_cpn represents the total number of projects based on educational goals. For example, for students who like creative expression, encourage them to participate in creative painting projects and competitions.

[0056] Personalized art education customized evaluation module: used to compare the customized indicators obtained by the customization module with the threshold, and evaluate the effect of the customized plan with a comparison result greater than or equal to 0, and then transmit the result of the effect evaluation to the personalized art education customized human-computer interaction module. Based on the customized indicators obtained in steps 4, 5 and 6, they are compared with the corresponding thresholds respectively. If the comparison result is less than 0, the personalized education customization plan is adjusted in real time; if the comparison result is greater than or equal to 0, the customization plan is evaluated, and the personalized art education customization plan effect evaluation index CEI is obtained through big data analysis technology. Where cc represents the number of clicks on the personalized recommended content by students, TC represents the total number of clicks by students, nw(now) represents the number of personalized works currently created by students, nw(bef) represents the number of personalized works at the previous evaluation time, s(now) represents the cumulative score of the current personalized works, s(bef) represents the cumulative score of the personalized works at the previous evaluation time, c1, c2 and c3 represent the weights of the personalized content click rate, the personalized works creation efficiency and the personalized works improvement rate respectively, for example, c1 = 0.3, c2 = 0.35 and c3 = 0.35;

[0057] Personalized art education customization human-computer interaction module: used to output the personalized art education customization program effect evaluation indicators obtained by the evaluation module to the administrator information terminal. If the personalized art education customization program effect evaluation indicators fall within the set allowable range, it means that the personalized art education customization effect is good; otherwise, the administrator is prompted to take timely measures to dynamically adjust the course content according to the students' interests and talents to ensure that the course matches the students' needs; try different teaching methods to find the teaching method that best suits the students, thereby more effectively improving the effect of personalized art education customization and meeting the diverse needs of students.

[0058] Conduct regular evaluations of students’ learning outcomes and adjust teaching content and methods based on the evaluation results to ensure that students achieve the best learning outcomes.

[0059] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0060] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A personalized art education customization system based on big data, characterized by: include: Art education student database: Through big data technology, collect and store students' art learning data from student information terminals to build an art education student database; Art education customized data collection module: collects students' art learning data from the art education student database and transmits it to the art education customized data analysis module, where the students' art learning data includes student identity data, student work data, student historical work test score data, and student work completion time data; Art education customized data analysis module: Through big data technology, the student art learning data obtained by the data collection module is analyzed, and the analysis results are transmitted to the personalized art education customized module; Personalized art education customization module: used to provide personalized education customization plan for each student according to the analysis results obtained by the data analysis module, obtain customized indicators, and transmit them to the personalized art education customization evaluation module; Personalized art education customized evaluation module: used to compare the customized indicators obtained by the customization module with the threshold, evaluate the effects of the customized solutions with comparison results greater than or equal to 0, and then transmit the results of the effect evaluation to the personalized art education customized human-computer interaction module; Personalized art education customization human-computer interaction module: used to output the personalized art education customization program effect evaluation indicators obtained by the evaluation module to the administrator information terminal.

2. According to the big data-based personalized art education customization system of claim 1, it is characterized by: The data analysis in the custom data analysis module for art education includes the following steps: Step 1: Students identify the analysis unit: Step 1.1: First, collect the student data set Sd through big data technology. Sd=[Sd1,Sd2,...,Sd i ,...,Sd n ], where Sd i represents the i-th student, n represents the number of students; then collect the art work data set Wd of each student i , Wd i =[Wd 1 ,Wd 2 ,...,Wd l ,...,Wd m ], where Wd l represents the lth art work of the ith student, and m represents the number of the ith student’s art works; Step 1.2: Based on the student dataset and the corresponding art dataset in step 1.1, obtain the painting theme and style dataset psd of each student's art work i , psd i =[(p,s) 1 ,(p,s) 2 ,...,(p,s) j ,...,(p,s) k ], where (P,S) j represents the jth painting theme and style of the i-th student.

3. According to the big data-based personalized art education customization system of claim 1, it is characterized by: The data analysis in the custom data analysis module for art education includes the following steps: Step 2: Analysis unit of students’ preference for art learning: Step 2.1: Based on step 1.2, obtain the painting theme and style dataset of each student's art works. Use big data technology to obtain the number of works of each painting theme and style for each student, and sort the painting theme and style dataset PSD according to the number from most to least. i , PSD i =[(p,s) 1 ,(p,s) 2 ,...,(p,s) J ,...,(p,s) K ],(p,s) J represents the J-th most common painting theme and style of the i-th student; Step 2.2: Based on step 1.2, obtain the painting theme and style dataset of each student's art work. Through big data analysis technology, obtain the average value avg of the test score of each painting theme and style from the art education student database. Use the average value as the quality evaluation index of each student's painting theme and style work, and sort the painting theme and style quality dataset WQD from the work quality evaluation index from large to small i , WQD(psd i )=[avg(p,s) 1 ,avg(p,s) 2 ,...,avg(p,s) I ,...,avg(p,s) N ], where avg(p,s) I represents the score of the work of the i-th student with the i-th painting theme and style; Step 2.3: Based on the number of works of each student for each painting theme and style obtained in step 2.1, first obtain the work completion time dataset TD (PSD) through timestamp technology i ),TD(PSD i )=[t(p,s) 1 ,t(p,s) 2 ,...,t(p,s) J ,...,t(p,s) K ], where t(p,s) J represents the cumulative completion time of the i-th student's J-th painting theme and style, and obtains the student's painting theme and style preference index PPI, Where n(p,s) J represents the number of works with the Jth most common painting theme and style, avg(p,s) I represents the score of the works of the i-th student's i-th painting theme and style, a1, a2 and a3 represent the weights of the proportion of works with a specific theme and style, the proportion of completion time and the proportion of work quality respectively; then, the painting theme and style of each student are sorted from large to small according to the preference index, and the sorted painting theme and style dataset S_PSD is obtained. i , S_PSD i =[(p,s) 1 ,(p,s) 2 ,...,(p,s) L ,...,(p,s) M ],(p,s) L The painting theme and style representing the Lth preference index.

4. According to the big data-based personalized art education customization system of claim 1, it is characterized by: The unit for analyzing the number of art learning difficulties for middle school students in the customized data analysis module for art education: based on the sorted painting theme and style data set obtained in step 2.3, first, according to each student's preferred painting theme and style, the total number of art education knowledge points KPT is listed in the curriculum outline and industry standards, and the knowledge points are first classified and then numbered; then, the learning management system is used to track the learning progress of the students under the preferred painting themes and styles, and the completion data of the works are obtained; finally, through the skill test results, the cosine similarity algorithm is used to traverse and analyze the similarity between the students' erroneous text content and the knowledge point list, and the knowledge point with the largest similarity is taken, and the number and type of knowledge points are counted to obtain the number DLN and classification number of the difficult knowledge points for each student's preferred painting theme and style, and obtain the art learning difficulty index LDI for each student. i , Among them, UNA represents the number of unfinished works, and T_A represents the total number of assignments.

5. According to the big data-based personalized art education customization system of claim 1, it is characterized by: The art course customization unit in the personalized art education customization module: based on the students' preferred painting themes and styles obtained in step 2.3, personalized course content is customized for each student through the art education resource database and in combination with the educational goals, and the course content customization index CCI is obtained, CCI = cn / sn, where cn represents the number of courses with preferred painting themes and styles, and sn represents the total number of courses based on educational goals.

6. According to the big data-based personalized art education customization system of claim 1, it is characterized by: The art education resource customization unit in the personalized art education customization module: based on the number of learning difficulties of each student's preferred painting themes and styles obtained in step 3, customize corresponding learning resources according to the learning difficulty knowledge points and classification numbers through the art education resource database, including personalized teaching methods and training work resources for the learning difficulty knowledge points, and obtain the art resource customization index ARI, ARI = lrn / T_lrn, where lrn represents the number of customized personalized resources, and T_lrn represents the total number of resources based on educational objectives.

7. The personalized art education customization system based on big data according to claim 1 is characterized by: The art project practice customization unit in the personalized art education customization module: based on the students' preferred painting themes and styles obtained in step 2.3 and the number of difficult knowledge points in learning the painting themes and styles preferred by each student obtained in step 3, customize the corresponding painting projects for each student, and obtain the project practice customization index PCI, PCI = cpn / T_cpn, where cpn represents the number of customized projects, and T_cpn represents the total number of projects based on educational objectives.

8. According to claim 1, a personalized art education customization system based on big data is characterized by: The personalized art education customization program effect evaluation index CEI in the personalized art education customization evaluation module is: Where cc represents the number of clicks on the students’ personalized recommended content, TC represents the total number of clicks by the students, nw(now) represents the number of personalized works currently created by the students, nw(bef) represents the number of personalized works at the previous evaluation time, s(now) represents the cumulative score of the current personalized works, s(bef) represents the cumulative score of the personalized works at the previous evaluation time, and c1, c2, and c3 represent the weights of the personalized content click-through rate, the personalized work creation efficiency, and the personalized work improvement rate, respectively.

Images