An adaptive smart education cloud platform
Through the design of the adaptive smart education cloud platform, the cloud knowledge base and multi-module collaborative work can be used to evaluate students' subject abilities and preferences, and generate the optimal educational resource plan, which solves the problem that cannot meet students' personalized needs in the existing technology. It realizes intelligent recommendation and career planning of educational resources.
Patent Information
- Application Number
- CN202411196167.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-08-29
AI Technical Summary
The existing smart education cloud platform lacks an effective feedback mechanism for student learning status, cannot analyze and predict students' own abilities, and is difficult to generate educational resource plans that meet students' own status, and cannot meet students' long-term development goals and learning career planning needs.
An adaptive smart education cloud platform was designed, including cloud knowledge base, capability assessment module, preference synchronization module, correlation evaluation module, personalized recommendation module and optimal educational resource screening module. By evaluating students' subject ability indicators and analyzing preferences Goals and educational changes, establish a personalized educational resource recommendation model, and generate the optimal educational resource plan.
It has realized intelligent recommendation of educational resources based on big data analysis, provided personalized educational resource planning, helped students to formulate long-term development goals and learning career plans, and improved the effectiveness of educational resource allocation.
Smart Images

Figure CN118710463B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of education recommendation, and in particular to an adaptive smart education cloud platform. Background Art
[0002] The existing teaching assistance cloud platform realizes synchronous teaching on the teacher and student sides through multimedia devices. However, the existing smart education cloud platform lacks an effective feedback mechanism for the learning status of the students, is unable to analyze and predict the students' own abilities, lacks consideration of external measures and factors, and is difficult to generate educational resource solutions that meet the students' own status. It cannot meet the needs of providing students with long-term development goals and learning career planning. Summary of the invention
[0003] In order to solve the above technical problems, an adaptive smart education cloud platform is provided. This technical solution solves the problem that the existing smart education cloud platform lacks an effective feedback mechanism for the learning status of the students, cannot analyze and predict the students' own abilities, lacks consideration of external measures and factors, and is difficult to generate educational resource solutions that meet the students' own status, and cannot meet the needs of providing students with long-term development goals and learning career planning.
[0004] In order to achieve the above purpose, the technical solution adopted by the present invention is:
[0005] An adaptive smart education cloud platform, comprising:
[0006] Cloud knowledge base, which contains all the knowledge data known in the current learning stage;
[0007] Ability assessment module, which is electrically connected to the cloud knowledge base. The ability assessment module is used to generate standard test questions corresponding to each subject based on the cloud knowledge base to evaluate students' ability indicators in each subject;
[0008] Preference synchronization module,The preference synchronization module is used to obtain students’ preference goals;
[0009] A relevance evaluation module, the relevance evaluation module is electrically connected to the ability evaluation module and the preference synchronization module, and the relevance evaluation module is used to analyze the relevance coefficient between the subject ability index of the student and the preference goal of the student based on the preference goal of the student;
[0010] A measure synchronization module, which is used to obtain real-time educational changes, including changes in the form of subject inspection and changes in the emphasis of subject inspection;
[0011] A personalized recommendation module, the personalized recommendation module is electrically connected to the ability assessment module, the relevance assessment module and the measure synchronization module, and the personalized recommendation module is used to establish a personalized education resource recommendation model based on the students' subject ability indicators, the correlation coefficient between the students' subject ability indicators and the students' preferred goals and the educational changes, and generate a number of education resource plans;
[0012] The optimal educational resource screening module is electrically connected to the personalized recommendation module. The optimal educational resource screening module is used to evaluate the benefit score of each educational resource plan based on several educational resource plans, and to sort and screen them to obtain the optimal educational resource plan.
[0013] Preferably, the capability assessment module includes:
[0014] The exercise generation unit generates exercises of different difficulty levels based on the syllabus and examination standard question framework of each subject;
[0015] The test unit conducts several rounds of tests on students using exercises of different difficulty levels in each subject, and calculates the correct rate of exercises of different difficulty levels;
[0016] Weighted units, based on the different difficulty types of exercises in each subject, assign corresponding weights to the exercises in each subject according to the difficulty type;
[0017] The ability assessment unit comprehensively assesses students' subject ability indicators based on the correct rate of exercises of different difficulty types in various subjects and the weight of each exercise in several rounds of tests;
[0018] Among them, the calculation expression of the student's subject ability index is:
[0019] ,
[0020] In the formula, is the ability index of the ith subject, is the correct rate of simple exercises in the ith subject, is the weight of simple type of exercises, is the correct rate of medium-type exercises in the ith subject, is the medium type of exercise weight, is the correct rate of difficult type exercises in the i-th subject, The weight of the difficult type of exercises.
[0021] Preferably, the relevance assessment module internally includes:
[0022] The visualization unit takes the students’ subject ability indicators and their preferred goals as associated variables and constructs a binary scatter plot between the growth values of the students’ subject ability indicators and their preferred goals;
[0023] The correlation calculation unit calculates the linear correlation coefficient between each subject ability indicator and the growth value of the preference target based on the binary scatter plot between the students' subject ability indicators and the preference target growth value, as the correlation coefficient between the students' subject ability indicators and the students' preference targets;
[0024] Wherein, the linear correlation coefficient calculation expression is:
[0025] ,
[0026] In the formula, is the correlation coefficient between the ability index of the i-th subject and the student’s preferred goal, In the scatter plot The subject ability indicators corresponding to the scattered points are is the preferred target growth value corresponding to the jth scatter point, and n is the total number of scatter points.
[0027] Preferably, the personalized recommendation module includes:
[0028] Model building unit, based on machine learning, builds a personalized education resource recommendation model;
[0029] The feature labeling unit takes the ability index of each student as the root node, determines the preference characteristics of each student, takes the preference characteristics of each student as the leaf node, and generates a personalized education resource recommendation model based on the student preference characteristics;
[0030] The condition restriction unit establishes the restriction conditions of education change based on the real-time education change;
[0031] The solution generation unit, based on the ability indicators of each subject of students, takes the correlation coefficient between the subject ability indicators of students and the preferred goals of students as the influencing factor under the restriction of educational changes, substitutes it into the personalized educational resource recommendation model of students' preference characteristics, and generates several educational resource solutions;
[0032] Among them, the personalized educational resource recommendation model expression of student preference characteristics is:
[0033] ,
[0034] In the formula, A collection of educational resource programs. Recommend model functions for personalized educational resources based on students’ preference characteristics, is the preference characteristic of the kth student, To change the constraints of education, is the weight coefficient of the i-th subject of the k-th student, is the impact factor of the ith discipline, is the ability index of the kth student in the ith subject, m is the total number of students, is the optimal solution function.
[0035] Preferably, the optimal educational resource screening module includes:
[0036] The educational resource capability quantification unit quantifies the comprehensive capability of each educational resource solution based on a number of educational resource solutions; the comprehensive capability of the educational resource solution refers to the potential development capability of the educational resource solution in terms of the optional professional direction;
[0037] A weighting unit assigns a weight to the comprehensive ability of each educational resource scheme according to the comprehensive ability of each educational resource scheme;
[0038] A benefit score calculation unit, which calculates the benefit score of each educational resource plan according to the comprehensive capabilities of each educational resource plan;
[0039] The comprehensive benefit scoring unit calculates the comprehensive benefit score of each educational resource plan based on the benefit score of each educational resource plan and the comprehensive capacity weight of each educational resource plan;
[0040] The sorting unit sorts and selects each educational resource plan according to its comprehensive benefit score to obtain the optimal educational resource plan;
[0041] Among them, the comprehensive benefit score of each educational resource plan is calculated as follows:
[0042] ,
[0043] In the formula, This is the first in the collection of educational resources The comprehensive benefit score of the educational resource program, This is the first in the collection of educational resources The comprehensive ability weight of the educational resource program, is the benefit score of the lth educational resource plan for the kth student in the set of educational resource plans.
[0044] Compared with the prior art, the present invention has the following beneficial effects:
[0045] The present invention proposes an intelligent recommendation scheme for educational resources based on big data analysis. By evaluating students' subject ability indicators and combining dynamic educational changes with students' own preferences, a personalized educational resource recommendation model is established. A comprehensive analysis is performed to generate the most suitable educational resource scheme for students, and the corresponding benefit score is evaluated for each educational resource scheme, and a positive ranking is performed. An auxiliary educational resource planning scheme is provided for students, and the possibility of long-term development goals and learning career planning is provided for each student. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 This is a framework diagram of an adaptive smart education cloud platform;
[0047] Figure 2 This is the internal framework diagram of the capability assessment module;
[0048] Figure 3 This is the internal framework diagram of the relevance assessment module;
[0049] Figure 4 This is the internal framework diagram of the personalized recommendation module:
[0050] Figure 5 This is the internal framework diagram of the optimal educational resource screening module. DETAILED DESCRIPTION
[0051] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.
[0052] Reference Figure 1 As shown, an adaptive smart education cloud platform includes:
[0053] Cloud knowledge base, which contains all the knowledge data known in the current learning stage;
[0054] Ability assessment module, which is electrically connected to the cloud knowledge base. The ability assessment module is used to generate standard test questions corresponding to each subject based on the cloud knowledge base to evaluate students' ability indicators in each subject;
[0055] Preference synchronization module,The preference synchronization module is used to obtain students’ preference goals;
[0056] A relevance evaluation module, the relevance evaluation module is electrically connected to the ability evaluation module and the preference synchronization module, and the relevance evaluation module is used to analyze the relevance coefficient between the subject ability index of the student and the preference goal of the student based on the preference goal of the student;
[0057] A measure synchronization module, which is used to obtain real-time educational changes, including changes in the form of subject inspection and changes in the emphasis of subject inspection;
[0058] A personalized recommendation module, the personalized recommendation module is electrically connected to the ability assessment module, the relevance assessment module and the measure synchronization module, and the personalized recommendation module is used to establish a personalized education resource recommendation model based on the students' subject ability indicators, the correlation coefficient between the students' subject ability indicators and the students' preferred goals and the educational changes, and generate a number of education resource plans;
[0059] The optimal educational resource screening module is electrically connected to the personalized recommendation module. The optimal educational resource screening module is used to evaluate the benefit score of each educational resource plan based on several educational resource plans, and to sort and screen them to obtain the optimal educational resource plan.
[0060] This program establishes a personalized education resource recommendation model by evaluating students' subject ability indicators, combining dynamic educational changes with students' own preferences, and comprehensively analyzing to generate the most suitable education resource plan for students. It also evaluates the corresponding benefit score for each education resource plan, performs positive sorting, and generates auxiliary education resource planning plans, providing students with the possibility of long-term development goals and learning career planning.
[0061] It is understandable that under the current measures, the professional enrollment method of colleges and universities takes into account the direction of students' educational resources. For example, if a student's preferred goal is to be a doctor, that is, when medical universities (colleges) in different provinces are faced with enrollment, the educational resources of Chinese, mathematics, English, Canada, physics, chemistry, and biology are the educational resource plans with the highest efficiency scores. However, considering the directionality of the preferred goal, that is, when there is a target school (college), the optimal educational resource plan for enrollment is the educational resource plan of the target school. Secondly, when students have no preferred goals, the most widely oriented educational resource plans are considered, namely Chinese, mathematics, English, Canada, physics, chemistry, and politics. Secondly, the educational resources with the strongest abilities can also be considered as the optimal educational resource plan.
[0062] Reference Figure 2 As shown, the capability assessment module includes:
[0063] The exercise generation unit generates exercises of different difficulty levels based on the syllabus and examination standard question framework of each subject;
[0064] The test unit conducts several rounds of tests on students using exercises of different difficulty levels in each subject, and calculates the correct rate of exercises of different difficulty levels;
[0065] Weighted units, based on the different difficulty types of exercises in each subject, assign corresponding weights to the exercises in each subject according to the difficulty type;
[0066] The ability assessment unit comprehensively assesses students' subject ability indicators based on the correct rate of exercises of different difficulty types in various subjects and the weight of each exercise in several rounds of tests;
[0067] Among them, the calculation expression of the student's subject ability index is:
[0068] ,
[0069] In the formula, is the capability index of the ith subject, is the correct rate of simple exercises in the ith subject, is the weight of simple type of exercises, is the correct rate of medium-type exercises in the ith subject, is the medium type of exercise weight, is the correct rate of difficult type exercises in the i-th subject, The weight of the difficult type of exercises.
[0070] Referring to 3, the relevance evaluation module includes:
[0071] The visualization unit takes the students’ subject ability indicators and their preferred goals as associated variables and constructs a binary scatter plot between the growth values of the students’ subject ability indicators and their preferred goals;
[0072] The correlation calculation unit calculates the linear correlation coefficient between each subject ability indicator and the growth value of the preference target based on the binary scatter plot between the students' subject ability indicators and the preference target growth value, as the correlation coefficient between the students' subject ability indicators and the students' preference targets;
[0073] Wherein, the linear correlation coefficient calculation expression is:
[0074] ,
[0075] In the formula, is the correlation coefficient between the ability index of the i-th subject and the student’s preferred goal, In the scatter plot The subject ability indicators corresponding to the scattered points are is the preferred target growth value corresponding to the jth scatter point, and n is the total number of scatter points.
[0076] It can be understood that the larger the correlation coefficient is, the greater the influence of the ability index of the current subject on the student's preference goal is, and the smaller the correlation coefficient is, the smaller the influence of the ability index of the current subject on the student's preference goal is. For example, when the student's preference goal is science, the correlation coefficient of the science ability index to the preference is the largest. Therefore, the growth value of the student's ability index and preference goal is analyzed to determine the importance of each subject.
[0077] Reference Figure 4 As shown, the personalized recommendation module includes:
[0078] Model building unit, based on machine learning, builds a personalized education resource recommendation model;
[0079] The feature labeling unit takes the ability index of each student as the root node, determines the preference characteristics of each student, takes the preference characteristics of each student as the leaf node, and generates a personalized education resource recommendation model based on the student preference characteristics;
[0080] The condition restriction unit establishes the restriction conditions of education change based on the real-time education change;
[0081] The solution generation unit, based on the ability indicators of each subject of students, takes the correlation coefficient between the subject ability indicators of students and the preferred goals of students as the influencing factor under the restriction of educational changes, substitutes it into the personalized educational resource recommendation model of students' preference characteristics, and generates several educational resource solutions;
[0082] Among them, the personalized educational resource recommendation model expression of student preference characteristics is:
[0083] ,
[0084] In the formula, A collection of educational resource programs. Recommend model functions for personalized educational resources based on students’ preference characteristics, is the preference characteristic of the kth student, To change the constraints of education, is the weight coefficient of the i-th subject of the k-th student, is the impact factor of the ith discipline, is the ability index of the kth student in the ith subject, m is the total number of students, is the optimal solution function.
[0085] By constructing a personalized education resource recommendation model based on student preference characteristics, students can be assisted to make more informed choices based on their preferences and strengths. Secondly, the currently implemented education changes are used as constraints to ensure that the recommended subject combinations meet the requirements of educational measures to improve the effectiveness of education resource allocation and promote the all-round development of each student.
[0086] Reference Figure 5 As shown, the optimal educational resource screening module includes:
[0087] The educational resource capability quantification unit quantifies the comprehensive capability of each educational resource solution based on a number of educational resource solutions; the comprehensive capability of the educational resource solution refers to the potential development capability of the educational resource solution in terms of the optional professional direction;
[0088] A weighting unit assigns a weight to the comprehensive ability of each educational resource scheme according to the comprehensive ability of each educational resource scheme;
[0089] A benefit score calculation unit, which calculates the benefit score of each educational resource plan according to the comprehensive capabilities of each educational resource plan;
[0090] The comprehensive benefit scoring unit calculates the comprehensive benefit score of each educational resource plan based on the benefit score of each educational resource plan and the comprehensive capacity weight of each educational resource plan;
[0091] The sorting unit sorts and selects each educational resource plan according to its comprehensive benefit score to obtain the optimal educational resource plan;
[0092] Among them, the comprehensive benefit score of each educational resource plan is calculated as follows:
[0093] ,
[0094] In the formula, This is the first in the collection of educational resources The comprehensive benefit score of the educational resource program, This is the first in the collection of educational resources The comprehensive ability weight of the educational resource program, is the benefit score of the lth educational resource plan for the kth student in the set of educational resource plans.
[0095] This solution provides a standardized method to help decision makers understand the impact of different choices on students' future development and find the best choice for students with specific conditions. By considering academic performance, personal development potential and market employment trends, etc., we can comprehensively evaluate the advantages and disadvantages of each educational resource combination, and sort and screen them accordingly to determine the optimal solution.
[0096] The usage process of an adaptive smart education cloud platform is as follows:
[0097] Step 1: The cloud knowledge base contains all the knowledge data known in the current learning stage;
[0098] Step 2: Generate exercises of different difficulty levels based on the syllabus and examination standard question framework of each subject;
[0099] Step 3: Conduct several rounds of tests on students on exercises of different difficulty levels in each subject, and calculate the correct rate of exercises of different difficulty levels;
[0100] Step 4: Based on the different difficulty types of exercises in each subject, assign corresponding weights to the exercises in each subject according to the difficulty type;
[0101] Step 5: Based on the correct rate of students' exercises of different difficulty levels in various subjects and the weight of each exercise in several rounds of tests, comprehensively evaluate students' subject ability indicators;
[0102] Step 6: Obtain students’ preferred goals;
[0103] Step 7: Take the students' subject ability indicators and their preferred goals as associated variables and construct a binary scatter plot between the growth values of the students' subject ability indicators and their preferred goals;
[0104] Step 8: Based on the bivariate scatter plot between the students' subject ability indicators and the growth value of their preferred goals, calculate the linear correlation coefficient between each subject ability indicator and the growth value of their preferred goals as the correlation coefficient between the students' subject ability indicators and their preferred goals;
[0105] Step 9: Obtain real-time education changes;
[0106] Step 10: Build a personalized education resource recommendation model based on machine learning;
[0107] Step 11: Take each student's ability index as the root node, determine each student's preference characteristics, take each student's preference characteristics as the leaf node, and generate a personalized education resource recommendation model based on student preference characteristics;
[0108] Step 12: Establishing education change restriction conditions based on real-time education changes;
[0109] Step 13: Based on the ability indicators of each subject of students, under the condition of educational change constraints, the correlation coefficient between the subject ability indicators of students and the preferred goals of students is used as an influencing factor, and substituted into the personalized educational resource recommendation model of students' preference characteristics to generate several educational resource plans;
[0110] Step 14: Based on several educational resource solutions, quantify the comprehensive capacity of each educational resource solution;
[0111] Step 15: assign weights to the comprehensive capabilities of each educational resource plan according to the comprehensive capabilities of each educational resource plan;
[0112] Step 16: The benefit scoring unit calculates the benefit score of each educational resource plan according to the comprehensive capability of each educational resource plan;
[0113] Step 17: Calculate the comprehensive benefit score of each education resource plan based on the benefit score of each education resource plan and the comprehensive capacity weight of each education resource plan;
[0114] Step 18: Sort and filter each educational resource plan according to its comprehensive benefit score to obtain the optimal educational resource plan.
[0115] In summary, the advantages of the present invention are: the above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may have various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention to be protected. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.
Claims
1. An adaptive smart education cloud platform, characterized in that: include: Cloud knowledge base, which contains all the knowledge data known in the current learning stage; Ability assessment module, which is electrically connected to the cloud knowledge base. The ability assessment module is used to generate standard test questions corresponding to each subject based on the cloud knowledge base to evaluate students' ability indicators in each subject; Preference synchronization module,The preference synchronization module is used to obtain students’ preference goals; A relevance evaluation module, the relevance evaluation module is electrically connected to the ability evaluation module and the preference synchronization module, and the relevance evaluation module is used to analyze the relevance coefficient between the subject ability index of the student and the preference goal of the student based on the preference goal of the student; A measure synchronization module, which is used to obtain real-time educational changes, including changes in the form of subject inspection and changes in the emphasis of subject inspection; A personalized recommendation module, the personalized recommendation module is electrically connected to the ability assessment module, the relevance assessment module and the measure synchronization module, and the personalized recommendation module is used to establish a personalized education resource recommendation model based on the students' subject ability indicators, the correlation coefficient between the students' subject ability indicators and the students' preferred goals and the educational changes, and generate a number of education resource plans; The optimal educational resource screening module is electrically connected to the personalized recommendation module. The optimal educational resource screening module is used to evaluate the benefit score of each educational resource scheme based on a number of educational resource schemes, and perform sorting and screening to obtain the optimal educational resource scheme; The relevance assessment module includes: The visualization unit takes the students’ subject ability indicators and their preferred goals as associated variables and constructs a binary scatter plot between the growth values of the students’ subject ability indicators and their preferred goals; The correlation calculation unit calculates the linear correlation coefficient between each subject ability indicator and the growth value of the preference target based on the binary scatter plot between the students' subject ability indicators and the preference target growth value, as the correlation coefficient between the students' subject ability indicators and the students' preference targets; The linear correlation coefficient calculation expression is: , In the formula, is the correlation coefficient between the ability index of the i-th subject and the student’s preferred goal, In the scatter plot The subject ability indicators corresponding to the scattered points are is the preferred target growth value corresponding to the jth scatter point, and n is the total number of scatter points; The personalized recommendation module includes: Model building unit, based on machine learning, builds a personalized education resource recommendation model; The feature labeling unit takes the ability index of each student as the root node, determines the preference characteristics of each student, takes the preference characteristics of each student as the leaf node, and generates a personalized education resource recommendation model based on the student preference characteristics; The condition restriction unit establishes the restriction conditions of education change based on the real-time education change; The solution generation unit, based on the ability indicators of each subject of students, takes the correlation coefficient between the subject ability indicators of students and the preferred goals of students as the influencing factor under the restriction of educational changes, substitutes it into the personalized educational resource recommendation model of students' preference characteristics, and generates several educational resource solutions; The expression of the personalized educational resource recommendation model based on student preference characteristics is: , In the formula, A collection of educational resource programs. Recommend model functions for personalized educational resources based on students’ preference characteristics, is the preference characteristic of the kth student, To change the constraints of education, is the weight coefficient of the i-th subject of the k-th student, is the impact factor of the ith discipline, is the ability index of the kth student in the ith subject, m is the total number of students, is the optimal solution function.
2. The adaptive smart education cloud platform according to claim 1, characterized in that: The capability assessment module includes: The exercise generation unit generates exercises of different difficulty levels based on the syllabus and examination standard question framework of each subject; The test unit conducts several rounds of tests on students using exercises of different difficulty levels in each subject, and calculates the correct rate of exercises of different difficulty levels; Weighted units, based on the different difficulty types of exercises in each subject, assign corresponding weights to the exercises in each subject according to the difficulty type; The ability assessment unit comprehensively assesses students' subject ability indicators based on the students' correct rate of exercises of different difficulty levels in various subjects and the weight of each exercise in several rounds of tests.
3. The adaptive smart education cloud platform according to claim 2, characterized in that: The calculation expression of the student's subject ability index is: , where is the ability index of the ith subject, is the correct rate of simple exercises in the ith subject, is the weight of simple type of exercises, is the correct rate of medium-type exercises in the ith subject, is the medium type of exercise weight, is the correct rate of difficult type exercises in the i-th subject, The weight of the difficult type of exercises.
4. The adaptive smart education cloud platform according to claim 3, characterized in that: The optimal educational resource screening module includes: The educational resource capability quantification unit quantifies the comprehensive capability of each educational resource solution based on a number of educational resource solutions; the comprehensive capability of the educational resource solution refers to the potential development capability of the educational resource solution in terms of the optional professional direction; A weighting unit assigns a weight to the comprehensive ability of each educational resource scheme according to the comprehensive ability of each educational resource scheme; A benefit score calculation unit, which calculates the benefit score of each educational resource plan according to the comprehensive capabilities of each educational resource plan; The comprehensive benefit scoring unit calculates the comprehensive benefit score of each educational resource plan based on the benefit score of each educational resource plan and the comprehensive capacity weight of each educational resource plan; The sorting unit sorts and screens each educational resource plan according to its comprehensive benefit score to obtain the optimal educational resource plan.
5. The adaptive smart education cloud platform according to claim 4, characterized in that: The comprehensive benefit score of each educational resource plan is calculated as follows: , In the formula, This is the first in the collection of educational resources The comprehensive benefit score of each educational resource plan, This is the first in the collection of educational resources The comprehensive ability weight of each educational resource program, is the benefit score of the lth educational resource plan for the kth student in the set of educational resource plans.
