CN117830042A - Learning power evaluation system based on AI (advanced technology attachment) for student personalized data analysis - Google Patents

Abstract

The invention relates to the technical field of data analysis and processing, and discloses a learning power assessment method and a learning power assessment system based on AI (advanced technology) for personalized data analysis of students, wherein the system comprises a learning power assessment data acquisition module, a learning power and learning power parameter processing module, a learning power parameter and learning power analysis processing module; classifying the acquired learning power test keywords according to personal targets, specific industry fields and national targets and calculating the duty ratio of the acquired learning power test keywords, so that the classification and quantification of the learning power keywords are realized, the learning power keywords with the largest duty ratio value are screened and matched with an AI intelligent recognition algorithm to carry out learning power score calculation, and the accurate measurement and analysis of the learning power of students are realized; and (3) carrying out numerical comparison by utilizing the ratio of the learning time of the students meeting the specified state to the total learning perseverance test time, and intuitively and quantitatively measuring the learning perseverance result of the students.

Description

A learning ability assessment system based on AI for personalized data analysis of students

Technical Field

The present invention relates to the technical field of data analysis and processing, and specifically to a learning ability assessment method and system based on AI for personalized data analysis of students.

Background technique

Learning power is the three elements of learning motivation, learning perseverance and learning ability. Learning power refers to the comprehensive manifestation of the motivation, perseverance and ability of a person, an enterprise or an organization to learn. Learning power is the ability to transform knowledge resources into knowledge capital. Learning power refers to the comprehensive manifestation of the motivation, perseverance and ability of a person, an enterprise or an organization to learn. Learning power is the ability to transform knowledge resources into knowledge capital. The learning power of an individual not only includes the total amount of knowledge, that is, the breadth of personal learning content and the degree of openness of the organization and the individual; it also includes the quality of knowledge, that is, the comprehensive quality, learning efficiency and learning quality of the learner; it also includes its learning flow, that is, the speed of learning and the ability to absorb and expand knowledge; more importantly, it looks at its knowledge increment, that is, the degree of innovation of learning results and the degree to which learners transform knowledge into value. Organizational learning power is a concentrated manifestation of people's innovation ability and can be directly transformed into innovation results. It advocates that team learning is more important than individual learning. The team has the ability to learn as a whole. Information and knowledge flow freely and are highly shared within the group. Team learning is not only a process of communication and exchange of ideas among team members, but also a process of seeking consensus and unified action, thus generating the team's "creative tension". In the field of education, how to accurately evaluate students' learning ability is a very important reference factor for implementing personalized teaching goals. Traditional student learning ability evaluation simply judges students' learning ability by the scores of students' answers at the same time through test questions. However, learning ability includes learning motivation, learning perseverance and learning ability. Test questions can only simply test students' learning ability, and cannot make a comprehensive judgment on students' learning motivation and learning perseverance. At the same time, in the learning ability test stage, only focusing on students' answering scores and not considering students' answering time can not scientifically test students' learning ability.

The Chinese invention patent application with publication number CN114491050A discloses a learning ability assessment method and system based on cognitive diagnosis, which obtains the user's answer record, performs labeling preprocessing on the user's answer record, obtains the answer record with label and the answer record without label; clusters the answer record without label according to the answer record with label, obtains the label of all the answer records; inputs all the answer records and their labels into the cognitive diagnosis model, and the cognitive diagnosis model outputs the correct probability of the user's answer, and evaluates the user's learning ability according to the correct probability of the user's answer. The present invention takes into account different types of answer information, marks the answer record, clusters the answer record without label and the answer record with label, and inputs the clustering result into the traditional learning diagnosis model to complete the evaluation of the user's learning ability, makes full use of the large amount of different types of data information contained in the user's answer record, and improves the accuracy of the cognitive diagnosis model. However, the above technical scheme only considers the evaluation of learning ability and does not consider the comprehensive scientific evaluation and analysis of the learning motivation and learning perseverance of the learning ability evaluation user.

Summary of the invention

1. Technical issues to be solved

To solve the above-mentioned problem that traditional student learning ability assessment simply judges students' learning ability through test questions and their answer scores at the same time, however, learning ability includes learning motivation, learning perseverance and learning ability, and test questions can only simply test students' learning ability, and cannot make a comprehensive judgment on students' learning motivation and learning perseverance. At the same time, in the learning ability test stage, only focusing on students' answer scores, not considering students' answering time, cannot scientifically test students' learning ability. In order to achieve the above comprehensive and scientific assessment of learning motivation, learning perseverance and learning ability, improve the accuracy of learning ability assessment, and truly test students' learning ability.

(II) Technical solution

The present invention is implemented by the following technical solution: a learning ability assessment method based on AI for personalized data analysis of students, the method comprising the following steps:

S1. Collecting learning motivation test keyword data, learning perseverance test compliance time data, learning ability test score result data, and learning ability test time result data;

S2. According to the learning motivation test keyword data, respectively measure the proportion of the number of keywords of the same type to the number of all keywords, and generate learning motivation test keyword proportion data, perform proportion numerical analysis according to the learning motivation test keyword proportion data, and screen out the maximum learning motivation test keyword proportion data;

S3, searching for the corresponding learning motivation test keyword data according to the maximum learning motivation test keyword proportion data and marking and constructing the determined learning motivation test keyword data;

S4, identifying the learning motivation test keyword data and the learning motivation test score classification data according to the learning motivation test keywords through a data recognition algorithm, and analyzing and generating student learning motivation test score data;

S5, measuring the ratio of the compliance time data of the learning perseverance test to the total time data of the learning perseverance test and constructing the ratio as the student's learning perseverance test score data;

S6, performing numerical measurement based on the learning ability test score result data and the learning ability test time result data and constructing the numerical values into student learning ability test score data;

S7. Perform numerical analysis and measurement based on the student's learning motivation test score data, the student's learning perseverance test score data, and the student's learning ability test score data to generate and output the student's learning ability comprehensive score calculation result data; use a data recognition algorithm to compare the student's learning ability comprehensive score calculation result data with the student's learning ability comprehensive score classification data according to the numerical value of the learning ability comprehensive score, and analyze and construct the student's learning ability evaluation result.

Preferably, the steps of collecting the learning motivation test keyword data, the learning perseverance test compliance time data, the learning ability test score result data, and the learning ability test time result data are as follows:

S11. Collecting the keyword data of students' learning motivation multiple times within a specified time through a questionnaire survey platform and generating a learning motivation test keyword data set A=(a ₁ ,…, _am ,…,a _θ ), m=1,2,3,…,θ; _whereinam represents the mth learning motivation test keyword data, andθ represents the maximum number of learning motivation test keyword data; the specified time includes any one of six months, twelve months, eighteen months, and twenty-four months; the learning motivation test keywords include at least one of learning for personal goals, learning for specific industry fields, and learning for national goals; the questionnaire survey platform includes any one of WJX, WeChat Questionnaire Mini Program, and QQ Questionnaire Mini Program;

The time that the student is in compliance with the study regulations when taking the study perseverance test is collected through the time measurement sensor and the compliance time data of the study perseverance test is ^generated ;

Test new knowledge points online through the school knowledge point test platform, count students' test scores and generate learning ability test score result data Γ ^nengli ;

Test new knowledge points online through the school knowledge point test platform, count students' test completion time and generate learning ability test time result data t ^nengli .

Preferably, the proportion of the number of keywords of the same type to the number of all keywords is measured based on the learning motivation test keyword data, and learning motivation test keyword proportion data is generated. The proportion numerical analysis is performed based on the learning motivation test keyword proportion data, and the operation steps of screening out the maximum learning motivation test keyword proportion data are as follows:

S21, obtaining a learning motivation test keyword data set A;

S22. Classify the learning motivation test keyword data a _m in the learning motivation test keyword data set A according to personal goal keywords, specific industry field keywords, and national goal keywords, calculate the proportion of the number of keywords of the same type to the number of all keywords, and generate a learning motivation test keyword proportion data set B = (b ₁ , b ₂ , b ₃ ), wherein b ₁ represents the ratio of the number of learning motivation test keyword data a _m belonging to personal goal keywords in the learning motivation test keyword data set A to the number of all learning motivation test keyword data, and the personal goal keywords include learning to improve personal basketball skills, learning to improve personal academic performance, learning to get parental recognition, and learning to change personal living conditions;

_b2 represents the ratio of the number of learning power test keyword data a _m belonging to specific industry field keywords in the learning power test keyword data set A to the number of all learning power test keyword data, wherein the specific industry field keywords include learning to improve the quality of rice seeds, learning to improve the level of film production industry, learning to improve the technology of unmanned aerial vehicles and learning to improve the level of automobile manufacturing;

_b3 represents the ratio of the number of learning motivation test keyword data a _m belonging to national target keywords in the learning motivation test keyword data set A to the number of all learning motivation test keyword data, wherein the national target keywords include learning to promote national economic development and learning to achieve a strong manufacturing country;

S23, using a breadth-first search algorithm to select the learning motivation test keyword proportion data set B with the largest proportion value according to the numerical value and mark it as the maximum learning motivation test keyword proportion data b _max .

Preferably, the operation steps of searching for the corresponding learning motivation test keyword data based on the maximum learning motivation test keyword proportion data and identifying and constructing the learning motivation test keyword data are as follows:

S31, obtaining the maximum learning motivation test keyword proportion data b _max ;

S32. Use a breadth-first search algorithm to search for the maximum learning motivation test keyword proportion data b _max corresponding to all specific learning motivation test keyword data a _m of the same type and identify and generate a determined learning motivation test keyword data set A', where A' belongs to a subset of A.

Preferably, the steps of identifying the learning motivation test keyword data and the learning motivation test score classification data according to the learning motivation test keywords through a data recognition algorithm and analyzing and generating the student learning motivation test score data are as follows:

S41, establishing a learning motivation test score classification data set C = (c ₁ , c ₂ , c ₃ ), where c ₁ represents the learning motivation test score classification data corresponding to the learning motivation test keyword data a _m belonging to the personal target keyword;

c ₂ represents the learning motivation test keyword data a _m corresponding to the learning motivation test score classification data belonging to the specific industry field keywords;

c ₃ represents the learning motivation test score classification data corresponding to the learning motivation test keyword data a _m belonging to the national target keyword, c ₁ +c ₂ +c ₃ =1;

S42, using a data recognition algorithm to perform keyword character recognition on the learning power test keyword data a _m in the determined learning power test keyword data set A' according to the learning power test keywords and the learning power test keywords corresponding to the learning power test score classification data in the learning power test score classification data set C, and analyzing and generating the learning power test score classification data c A' corresponding to the determined learning power test keyword data set A _' , the specific steps of the data recognition algorithm analyzing and generating the learning power test score classification data c _A' are as follows:

S421, initialization, randomly initializing the population in the optimization space of the learning dynamics test score classification data set C and updating the maximum number of iterations N of the algorithm;

Where Zi _,j is the position of the learning power test score search raccoon individual i in the j-dimensional space, that is, the position of the learning power test score search raccoon individual i in the learning power test score classification data set C search space, ψ is the upper boundary of the optimization, ζ is the lower boundary of the optimization, /> is a random number between [0,1];

S422, hunting and attacking, the first stage of updating the learning dynamics test score search raccoon population in the search space of the learning dynamics test score classification data set C is modeled based on simulating their strategy when attacking iguanas. In the execution strategy, a group of learning dynamics test score search raccoons climb up a tree to contact an iguana and scare it, and other learning dynamics test score search raccoons wait under the tree until the iguana falls to the ground. After the iguana falls to the ground, the learning dynamics test score search raccoons attack and hunt the iguana, that is, the learning dynamics test score classification data set C is searched for learning dynamics test score classification data that matches the same type of learning dynamics test keyword data a _m in the determined learning dynamics test keyword data set A'. This strategy causes the learning dynamics test score search raccoons to move to different positions in the search space of the learning dynamics test score classification data set C;

S423, escape from predator, the second step of the process of updating the position of the learning power test score search raccoon in the search space of the learning power test score classification data set C is to mathematically model the natural behavior of the learning power test score search raccoon when encountering a predator and escaping from a predator. When a predator attacks a learning power test score search raccoon, it will flee from its own position, that is, the learning power test score classification data set C is searched for the learning power test score classification data that does not match the same type of learning power test keyword data a _m in the determined learning power test keyword data set A', and the learning power test score search raccoon's move in this strategy puts it in a safe position close to the current position; use simulated behavior calculation to generate a random position near the position of each learning power test score search raccoon;

S424, when the maximum number of iterations is met, output the learning power test score classification data corresponding to the learning power test keyword data set A', otherwise, loop through steps S422 to S424 until the maximum number of iterations is reached;

S43, generating the learning motivation test score classification data identifier corresponding to the learning motivation test keyword data set A' output in step S424 as the learning motivation test score classification data c _A' .

Preferably, the operation steps of measuring the ratio of the compliance time data of the learning perseverance test to the total time data of the learning perseverance test and constructing the ratio as the student learning perseverance test score data are as follows:

S51. Establish the total time data of learning perseverance test The total time for the learning perseverance test is the total time required for students to take the learning perseverance test;

S52, obtaining the compliance time data t ^yili of the learning perseverance test;

S53, comparing the compliance time data of the learning perseverance test ^to the total time data of the learning perseverance test Calculate the ratio and generate the student learning perseverance test score data/> Where d takes the value [0,1].

Preferably, the operation steps of performing numerical measurement based on the learning ability test score result data and the learning ability test time result data and constructing the numerical values into student learning ability test score data are as follows:

S61, obtaining the learning ability test score result data Γ ^nengli and the learning ability test time result data t ^nengli ;

S62, measuring the ratio of the learning ability test score result data Γ ^nengli and the learning ability test time result data t ^nengli and generating the student learning ability test score data Where Γ ^nengli ranges from [0,100], t ^nengli is in minutes, t ^nengli ranges from [0,60], and e ranges from [0,0.2];

Preferably, the steps of performing numerical analysis and measurement based on the student learning motivation test score data, the student learning perseverance test score data, and the student learning ability test score data to generate and output the student learning ability comprehensive score calculation result data; using a data recognition algorithm to compare the student learning ability comprehensive score calculation result data with the student learning ability comprehensive score classification data according to the numerical value of the learning ability comprehensive score, and analyzing and constructing the student learning ability evaluation result are as follows:

S71, obtaining the student's learning motivation test score data c _A' , the student's learning perseverance test score data d, and the student's learning ability test score data e;

S72, numerically analyzing the student learning motivation test score data c _A' , the student learning perseverance test score data d, and the student learning ability test score data e to calculate the student learning ability comprehensive score calculation result data F = c _A' × d × e × 10 ⁴ , where F has a value range of [0, 100];

S73, establish a classification data set of students' comprehensive learning ability scores G = ([0, 30) ^poor , [30, 70) ^normal , [70, 100] ^excellent ), where [0, 30) ^poor means that the comprehensive learning ability score of the student is in the range of [0, 30) and the learning ability is poor;

[30, 70) ^Normal means that the comprehensive score of students' learning ability is in the range of [30, 70) and their learning ability is normal;

[70, 100] ^Excellent means that the comprehensive score of the student's learning ability is in the range of [70, 100] and the learning ability is excellent;

S74, using the data recognition algorithm in step S42 to compare the student learning ability comprehensive score calculation result data F with the student learning ability comprehensive score classification data in the student learning ability comprehensive score classification data set G according to the numerical value of the learning ability comprehensive score, match the student learning ability comprehensive score classification data corresponding to the student learning ability comprehensive score calculation result data F and identify and generate the student learning ability evaluation result

A system for implementing the learning ability assessment method based on AI for personalized data analysis of students, the system comprising a learning ability assessment data acquisition module, a learning motivation and learning perseverance parameter processing module, and a learning ability parameter and learning ability analysis processing module;

The learning ability assessment data collection module includes a learning motivation test keyword collection unit, a learning perseverance test compliance time collection unit, a learning ability test score result collection unit, and a learning ability test time result collection unit;

The learning motivation test keyword collection unit collects learning motivation test keyword data through a questionnaire survey platform; the learning perseverance test compliance time collection unit collects learning perseverance test compliance time collection unit through a time measurement sensor; the learning ability test score result collection unit collects learning ability test score result collection unit through a school knowledge point test platform; the learning ability test time result collection unit collects learning ability test time result collection unit through a school knowledge point test platform;

The learning motivation and learning perseverance parameter processing module includes a learning motivation test keyword weight measurement screening unit, a learning motivation test score classification storage unit, a learning motivation test score analysis unit, a learning perseverance test total time storage unit, and a learning perseverance test score analysis unit;

The learning motivation test keyword proportion measurement and screening unit measures the proportion of the number of keywords of the same type to the total number of keywords based on the learning motivation test keyword data, and generates learning motivation test keyword proportion data, performs proportion numerical analysis based on the learning motivation test keyword proportion data, and screens out the maximum learning motivation test keyword proportion data; searches out the corresponding learning motivation test keyword data based on the maximum learning motivation test keyword proportion data and identifies and constructs the determined learning motivation test keyword data; the learning motivation test score classification storage unit is used to store the learning motivation test score classification data; the learning motivation test score analysis unit identifies the determined learning motivation test keyword data and the learning motivation test score classification data according to the learning motivation test keywords through a data recognition algorithm, and analyzes and generates student learning motivation test score data; the learning perseverance test total time storage unit is used to store the learning perseverance test total time data; the learning perseverance test score analysis unit performs ratio measurement based on the learning perseverance test compliance time data and the learning perseverance test total time data and constructs the ratio as the student learning perseverance test score data;

The learning ability parameter and learning ability analysis processing module includes a learning ability test score analysis unit, a student learning ability comprehensive score classification storage unit, and a student learning ability comprehensive analysis output unit;

The learning ability test score analysis unit performs numerical measurement based on the learning ability test score result data and the learning ability test time result data and constructs the numerical value into the student learning ability test score data; the student learning ability comprehensive score classification storage unit is used to store the student learning ability comprehensive score classification data; the student learning ability comprehensive analysis output unit performs numerical analysis and measurement based on the student learning motivation test score data, the student learning perseverance test score data, and the student learning ability test score data to generate and output the student learning ability comprehensive score calculation result data; uses a data recognition algorithm to compare the student learning ability comprehensive score calculation result data with the student learning ability comprehensive score classification data according to the numerical value of the learning ability comprehensive score, and analyzes and constructs the student learning ability evaluation result.

(III) Beneficial effects

The present invention provides a learning ability assessment method and system based on AI for personalized data analysis of students. It has the following beneficial effects:

1. Through the learning motivation test keyword collection unit, the students' learning motivation keywords are scientifically obtained through the questionnaire survey platform according to the prescribed time period, providing data support for the subsequent precise analysis of students' learning motivation, and realizing accurate online measurement of students' learning motivation; the learning perseverance test compliance time collection unit accurately collects the amount of time that conforms to the learning state of students' learning perseverance test through the time measurement sensor, realizes the quantitative processing of students' learning perseverance, and improves the accuracy of the measurement results of students' learning ability; the learning ability test score result collection unit and the learning ability test time result collection unit cooperate with each other to efficiently collect students' test scores and test time parameters for new knowledge points online through the knowledge point test platform, accurately measure students' learning ability, and improve the accuracy of students' learning ability assessment.

2. Through the cooperation of the learning motivation test keyword proportion measurement screening unit and the learning motivation test score analysis unit, the collected learning motivation test keywords are classified and their proportions are calculated according to personal goals, specific industry fields, and national goals, so as to achieve accurate classification and quantification of learning motivation keywords, screen the learning motivation keywords with the largest proportion and cooperate with the AI intelligent recognition algorithm to calculate the learning motivation score, thereby achieving accurate measurement and analysis of students' learning motivation; the learning perseverance test score analysis unit uses the ratio of students' learning time in accordance with the specified status to the total time of the learning perseverance test for numerical comparison, so as to intuitively and quantitatively measure students' learning perseverance results.

3. The learning ability test score analysis unit measures students' test scores and test time for new knowledge points in a scientific way, thereby improving the efficiency of students' learning ability assessment and analysis. The student learning ability comprehensive analysis output unit comprehensively utilizes the parameters of students' learning motivation, learning perseverance, and learning ability to comprehensively and accurately calculate the student's comprehensive learning ability score, and combines the AI intelligent recognition algorithm with the student's learning ability type to match the learning ability score value, and efficiently and intelligently calculates the student's learning ability assessment results, thereby improving the accuracy and intuitiveness of the student's learning ability assessment results, and enhancing the authenticity of the student's learning ability assessment results.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a module schematic diagram of a learning ability assessment system based on AI for personalized data analysis of students provided by the present invention;

FIG2 is a flow chart of a learning ability assessment method based on AI for personalized data analysis of students provided by the present invention.

Detailed ways

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

The embodiments of the learning ability assessment method and system based on AI for personalized data analysis of students are as follows:

Please refer to Figures 1 and 2 for a learning ability assessment method based on AI for personalized data analysis of students. The method includes the following steps:

S1. Collecting learning motivation test keyword data, learning perseverance test compliance time data, learning ability test score result data, and learning ability test time result data;

S2. According to the learning motivation test keyword data, the proportion of the number of keywords of the same type to the total number of keywords is respectively measured, and learning motivation test keyword proportion data is generated. According to the learning motivation test keyword proportion data, a numerical analysis of the proportion is performed to screen out the maximum learning motivation test keyword proportion data;

S3, searching for corresponding learning motivation test keyword data according to the maximum learning motivation test keyword proportion data and marking and constructing the determined learning motivation test keyword data;

S4, identifying the learning motivation test keywords and the learning motivation test score classification data through a data recognition algorithm according to the learning motivation test keywords, and analyzing and generating the student learning motivation test score data;

S5. Calculate the ratio of the compliance time data of the learning perseverance test to the total time data of the learning perseverance test and construct the ratio as the student learning perseverance test score data;

S6, performing numerical measurement based on the learning ability test score result data and the learning ability test time result data and constructing the numerical value into the student learning ability test score data;

S7. Perform numerical analysis and measurement based on the students' learning motivation test score data, the students' learning perseverance test score data, and the students' learning ability test score data to generate and output the students' learning ability comprehensive score calculation result data; use data recognition algorithm to compare the students' learning ability comprehensive score calculation result data with the students' learning ability comprehensive score classification data according to the numerical size of the learning ability comprehensive score, and analyze and construct the students' learning ability evaluation results.

Further, please refer to Figures 1-2. The operation steps for collecting learning motivation test keyword data, learning perseverance test compliance time data, learning ability test score result data, and learning ability test time result data are as follows:

S11. Collect the keyword data of students' learning motivation multiple times within a specified time through a questionnaire survey platform and generate a learning motivation test keyword data set A = (a ₁ , ..., a _m , ..., a _θ ), m = 1, 2, 3, ..., θ; wherein a _m represents the mth learning motivation test keyword data, and θ represents the maximum number of learning motivation test keyword data; the specified time includes any time period of six months, twelve months, eighteen months, and twenty-four months; the learning motivation test keywords include at least one of learning for personal goals, learning for specific industry fields, and learning for national goals; the questionnaire survey platform includes any one of WJX, WeChat Questionnaire Mini Program, and QQ Questionnaire Mini Program;

The time that the student is in compliance with the study regulations when taking the study perseverance test is collected through the time measurement sensor and the compliance time data of the study perseverance test is ^generated ;

Test new knowledge points online through the school knowledge point test platform, count students' test scores and generate learning ability test score result data Γ ^nengli ;

Test new knowledge points online through the school knowledge point test platform, count students' test completion time and generate learning ability test time result data t ^nengli .

The learning motivation test keyword collection unit uses the questionnaire survey platform to scientifically obtain students' learning motivation keywords according to the prescribed time period, providing data support for subsequent precise analysis of students' learning motivation, and realizing accurate online measurement of students' learning motivation; the learning perseverance test compliance time collection unit accurately collects the amount of time that conforms to the learning state of students' learning perseverance test through time measurement sensors, realizes quantitative processing of students' learning perseverance, and improves the accuracy of measurement results of students' learning ability; the learning ability test score result collection unit and the learning ability test time result collection unit cooperate with each other to efficiently collect students' test scores and test time parameters for new knowledge points online through the knowledge point test platform, accurately measure students' learning ability, and improve the accuracy of students' learning ability assessment.

Further, please refer to Figures 1 and 2. According to the learning motivation test keyword data, the proportion of the number of keywords of the same type to the total number of keywords is respectively measured, and the learning motivation test keyword proportion data is generated. According to the learning motivation test keyword proportion data, the proportion numerical analysis is performed, and the operation steps of screening out the maximum learning motivation test keyword proportion data are as follows:

S21, obtaining a learning motivation test keyword data set A;

S22. Classify the learning motivation test keyword data a _m in the learning motivation test keyword data set A according to personal goal keywords, specific industry keywords, and national goal keywords, calculate the proportion of the number of keywords of the same type to the number of all keywords, and generate a learning motivation test keyword proportion data set B = (b ₁ , b ₂ , b ₃ ), where b ₁ represents the ratio of the number of learning motivation test keyword data a _m belonging to personal goal keywords in the learning motivation test keyword data set A to the number of all learning motivation test keyword data, and personal goal keywords include learning to improve personal basketball skills, learning to improve personal academic performance, learning to get parental recognition, and learning to change personal living conditions;

_b2 represents the ratio of the number of learning power test keyword data a _m belonging to specific industry keywords in the learning power test keyword data set A to the number of all learning power test keyword data. The specific industry keywords include learning to improve the quality of rice seeds, learning to improve the level of film production industry, learning to improve drone technology, and learning to improve the level of automobile manufacturing.

b ₃ represents the ratio of the number of learning motivation test keyword data a _m belonging to national target keywords in the learning motivation test keyword data set A to the number of all learning motivation test keyword data. National target keywords include learning to promote national economic development and learning to achieve a strong manufacturing country.

S23, using a breadth-first search algorithm to select the learning motivation test keyword proportion data set B with the largest proportion value according to the numerical value and mark it as the maximum learning motivation test keyword proportion data b _max .

The operation steps for searching for corresponding learning motivation test keyword data based on the maximum learning motivation test keyword proportion data and identifying and constructing the learning motivation test keyword data are as follows:

S31, obtaining the maximum learning motivation test keyword proportion data b _max ;

S32. Use a breadth-first search algorithm to search for the maximum learning motivation test keyword proportion data b _max corresponding to all specific learning motivation test keyword data a _m of the same type and identify and generate a determined learning motivation test keyword data set A', where A' belongs to a subset of A.

Based on the determined learning motivation test keyword data and learning motivation test score classification data, the data recognition algorithm is used to identify the learning motivation test keywords and analyze and generate the student learning motivation test score data as follows:

S41, establishing a learning motivation test score classification data set C = (c ₁ , c ₂ , c ₃ ), where c ₁ represents the learning motivation test score classification data corresponding to the learning motivation test keyword data a _m belonging to the personal target keyword;

c ₂ represents the learning motivation test keyword data a _m corresponding to the learning motivation test score classification data belonging to the specific industry field keywords;

c ₃ represents the learning motivation test score classification data corresponding to the learning motivation test keyword data a _m belonging to the national target keyword, c ₁ +c ₂ +c ₃ =1;

S42, using a data recognition algorithm to determine the learning power test keyword data a _m in the learning power test keyword data set A' according to the learning power test keywords and the learning power test keywords corresponding to the learning power test score classification data in the learning power test score classification data set C, and analyzing and generating the learning power test score classification data c _A ' corresponding to the learning power test keyword data set A'. The specific steps of the data recognition algorithm analyzing and generating the learning power test score classification data c _A' are as follows:

S421, initialization, randomly initializing the population in the optimization space of the learning dynamics test score classification data set C and updating the maximum number of iterations N of the algorithm;

Where Zi _,j is the position of the learning power test score search raccoon individual i in the j-dimensional space, that is, the position of the learning power test score search raccoon individual i in the learning power test score classification data set C search space, ψ is the upper boundary of the optimization, ζ is the lower boundary of the optimization, /> is a random number between [0,1];

S422, hunting and attacking, the first stage of updating the learning dynamics test score search raccoon population in the search space of the learning dynamics test score classification data set C is modeled based on simulating their strategy when attacking iguanas. In the execution strategy, a group of learning dynamics test score search raccoons climb up a tree to contact an iguana and scare it, and other learning dynamics test score search raccoons wait under the tree until the iguana falls to the ground. After the iguana falls to the ground, the learning dynamics test score search raccoons attack and hunt the iguana, that is, the learning dynamics test score classification data set C is searched for learning dynamics test score classification data that matches the same type of learning dynamics test keyword data a _m in the determined learning dynamics test keyword data set A'. This strategy causes the learning dynamics test score search raccoons to move to different positions in the search space of the learning dynamics test score classification data set C;

S423, escape from predator, the second step of the process of updating the position of the learning power test score search raccoon in the search space of the learning power test score classification data set C is to mathematically model the natural behavior of the learning power test score search raccoon when encountering a predator and escaping from a predator. When a predator attacks a learning power test score search raccoon, it will flee from its own position, that is, the learning power test score classification data set C is searched for the learning power test score classification data that does not match the same type of learning power test keyword data a _m in the determined learning power test keyword data set A', and the learning power test score search raccoon's move in this strategy puts it in a safe position close to the current position; use simulated behavior calculation to generate a random position near the position of each learning power test score search raccoon;

S424, when the maximum number of iterations is met, output the learning power test score classification data corresponding to the learning power test keyword data set A', otherwise, loop through steps S422 to S424 until the maximum number of iterations is reached;

S43, generating the learning motivation test score classification data identifier corresponding to the learning motivation test keyword data set A' output in step S424 as the learning motivation test score classification data c _A' .

The steps for measuring the ratio of the compliance time data of the learning perseverance test to the total time data of the learning perseverance test and constructing the ratio into the student learning perseverance test score data are as follows:

S51. Establish the total time data of learning perseverance test The total time for the learning perseverance test is the total time required for students to take the learning perseverance test;

S52, obtaining the compliance time data of the learning perseverance test t ^yili ;

S53, compare the compliance time data ^of the learning perseverance test with the total time data of the learning perseverance test Calculate the ratio and generate the student learning perseverance test score data/> Where d takes the value [0,1].

Through the cooperation of the learning motivation test keyword proportion measurement screening unit and the learning motivation test score analysis unit, the collected learning motivation test keywords are classified and their proportions are calculated according to personal goals, specific industry fields, and national goals, so as to achieve accurate classification and quantification of learning motivation keywords, and screen the learning motivation keywords with the largest proportion and cooperate with the AI intelligent recognition algorithm to calculate the learning motivation score, thereby achieving accurate measurement and analysis of students' learning motivation; the learning perseverance test score analysis unit uses the ratio of students' learning time in accordance with the specified status to the total time of the learning perseverance test for numerical comparison, so as to intuitively and quantitatively measure students' learning perseverance results.

Further, referring to Figures 1 and 2, the operation steps of numerically measuring the learning ability test score result data and the learning ability test time result data and constructing the numerical values into the student learning ability test score data are as follows:

S61, obtaining learning ability test score result data Γ ^nengli and learning ability test time result data t ^nengli ;

S62, calculate the ratio of the learning ability test score result data Γ ^nengli and the learning ability test time result data t ^nengli and generate the student learning ability test score data Where Γ ^nengli ranges from [0,100], t ^nengli is in minutes, t ^nengli ranges from [0,60], and e ranges from [0,0.2];

Based on the student learning motivation test score data, the student learning perseverance test score data, and the student learning ability test score data, numerical analysis is performed to generate and output the student learning ability comprehensive score calculation result data; the student learning ability comprehensive score calculation result data and the student learning ability comprehensive score classification data are compared according to the numerical value of the learning ability comprehensive score using a data recognition algorithm, and the operation steps for analyzing and constructing the student learning ability evaluation result are as follows:

S71, obtaining the student learning motivation test score data c _A' , the student learning perseverance test score data d, and the student learning ability test score data e;

S72, numerically analyzing the student learning motivation test score data c _A' , the student learning perseverance test score data d, and the student learning ability test score data e to calculate the student learning ability comprehensive score calculation result data F = c _A' × d × e × 10 ⁴ , where F has a value range of [0,100];

S73, establish a classification data set of students' comprehensive learning ability scores G = ([0, 30) ^poor , [30, 70) ^normal , [70, 100] ^excellent ), where [0, 30) ^poor means that the comprehensive learning ability score of the student is in the range of [0, 30) and the learning ability is poor;

[30, 70) ^Normal means that the comprehensive score of students' learning ability is in the range of [30, 70) and their learning ability is normal;

[70, 100] ^Excellent means that the comprehensive score of the student's learning ability is in the range of [70, 100] and the learning ability is excellent;

S74, using the data recognition algorithm in step S42, compare the student learning ability comprehensive score calculation result data F with the student learning ability comprehensive score classification data in the student learning ability comprehensive score classification data set G according to the numerical value of the learning ability comprehensive score, match the student learning ability comprehensive score classification data corresponding to the student learning ability comprehensive score calculation result data F, and identify and generate the student learning ability evaluation result.

The learning ability test score analysis unit measures students' test scores and test time on new knowledge points scientifically, thereby improving the efficiency of student learning ability assessment and analysis; the student learning ability comprehensive analysis output unit comprehensively utilizes the parameters of students' learning motivation, learning perseverance, and learning ability to comprehensively and accurately calculate the student's comprehensive learning ability score, and combines the AI intelligent recognition algorithm with the student's learning ability type to match the learning ability score value, and efficiently and intelligently calculates the student's learning ability assessment results, thereby improving the accuracy and intuitiveness of the student's learning ability assessment results, and enhancing the authenticity of the student's learning ability assessment results.

A system for implementing a learning ability assessment method based on AI for personalized data analysis of students, the system includes a learning ability assessment data collection module, a learning motivation and learning perseverance parameter processing module, and a learning ability parameter and learning ability analysis processing module;

The learning ability assessment data collection module includes a learning motivation test keyword collection unit, a learning perseverance test compliance time collection unit, a learning ability test score result collection unit, and a learning ability test time result collection unit;

Learning motivation test keyword collection unit, collects learning motivation test keyword data through the questionnaire survey platform; learning perseverance test compliance time collection unit, collects learning perseverance test compliance time collection unit through the time measurement sensor; learning ability test score result collection unit, collects learning ability test score result collection unit through the school knowledge point test platform; learning ability test time result collection unit, collects learning ability test time result collection unit through the school knowledge point test platform;

The learning motivation and learning perseverance parameter processing module includes a learning motivation test keyword weight measurement screening unit, a learning motivation test score classification storage unit, a learning motivation test score analysis unit, a learning perseverance test total time storage unit, and a learning perseverance test score analysis unit;

A learning motivation test keyword proportion measurement and screening unit measures the proportion of the number of keywords of the same type to the total number of keywords based on the learning motivation test keyword data, and generates learning motivation test keyword proportion data, performs numerical analysis of the proportion based on the learning motivation test keyword proportion data, and screens out the maximum learning motivation test keyword proportion data; searches out the corresponding learning motivation test keyword data based on the maximum learning motivation test keyword proportion data and identifies and constructs the determined learning motivation test keyword data; a learning motivation test score classification storage unit is used to store the learning motivation test score classification data; a learning motivation test score analysis unit identifies the determined learning motivation test keyword data and the learning motivation test score classification data according to the learning motivation test keywords through a data recognition algorithm, and analyzes and generates student learning motivation test score data; a learning perseverance test total time storage unit is used to store the learning perseverance test total time data; a learning perseverance test score analysis unit performs ratio measurement based on the learning perseverance test compliance time data and the learning perseverance test total time data and constructs the ratio as the student learning perseverance test score data;

The learning ability parameter and learning ability analysis processing module includes a learning ability test score analysis unit, a student learning ability comprehensive score classification storage unit, and a student learning ability comprehensive analysis output unit;

A learning ability test score analysis unit performs numerical measurement based on the learning ability test score result data and the learning ability test time result data and constructs the numerical value into the student learning ability test score data; a student learning ability comprehensive score classification storage unit is used to store the student learning ability comprehensive score classification data; a student learning ability comprehensive analysis output unit performs numerical analysis and measurement based on the student learning motivation test score data, the student learning perseverance test score data, and the student learning ability test score data to generate and output the student learning ability comprehensive score calculation result data; a data recognition algorithm is used to compare the student learning ability comprehensive score calculation result data with the student learning ability comprehensive score classification data according to the numerical value of the learning ability comprehensive score, and the student learning ability evaluation result is analyzed and constructed.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims (9)

1. A learning ability assessment method based on AI for personalized data analysis of students, characterized in that the method comprises the following steps: S1. Collecting learning motivation test keyword data, learning perseverance test compliance time data, learning ability test score result data, and learning ability test time result data; S2. According to the learning motivation test keyword data, respectively measure the proportion of the number of keywords of the same type to the number of all keywords, and generate learning motivation test keyword proportion data, perform proportion numerical analysis according to the learning motivation test keyword proportion data, and screen out the maximum learning motivation test keyword proportion data; S3, searching for the corresponding learning motivation test keyword data according to the maximum learning motivation test keyword proportion data and marking and constructing the determined learning motivation test keyword data; S4, identifying the learning motivation test keyword data and the learning motivation test score classification data according to the learning motivation test keywords through a data recognition algorithm, and analyzing and generating student learning motivation test score data; S5, measuring the ratio of the compliance time data of the learning perseverance test to the total time data of the learning perseverance test and constructing the ratio as the student's learning perseverance test score data; S6, performing numerical measurement based on the learning ability test score result data and the learning ability test time result data and constructing the numerical values into student learning ability test score data; S7. Perform numerical analysis and measurement based on the student's learning motivation test score data, the student's learning perseverance test score data, and the student's learning ability test score data to generate and output the student's learning ability comprehensive score calculation result data; use a data recognition algorithm to compare the student's learning ability comprehensive score calculation result data with the student's learning ability comprehensive score classification data according to the numerical value of the learning ability comprehensive score, and analyze and construct the student's learning ability evaluation result. 2. According to claim 1, the learning ability assessment method based on AI for personalized data analysis of students is characterized in that: the operation steps of collecting learning motivation test keyword data, learning perseverance test compliance time data, learning ability test score result data, and learning ability test time result data are as follows: S11. Collecting the keyword data of students' learning motivation multiple times within a specified time through a questionnaire survey platform and generating a learning motivation test keyword data set A=(a ₁ ,…, _am ,…,a _θ ), m=1,2,3,…,θ; _whereinam represents the mth learning motivation test keyword data, andθ represents the maximum number of learning motivation test keyword data; the specified time includes any one of six months, twelve months, eighteen months, and twenty-four months; the learning motivation test keywords include at least one of learning for personal goals, learning for specific industry fields, and learning for national goals; the questionnaire survey platform includes any one of WJX, WeChat Questionnaire Mini Program, and QQ Questionnaire Mini Program; The time that the student is in compliance with the study regulations when taking the study perseverance test is collected through the time measurement sensor and the compliance time data of the study perseverance test is ^generated ; Test new knowledge points online through the school knowledge point test platform, count students' test scores and generate learning ability test score result data Γ ^nengli ; Test new knowledge points online through the school knowledge point test platform, count students' test completion time and generate learning ability test time result data t ^nengli . 3. According to claim 2, the learning ability assessment method based on AI for personalized data analysis of students is characterized in that: the proportion of the number of keywords of the same type to the number of all keywords is respectively measured based on the learning motivation test keyword data, and learning motivation test keyword proportion data is generated, and the proportion numerical analysis is performed based on the learning motivation test keyword proportion data, and the operation steps of screening out the maximum learning motivation test keyword proportion data are as follows: S21, obtaining a learning motivation test keyword data set A; S22, classify the learning motivation test keyword data a _m in the learning motivation test keyword data set A according to personal target keywords, specific industry field keywords, and national target keywords, calculate the proportion of the number of keywords of the same type to the number of all keywords, and generate a learning motivation test keyword proportion data set B = (b ₁ , b ₂ , b ₃ ), where b ₁ represents the ratio of the number of learning motivation test keyword data a _m belonging to personal target keywords in the learning motivation test keyword data set A to the number of all learning motivation test keyword data; _b2 represents the ratio of the number of learning motivation test keyword data a _m belonging to specific industry field keywords in the learning motivation test keyword data set A to the number of all learning motivation test keyword data; b ₃ represents the ratio of the number of learning motivation test keyword data a _m belonging to the national target keyword in the learning motivation test keyword data set A to the number of all learning motivation test keyword data; S23, using a breadth-first search algorithm to select the learning motivation test keyword proportion data set B with the largest proportion value according to the numerical value and mark it as the maximum learning motivation test keyword proportion data b _max . 4. According to the learning ability assessment method based on AI for personalized data analysis of students according to claim 3, it is characterized in that: the operation steps of searching for the corresponding learning motivation test keyword data based on the maximum learning motivation test keyword proportion data and marking and constructing the learning motivation test keyword data are as follows: S31, obtaining the maximum learning motivation test keyword proportion data b _max ; S32. Use a breadth-first search algorithm to search for the maximum learning motivation test keyword proportion data b _max corresponding to all specific learning motivation test keyword data a _m of the same type and identify and generate a determined learning motivation test keyword data set A′, where A′ belongs to a subset of A. 5. According to the learning ability assessment method based on AI for personalized data analysis of students according to claim 4, it is characterized in that: the operation steps of identifying the learning motivation test keyword data and the learning motivation test score classification data according to the learning motivation test keywords through the data recognition algorithm, and analyzing and generating the student learning motivation test score data are as follows: S41, establishing a learning motivation test score classification data set C = (c ₁ , c ₂ , c ₃ ), where c ₁ represents the learning motivation test score classification data corresponding to the learning motivation test keyword data a _m belonging to the personal target keyword; c ₂ represents the learning motivation test keyword data a _m corresponding to the learning motivation test score classification data belonging to the specific industry field keywords; c ₃ represents the learning motivation test score classification data corresponding to the learning motivation test keyword data a _m belonging to the national target keyword, c ₁ +c ₂ +c ₃ =1; S42, using a data recognition algorithm to perform keyword character recognition on the learning motivation test keyword data a _m in the determined learning motivation test keyword data set A′ according to the learning motivation test keywords and the learning motivation test keywords corresponding to the learning motivation test score classification data in the learning motivation test score classification data set C, and analyzing and generating the learning motivation test score classification data c A′ corresponding to the determined learning motivation test keyword data set A _′ , the specific steps of the data recognition algorithm analyzing and generating the learning motivation test score classification data c _A′ are as follows: S421, initialization, randomly initializing the population in the optimization space of the learning dynamics test score classification data set C and updating the maximum number of iterations N of the algorithm; Where Zi _,j is the position of the learning power test score search raccoon individual i in the j-dimensional space, that is, the position of the learning power test score search raccoon individual i in the learning power test score classification data set C search space, ψ is the upper boundary of the optimization, ζ is the lower boundary of the optimization, /> is a random number between [0,1]; S422, hunting and attacking, the first stage of updating the learning dynamic test score search raccoon population in the learning dynamic test score classification data set C search space is modeled based on simulating their strategy when attacking iguanas. In the execution strategy, a group of learning dynamic test score search raccoons climb up a tree to contact an iguana and scare it, and other learning dynamic test score search raccoons wait under the tree until the iguana falls to the ground. After the iguana falls to the ground, the learning dynamic test score search raccoons attack and hunt the iguana, that is, the learning dynamic test score classification data set C is searched for learning dynamic test score classification data that matches the same type of learning dynamic test keyword data a _m in the determined learning dynamic test keyword data set A′. This strategy causes the learning dynamic test score search raccoons to move to different positions in the learning dynamic test score classification data set C search space; S423, escape from predator, the second step of the process of updating the position of the learning power test score search raccoon in the search space of the learning power test score classification data set C is to mathematically model the natural behavior of the learning power test score search raccoon when encountering a predator and escaping from a predator. When a predator attacks a learning power test score search raccoon, it will escape from its own position, that is, the learning power test score classification data set C is searched for the learning power test score classification data that does not match the same type of learning power test keyword data a _m in the determined learning power test keyword data set A′, and the learning power test score search raccoon's move in this strategy puts it in a safe position close to the current position; use simulated behavior calculation to generate a random position near the position of each learning power test score search raccoon; S424, when the maximum number of iterations is met, output the learning power test score classification data corresponding to the learning power test keyword data set A′, otherwise, loop through steps S422 to S424 until the maximum number of iterations is reached; S43, generating the learning motivation test score classification data identifier corresponding to the learning motivation test keyword data set A′ output in step S424 as learning motivation test score classification data c _A′ . 6. The learning ability assessment method based on AI for personalized data analysis of students according to claim 5 is characterized in that: the operation steps of measuring the ratio of the compliance time data of the learning perseverance test to the total time data of the learning perseverance test and constructing the ratio as the student learning perseverance test score data are as follows: S51. Establish the total time data of learning perseverance test The total time for the learning perseverance test is the total time required for students to take the learning perseverance test; S52, obtaining the compliance time data t ^yili of the learning perseverance test; S53, comparing the compliance time data of the learning perseverance test ^to the total time data of the learning perseverance test Calculate the ratio and generate the student learning perseverance test score data/> Where d takes the value [0,1]. 7. The learning ability assessment method based on AI for personalized data analysis of students according to claim 6 is characterized in that: the operation steps of numerically measuring the learning ability test score result data and the learning ability test time result data and constructing the numerical values into student learning ability test score data are as follows: S61, obtaining the learning ability test score result data Γ ^nengli and the learning ability test time result data t ^nengli ; S62, measuring the ratio of the learning ability test score result data Γ ^nengli and the learning ability test time result data t ^nengli and generating the student learning ability test score data Where Γ ^nengli ranges from [0,100], t ^nengli is in minutes, t ^nengli ranges from [0,60], and e ranges from [0,0.2]. 8. According to the AI-based learning ability assessment method for personalized data analysis of students in claim 7, it is characterized by: the numerical analysis and measurement are performed based on the student learning motivation test score data, the student learning perseverance test score data, and the student learning ability test score data to generate and output the student learning ability comprehensive score calculation result data; the data recognition algorithm is used to compare the student learning ability comprehensive score calculation result data with the student learning ability comprehensive score classification data according to the numerical value of the learning ability comprehensive score, and the operation steps of analyzing and constructing the student learning ability assessment result are as follows: S71, obtaining the student's learning motivation test score data c _A' , the student's learning perseverance test score data d, and the student's learning ability test score data e; S72, numerically analyzing the student learning motivation test score data c _A' , the student learning perseverance test score data d, and the student learning ability test score data e to calculate the student learning ability comprehensive score calculation result data F = c _A' × d × e × 10 ⁴ , where F has a value range of [0, 100]; S73, establish a classification data set of students' comprehensive learning ability scores G = ([0, 30) ^poor , [30, 70) ^normal , [70, 100] ^excellent ), where [0, 30) ^poor means that the comprehensive learning ability score of the student is in the range of [0, 30) and the learning ability is poor; [30, 70) ^Normal means that the comprehensive score of students' learning ability is in the range of [30, 70) and their learning ability is normal; [70, 100] ^Excellent means that the comprehensive score of the student's learning ability is in the range of [70, 100] and the learning ability is excellent; S74, using the data recognition algorithm in step S42, compare the student learning ability comprehensive score calculation result data F with the student learning ability comprehensive score classification data in the student learning ability comprehensive score classification data set G according to the numerical value of the learning ability comprehensive score, match the student learning ability comprehensive score classification data corresponding to the student learning ability comprehensive score calculation result data F and identify and generate the student learning ability evaluation result. 9. A system for implementing a learning ability assessment method based on AI for personalized data analysis of students as described in any one of claims 1 to 8.