Student guidance data processing method and system based on multiple AI models

Abstract

The invention discloses a multi-AI model-based student guidance data processing method and system. The method comprises the steps of obtaining student parameters and examination data corresponding to a to-be-guided student; inputting the student parameters into a plurality of scheme prediction AI models corresponding to a plurality of associated subjects or associated learning strategies to obtain a plurality of recommended learning schemes; inputting the examination data into a plurality of score analysis AI models corresponding to a plurality of associated subjects or associated learning strategies to obtain a plurality of score analysis results; and integrating and correcting the plurality of recommended learning schemes according to the plurality of score analysis results to obtain a learning guidance scheme of the next stage corresponding to the to-be-guided student. Therefore, comprehensive analysis of the learning condition of the student can be realized based on the multi-subject or multi-strategy AI model, more targeted learning guidance is realized, and the learning guidance effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a student guidance data processing method and system based on multiple AI models. Background Art

[0002] The traditional teaching model has the disadvantages of ignoring individual differences among students, lacking personalized support, and limiting students' initiative. Personalized teaching is student-centered, focusing on meeting students' learning needs and improving learning outcomes. It can better meet students' learning characteristics and needs and cultivate students' lifelong learning ability through personalized teaching resources, the cultivation of autonomous learning and participation, and the provision of personalized feedback. The implementation of personalized teaching will provide students with more targeted and effective education, promote their all-round development and achieve better learning outcomes. The existing technical solutions still rely heavily on manual analysis of students' personalities and learning situations to determine the guidance plan when implementing personalized guidance for students. It does not take into account the AI ​​models corresponding to multiple subjects to achieve a comprehensive prediction of students' guidance plans. Therefore, it is impossible to comprehensively analyze students' learning situations, and the guidance effect is lacking. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a student guidance data processing method and system based on multiple AI models, which can realize a comprehensive analysis of students' learning situation based on multi-subject or multi-strategy AI models, realize more targeted learning guidance, and improve the learning guidance effect.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a student guidance data processing method based on multiple AI models, the method comprising: Obtain student parameters and test data corresponding to the students to be guided; Inputting the student parameters into multiple program prediction AI models corresponding to multiple related subjects or related learning strategies to obtain multiple recommended learning programs; Inputting the test data into multiple performance analysis AI models corresponding to multiple related subjects or related learning strategies to obtain multiple performance analysis results; The plurality of recommended learning plans are integrated and corrected according to the plurality of performance analysis results to obtain a learning guidance plan for the next stage corresponding to the student to be guided.

[0005] As an optional embodiment, in the first aspect of the present invention, the student parameters include student grade, student age, student class, student gender and student physiological parameters.

[0006] As an optional implementation, in the first aspect of the present invention, the inputting of the student parameters into multiple program prediction AI models corresponding to multiple associated subjects or associated learning strategies to obtain multiple recommended learning programs includes: According to the preset correspondence rules between the student parameters and the learning subjects or learning strategies, determining a plurality of associated subjects and a plurality of associated learning strategies corresponding to the student parameters; Determine in a preset prediction model library the solution prediction AI model corresponding to each of the associated subjects and the solution prediction AI model corresponding to each of the associated learning strategies; The student parameters are input into each of the solution prediction AI models to obtain multiple recommended learning solutions output by multiple solution prediction AI models.

[0007] As an optional embodiment, in the first aspect of the present invention, the associated learning strategy is a cognitive strategy, a metacognitive strategy or a resource management strategy; the cognitive strategy is a repetition strategy, an elaboration strategy or an organization strategy; the metacognitive strategy is a planning strategy, a monitoring strategy or an adjustment strategy; the solution prediction AI model is an LLM model, which is trained by a training data set including multiple training learning parameters related to corresponding associated subjects or associated learning strategies and corresponding recommended learning solutions.

[0008] As an optional implementation, in the first aspect of the present invention, the test data is input into multiple performance analysis AI models corresponding to multiple associated subjects or associated learning strategies to obtain multiple performance analysis results, including: Inputting the test data into a preset type classifier algorithm model to obtain data portions of multiple different test types in the test data; the test types are pre-study test, review test, mid-term test, final test, single subject test or cross-subject test; Determine in a preset prediction model library the AI ​​model for grade analysis corresponding to each of the associated subjects and the AI ​​model for grade analysis corresponding to each of the associated learning strategies; the AI ​​model for grade analysis is an LLM model, which is obtained by training a training data set including a plurality of test data and corresponding grade analysis conclusion annotations; The data portion is input into each of the performance analysis AI models to obtain multiple performance analysis results output by multiple performance analysis AI models.

[0009] As an optional implementation, in the first aspect of the present invention, the step of inputting the data portion into each of the performance analysis AI models to obtain a plurality of performance analysis results output by the plurality of performance analysis AI models comprises: For each of the performance analysis AI models, obtain historical training records and historical analysis records of the performance analysis AI model; Calculating a first similarity between the test type corresponding to each of the data portions and the test type labels in all the test data in the historical training record; Calculating a second similarity between the test type corresponding to each of the data parts and the test type information in all analyzed input test data in the historical analysis record; Calculating the scores of the first similarity and the second similarity corresponding to each of the data parts to obtain a matching degree corresponding to each of the data parts; Determine the union of all the data parts whose matching degree is higher than a preset matching degree threshold as the test data to be analyzed corresponding to the score analysis AI model; The corresponding test data to be analyzed is input into each of the performance analysis AI models to obtain multiple performance analysis results output by multiple performance analysis AI models.

[0010] As an optional implementation, in the first aspect of the present invention, the integrating and correcting the multiple recommended learning plans according to the multiple performance analysis results to obtain the next stage of learning guidance plan corresponding to the student to be guided includes: Calculating the intersection of the analysis conclusions in the multiple performance analysis results to obtain a set of analysis conclusions corresponding to the student to be guided; Calculating the guidance matching degree between each analysis conclusion in the analysis conclusion set and each recommended learning scheme; For each of the recommended learning schemes, a weighted sum average of all the guidance matching degrees corresponding to the recommended learning scheme is calculated to obtain a matching parameter corresponding to the recommended learning scheme; Calculate the average value of the similarity between the content of the recommended learning solution and the content of all other recommended learning solutions to obtain reasonable parameters of the solution corresponding to the recommended learning solution; Calculate the product of the matching parameter and the reasonable parameter of the scheme to obtain the recommended parameter of the recommended learning scheme; Sorting all the recommended learning schemes from high to low according to the recommended parameters to obtain a scheme sequence; Determine the first recommended learning scheme in the scheme sequence as a basic learning scheme, and determine a preset number of recommended learning schemes other than the basic learning scheme in the scheme sequence as correction learning schemes; All the correction learning plans are combined into prompts for correction instructions, and are input into a preset LLM model together with the basic learning plan to obtain the output of the next stage of learning guidance plan corresponding to the student to be guided.

[0011] As an optional implementation, in the first aspect of the present invention, the calculating the guidance matching degree between each analysis conclusion in the analysis conclusion set and each recommended learning scheme includes: For each analysis conclusion and each recommended learning solution in the analysis conclusion combination, the analysis conclusion is input into the solution prediction AI model corresponding to the recommended learning solution to obtain a re-recommended solution as output; Calculating a first similarity between the recommended learning solution and the re-recommended solution; Input all pre-application test data in the historical application record corresponding to the recommended learning plan into the performance analysis AI model corresponding to the analysis conclusion to obtain an output re-analysis result; Calculating a second similarity between the analysis conclusion and the re-analysis result; The product of the first similarity and the second similarity is calculated to obtain a guidance matching degree between the analysis conclusion and the recommended learning plan.

[0012] A second aspect of an embodiment of the present invention discloses a student guidance data processing system based on multiple AI models, the system comprising: An acquisition module is used to acquire student parameters and test data corresponding to the students to be guided; A recommendation module, used for inputting the student parameters into multiple program prediction AI models corresponding to multiple related subjects or related learning strategies to obtain multiple recommended learning programs; An analysis module, used for inputting the test data into multiple performance analysis AI models corresponding to multiple related subjects or related learning strategies to obtain multiple performance analysis results; The guidance module is used to integrate and correct the multiple recommended learning plans according to the multiple performance analysis results to obtain a learning guidance plan for the next stage corresponding to the student to be guided.

[0013] As an optional embodiment, in the second aspect of the present invention, the student parameters include student grade, student age, student class, student gender and student physiological parameters.

[0014] As an optional implementation, in the second aspect of the present invention, the recommendation module inputs the student parameters into multiple program prediction AI models corresponding to multiple associated subjects or associated learning strategies to obtain a specific method of multiple recommended learning programs, including: According to the preset correspondence rules between the student parameters and the learning subjects or learning strategies, determining a plurality of associated subjects and a plurality of associated learning strategies corresponding to the student parameters; Determine in a preset prediction model library the solution prediction AI model corresponding to each of the associated subjects and the solution prediction AI model corresponding to each of the associated learning strategies; The student parameters are input into each of the solution prediction AI models to obtain multiple recommended learning solutions output by multiple solution prediction AI models.

[0015] As an optional embodiment, in the second aspect of the present invention, the associated learning strategy is a cognitive strategy, a metacognitive strategy or a resource management strategy; the cognitive strategy is a repetition strategy, an elaboration strategy or an organization strategy; the metacognitive strategy is a planning strategy, a monitoring strategy or an adjustment strategy; the solution prediction AI model is an LLM model, which is trained by a training data set including multiple training learning parameters related to corresponding associated subjects or associated learning strategies and corresponding recommended learning solutions.

[0016] As an optional implementation, in the second aspect of the present invention, the analysis module inputs the test data into multiple performance analysis AI models corresponding to multiple associated subjects or associated learning strategies to obtain multiple performance analysis results, including: Inputting the test data into a preset type classifier algorithm model to obtain data portions of multiple different test types in the test data; the test types are pre-study test, review test, mid-term test, final test, single subject test or cross-subject test; Determine in a preset prediction model library the AI ​​model for grade analysis corresponding to each of the associated subjects and the AI ​​model for grade analysis corresponding to each of the associated learning strategies; the AI ​​model for grade analysis is an LLM model, which is obtained by training a training data set including a plurality of test data and corresponding grade analysis conclusion annotations; The data portion is input into each of the performance analysis AI models to obtain multiple performance analysis results output by multiple performance analysis AI models.

[0017] As an optional implementation, in the second aspect of the present invention, the specific manner in which the analysis module inputs the data portion into each of the performance analysis AI models to obtain multiple performance analysis results output by multiple performance analysis AI models includes: For each of the performance analysis AI models, obtain historical training records and historical analysis records of the performance analysis AI model; Calculating a first similarity between the test type corresponding to each of the data portions and the test type labels in all the test data in the historical training record; Calculating a second similarity between the test type corresponding to each of the data parts and the test type information in all analyzed input test data in the historical analysis record; Calculating the scores of the first similarity and the second similarity corresponding to each of the data parts to obtain a matching degree corresponding to each of the data parts; Determine the union of all the data parts whose matching degree is higher than a preset matching degree threshold as the test data to be analyzed corresponding to the score analysis AI model; The corresponding test data to be analyzed is input into each of the performance analysis AI models to obtain multiple performance analysis results output by multiple performance analysis AI models.

[0018] As an optional implementation, in the second aspect of the present invention, the guidance module integrates and corrects the multiple recommended learning plans according to the multiple performance analysis results to obtain a specific method of the next stage of learning guidance plan corresponding to the student to be guided, including: Calculating the intersection of the analysis conclusions in the multiple performance analysis results to obtain a set of analysis conclusions corresponding to the student to be guided; Calculating the guidance matching degree between each analysis conclusion in the analysis conclusion set and each recommended learning scheme; For each of the recommended learning schemes, a weighted sum average of all the guidance matching degrees corresponding to the recommended learning scheme is calculated to obtain a matching parameter corresponding to the recommended learning scheme; Calculate the average value of the similarity between the content of the recommended learning solution and the content of all other recommended learning solutions to obtain reasonable parameters of the solution corresponding to the recommended learning solution; Calculate the product of the matching parameter and the reasonable parameter of the scheme to obtain the recommended parameter of the recommended learning scheme; Sorting all the recommended learning schemes from high to low according to the recommended parameters to obtain a scheme sequence; Determine the first recommended learning scheme in the scheme sequence as a basic learning scheme, and determine a preset number of recommended learning schemes other than the basic learning scheme in the scheme sequence as correction learning schemes; All the correction learning plans are combined into prompts for correction instructions, and are input into a preset LLM model together with the basic learning plan to obtain the output of the next stage of learning guidance plan corresponding to the student to be guided.

[0019] As an optional implementation, in the second aspect of the present invention, the specific manner in which the guidance module calculates the guidance matching degree between each analysis conclusion in the analysis conclusion set and each recommended learning scheme includes: For each analysis conclusion and each recommended learning solution in the analysis conclusion combination, the analysis conclusion is input into the solution prediction AI model corresponding to the recommended learning solution to obtain a re-recommended solution as output; Calculating a first similarity between the recommended learning solution and the re-recommended solution; Input all pre-application test data in the historical application record corresponding to the recommended learning plan into the performance analysis AI model corresponding to the analysis conclusion to obtain an output re-analysis result; Calculating a second similarity between the analysis conclusion and the re-analysis result; The product of the first similarity and the second similarity is calculated to obtain a guidance matching degree between the analysis conclusion and the recommended learning plan.

[0020] The third aspect of the present invention discloses another student guidance data processing system based on multiple AI models, the system comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part or all of the steps in the student guidance data processing method based on multiple AI models disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps in the student guidance data processing method based on multiple AI models disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention can implement solution recommendation and performance analysis based on the solution prediction AI model and performance analysis AI model corresponding to multiple related subjects or related learning strategies, and integrate the most comprehensive and matching learning guidance plan for students based on the analysis results and recommendation results, thereby being able to implement a comprehensive analysis of students' learning situation based on multi-subject or multi-strategy AI models, achieve more targeted learning guidance, and improve the effectiveness of learning guidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flowchart of a student guidance data processing method based on multiple AI models disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural schematic diagram of a student guidance data processing system based on multiple AI models disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural schematic diagram of another student guidance data processing system based on multiple AI models disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0028] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The present invention discloses a student guidance data processing method and system based on multiple AI models, which can implement solution recommendation and score analysis based on solution prediction AI models and score analysis AI models corresponding to multiple related subjects or related learning strategies, and integrate the most comprehensive and matching learning guidance solutions for students based on the analysis results and recommendation results, so as to realize comprehensive analysis of students' learning situations based on multi-subject or multi-strategy AI models, realize more targeted learning guidance, and improve learning guidance effects. The following are detailed descriptions.

[0031] Embodiment 1 See also Figure 1 , Figure 1 : is a flow chart of a method for processing student guidance data based on multiple AI models disclosed in an embodiment of the present invention. Figure 1 The described student guidance data processing method based on multiple AI models can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the student guidance data processing method based on multiple AI models may include the following operations: 101. Obtain student parameters and test data corresponding to the students to be guided.

[0032] 102. Input the student parameters into multiple program prediction AI models corresponding to multiple related subjects or related learning strategies to obtain multiple recommended learning programs. 103. Input the test data into multiple performance analysis AI models corresponding to multiple related subjects or related learning strategies to obtain multiple performance analysis results. 104. Integrate and correct multiple recommended learning plans based on multiple performance analysis results to obtain a learning guidance plan for the next stage corresponding to the students to be guided.

[0033] It can be seen that the above-mentioned embodiments of the invention can implement solution recommendation and performance analysis based on the solution prediction AI model and performance analysis AI model corresponding to multiple related subjects or related learning strategies, and integrate the most comprehensive and matching learning guidance plan for students based on the analysis results and recommendation results, thereby being able to implement a comprehensive analysis of students' learning situation based on multi-subject or multi-strategy AI models, achieve more targeted learning guidance, and improve the effectiveness of learning guidance.

[0034] As an optional embodiment, in the above steps, the student parameters include student grade, student age, student class, student gender and student physiological parameters.

[0035] It can be seen that through the above optional embodiments, the content of student parameters is clarified, which can more accurately and comprehensively characterize the student situation, assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of the student's learning situation, achieve more targeted learning guidance, and improve the learning guidance effect.

[0036] As an optional embodiment, in the above steps, the student parameters are input into multiple program prediction AI models corresponding to multiple related subjects or related learning strategies to obtain multiple recommended learning programs, including: According to the preset correspondence rules between the student parameters and the learning subjects or learning strategies, a plurality of associated subjects and a plurality of associated learning strategies corresponding to the student parameters are determined; Determine the solution prediction AI model corresponding to each associated subject and the solution prediction AI model corresponding to each associated learning strategy in the preset prediction model library; The student parameters are input into each solution prediction AI model to obtain multiple recommended learning solutions output by multiple solution prediction AI models.

[0037] It can be seen that through the above-mentioned optional embodiments, it is possible to predict multiple recommended learning plans corresponding to student parameters based on the plan prediction AI model corresponding to multiple related subjects and multiple related learning strategies, so as to facilitate subsequent integration and correction to obtain the most comprehensive and matching learning guidance plan for students, and assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of students' learning situation, achieve more targeted learning guidance, and improve the learning guidance effect.

[0038] As an optional embodiment, in the above steps, the associated learning strategy is a cognitive strategy, a metacognitive strategy or a resource management strategy; the cognitive strategy is a repetition strategy, an elaboration strategy or an organization strategy; the metacognitive strategy is a planning strategy, a monitoring strategy or an adjustment strategy; the solution prediction AI model is an LLM model, which is obtained by training a training data set including multiple training learning parameters related to corresponding associated subjects or associated learning strategies and corresponding recommended learning solutions.

[0039] It can be seen that through the above-mentioned optional embodiments, the types of learning strategies and the model details of the solution prediction AI model are limited, so that multiple recommended learning plans corresponding to student parameters can be predicted in the subsequent period, so as to facilitate subsequent integration and correction to obtain the most comprehensive and matching learning guidance plan for students, and assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of students' learning situation, realize more targeted learning guidance, and improve the learning guidance effect.

[0040] As an optional embodiment, in the above steps, the test data is input into multiple performance analysis AI models corresponding to multiple related subjects or related learning strategies to obtain multiple performance analysis results, including: Input the test data into a preset type classifier algorithm model to obtain data portions of multiple different test types in the test data; optionally, the test type is a pre-study test, a review test, a mid-term test, a final test, a single subject test, or a cross-subject test; Determine the performance analysis AI model corresponding to each associated subject and the performance analysis AI model corresponding to each associated learning strategy in the preset prediction model library; optionally, the performance analysis AI model is an LLM model, which is trained by a training data set including a plurality of test data and corresponding performance analysis conclusion annotations; The data portion is input into each performance analysis AI model to obtain multiple performance analysis results output by multiple performance analysis AI models.

[0041] It can be seen that through the above-mentioned optional embodiments, it is possible to predict multiple score analysis results corresponding to the test data based on the score analysis AI model corresponding to multiple related subjects and multiple related learning strategies, so as to facilitate subsequent integration and correction to obtain the most comprehensive and matching learning guidance plan for students, and assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of students' learning situation, achieve more targeted learning guidance, and improve the learning guidance effect.

[0042] As an optional embodiment, in the above steps, the data part is input into each performance analysis AI model to obtain multiple performance analysis results output by multiple performance analysis AI models, including: For each performance analysis AI model, obtain the historical training records and historical analysis records of the performance analysis AI model; Calculate a first similarity between the test type corresponding to each data portion and the test type labels in all test data in the historical training record; calculating a second similarity between the test type corresponding to each data portion and the test type information in all analyzed input test data in the historical analysis record; Calculate the scores of the first similarity and the second similarity corresponding to each data part to obtain the matching degree corresponding to each data part; The union of all data parts with a matching degree higher than a preset matching degree threshold is determined as the test data to be analyzed corresponding to the score analysis AI model; The corresponding test data to be analyzed is input into each score analysis AI model to obtain multiple score analysis results output by multiple score analysis AI models.

[0043] It can be seen that through the above-mentioned optional embodiments, the corresponding data to be analyzed can be screened out from the test data based on the historical training records and historical analysis records of each performance analysis AI model for analyzing multiple performance analysis results corresponding to the test data, so as to facilitate subsequent integration and correction to obtain the most comprehensive and matching learning guidance plan for students, and assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of students' learning situation, achieve more targeted learning guidance, and improve the effectiveness of learning guidance.

[0044] As an optional embodiment, in the above steps, the multiple recommended learning plans are integrated and corrected according to the multiple performance analysis results to obtain the next stage of learning guidance plan corresponding to the students to be guided, including: Calculate the intersection of the analysis conclusions in the multiple performance analysis results to obtain the analysis conclusion set corresponding to the students to be guided; Calculate the guidance matching degree between each analysis conclusion in the analysis conclusion set and each recommended learning plan; For each recommended learning plan, calculate the weighted sum average of all guidance matching degrees corresponding to the recommended learning plan to obtain the matching parameter corresponding to the recommended learning plan; Calculate the average value of the similarity between the content of the recommended learning solution and the content of all other recommended learning solutions to obtain reasonable parameters of the solution corresponding to the recommended learning solution; Calculate the product of the matching parameters and the reasonable parameters of the scheme to obtain the recommended parameters of the recommended learning scheme; Sort all recommended learning schemes from high to low according to the recommended parameters to obtain a scheme sequence; The first recommended learning plan in the plan sequence is determined as the basic learning plan, and the first preset number of recommended learning plans in the plan sequence other than the basic learning plan are determined as correction learning plans; All correction learning plans are composed of prompts for correction instructions, and are input into the preset LLM model together with the basic learning plan to obtain the output of the next stage of learning guidance plan corresponding to the students to be guided.

[0045] It can be seen that through the above-mentioned optional embodiments, it is possible to screen out more suitable recommended learning plans by calculating the matching parameters between the analysis conclusions and the recommended learning plans, as well as calculating the similarity between the content of the recommended learning plans and other plans, and fine-tune the basic optimal plan based on the recommended learning plans with lower suitability according to the LLM model to obtain the optimal learning guidance plan, and realize a comprehensive analysis of students' learning situation based on a multi-subject or multi-strategy AI model, achieve more targeted learning guidance, and improve the learning guidance effect.

[0046] As an optional embodiment, in the above step, calculating the guidance matching degree between each analysis conclusion in the analysis conclusion set and each recommended learning scheme includes: For each analysis conclusion and each recommended learning plan in the analysis conclusion combination, the analysis conclusion is input into the plan prediction AI model corresponding to the recommended learning plan to obtain the output re-recommended plan; Calculating a first similarity between the recommended learning solution and the re-recommended solution; Input all pre-application test data in the historical application records corresponding to the recommended learning plan into the performance analysis AI model corresponding to the analysis conclusion to obtain an output re-analysis result; Calculating a second similarity between the analysis conclusion and the re-analysis result; The product of the first similarity and the second similarity is calculated to obtain a guidance matching degree between the analysis conclusion and the recommended learning scheme.

[0047] It can be seen that through the above-mentioned optional embodiments, it is possible to cross-re-predict the analysis conclusions and recommended learning plans to accurately calculate the degree of guidance matching between the two, so as to assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of students' learning situation, achieve more targeted learning guidance, and improve the learning guidance effect.

[0048] Embodiment 2 See also Figure 2 , Figure 2 : is a schematic diagram of a student guidance data processing system based on multiple AI models disclosed in an embodiment of the present invention. Figure 2 The described student guidance data processing system based on multiple AI models can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the student guidance data processing system based on multiple AI models may include: The acquisition module 201 is used to acquire student parameters and test data corresponding to the students to be guided.

[0049] The recommendation module 202 is used to input student parameters into multiple program prediction AI models corresponding to multiple related subjects or related learning strategies to obtain multiple recommended learning programs. The analysis module 203 is used to input the test data into multiple performance analysis AI models corresponding to multiple related subjects or related learning strategies to obtain multiple performance analysis results. The guidance module 204 is used to integrate and correct multiple recommended learning plans according to multiple performance analysis results to obtain a learning guidance plan for the next stage corresponding to the students to be guided.

[0050] It can be seen that the above-mentioned embodiments of the invention can implement solution recommendation and performance analysis based on the solution prediction AI model and performance analysis AI model corresponding to multiple related subjects or related learning strategies, and integrate the most comprehensive and matching learning guidance plan for students based on the analysis results and recommendation results, thereby being able to implement a comprehensive analysis of students' learning situation based on multi-subject or multi-strategy AI models, achieve more targeted learning guidance, and improve the effectiveness of learning guidance.

[0051] As an optional embodiment, the student parameters include student grade, student age, student class, student gender and student physiological parameters.

[0052] It can be seen that through the above optional embodiments, the content of student parameters is clarified, which can more accurately and comprehensively characterize the student situation, assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of the student's learning situation, achieve more targeted learning guidance, and improve the learning guidance effect.

[0053] As an optional embodiment, the recommendation module inputs the student parameters into multiple program prediction AI models corresponding to multiple related subjects or related learning strategies to obtain a specific method of recommending multiple learning programs, including: According to the preset correspondence rules between the student parameters and the learning subjects or learning strategies, a plurality of associated subjects and a plurality of associated learning strategies corresponding to the student parameters are determined; Determine the solution prediction AI model corresponding to each associated subject and the solution prediction AI model corresponding to each associated learning strategy in the preset prediction model library; The student parameters are input into each solution prediction AI model to obtain multiple recommended learning solutions output by multiple solution prediction AI models.

[0054] It can be seen that through the above-mentioned optional embodiments, it is possible to predict multiple recommended learning plans corresponding to student parameters based on the plan prediction AI model corresponding to multiple related subjects and multiple related learning strategies, so as to facilitate subsequent integration and correction to obtain the most comprehensive and matching learning guidance plan for students, and assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of students' learning situation, achieve more targeted learning guidance, and improve the learning guidance effect.

[0055] As an optional embodiment, the associated learning strategy is a cognitive strategy, a metacognitive strategy or a resource management strategy; the cognitive strategy is a repetition strategy, an elaboration strategy or an organization strategy; the metacognitive strategy is a planning strategy, a monitoring strategy or an adjustment strategy; the solution prediction AI model is an LLM model, which is trained by a training data set including multiple training learning parameters related to corresponding associated subjects or associated learning strategies and corresponding recommended learning solutions.

[0056] It can be seen that through the above-mentioned optional embodiments, the types of learning strategies and the model details of the solution prediction AI model are limited, so that multiple recommended learning plans corresponding to student parameters can be predicted in the subsequent period, so as to facilitate subsequent integration and correction to obtain the most comprehensive and matching learning guidance plan for students, and assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of students' learning situation, realize more targeted learning guidance, and improve the learning guidance effect.

[0057] As an optional embodiment, the analysis module inputs the test data into multiple performance analysis AI models corresponding to multiple related subjects or related learning strategies to obtain multiple performance analysis results, including: Input the test data into a preset type classifier algorithm model to obtain data portions of multiple different test types in the test data; optionally, the test type is a pre-study test, a review test, a mid-term test, a final test, a single subject test, or a cross-subject test; Determine the performance analysis AI model corresponding to each associated subject and the performance analysis AI model corresponding to each associated learning strategy in the preset prediction model library; optionally, the performance analysis AI model is an LLM model, which is trained by a training data set including a plurality of test data and corresponding performance analysis conclusion annotations; The data portion is input into each performance analysis AI model to obtain multiple performance analysis results output by multiple performance analysis AI models.

[0058] It can be seen that through the above-mentioned optional embodiments, it is possible to predict multiple score analysis results corresponding to the test data based on the score analysis AI model corresponding to multiple related subjects and multiple related learning strategies, so as to facilitate subsequent integration and correction to obtain the most comprehensive and matching learning guidance plan for students, and assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of students' learning situation, achieve more targeted learning guidance, and improve the learning guidance effect.

[0059] As an optional embodiment, the specific manner in which the analysis module inputs the data portion into each performance analysis AI model to obtain multiple performance analysis results output by multiple performance analysis AI models includes: For each performance analysis AI model, obtain the historical training records and historical analysis records of the performance analysis AI model; Calculate a first similarity between the test type corresponding to each data portion and the test type labels in all test data in the historical training record; calculating a second similarity between the test type corresponding to each data portion and the test type information in all analyzed input test data in the historical analysis record; Calculate the scores of the first similarity and the second similarity corresponding to each data part to obtain the matching degree corresponding to each data part; The union of all data parts with a matching degree higher than a preset matching degree threshold is determined as the test data to be analyzed corresponding to the score analysis AI model; The corresponding test data to be analyzed is input into each score analysis AI model to obtain multiple score analysis results output by multiple score analysis AI models.

[0060] It can be seen that through the above-mentioned optional embodiments, the corresponding data to be analyzed can be screened out from the test data based on the historical training records and historical analysis records of each performance analysis AI model for analyzing multiple performance analysis results corresponding to the test data, so as to facilitate subsequent integration and correction to obtain the most comprehensive and matching learning guidance plan for students, and assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of students' learning situation, achieve more targeted learning guidance, and improve the effectiveness of learning guidance.

[0061] As an optional embodiment, the guidance module integrates and corrects multiple recommended learning plans according to multiple performance analysis results to obtain a specific method for the next stage of learning guidance plan corresponding to the student to be guided, including: Calculate the intersection of the analysis conclusions in the multiple performance analysis results to obtain the analysis conclusion set corresponding to the students to be guided; Calculate the guidance matching degree between each analysis conclusion in the analysis conclusion set and each recommended learning plan; For each recommended learning plan, calculate the weighted sum average of all guidance matching degrees corresponding to the recommended learning plan to obtain the matching parameter corresponding to the recommended learning plan; Calculate the average value of the similarity between the content of the recommended learning solution and the content of all other recommended learning solutions to obtain reasonable parameters of the solution corresponding to the recommended learning solution; Calculate the product of the matching parameters and the reasonable parameters of the scheme to obtain the recommended parameters of the recommended learning scheme; Sort all recommended learning schemes from high to low according to the recommended parameters to obtain a scheme sequence; The first recommended learning plan in the plan sequence is determined as the basic learning plan, and the first preset number of recommended learning plans in the plan sequence other than the basic learning plan are determined as correction learning plans; All correction learning plans are composed of prompts for correction instructions, and are input into the preset LLM model together with the basic learning plan to obtain the output of the next stage of learning guidance plan corresponding to the students to be guided.

[0062] It can be seen that through the above-mentioned optional embodiments, it is possible to screen out more suitable recommended learning plans by calculating the matching parameters between the analysis conclusions and the recommended learning plans, as well as calculating the similarity between the content of the recommended learning plans and other plans, and fine-tune the basic optimal plan based on the recommended learning plans with lower suitability according to the LLM model to obtain the optimal learning guidance plan, and realize a comprehensive analysis of students' learning situation based on a multi-subject or multi-strategy AI model, achieve more targeted learning guidance, and improve the learning guidance effect.

[0063] As an optional embodiment, the specific manner in which the guidance module calculates the guidance matching degree between each analysis conclusion in the analysis conclusion set and each recommended learning scheme includes: For each analysis conclusion and each recommended learning plan in the analysis conclusion combination, the analysis conclusion is input into the plan prediction AI model corresponding to the recommended learning plan to obtain the output re-recommended plan; Calculating a first similarity between the recommended learning solution and the re-recommended solution; Input all pre-application test data in the historical application records corresponding to the recommended learning plan into the performance analysis AI model corresponding to the analysis conclusion to obtain an output re-analysis result; Calculating a second similarity between the analysis conclusion and the re-analysis result; The product of the first similarity and the second similarity is calculated to obtain a guidance matching degree between the analysis conclusion and the recommended learning scheme.

[0064] It can be seen that through the above-mentioned optional embodiments, it is possible to cross-re-predict the analysis conclusions and recommended learning plans to accurately calculate the degree of guidance matching between the two, so as to assist in realizing an AI model based on multiple subjects or multiple strategies to achieve a comprehensive analysis of students' learning situation, achieve more targeted learning guidance, and improve the learning guidance effect.

[0065] Embodiment 3 See also Figure 3 , Figure 3 It is another student guidance data processing system based on multiple AI models disclosed in an embodiment of the present invention. Figure 3 The described student guidance data processing system based on multiple AI models is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the student guidance data processing system based on multiple AI models may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the student guidance data processing method based on multiple AI models described in the first embodiment.

[0066] Embodiment 4 An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the student-guided data processing method based on multiple AI models described in the first embodiment.

[0067] Embodiment 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the student guidance data processing method based on multiple AI models described in Example 1.

[0068] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0070] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0071] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0072] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0075] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0076] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0077] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0079] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0080] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0081] Finally, it should be noted that the student guidance data processing method and system based on multiple AI models disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical scheme of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical schemes described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical schemes from the spirit and scope of the technical schemes of the embodiments of the present invention.

Claims

1. A student guidance data processing method based on multiple AI models, characterized in that: The method comprises: Obtain student parameters and test data corresponding to the students to be guided; Inputting the student parameters into multiple program prediction AI models corresponding to multiple related subjects or related learning strategies to obtain multiple recommended learning programs; Inputting the test data into multiple performance analysis AI models corresponding to multiple related subjects or related learning strategies to obtain multiple performance analysis results; The plurality of recommended learning plans are integrated and corrected according to the plurality of performance analysis results to obtain a learning guidance plan for the next stage corresponding to the student to be guided.

2. The student guidance data processing method based on multiple AI models according to claim 1 is characterized in that: The student parameters include student grade, student age, student class, student gender and student physiological parameters.

3. The student guidance data processing method based on multiple AI models according to claim 2 is characterized in that: The step of inputting the student parameters into multiple program prediction AI models corresponding to multiple related subjects or related learning strategies to obtain multiple recommended learning programs includes: According to the preset correspondence rules between the student parameters and the learning subjects or learning strategies, determining a plurality of associated subjects and a plurality of associated learning strategies corresponding to the student parameters; Determine in a preset prediction model library the solution prediction AI model corresponding to each of the associated subjects and the solution prediction AI model corresponding to each of the associated learning strategies; The student parameters are input into each of the solution prediction AI models to obtain multiple recommended learning solutions output by multiple solution prediction AI models.

4. The student guidance data processing method based on multiple AI models according to claim 3 is characterized in that: The associated learning strategy is a cognitive strategy, a metacognitive strategy or a resource management strategy; the cognitive strategy is a repetition strategy, an elaboration strategy or an organization strategy; the metacognitive strategy is a planning strategy, a monitoring strategy or an adjustment strategy; the solution prediction AI model is an LLM model, which is trained by a training data set including multiple training learning parameters related to corresponding associated subjects or associated learning strategies and corresponding recommended learning solutions.

5. The student guidance data processing method based on multiple AI models according to claim 3 is characterized in that: The test data is input into multiple performance analysis AI models corresponding to multiple related subjects or related learning strategies to obtain multiple performance analysis results, including: Inputting the test data into a preset type classifier algorithm model to obtain data portions of multiple different test types in the test data; the test types are pre-study test, review test, mid-term test, final test, single subject test or cross-subject test; Determine in a preset prediction model library the AI ​​model for grade analysis corresponding to each of the associated subjects and the AI ​​model for grade analysis corresponding to each of the associated learning strategies; the AI ​​model for grade analysis is an LLM model, which is obtained by training a training data set including a plurality of test data and corresponding grade analysis conclusion annotations; The data portion is input into each of the performance analysis AI models to obtain multiple performance analysis results output by multiple performance analysis AI models.

6. The student guidance data processing method based on multiple AI models according to claim 5 is characterized in that: The step of inputting the data portion into each of the performance analysis AI models to obtain a plurality of performance analysis results output by the plurality of performance analysis AI models includes: For each of the performance analysis AI models, obtain historical training records and historical analysis records of the performance analysis AI model; Calculating a first similarity between the test type corresponding to each of the data portions and the test type labels in all the test data in the historical training record; Calculating a second similarity between the test type corresponding to each of the data parts and the test type information in all analyzed input test data in the historical analysis record; Calculating the scores of the first similarity and the second similarity corresponding to each of the data parts to obtain a matching degree corresponding to each of the data parts; Determine the union of all the data parts whose matching degree is higher than a preset matching degree threshold as the test data to be analyzed corresponding to the score analysis AI model; The corresponding test data to be analyzed is input into each of the performance analysis AI models to obtain multiple performance analysis results output by multiple performance analysis AI models.

7. The student guidance data processing method based on multiple AI models according to claim 1 is characterized in that: The integrating and correcting the plurality of recommended learning plans according to the plurality of performance analysis results to obtain a learning guidance plan for the next stage corresponding to the student to be guided includes: Calculating the intersection of the analysis conclusions in the multiple performance analysis results to obtain a set of analysis conclusions corresponding to the student to be guided; Calculating the guidance matching degree between each analysis conclusion in the analysis conclusion set and each recommended learning scheme; For each of the recommended learning schemes, a weighted sum average of all the guidance matching degrees corresponding to the recommended learning scheme is calculated to obtain a matching parameter corresponding to the recommended learning scheme; Calculate the average value of the similarity between the content of the recommended learning solution and the content of all other recommended learning solutions to obtain reasonable parameters of the solution corresponding to the recommended learning solution; Calculate the product of the matching parameter and the reasonable parameter of the scheme to obtain the recommended parameter of the recommended learning scheme; Sorting all the recommended learning schemes from high to low according to the recommended parameters to obtain a scheme sequence; Determine the first recommended learning scheme in the scheme sequence as a basic learning scheme, and determine a preset number of recommended learning schemes other than the basic learning scheme in the scheme sequence as correction learning schemes; All the correction learning plans are combined into prompts for correction instructions, and are input into a preset LLM model together with the basic learning plan to obtain the output of the next stage of learning guidance plan corresponding to the student to be guided.

8. The method for processing student guidance data based on multiple AI models according to claim 7, characterized in that: The calculating the guidance matching degree between each analysis conclusion in the analysis conclusion set and each recommended learning scheme includes: For each analysis conclusion and each recommended learning solution in the analysis conclusion combination, the analysis conclusion is input into the solution prediction AI model corresponding to the recommended learning solution to obtain a re-recommended solution as output; Calculating a first similarity between the recommended learning solution and the re-recommended solution; Input all pre-application test data in the historical application record corresponding to the recommended learning plan into the performance analysis AI model corresponding to the analysis conclusion to obtain an output re-analysis result; Calculating a second similarity between the analysis conclusion and the re-analysis result; The product of the first similarity and the second similarity is calculated to obtain a guidance matching degree between the analysis conclusion and the recommended learning plan.

9. A student guidance data processing system based on multiple AI models, characterized in that: The system comprises: An acquisition module is used to acquire student parameters and test data corresponding to the students to be guided; A recommendation module, used for inputting the student parameters into multiple program prediction AI models corresponding to multiple related subjects or related learning strategies to obtain multiple recommended learning programs; An analysis module, used for inputting the test data into multiple performance analysis AI models corresponding to multiple related subjects or related learning strategies to obtain multiple performance analysis results; The guidance module is used to integrate and correct the multiple recommended learning plans according to the multiple performance analysis results to obtain a learning guidance plan for the next stage corresponding to the student to be guided.

10. A student guidance data processing system based on multiple AI models, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the student guidance data processing method based on multiple AI models as described in any one of claims 1-8.

Images