Personalized learning planning analysis method based on beauty teaching

Abstract

The invention provides a personalized learning planning analysis method based on beauty teaching, and the method comprises the following steps: collecting multi-dimensional data, and constructing a multi-level comprehensive portrait; constructing a target library and a demand analysis model, obtaining a to-be-improved capability list, and customizing a learning target; designing a path planning algorithm, obtaining and adjusting an optimal path, and generating a personalized learning route map; performing multi-dimensional evaluation on the real-time learning condition data to obtain a learning condition deviation value, and judging whether a dynamic adjustment mechanism is automatically triggered or not; and carrying out acceptance and analysis on the learning achievements to obtain a learning achievement report, and carrying out optimization and adjustment on teacher teaching. According to the invention, the method can deeply analyze the conditions of students, lays a data foundation, achieves the precise customization and planning of learning targets and learning paths, achieves the accurate evaluation of learning conditions, dynamically adjusts teaching strategies, and improves the learning efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of aesthetic education teaching, and in particular to a personalized learning planning analysis method based on aesthetic education teaching. Background Art

[0002] Aesthetic education, as a crucial component of quality-oriented education, encompasses a wide range of fields, from traditional art forms like painting, music, and dance to comprehensive artistic expressions like literature, drama, and film, as well as aesthetic fields closely related to daily life, such as architecture and design. Within this diverse and rich world of aesthetic education, students' artistic interests vary greatly. Some are extremely sensitive to color and line, passionate about expressing their inner wonders through painting; others possess a unique sense of rhythm and melody. Students' developmental goals are equally diverse. Some hope to cultivate their aesthetic qualities through aesthetic education, enabling them to discern beauty in everyday life and enhance their quality of life; while others see art as a future career path, aspiring to cultivate a career in the field and become professional artists. Furthermore, students' personalities vary greatly. Some are outgoing and extroverted, excelling in stage performance-related aesthetic activities, while others are more reserved and prefer to pursue artistic creation in a quiet environment.

[0003] Based on the above differences between students, accurate personalized learning plans are crucial to improving the quality of aesthetic education. Personalized learning plans can fully respect and tap the unique artistic potential of each student, enabling them to find the most suitable development path for themselves in the process of aesthetic education, thereby greatly improving students' enthusiasm and initiative in participating in aesthetic education. At present, common methods of personalized learning planning for aesthetic education include teachers' judgments based on experience. With long-term teaching experience, teachers observe students' performance in class, homework completion, and daily communication with students to develop a rough learning plan for students. There are also questionnaires to understand students' interests, hobbies, learning goals and other information, and design personalized plans based on this. In addition, some institutions use intelligent assessment tools to evaluate students' artistic abilities from multiple dimensions, and then generate personalized learning suggestions.

[0004] However, these existing methods have many shortcomings. 1) Fuzzy paths: Traditional education methods lack precise planning for students' learning paths, and often use a "broad and general" approach to cover teaching content, ignoring individual differences. 2) Disconnection between goals and needs: There is no systematic method to link students' interests and career inclinations with teaching goals, which easily leads to ambiguity in the direction of training. 3) Large deviations in learning situation assessment: Traditional learning situation assessments often rely on the evaluation and scoring of teachers or students, which are highly subjective and often deviate greatly from the actual learning situation. There is a lack of a specific quantitative system for learning situation assessment, which affects learning progress. Summary of the Invention

[0005] In order to overcome the shortcomings of the existing technology, the purpose of the present invention is to provide a personalized learning planning analysis method based on aesthetic education teaching, which can deeply analyze the students' own situation to lay a data foundation, realize the precise customization and planning of learning goals and learning paths, accurately evaluate the learning situation, dynamically adjust teaching strategies, and improve learning efficiency.

[0006] To achieve the above objectives, the present invention provides the following solution: a personalized learning planning analysis method based on aesthetic education, comprising the following steps:

[0007] Collect multi-dimensional data and conduct interest analysis, ability analysis, behavior analysis, and background analysis based on the multi-dimensional data to generate a multi-level comprehensive portrait of the students;

[0008] Based on the teaching objectives, a goal library is constructed. Based on the student needs, a demand analysis model is constructed. The goal library is matched and mapped with the demand analysis model to obtain a list of abilities to be improved. Based on the list of abilities to be improved, learning objectives are customized.

[0009] Based on the multi-level comprehensive portrait, the learning goals and the aesthetic education resource database, a path planning algorithm is used to calculate the optimal route, and the optimal route is adjusted in combination with multi-dimensional factors to obtain a personalized learning roadmap;

[0010] According to predefined learning situation determination rules, a multi-dimensional evaluation is performed on the real-time learning situation data to obtain a learning situation deviation value, and it is determined whether the learning situation deviation value exceeds a preset deviation threshold. If so, the dynamic adjustment mechanism of the personalized learning roadmap is automatically triggered;

[0011] According to the preset achievement evaluation system, the learning achievements based on the personalized learning roadmap are inspected and analyzed to obtain a learning achievement report, and the teacher's teaching is optimized and adjusted based on the learning achievement report.

[0012] Optionally, collect multi-dimensional data and conduct interest analysis, ability analysis, behavior analysis, and background analysis based on the multi-dimensional data to generate a multi-level comprehensive profile of the student, including:

[0013] Collecting student self-evaluation data, teacher evaluation data, student interaction behavior data, and student implicit data to obtain multi-dimensional data, and processing and storing the multi-dimensional data; wherein the student implicit data includes family and social background and career tendency analysis;

[0014] Based on the student interaction behavior data, the TF-IDF algorithm is used to analyze and obtain the current interest preference; based on the teacher evaluation data and homework grading records, the student's technical ability is analyzed to obtain the ability label;

[0015] Mapping the weight distribution of the current interests and hobbies onto a two-dimensional or multi-dimensional interest map, and constructing an interest coordinate system with the current interests and hobbies and the ability labels as dimensions, and then statistically analyzing the student behavior and performance data to obtain behavioral characteristics and stage performance;

[0016] The student's implicit data is mined to obtain background information and implicit career tendencies, and then the student's basic information, the current interest preference, the ability label, the behavioral characteristics, the stage performance, the background information and the implicit career tendencies are combined to generate a multi-level comprehensive portrait.

[0017] Optionally, a goal library is constructed based on teaching objectives, and a demand analysis model is constructed based on student needs. The goal library and the demand analysis model are matched and mapped to obtain a list of abilities to be improved. Learning objectives are customized based on the list of abilities to be improved, including:

[0018] Decompose and layer the aesthetic education teaching objectives to obtain multiple sub-goals and hierarchical objectives, describe and define each sub-goal, and then build a goal library based on the sub-goals, the descriptions and definitions of the sub-goals, and the hierarchical objectives;

[0019] Collect student demand data, build a demand analysis model based on the student demand data to extract students' interests and ability shortcomings, and match the interests and ability shortcomings with the target library to obtain a list of abilities to be improved;

[0020] According to the list of abilities to be improved, the completion indicators of each sub-goal are defined, the customization of the learning goals is completed, and a student stage completion report is generated; the student stage completion report includes the target completion ratio and the visualization results of the current ability improvement.

[0021] Optionally, student demand data is collected and a demand analysis model is constructed based on the student demand data to extract student interests and ability shortcomings, and the student interests and ability shortcomings are matched and mapped with the target library. The list of abilities to be improved includes:

[0022] Collecting students' explicit needs from interest questionnaires, self-assessment forms, and teacher evaluation suggestions, and collecting students' implicit needs from the student interaction behavior data and homework performance evaluation data, and then structurally processing the students' explicit needs and the students' implicit needs to obtain student demand data;

[0023] Based on the student demand data, demand features are extracted, and the demand features are associated with the target library to obtain an interest heat map model. A collaborative filtering algorithm is used to infer the student's possible interest targets, and the student's interest points are obtained by combining the interest heat map model and the possible interest targets;

[0024] Construct a knowledge graph, automatically associate the student's interests with the target library, and complete interest-target matching mapping;

[0025] Analyze students' weaknesses based on test data and homework data, set priority recommendation rules based on the behavioral characteristics and the students' weaknesses, and then automatically associate the priority recommendation rules with the target library to complete the weak point-target matching mapping;

[0026] Combining the results of interest-goal matching mapping and weakness-goal matching mapping, a list of capabilities to be improved is obtained.

[0027] Optionally, based on the multi-level comprehensive portrait, the learning goals, and the aesthetic education resource database, a path planning algorithm is used to calculate the optimal route, and the optimal route is adjusted in combination with multi-dimensional factors to obtain a personalized learning roadmap, including:

[0028] Classify and integrate the multi-level comprehensive portrait, the learning objectives, and the aesthetic education resource database, and uniformly quantify the learning objectives and resource database according to difficulty, time requirement, and content structure to obtain an input data table consisting of a student status table, a goal table, and a resource table;

[0029] Combining a heuristic search algorithm and a genetic algorithm to obtain a path planning algorithm, inputting the input data table into the path planning algorithm for calculation to obtain an optimal route;

[0030] The optimal route is adjusted in combination with learning time, difficulty gradient, resource availability and the student's interests to obtain a personalized learning roadmap.

[0031] Optionally, the calculation expression of the optimal route is:

[0032]

[0033] Among them, P * is the optimal path, W(i,j) is the learning path weight from node i to node j, R(i) is the student's real-time interest offset value, E(i,j) is the historical learning progress efficiency, and ψ and φ are dynamic adjustment factors.

[0034] Optionally, a multi-dimensional evaluation is performed on the real-time learning situation data according to predefined learning situation determination rules to obtain a learning situation deviation value, and it is determined whether the learning situation deviation value exceeds a preset deviation threshold. If so, a dynamic adjustment mechanism of the personalized learning roadmap is automatically triggered, including:

[0035] In combination with tracking tools, the student interaction behavior data, the test data, the homework data, and the interest deviation data are collected to obtain real-time learning data, and the real-time learning data is cleaned and stored;

[0036] Defining learning progress lag conditions, interest transfer detection conditions, and learning difficulty assessment conditions to obtain learning situation determination rules. Based on the learning situation determination rules, performing a multi-dimensional assessment on the real-time learning situation data to obtain a learning situation deviation value.

[0037] Determine whether the learning situation deviation value exceeds a preset deviation threshold, and if so, automatically trigger the dynamic adjustment mechanism of the personalized learning roadmap.

[0038] Optionally, the learning progress lag condition is determined by constructing a progress target curve for matching actual progress with target progress to determine whether the homework submission lag rate exceeds 30% and whether the learning resource completion rate is less than 50%. If so, it is determined that the learning progress is lagging, and a learning lag score is calculated;

[0039] The interest transfer detection condition uses an interest heat map algorithm to determine whether the browsing weight of the target resource in the student's current path decreases by more than 30%. If so, it is determined to be an interest transfer and the interest change rate is calculated;

[0040] The learning difficulty assessment criteria are determined by judging whether the test score is lower than the minimum standard of the target skill and whether the time it takes for the student to complete the practice task exceeds 150% of the preset time. If so, it is determined to be a learning difficulty and a learning difficulty score is calculated.

[0041] Optionally, the calculation expression of the learning lag score is:

[0042] P delay =w h ·R h +w r ·(1-C r )

[0043] Among them, P delay is the learning lag score, R h is the delayed submission rate, C r is the completion of learning resources, w h 、w r All are dynamic weights;

[0044] The calculation expression of the interest change rate is:

[0045]

[0046] Among them, I change is the interest change rate, W prev is the historical browsing weight, W curr is the current browsing weight;

[0047] The calculation expression of the learning difficulty score is:

[0048]

[0049] Among them, D difficulty is the learning difficulty score, S is the test score, T actual is the actual practice time, T expected Estimated practice time

[0050] The calculation expression of the learning situation deviation value is:

[0051] D total =w p ·P delay +w i I change +w d ·D difficulty

[0052] Among them, D total is the learning deviation value, w p 、w i 、w d All are dynamic weights.

[0053] Optionally, based on a preset achievement evaluation system, the learning achievements based on the personalized learning roadmap are inspected and analyzed to obtain a learning achievement report. Based on the learning achievement report, the teacher's teaching is optimized and adjusted, including:

[0054] Define dynamic evaluation indicators including basic and personalized dimensions, and collect knowledge learning outcomes and skill learning outcomes based on the personalized learning roadmap; the basic dimensions include knowledge mastery and task completion rate, the personalized dimensions include learning efficiency, interest participation, and ability expansion, the knowledge learning outcomes include test data and homework accuracy, and the skill learning outcomes include practice time and learning speed;

[0055] Integrate learning outcomes to obtain a learning outcome report, extract student weaknesses and points of interest from the learning outcome report, combine the extracted weaknesses and points of interest, and use a genetic algorithm or a multi-objective optimization algorithm to optimize and adjust teaching.

[0056] The present invention provides a personalized learning planning analysis method based on aesthetic education, which discloses the following technical effects:

[0057] 1. In-depth, multi-factor analysis of students' personal circumstances: This platform collects data on students' personality traits, interests, artistic foundation, professional focus, and periodic learning performance (which can be derived from self-assessment questionnaires, teacher evaluations, platform logs, etc.). This data is combined with "implicit information" such as their life background, cultural characteristics, and career aspirations to construct a comprehensive profile of the student, laying a precise data foundation for planning solutions.

[0058] 2. Precise customization of learning objectives: Ability to decompose aesthetic education teaching objectives into small, actionable goals and subtasks, reduce students' learning pressure, and enhance their sense of achievement. Through correlation analysis, hidden needs (such as expanding interest boundaries), points of interest and weaknesses are found, and a list of areas for improvement is obtained, thus achieving precise customization of learning objectives.

[0059] 3. Accurate learning path planning: Using heuristic search and genetic algorithms, we comprehensively consider time, difficulty, and available resources to generate optimal or near-optimal paths, avoiding duplication and inefficient paths. We also comprehensively consider multiple factors such as interest, time, and difficulty to generate highly personalized learning paths.

[0060] 4. Accurate Assessment and Dynamic Adjustment of Learning Status: This system monitors students' progress according to their learning plans, comprehensively assessing and quantifying their learning status in real time based on factors such as learning progress, interest shifts, and learning difficulties, allowing for accurate assessment of their learning status. It also provides comprehensive evaluation of learning outcomes by setting multiple evaluation indicators, helping to better identify weaknesses and areas of interest during the current learning phase, optimize teaching, improve the efficiency of aesthetic learning, and enhance the flexibility and adaptability of teaching.

[0061] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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.

[0063] Figure 1 A schematic diagram of a method flow chart provided by an embodiment of the present invention;

[0064] Figure 2 A schematic diagram of the process of constructing a portrait provided by an embodiment of the present invention;

[0065] Figure 3A schematic diagram of the learning route planning process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0067] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0068] like Figure 1 As shown, the present invention provides a personalized learning planning analysis method based on aesthetic education teaching, comprising the following steps:

[0069] 1. If Figure 2 As shown, we collect multi-dimensional data and conduct interest analysis, ability analysis, behavior analysis, and background analysis based on the multi-dimensional data to generate a multi-level comprehensive portrait of the students. This includes:

[0070] 1.1 Collect student self-evaluation data, teacher evaluation data, student interaction behavior data and student implicit data to obtain multi-dimensional data, and process and store the multi-dimensional data; wherein, the student implicit data includes family and social background and career tendency analysis.

[0071] Student self-assessment data: Online questionnaire tools (such as Google Forms and Wenjuanxing) are embedded in the platform to design self-assessment questionnaires that indicate students' interests, goals, and artistic preferences. Examples include areas of interest (e.g., painting, music, dance), skill self-assessment (e.g., "I am good at sketching"), and goal statements (e.g., "I hope to become a designer in the future").

[0072] Teacher evaluation: Teachers’ evaluation data for students, covering dimensions such as technical ability and creative performance. Collect student feedback on their performance in class (communication, problem awareness, etc.).

[0073] Student interaction behavior data (platform interaction logs): browsing time, learning path, interaction frequency (such as number of questions asked), completion and quality of submitted assignments. Behavioral data collection is achieved through tracking tools (such as Mixpanel and Google Analytics).

[0074] Implicit data: Family and social background, including information on the student's region and cultural characteristics (such as ethnic artistic interests). Career orientation analysis involves students completing a questionnaire about their future artistic career plans, which is systematically recorded and structured.

[0075] 1.2 Based on the student interaction behavior data, the TF-IDF algorithm is used (to extract frequently encountered content feature keywords) to analyze and obtain current interest preferences. Based on the teacher evaluation data and homework grading records, the student's technical ability is analyzed to obtain ability labels. For example, if the sketching score is outstanding, a "strong sketching ability" label is generated.

[0076] 1.3 Map the weight distribution of the current interests and hobbies onto a two-dimensional or multi-dimensional interest map, and construct an interest coordinate system with the current interests and hobbies and the ability labels as dimensions. Then, statistically analyze the student behavior and performance data to obtain behavioral characteristics (initiative, high-frequency questioning / discussion) and stage-by-stage performance (changing trends in learning behavior, and the duration of practice from stable growth to leapfrog progress).

[0077] 1.4 Mining the student's implicit data to obtain background information and implicit career tendencies, and then combining the student's basic information, the current interest preferences, the ability labels, the behavioral characteristics, the stage performance, the background information and the implicit career tendencies to generate a multi-level comprehensive portrait.

[0078] Background information: Regional culture and the arts. For example, minority students may show a greater interest in folk dance and music. Family arts resources: whether the student has access to private tutors or art communities.

[0079] Implicit Career Preference: This method extracts implicit career preferences based on the influence of parents' occupations and the student's stated career path. For example, if 75% of the family members have art-related careers, the career preference weighting will shift toward "art and design."

[0080] Multi-level comprehensive portrait:

[0081] Basic information layer: age, grade, and gender.

[0082] Interest feature layer: interest areas (such as music, dance), activity level, and course preferences.

[0083] Aptitude layer: Skill point scoring labels (such as "Composition skills: 80 / 100").

[0084] Background layer: region, cultural characteristics, and family environment.

[0085] Career direction layer: career orientation labels and matching degree

[0086] Personalized characteristics mainly refer to the personality characteristics of students, that is, psychological characteristics. Psychological characteristic analysis includes: ability difference characteristics, personality difference characteristics (differences in character, temperament, attitude, such as volatility, stability, extroversion, introversion, etc.), interest characteristics, cognitive development characteristics, emotional and emotional characteristics, will quality characteristics, social adaptability characteristics, and sexual psychological development characteristics), so as to more accurately customize learning plans according to students' personalities.

[0087] Based on the above, the individual characteristics of students generally include:

[0088] Learning styles: visual, auditory, kinesthetic, etc.

[0089] Interests: preference for painting, music, dancing, etc.

[0090] Knowledge mastery, ability strengths and weaknesses.

[0091] Behavioral habits, learning frequency, interactive activity, time to complete homework, etc.

[0092] We provide tailored instruction based on individual student characteristics, helping students leverage their strengths and mitigate weaknesses, addressing shortcomings, exploring their potential, interests, and areas of strength, enhancing their confidence, and dynamically adjusting teaching methods to improve teaching effectiveness and student satisfaction. We also provide real-time monitoring and early warning of learning issues to assist teachers in management.

[0093] 2. If Figure 3 As shown, based on the teaching objectives, a target library is constructed, and based on the student needs, a demand analysis model is constructed. The target library is matched and mapped with the demand analysis model to obtain a list of abilities to be improved, and learning objectives are customized based on the list of abilities to be improved. This includes:

[0094] 2.1 Decompose and stratify the aesthetic education teaching objectives to obtain multiple sub-goals and hierarchical goals, and describe and define each sub-goal.

[0095] The sub-goals mainly include:

[0096] Skill points: Specific artistic expression skills, such as sketching techniques, color matching ability, and vocal training.

[0097] Knowledge points: Background knowledge of art theories and art schools, such as the characteristics of Renaissance painting.

[0098] Artistic aesthetic point: students' ability to perceive works and aesthetic expression of personal style.

[0099] Target stratification:

[0100] Basic Goal (suitable for beginners): Master basic skills and tool usage, such as introductory sketching and line drawing, or basic music beat control.

[0101] Advanced goals (suitable for the expansion stage): such as being able to imitate artistic creations of a specific style and understanding the cultural background behind the creations.

[0102] Advanced goal (for professional learning): Integrate multiple skills to complete original works of art, such as personal performances and independent design projects.

[0103] Then, based on the sub-goals, the descriptions and definitions of the sub-goals, and the hierarchical goals, a goal library is constructed, as shown in Table 1 below:

[0104] Table 1 Target library

[0105]

[0106] 2.2 Collect student demand data, build a demand analysis model based on the student demand data to extract students' interests and ability shortcomings, and match the interests and ability shortcomings with the target library to obtain a list of abilities to be improved. This includes:

[0107] 2.2.1 Collect students' explicit needs from interest questionnaires, self-assessment forms (career planning, interest preference data) and teacher evaluation suggestions, collect students' implicit needs from the student interaction behavior data and homework performance evaluation data, and then structure the students' explicit needs and the students' implicit needs to obtain student demand data.

[0108] 2.2.2 Based on the student demand data, demand features are extracted and associated with the target library to obtain an interest heat map model. A collaborative filtering algorithm is used to infer students' possible interest targets (infer the current students' possible learning needs from the past learning goals of students with similar profiles). The interest heat map model and the possible interest targets are combined to obtain students' interest points.

[0109] Interest heat map models such as:

[0110] Row: Student portrait (interest tags, behavioral characteristics).

[0111] Column: Labels in the target library, such as "Basics of Painting" and "High-Difficulty Techniques".

[0112] Output: The degree to which each student matches each type of learning objective.

[0113] 2.2.3 Build a knowledge graph, automatically associate the student's interests with the target library, and complete interest-target matching mapping;

[0114] 2.2.4 Analyze students' weaknesses based on test data and homework data, set priority recommendation rules based on the behavioral characteristics and the student's weaknesses, and then automatically associate the priority recommendation rules with the target library to complete the weak point-target matching mapping;

[0115] 2.2.5 Combine the results of interest-goal matching mapping and weakness-goal matching mapping to obtain a list of capabilities to be improved.

[0116] Examples of competence tables to be improved include:

[0117] Student A, extracts demand analysis from the portrait:

[0118] Interests: Painting (50%), Music (30%), Film and Television Editing (20%)

[0119] Weak skills: light and shadow expression, line expression

[0120] Recommended objectives: 1) Basics of Sketching (skill points) - Course a, 2) Analysis of light and shadow contrast in artworks (artistic aesthetic points) - Special Lecture b.

[0121] 2.3 Based on the list of abilities to be improved, define the completion indicators for each sub-goal, complete the customization of the learning goals, and generate a student's stage-by-stage completion report; the student's stage-by-stage completion report includes the goal completion ratio and the visualization results of the current ability improvement.

[0122] 3. If Figure 3 As shown, based on the multi-level comprehensive portrait, the learning goals and the aesthetic education resource database, the path planning algorithm is used to calculate the optimal route, and the optimal route is adjusted in combination with multi-dimensional factors to obtain a personalized learning roadmap. It includes:

[0123] 3.1 Classify and integrate the multi-level comprehensive portrait (interest tendency, learning stage, current skills and shortcomings), the learning objectives (skill points, knowledge points, artistic aesthetic points) and the aesthetic education resource database (courses, practice materials, project tasks, etc.), and uniformly quantify the learning objectives and resource database according to difficulty, time requirements and content structure to obtain an input data table consisting of a student status table, a goal table and a resource table.

[0124] Difficulty (1-5): calculated based on target complexity and resource level;

[0125] Time requirement (minutes): Estimate the standard completion time based on the number of resources;

[0126] Student status table: skill proficiency, performance, and stage goals;

[0127] Target table: time required, difficulty and achievement criteria corresponding to target skill points;

[0128] Resource table: includes the learning time, content classification, teacher evaluation resources and availability information of the course resources (such as video size and whether loading timeout occurs).

[0129] 3.2 Combining the heuristic search algorithm and the genetic algorithm, a path planning algorithm is obtained. The input data table is input into the path planning algorithm for calculation to obtain the optimal route. The calculation expression of the optimal route is:

[0130]

[0131] Among them, P * is the optimal path, W(i,j) is the learning path weight from node i to node j, R(i) is the student's real-time interest offset value, E(i,j) is the historical learning progress efficiency, and ψ and φ are dynamic adjustment factors.

[0132] 3.3 The optimal route is adjusted based on the learning time, difficulty level, resource availability, and student interests to obtain a personalized learning roadmap.

[0133] Learning roadmap example:

[0134] Learning Path:

[0135] 1) Improving drawing perspective skills → Course X;

[0136] 2) Layered color matching → Workshop Y;

[0137] 3) Imitating Renaissance painting → Video Z;

[0138] Time needed: 15 hours.

[0139] 4. According to the predefined learning situation judgment rules, a multi-dimensional evaluation is performed on the real-time learning situation data to obtain the learning situation deviation value, and it is determined whether the learning situation deviation value exceeds the preset deviation threshold. If so, the dynamic adjustment mechanism of the personalized learning roadmap is automatically triggered. Including:

[0140] 4.1 Combined with tracking tools (such as Google Analytics or Mixpanel), collect the student interaction behavior data, the test data, homework data and interest deviation data to obtain real-time learning data, and clean and store the real-time learning data.

[0141] 4.2 Define the learning progress lag conditions, interest transfer detection conditions and learning difficulty assessment conditions to obtain learning situation determination rules. Based on the learning situation determination rules, perform a multi-dimensional evaluation of the real-time learning situation data to obtain the learning situation deviation value.

[0142] The learning progress lag condition is determined by constructing a progress target curve for matching actual progress with target progress to determine whether the homework submission lag rate exceeds 30% and whether the learning resource completion rate is less than 50%. If so, it is determined that the learning progress is lagging, and a learning lag score is calculated. The calculation expression of the learning lag score is:

[0143] P delay =w h ·R h +w r ·(1-C r )

[0144] Among them, P delay is the learning lag score (>0.7 is considered as learning progress lag), R h is the delayed submission rate, C r is the completion of learning resources, w h 、w r All are dynamic weights.

[0145] The interest transfer detection condition uses the interest heat map algorithm to determine whether the target resource browsing weight of the student's current path has dropped by more than 30%. If so, it is determined to be an interest transfer and the interest change rate is calculated; the calculation expression of the interest change rate is:

[0146]

[0147] Among them, I change is the interest change rate (>30% is considered as interest transfer), W prev is the historical browsing weight, W curr The current browsing weight.

[0148] The learning difficulty assessment criteria are determined by judging whether the test score is lower than the minimum standard of the target skill and whether the time it takes for the student to complete the practice task exceeds 150% of the preset time. If so, it is determined to be learning difficulty and a learning difficulty score is calculated. The calculation expression of the learning difficulty score is:

[0149]

[0150] Among them, D difficulty is the learning difficulty score (>0.8 is considered as learning difficulty), S is the test score, T actual is the actual practice time, T expected Estimated practice time.

[0151] 4.3 Determine whether the learning situation deviation value exceeds a preset deviation threshold. If so, automatically trigger the dynamic adjustment mechanism of the personalized learning roadmap.

[0152] The calculation expression of the learning situation deviation value is:

[0153] D total =w p ·P delay +w i I change +w d ·D difficulty

[0154] Among them, D total is the learning deviation value, w p 、w i 、w d Are dynamic weights, when P delay >0.7, improve w p , when I change >30%, improve w i , when D difficulty >0.8, improve w d .

[0155] 5. According to the preset achievement evaluation system, the learning achievements based on the personalized learning roadmap are inspected and analyzed to obtain a learning achievement report. Based on the learning achievement report, the teacher's teaching is optimized and adjusted. Including:

[0156] 5.1 Define dynamic evaluation indicators, including basic and personalized dimensions, and collect knowledge and skill learning outcomes based on the personalized learning roadmap. The basic dimensions (common to all students) include knowledge mastery and task completion rate, and the personalized dimensions (specific to student profiles) include learning efficiency, interest engagement, and ability expansion. Knowledge learning outcomes include test data and assignment accuracy, and skill learning outcomes include practice time and learning speed.

[0157] 5.2 Integrate the learning outcomes to obtain a learning outcome report, extract the students' weaknesses and interests in the learning outcome report, and optimize and adjust the teaching by combining the extracted weaknesses and interests with a genetic algorithm or a multi-objective optimization algorithm.

[0158] In summary, the present invention can automatically generate personalized teaching strategies based on the analysis results of learning insights. For example, for students who are weak in painting composition but have keen color perception, the system will give priority to pushing courses on composition principles, with targeted composition practice tasks, and recommend extended learning resources related to color matching to strengthen their advantages while making up for their shortcomings. In terms of teaching progress arrangement, the course difficulty and advancement rhythm are flexibly adjusted according to the students' learning speed and ability, providing advanced content for students with strong learning ability, and providing more basic consolidation links and tutoring resources for students with learning difficulties, truly realizing teaching students in accordance with their aptitude.

[0159] Therefore, the present invention provides a personalized learning planning analysis method based on aesthetic education, which can deeply analyze students' own situation to lay a data foundation, realize the precise customization and planning of learning goals and learning paths, accurately evaluate the learning situation, dynamically adjust teaching strategies, and improve learning efficiency.

[0160] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0161] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A personalized learning planning analysis method based on aesthetic education, characterized by: The following steps are involved: Collect multi-dimensional data and conduct interest analysis, ability analysis, behavior analysis, and background analysis based on the multi-dimensional data to generate a multi-level comprehensive portrait of the students; Based on the teaching objectives, a goal library is constructed. Based on the student needs, a demand analysis model is constructed. The goal library is matched and mapped with the demand analysis model to obtain a list of abilities to be improved. Based on the list of abilities to be improved, learning objectives are customized. Based on the multi-level comprehensive portrait, the learning goals and the aesthetic education resource database, a path planning algorithm is used to calculate the optimal route, and the optimal route is adjusted in combination with multi-dimensional factors to obtain a personalized learning roadmap; According to predefined learning situation determination rules, a multi-dimensional evaluation is performed on the real-time learning situation data to obtain a learning situation deviation value, and it is determined whether the learning situation deviation value exceeds a preset deviation threshold. If so, the dynamic adjustment mechanism of the personalized learning roadmap is automatically triggered; According to the preset achievement evaluation system, the learning achievements based on the personalized learning roadmap are inspected and analyzed to obtain a learning achievement report, and the teacher's teaching is optimized and adjusted based on the learning achievement report.

2. The method for analyzing personalized learning plans based on aesthetic education according to claim 1, characterized in that: Collect multi-dimensional data and conduct interest analysis, ability analysis, behavior analysis, and background analysis based on the multi-dimensional data to generate a multi-level comprehensive portrait of the student, including: Collecting student self-evaluation data, teacher evaluation data, student interaction behavior data, and student implicit data to obtain multi-dimensional data, and processing and storing the multi-dimensional data; wherein the student implicit data includes family and social background and career tendency analysis; Based on the student interaction behavior data, the TF-IDF algorithm is used to analyze and obtain the current interest preference; based on the teacher evaluation data and homework grading records, the student's technical ability is analyzed to obtain the ability label; Mapping the weight distribution of the current interests and hobbies onto a two-dimensional or multi-dimensional interest map, and constructing an interest coordinate system with the current interests and hobbies and the ability labels as dimensions, and then statistically analyzing the student behavior and performance data to obtain behavioral characteristics and stage performance; The student's implicit data is mined to obtain background information and implicit career tendencies, and then the student's basic information, the current interest preference, the ability label, the behavioral characteristics, the stage performance, the background information and the implicit career tendencies are combined to generate a multi-level comprehensive portrait.

3. The method for analyzing personalized learning planning based on aesthetic education according to claim 2, characterized in that: Based on the teaching objectives, a goal library is constructed. Based on the student needs, a demand analysis model is constructed. The goal library is matched and mapped with the demand analysis model to obtain a list of abilities to be improved. Based on the list of abilities to be improved, learning objectives are customized, including: Decompose and layer the aesthetic education teaching objectives to obtain multiple sub-goals and hierarchical objectives, describe and define each sub-goal, and then build a goal library based on the sub-goals, the descriptions and definitions of the sub-goals, and the hierarchical objectives; Collect student demand data, build a demand analysis model based on the student demand data to extract students' interests and ability shortcomings, and match the interests and ability shortcomings with the target library to obtain a list of abilities to be improved; According to the list of abilities to be improved, the completion indicators of each sub-goal are defined, the customization of the learning goals is completed, and a student stage completion report is generated; the student stage completion report includes the target completion ratio and the visualization results of the current ability improvement.

4. The method for analyzing personalized learning plans based on aesthetic education according to claim 3, characterized in that: Collect student demand data, build a demand analysis model based on the student demand data to extract student interests and ability shortcomings, and match and map the student interests and ability shortcomings with the target library. The list of abilities to be improved includes: Collecting students' explicit needs from interest questionnaires, self-assessment forms, and teacher evaluation suggestions, and collecting students' implicit needs from the student interaction behavior data and homework performance evaluation data, and then structurally processing the students' explicit needs and the students' implicit needs to obtain student demand data; Based on the student demand data, demand features are extracted, and the demand features are associated with the target library to obtain an interest heat map model. A collaborative filtering algorithm is used to infer the student's possible interest targets, and the student's interest points are obtained by combining the interest heat map model and the possible interest targets; Construct a knowledge graph, automatically associate the student's interests with the target library, and complete interest-target matching mapping; Analyze students' weaknesses based on test data and homework data, set priority recommendation rules based on the behavioral characteristics and the students' weaknesses, and then automatically associate the priority recommendation rules with the target library to complete the weak point-target matching mapping; Combining the results of interest-goal matching mapping and weakness-goal matching mapping, a list of capabilities to be improved is obtained.

5. The method for analyzing personalized learning plans based on aesthetic education according to claim 4, characterized in that: Based on the multi-level comprehensive portrait, the learning goals, and the aesthetic education resource database, a path planning algorithm is used to calculate the optimal route. The optimal route is adjusted based on multi-dimensional factors to obtain a personalized learning roadmap, including: Classify and integrate the multi-level comprehensive portrait, the learning objectives, and the aesthetic education resource database, and uniformly quantify the learning objectives and resource database according to difficulty, time requirement, and content structure to obtain an input data table consisting of a student status table, a goal table, and a resource table; Combining a heuristic search algorithm and a genetic algorithm to obtain a path planning algorithm, inputting the input data table into the path planning algorithm for calculation to obtain an optimal route; The optimal route is adjusted in combination with learning time, difficulty gradient, resource availability and the student's interests to obtain a personalized learning roadmap.

6. The method for analyzing personalized learning plans based on aesthetic education according to claim 5, characterized in that: The calculation expression of the optimal route is: Among them, P * is the optimal path, W(i,j) is the learning path weight from node i to node j, R(i) is the student's real-time interest offset value, E(i,j) is the historical learning progress efficiency, and ψ and φ are dynamic adjustment factors.

7. The method for analyzing personalized learning plans based on aesthetic education according to claim 6, characterized in that: According to predefined learning situation determination rules, a multi-dimensional evaluation is performed on the real-time learning situation data to obtain a learning situation deviation value, and it is determined whether the learning situation deviation value exceeds a preset deviation threshold. If so, the dynamic adjustment mechanism of the personalized learning roadmap is automatically triggered, including: In combination with tracking tools, the student interaction behavior data, the test data, the homework data, and the interest deviation data are collected to obtain real-time learning data, and the real-time learning data is cleaned and stored; Defining learning progress lag conditions, interest transfer detection conditions, and learning difficulty assessment conditions to obtain learning situation determination rules. Based on the learning situation determination rules, performing a multi-dimensional assessment on the real-time learning situation data to obtain a learning situation deviation value. Determine whether the learning situation deviation value exceeds a preset deviation threshold, and if so, automatically trigger the dynamic adjustment mechanism of the personalized learning roadmap.

8. The method for analyzing personalized learning plans based on aesthetic education according to claim 7, characterized in that: The learning progress lag condition is determined by constructing a progress target curve for matching actual progress with target progress to determine whether the homework submission lag rate exceeds 30% and whether the learning resource completion rate is less than 50%. If so, it is determined that the learning progress is lagging, and a learning lag score is calculated; The interest transfer detection condition uses an interest heat map algorithm to determine whether the browsing weight of the target resource in the student's current path decreases by more than 30%. If so, it is determined to be an interest transfer and the interest change rate is calculated; The learning difficulty assessment criteria are determined by judging whether the test score is lower than the minimum standard of the target skill and whether the time it takes for the student to complete the practice task exceeds 150% of the preset time. If so, it is determined to be a learning difficulty and a learning difficulty score is calculated.

9. The method for analyzing personalized learning plans based on aesthetic education according to claim 8, characterized in that: The calculation expression of the learning lag score is: P delay =w h ·R h +w r ·(1-C r ) Among them, P delay is the learning lag score, R h is the delayed submission rate, C r is the completion of learning resources, w h 、w r All are dynamic weights; The calculation expression of the interest change rate is: Among them, I change is the interest change rate, W prev is the historical browsing weight, W curr is the current browsing weight; The calculation expression of the learning difficulty score is: Among them, D difficulty is the learning difficulty score, S is the test score, T actual is the actual practice time, T expected Estimated practice time The calculation expression of the learning situation deviation value is: D total =w p ·P delay +w i ·I change +w d ·D difficulty Among them, D total is the learning deviation value, w p 、w i 、w d All are dynamic weights.

10. The method for analyzing personalized learning plans based on aesthetic education according to claim 9, characterized in that: According to the preset achievement evaluation system, the learning achievements based on the personalized learning roadmap are inspected and analyzed to obtain a learning achievement report. Based on the learning achievement report, the teacher's teaching is optimized and adjusted, including: Define dynamic evaluation indicators including basic and personalized dimensions, and collect knowledge learning outcomes and skill learning outcomes based on the personalized learning roadmap; the basic dimensions include knowledge mastery and task completion rate, the personalized dimensions include learning efficiency, interest participation, and ability expansion, the knowledge learning outcomes include test data and homework accuracy, and the skill learning outcomes include practice time and learning speed; Integrate learning outcomes to obtain a learning outcome report, extract student weaknesses and points of interest from the learning outcome report, combine the extracted weaknesses and points of interest, and use a genetic algorithm or a multi-objective optimization algorithm to optimize and adjust teaching.

Images