Student specialty orientation method and device based on GPS evaluation data

The method and device for student major orientation using GPS evaluation data address subjective major selection issues by integrating cognitive abilities, soft skills, and professional interests, offering precise major recommendations through a systematic approach.

CN119089035AInactive Publication Date: 2024-12-06ASK XIANG EDUCATION TECH (SHANGHAI) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411067009.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing methods for high school students to choose their majors are often based on subjective judgment, leading to incomplete and inaccurate major selection.

Method used

A method and device for student major orientation using GPS evaluation data, including collection, processing, and matching modules to derive professional recommendation information based on underlying cognitive abilities, personal soft skills, and professional interests, utilizing 3PL model algorithms, normalized standard scores, and machine learning for accurate major recommendations.

Benefits of technology

Provides accurate and efficient major recommendations by integrating cognitive abilities, soft skills, and professional interests, helping students identify suitable university majors and career directions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089035A_ABST
    Figure CN119089035A_ABST
Patent Text Reader

Abstract

The invention provides a student specialty orientation method and equipment based on GPS evaluation data, the GPS evaluation data of a student is acquired through an acquisition module, and the GPS evaluation data comprises a bottom cognitive ability display score, a personal soft skill display score and a specialty interest display score of the student; checking and cleaning the collected GPS evaluation data of the students to obtain processed GPS evaluation data of the students; and the specialty category matching model module obtains specialty recommendation information corresponding to the students based on the input processed GPS evaluation data of the students. According to the method, the underlying cognitive competence, personal soft skills and professional interests of the students are combined, the professional category matching model is trained, professional recommendation information can be provided for the students more accurately and efficiently, and the students are helped to locate the directions of future university majors and future occupations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of student major recommendation, and in particular to a student major orientation method and device based on GPS evaluation data. Background Art

[0002] Existing high school students choose their majors mostly manually, which may result in incomplete considerations and inaccurate major selection based on subjective judgment. Summary of the invention

[0003] The purpose of the present invention is to provide a method and device for student major orientation based on GPS evaluation data.

[0004] To solve the above problems, the present invention provides a method and device for student major orientation based on GPS evaluation data, including:

[0005] The collection module obtains the GPS evaluation data of the student, wherein the GPS evaluation data includes: the student's underlying cognitive ability display score, personal soft skill display score and professional interest display score;

[0006] The processing module checks and cleans the collected GPS evaluation data of students to obtain processed GPS evaluation data of students;

[0007] The professional category matching model module obtains the professional recommendation information corresponding to the students based on the input processed GPS evaluation data of the students.

[0008] Furthermore, in the above-mentioned student major orientation method based on GPS assessment data, the acquisition module obtains the student's underlying cognitive ability display score, including:

[0009] Based on the original assessment scores of each dimension i of the student's underlying cognitive ability, the final ability estimate θ of each dimension of the student's underlying cognitive ability is calculated through the 3PL model algorithm of IRT:

[0010]

[0011] Among them, a is the discrimination, b is the difficulty, c is the guessing degree, and d is a constant of 1.702;

[0012] Based on the final ability estimation value θ of each dimension of the student's underlying cognitive ability, the P of each dimension of the student's underlying cognitive ability is calculated through transformation into the normal distribution POZ table, where θ corresponds to Z in the POZ table;

[0013] The underlying cognitive ability display score of each dimension of the student's underlying cognitive ability is calculated using the formula (1-P)*100, rounded to 2 decimal places.

[0014] Furthermore, in the above-mentioned student major orientation method based on GPS assessment data, the acquisition module obtains the student's personal soft skill display score, including:

[0015] Based on the original assessment score of each dimension of the student's personal soft skills, the standard score Z of each dimension of the student's personal soft skills is calculated by the following normalized standard score algorithm:

[0016]

[0017] Among them, X is the original evaluation score of a certain dimension of the student's personal soft skills, μ is the mean of a certain dimension of the student's norm group, and σ is the standard deviation of a certain dimension of the student's norm group;

[0018] Based on the first standard score Z of each dimension of students' personal soft skills, the P of each dimension of students' personal soft skills is calculated through transformation of the normal distribution POZ table;

[0019] The personal soft skill display score for each dimension of the student’s personal soft skills is calculated using the formula (1-P)*100, rounded to 2 decimal places.

[0020] Furthermore, in the above-mentioned student major orientation method based on GPS evaluation data, the acquisition module obtains the student's major interest display score, including:

[0021] Based on the original assessment scores of each dimension of the student's professional interests, the second standard score Z of each dimension of the student's professional interests is calculated by the following normalized standard score algorithm:

[0022]

[0023] Among them, X is the original evaluation score of a certain dimension of the student's professional interest, μ is the mean of a certain dimension of the professional interest of the student's norm group, and σ is the standard deviation of a certain dimension of the professional interest of the student's norm group;

[0024] Based on the second standard score Z of each dimension of students' professional interests, P of each dimension of students' professional interests is calculated through transformation of the normal distribution POZ table;

[0025] The professional interest display score for each dimension of professional interest is calculated using the formula (1-P)*100, rounded to 2 decimal places.

[0026] Furthermore, the above-mentioned student major orientation method based on GPS evaluation data also includes: a major category matching model module, which constructs a major category matching model in the following way:

[0027] The professional category matching model module is based on the average score of the underlying cognitive ability display score and the personal soft skill display score corresponding to each professional category. For each professional category, the evaluation display scores of at least n first-year college students in the professional category are collected, where n = the number of competency dimensions in a professional category + 1;

[0028] The professional category matching model module builds a professional category matching model based on the evaluation scores of each student's competency in each professional category, and selects the optimal matching model of the professional category matching model through big data and machine learning algorithms.

[0029] Furthermore, in the above-mentioned student major orientation method based on GPS evaluation data, the major category matching model module constructs a major category matching model based on the evaluation display score of each student's competency in each major category, and selects the optimal matching model of the major category matching model through big data and machine learning algorithms, including:

[0030] The professional category matching model module uses, for each professional category, the evaluation scores of at least n (n = the number of competency dimensions in a professional category + 1) first-year college students in the professional category and the interest scores of the n first-year college students in the professional category as independent variables;

[0031] The major category matching model module collects the comprehensive academic performance of each major category of the n students when they graduate from university as the dependent variable, and regards the dependent variable as a measure of whether the students are suitable for studying the major category, which serves as the basis for major category matching;

[0032] The professional category matching model module selects one of the machine learning models, establishes a mapping relationship between the independent variables and the dependent variables, applies machine learning and uses cross-validation to verify the calculation effect of the model, and selects the optimal matching model of the professional category matching model from the alternative models.

[0033] Furthermore, in the above-mentioned student major orientation method based on GPS assessment data, the alternative model includes:

[0034] Least squares regression, generalized linear models, lasso regression, ridge regression, and random forests.

[0035] Furthermore, in the above-mentioned student major orientation method based on GPS assessment data, the major category matching model module obtains the student's corresponding major recommendation information based on the input processed student attribute data, including:

[0036] The professional category matching model module predicts the student's future comprehensive academic performance in each professional category based on the evaluation display score of the student's competence in each professional category and the student's interest display score in each professional category, that is, to obtain the student's comprehensive matching index in each professional category;

[0037] The professional category matching model module obtains the student's corresponding professional recommendation information based on the student's comprehensive matching index in various professional categories.

[0038] Furthermore, in the above-mentioned student major orientation method based on GPS evaluation data, the major category matching model module obtains the student's corresponding major recommendation information based on the comprehensive matching index of the student in various major categories, including:

[0039] The professional category matching model module summarizes the comprehensive matching index of students in various professional categories and ranks them in descending order. If the comprehensive matching index scores are the same, they are ranked by professional interest, and then ranked by professional competence.

[0040] The professional category matching model module takes out the corresponding professional category with the top preset name in the comprehensive matching index ranking as the student's advantageous major;

[0041] The professional category matching model module matches the corresponding professional resource library and career resource library according to the students' advantageous majors, including information on professional fields, related major categories and branches, strong universities and related employment directions.

[0042] According to another aspect of the present invention, there is further provided a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: execute any of the methods described above.

[0043] Compared with the prior art, the present invention obtains students' GPS evaluation data through a collection module, wherein the GPS evaluation data shown includes: students' underlying cognitive ability display score, personal soft skill display score and professional interest display score; the collected students' GPS evaluation data are checked and cleaned to obtain processed students' GPS evaluation data; the professional category matching model module obtains students' corresponding professional recommendation information based on the input processed students' GPS evaluation data. The present invention combines students' underlying cognitive ability, personal soft skills and professional interests to train professional category matching models, which can provide students with professional recommendation information more accurately and efficiently, and help students such as high school students locate future university majors and future career directions. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of a method for student major orientation based on GPS assessment data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0046] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (CPU), input / output interfaces, network interfaces and memories.

[0047] 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.

[0048] 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 tape 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 non-transitory media such as modulated data signals and carrier waves.

[0049] like Figure 1 As shown, the student major orientation method based on GPS evaluation data includes: steps S1 to S3, wherein:

[0050] Step S1: The collection module collects students' attribute data.

[0051] Preferably, the attribute data of students include: three types of data: one is the basic information of students, including name, gender, student number, class, grade, and school; the second is the GPS evaluation data of students; and the third is the major and occupation information.

[0052] Preferably, the student's GPS assessment data includes:

[0053] The student's G factor (General aptitudes)-the score showing the underlying cognitive ability, P factor (Personal attributes)-the score showing personal soft skills and S factor (Special interests)-the score showing professional interests.

[0054] Here, the present invention uses a scientific career navigation model GPS to measure and analyze students' G factors (General aptitudes) - underlying cognitive abilities, P factors (Personal attributes) - personal soft skills, and S factors (Special interests) - professional interests, and gives accurate professional recommendation information based on the measurement results.

[0055] Among them, the underlying cognitive abilities include various dimensions such as numerical reasoning, graphic reasoning, spatial perception, textual reasoning, and verbal comprehension;

[0056] Personal soft skills, including analytical ability, leadership and other dimensions;

[0057] Preferably, the acquisition module obtains the student's G factor (General aptitudes) - the underlying cognitive ability display score in the following manner:

[0058] The first step: Based on the original assessment scores of each dimension i of the student's underlying cognitive ability, the final ability estimate θ of each dimension of the student's underlying cognitive ability is calculated through the 3PL model algorithm of IRT:

[0059]

[0060] Among them, a is the discrimination, b is the difficulty, c is the guessing degree, and d is a constant of 1.702;

[0061] Step 1: Based on the final ability estimate θ of each dimension of the student's underlying cognitive ability, calculate the P of each dimension of the student's underlying cognitive ability through the normal distribution POZ table transformation, where θ corresponds to Z in the POZ table;

[0062] Step 13: Calculate the underlying cognitive ability display score of each dimension of the student's underlying cognitive ability by using the formula (1-P)*100, rounded to 2 decimal places;

[0063] Preferably, the acquisition module obtains the student's P factor (Personal attributes) - personal soft skills display score in the following manner:

[0064] Step 2: Based on the original assessment scores of each dimension of the student's personal soft skills, calculate the standard score Z of each dimension of the student's personal soft skills through the following normalized standard score algorithm:

[0065]

[0066] Among them, X is the original evaluation score of a certain dimension of the student's personal soft skills, μ is the mean of a certain dimension of the student's norm group, and σ is the standard deviation of a certain dimension of the student's norm group;

[0067] Step 2: Based on the first standard score Z of each dimension of students’ personal soft skills, calculate the P of each dimension of students’ personal soft skills through the normal distribution POZ table transformation;

[0068] Step 2 and 3: Calculate the personal soft skill display score for each dimension of the student's personal soft skills by using the formula (1-P)*100, rounding to 2 decimal places.

[0069] Preferably, the acquisition module obtains the student's S factor - professional interest display score in the following calculation method:

[0070] Step 3: Based on the original assessment scores of each dimension of the student's professional interests, calculate the second standard score Z for each dimension of the student's professional interests through the following normalized standard score algorithm:

[0071]

[0072] Among them, X is the original evaluation score of a certain dimension of the student's professional interest, μ is the mean of a certain dimension of the professional interest of the student's norm group, and σ is the standard deviation of a certain dimension of the professional interest of the student's norm group;

[0073] Step 3: Based on the second standard score Z of each dimension of students’ professional interests, calculate the P of each dimension of students’ professional interests through transformation of the normal distribution POZ table;

[0074] Step 3 and 4: Calculate the professional interest display score for each dimension of professional interest by using the formula (1-P)*100, rounding to 2 decimal places.

[0075] Specifically, for example, Zhang San’s dimension scores on the “China Student Development GPS Assessment” are shown in the table below.

[0076]

[0077] Step S2: The processing module processes the student's attribute data.

[0078] Preferably, the processing module processes the student's attribute data including GPS evaluation data, including: checking and cleaning the collected student's GPS evaluation data to obtain processed student's GPS evaluation data; ensuring that the processed student's GPS evaluation data meets the data quality requirements of subsequent analysis and calculation steps.

[0079] Step S3: The major category matching model module obtains the major recommendation information corresponding to the student based on the input processed GPS evaluation data of the student.

[0080] The present invention combines students' underlying cognitive abilities, personal soft skills and professional interests to train a professional category matching model, which can provide students with professional recommendation information more accurately and efficiently, and help students identify future university majors and future career directions.

[0081] Preferably, the professional category matching model is constructed in the following way:

[0082] Step 4: The professional category matching model module calculates the evaluation display score of each student's competency in each professional category, that is, the average score of the underlying cognitive ability display score and the personal soft skill display score corresponding to each professional category; for each professional category, the evaluation display scores of at least n first-year college students in the professional category are collected, where n = the number of competency dimensions in a professional category + 1;

[0083] Step 42: The professional category matching model module builds a professional category matching model based on the evaluation display score of each student's professional category competency, and selects the optimal matching model of the professional category matching model through big data and machine learning algorithms. It includes the following sub-steps:

[0084] (1) The professional category matching model module uses, for each professional category, the competency evaluation scores of at least n (n = the number of competency dimensions in a professional category + 1) first-year college students in the professional category and the interest scores of the n first-year college students in the professional category as independent variables;

[0085] (2) The major category matching model module collects the comprehensive academic performance of each major category of the n students when they graduate from college as the dependent variable. The dependent variable is regarded as a measure of whether the students are suitable for studying the major category, which is used as the basis for major category matching, such as the average credit point average (GPA);

[0086] (3) Professional category matching model module, selects one of the machine learning models, establishes a mapping relationship between independent variables and dependent variables, applies machine learning and uses cross-validation to verify the calculation effect of the model, and selects the optimal matching model of the professional category matching model from the alternative models.

[0087] Preferably, the alternative model includes:

[0088] Least squares regression (ordinary least squares regression, OLS), generalized linear model (generalized linear model, GLM), Lasso regression (The Least Absolute Shrinkage and Selection Operator Regression, LASSO regression), ridge regression (ridge regression, RR), random forest (Random Forest, RF).

[0089] Preferably, step S3: the major category matching model module obtains the major recommendation information corresponding to the student based on the input processed attribute data of the student, including:

[0090] Step S31, the professional category matching model module predicts the student's future comprehensive academic performance in each professional category based on the evaluation display score of the student's competence in each professional category and the student's interest display score in each professional category, that is, obtains the student's comprehensive matching index in each professional category;

[0091] Specifically, assuming that the "professional category matching models" after big data training and screening are all LASSO regression (The Least Absolute Shrinkage and Selection Operator Regression, LASSO regression) models, the corresponding competency and professional interest regression coefficients of each major are shown in the following table, without intercept terms.

[0092]

[0093] Based on the above-constructed "professional category matching model", we can derive Zhang San's comprehensive matching index in various professional categories.

[0094] Step S32, the major category matching model module obtains the major recommendation information corresponding to the student based on the comprehensive matching index of the student in various major categories.

[0095] Here, the evaluation scores of the students to be tested in terms of competence in each professional category can be obtained by referring to the fourth step; the interest scores of the students to be tested in each professional category can be obtained by referring to the third step to the third and fourth steps.

[0096] Preferably, in step S32, the major category matching model module obtains the major recommendation information corresponding to the student based on the comprehensive matching index of the student in various major categories, including:

[0097] Step S321, the major category matching model module summarizes the comprehensive matching index of students in various major categories and ranks them in descending order;

[0098] Step S322, the major category matching model module takes out the corresponding major category with the preset name before the comprehensive matching index ranking as the student's advantage major. In the case of the same comprehensive matching index score, the ranking is based on the major interest score, and then the ranking is based on the professional competence score;

[0099] Step S323, the professional category matching model module matches the corresponding professional resource library and career resource library according to the student's advantageous major, including information on professional fields, related major categories and branches, strong universities and related employment directions.

[0100] Specifically, the top five majors can be selected as the students' advantage majors. If the comprehensive matching index scores are the same, they can be ranked by professional interest, and then ranked by professional competence if the scores are the same. As shown in the following table:

[0101]

[0102] According to another aspect of the present invention, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein when the computer-executable instructions are executed by a processor, the processor is caused to execute the method described in any of the above embodiments.

[0103] The detailed contents of the device embodiments of the present invention can be found in the corresponding parts of the method embodiments, which will not be described in detail here.

[0104] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0105] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including related data structures) can be stored in a computer readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some steps or functions of the present invention can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0106] In addition, a part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. The program instruction for calling the method of the present invention may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-bearing medium, and / or stored in a working memory of a computer device that runs according to the program instruction. Here, according to an embodiment of the present invention, a device is included, the device including a memory for storing computer program instructions and a processor for executing program instructions, wherein, when the computer program instruction is executed by the processor, the device is triggered to run the method and / or technical solution based on the aforementioned multiple embodiments of the present invention.

[0107] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for student major orientation based on GPS assessment data, characterized in that: include: The collection module obtains the GPS evaluation data of the student, wherein the GPS evaluation data includes: the student's underlying cognitive ability display score, personal soft skill display score and professional interest display score; The processing module checks and cleans the collected GPS evaluation data of students to obtain processed GPS evaluation data of students; The professional category matching model module obtains the professional recommendation information corresponding to the students based on the input processed GPS evaluation data of the students.

2. The method for student major orientation based on GPS assessment data as claimed in claim 1, characterized in that: The acquisition module obtains students' underlying cognitive ability display scores, including: Based on the original assessment scores of each dimension i of the student's underlying cognitive ability, the final ability estimate θ of each dimension of the student's underlying cognitive ability is calculated through the 3PL model algorithm of IRT: Among them, a is the discrimination, b is the difficulty, c is the guessing degree, and d is a constant of 1.702; Based on the final ability estimation value θ of each dimension of the student's underlying cognitive ability, the P of each dimension of the student's underlying cognitive ability is calculated through transformation into the normal distribution POZ table, where θ corresponds to Z in the POZ table; The underlying cognitive ability display score of each dimension of the student's underlying cognitive ability is calculated using the formula (1-P)*100, rounded to 2 decimal places.

3. The method for student major orientation based on GPS assessment data as claimed in claim 1, characterized in that: The collection module obtains students' personal soft skills display scores, including: Based on the original assessment score of each dimension of the student's personal soft skills, the standard score Z of each dimension of the student's personal soft skills is calculated by the following normalized standard score algorithm: Among them, X is the original evaluation score of a certain dimension of the student's personal soft skills, μ is the mean of a certain dimension of the student's norm group, and σ is the standard deviation of a certain dimension of the student's norm group; Based on the first standard score Z of each dimension of students' personal soft skills, the P of each dimension of students' personal soft skills is calculated through transformation of the normal distribution POZ table; The personal soft skill display score for each dimension of the student’s personal soft skills is calculated using the formula (1-P)*100, rounded to 2 decimal places.

4. The method for student major orientation based on GPS assessment data as claimed in claim 1, characterized in that: The collection module obtains students' professional interest display scores, including: Based on the original assessment scores of each dimension of the student's professional interests, the second standard score Z of each dimension of the student's professional interests is calculated by the following normalized standard score algorithm: Among them, X is the original evaluation score of a certain dimension of the student's professional interest, μ is the mean of a certain dimension of the professional interest of the student's norm group, and σ is the standard deviation of a certain dimension of the professional interest of the student's norm group; Based on the second standard score Z of each dimension of students' professional interests, P of each dimension of students' professional interests is calculated through transformation of the normal distribution POZ table; The professional interest display score for each dimension of professional interest is calculated using the formula (1-P)*100, rounded to 2 decimal places.

5. The method for student major orientation based on GPS assessment data as claimed in claim 1, characterized in that: Also includes: The professional category matching model module builds the professional category matching model in the following way: The professional category matching model module is based on the average score of the underlying cognitive ability display score and the personal soft skill display score corresponding to each professional category. For each professional category, the evaluation display scores of at least n first-year college students in the professional category are collected, where n = the number of competency dimensions in a professional category + 1; The professional category matching model module builds a professional category matching model based on the evaluation scores of each student's competency in each professional category, and selects the optimal matching model of the professional category matching model through big data and machine learning algorithms.

6. The method for student major orientation based on GPS assessment data as claimed in claim 5, characterized in that: The professional category matching model module builds a professional category matching model based on the evaluation display score of each student's competency in each professional category, and selects the optimal matching model of the professional category matching model through big data and machine learning algorithms, including: The professional category matching model module uses, for each professional category, the evaluation scores of at least n first-year college students in the professional category and the interest scores of the n first-year college students in the professional category as independent variables; The major category matching model module collects the comprehensive academic performance of each major category of the n students when they graduate from university as the dependent variable, and regards the dependent variable as a measure of whether the students are suitable for studying the major category, which serves as the basis for major category matching; The professional category matching model module selects one of the machine learning models, establishes a mapping relationship between the independent variables and the dependent variables, applies machine learning and uses cross-validation to verify the calculation effect of the model, and selects the optimal matching model of the professional category matching model from the alternative models.

7. The method for student major orientation based on GPS assessment data as claimed in claim 6, characterized in that: The alternative model includes: Least squares regression, generalized linear models, lasso regression, ridge regression, and random forests.

8. The method for student major orientation based on GPS assessment data as claimed in claim 6, characterized in that: The major category matching model module obtains the major recommendation information corresponding to the student based on the input processed student attribute data, including: The professional category matching model module predicts the student's future comprehensive academic performance in each professional category based on the evaluation display score of the student's competence in each professional category and the student's interest display score in each professional category, that is, to obtain the student's comprehensive matching index in each professional category; The professional category matching model module obtains the student's corresponding professional recommendation information based on the student's comprehensive matching index in various professional categories.

9. The method for student major orientation based on GPS assessment data as claimed in claim 1, characterized in that: The professional category matching model module obtains the student's corresponding professional recommendation information based on the student's comprehensive matching index in various professional categories, including: The professional category matching model module summarizes the comprehensive matching index of students in various professional categories and ranks them in descending order. If the comprehensive matching index scores are the same, they are ranked by professional interest, and then ranked by professional competence. The professional category matching model module takes out the corresponding professional category with the top preset name in the comprehensive matching index ranking as the student's advantageous major; The professional category matching model module matches the corresponding professional resource library and career resource library according to the students' advantageous majors. The professional resource library and career resource library include: professional fields, relevant major categories and branches, strong universities and information on relevant employment directions.

10. A computer-readable storage medium having computer-executable instructions stored thereon, wherein: When the computer executable instructions are executed by a processor, the processor is caused to: perform the method according to any one of claims 1 to 9.