New college entrance examination application multi-dimensional recommendation system and method based on big data and artificial intelligence

Abstract

The invention discloses a new college entrance examination application multi-dimensional recommendation system and method based on big data and artificial intelligence. The multi-dimensional recommendation method comprises multi-dimensional personalized evaluation including occupational character testing, occupational interest testing, occupational ability evaluation, occupational positioning evaluation and the like, and an evaluation result is combined with a subject selection type to accurately match and recommend a specialty through AI machine learning and deep learning. The multi-dimensional voluntary recommendation system comprises a past year college entrance examination database module, a multi-dimensional evaluation module, an intelligent data processing module, a multi-dimensional voluntary recommendation module and a voluntary scheme display module, and the multi-dimensional voluntary recommendation module comprises multi-dimensional accurate recommendation voluntary such as equivalent order, equivalent score, college priority, specialty priority and region priority. Recommended voluntary willingness is divided into three gradients according to the risk size, and personalized accurate recommendation is carried out on the three gradients. According to the method, subjectivity and blindness of new college entrance examination application filling can be effectively reduced, and scientificity, accuracy and success rate of application are improved.

Description

Technical Field

[0001] This invention relates to the field of college entrance examination application technology, and in particular to a new multi-dimensional recommendation system and method for college entrance examination applications based on big data and artificial intelligence. Background Technology

[0002] College application is a complex and systematic process involving a range of factors, including scores, rankings, elective subjects, city of residence, university reputation, popularity and prospects of majors, number of applicants, and enrollment quotas. Currently, the admission rules in various provinces of my country are based on the candidates' college entrance examination scores for admission, and universities admit students according to their enrollment quotas, either by their college entrance examination scores or their provincial ranking.

[0003] Traditional college application methods typically rely on limited information available to students and parents, subjective judgments, or advice from college application advisors. These methods are not only inefficient and expensive, but also often highly subjective and uninformed, failing to fully consider the individual characteristics and diverse development potential of students.

[0004] With the development of science, some patent applications for college application guidance have emerged in recent years. For example, patent CN119598015 A discloses a method that uses scores, rankings, and elective subjects as input parameters to obtain college application recommendations, and then filters the recommendations based on student preferences. Patent CN 119251020 A, based on big data analysis and artificial intelligence technologies, generates personalized college application plans according to students' personal information and preferences. However, existing college application guidance patents lack multi-dimensional recommendations such as equivalent ranking, equivalent scores, university priority, major priority, and region priority, and do not consider the impact of changes in the number of students, the number of students choosing different subjects, changes in enrollment plans, and changes in provincial control lines each year on the admission or cut-off scores. While some patents, such as CN 120125398 A, use AI large-scale model analysis modules to obtain students' personality traits and provide reference for generating college application plans, and CN 119357467 A, provide preliminary professional recommendations based on users' personality traits, academic strengths and weaknesses, and social and industry needs, their psychological assessments do not directly match professional choices with the new college entrance examination subject selection combinations based on the assessment results. This lack of precise and personalized customization and recommendations leads to the subjectivity, homogenization, or ambiguity of college application plan recommendations, failing to truly meet students' expectations for precision, science, and personalization.

[0005] Research shows that approximately 67% of test-takers are completely unfamiliar with the majors they applied for, 71.2% regret their chosen universities and majors, and 67.9% admit to having made a blind choice when selecting their majors. Therefore, it is particularly urgent to recommend majors based on personalized assessments of students' personality, interests, abilities, strengths, and career inclinations, as well as to recommend majors based on multiple dimensions such as equivalent ranking, equivalent scores, university priority, major priority, and region priority.

[0006] Currently, 29 provinces and municipalities across the country have implemented the new college entrance examination's 3+1+2 or 3+3 subject selection model. To cope with the 12 subject selection options in the 3+1+2 model, the 20 subject selection options in the 3+3 model, and the 35 subject selection options in Zhejiang's 3+3 model (including technical subjects), higher demands are placed on college application recommendations. However, existing college application recommendation methods lack truly personalized and targeted measures, making it difficult to meet the needs of students and parents under the new college entrance examination situation. This necessitates the use of big data and artificial intelligence technologies to personalize the application for candidates and perform multi-dimensional AI matching. Furthermore, it is necessary to utilize multi-dimensional assessments based on psychology, education, and other disciplines, along with AI algorithms, to accurately recommend majors or universities, allowing artificial intelligence technology, supported by big data, to benefit candidates taking the new college entrance examination. Summary of the Invention

[0007] The purpose of this invention is to address the shortcomings of existing technologies by proposing a new multi-dimensional recommendation system and method for college entrance examination applications based on big data and artificial intelligence.

[0008] To achieve the above objectives, the present invention adopts the following technical solution:

[0009] A new college entrance examination application multi-dimensional recommendation system and method based on big data and artificial intelligence, wherein the new college entrance examination application multi-dimensional recommendation method includes: career personality test, career interest test, career ability assessment, career positioning assessment, etc.

[0010] (1) The career personality test involves students filling out a career personality test form in the system. Based on the test results, the Myers-Briggs (MBTI) algorithm is used to obtain the career personality type code. The career personality type code is then combined with the subject selection type to accurately match and recommend majors using AI machine learning and deep learning. The content includes the characteristics of the career personality type, suitable majors and reasons, major coverage, career development direction, etc., for students to refer to when choosing a major.

[0011] (2) The career interest test involves students filling out a career interest test form in the system. Based on the test results, the system uses John Holland's personality-career matching theory to obtain a career interest type code. The career interest type code is then combined with the subject selection type to accurately match and recommend majors using AI machine learning and deep learning. The content includes the characteristics of the career interest type, suitable majors and reasons, major coverage, career development direction, etc., for students to refer to when choosing a major.

[0012] (3) The vocational ability assessment involves students filling out a vocational ability assessment form in the system. Based on the assessment results, the system uses Howard Gardner's theory of multiple intelligences to obtain vocational ability type codes. The vocational ability type codes are then combined with the subject selection type to accurately match and recommend majors using AI machine learning and deep learning. The content includes the characteristics of vocational ability types, suitable majors and reasons, major coverage, career development direction, etc., for students to refer to when choosing a major.

[0013] (4) The career positioning assessment involves students filling out a career positioning assessment form in the system. Based on the assessment results, the Edgar H. Schein career anchor theory is used to obtain the career positioning type code. The career positioning type code is then combined with the subject selection type to accurately match and recommend majors using AI machine learning and deep learning. The content includes the characteristics of the career positioning type, suitable majors and reasons, major coverage, career development direction, etc., for students to refer to when choosing a major.

[0014] A new college entrance examination application multi-dimensional recommendation system and method based on big data and artificial intelligence, wherein the new college entrance examination application multi-dimensional recommendation system includes: a historical college entrance examination database module, a multi-dimensional assessment module, an intelligent data processing module, a multi-dimensional application recommendation module, and an application scheme display module.

[0015] The database module for past college entrance examinations includes: data fields for university introductions, major introductions, admission batches, early admission batches, cut-off scores, major scores, enrollment plans, score distribution, tie-breaking destinations, special admissions, and admission restrictions.

[0016] The multi-dimensional assessment module includes test scales and type codes for occupational personality tests, occupational interest tests, occupational ability assessments, and occupational positioning assessments.

[0017] The intelligent data processing module includes: after receiving the above data, it uses a college application recommendation AI algorithm to analyze historical college entrance examination data and assessment results.

[0018] The multi-dimensional college application recommendation module includes: precise recommendations based on big data and artificial intelligence, such as equivalent ranking, equivalent score, priority of universities, priority of majors, and priority of regions. The recommendation results are divided into three tiers of "ambitious, stable, and safe" based on the level of risk for personalized and precise recommendations.

[0019] The equivalent position: For provinces using the 3+1+2 model, the equivalent ranking is calculated as: the ranking in the college entrance examination that year × [the number of physics (or history) candidates in previous years / the number of physics (or history) candidates in the current year] × [the number of undergraduate (or associate degree) students admitted in physics (or history) in previous years / the number of undergraduate (or associate degree) students admitted in physics (or history) in the current year]; For provinces using the 3+3 model, the equivalent ranking is calculated as follows: (Rank in the college entrance examination of the current year) × (Number of candidates who chose this subject in previous years / Number of candidates who chose this subject in the current year) × (Number of undergraduate (or junior college) students admitted to this subject in previous years / Number of undergraduate (or junior college) students admitted to this subject in the current year).

[0020] Candidates can directly enter their college entrance examination ranking in the "Equivalent Ranking" field of the system. The system will automatically match the equivalent ranking scores from previous years based on the "One-Point-One-Segment Table". It will calculate the average equivalent scores from the previous 3 years or more, add 5-15 points to the "Aim High" score, add 5 points to the "Stable" score and subtract 10 points to the "Safe" score, and subtract 10-30 points to the "Guaranteed" score. The system will automatically lock the matching universities or majors corresponding to the "Aim High", "Stable", and "Guaranteed" scores based on the admission scores of various universities or majors in previous years.

[0021] The equivalent fraction: Equivalent score = Current year's score + (Previous year's provincial control line - Current year's provincial control line). Candidates should directly enter their current year's college entrance examination score in the "Equivalent Score" field of the system, and the system will automatically match it with equivalent scores from previous years. The calculation formula is as follows: For candidates whose scores are above the special control line: Equivalent score = Current year's score + (Previous year's special control line - Current year's special control line); For candidates whose scores are below the special control line but above the undergraduate line: Equivalent score = Current year's score + (Previous year's undergraduate line - Current year's undergraduate line); For candidates whose scores are below the undergraduate admission line but above the junior college admission line: Equivalent score = Current year's score + (Previous year's junior college admission line - Current year's junior college admission line).

[0022] The system calculates the average equivalent score for the previous 3 years or more, adds 5-15 points to the score for "ambitious choice", adds 5 points to the score for "stable choice", and subtracts 10 points from the score for "safe choice". The system will automatically lock the matching universities or majors corresponding to "ambitious choice", "stable choice" and "safe choice" based on the admission scores of each university or major in previous years.

[0023] The "University Priority" policy prioritizes universities when recommending applications. The system considers the overall strength, brand reputation, and social recognition of universities as primary factors, matching eligible universities first, while the choice of major is given relative less weight. The specific calculation method is as follows: The system calculates the average score of the equivalent scores for the previous 3 years or more, adds 5-15 points to the score for "ambitious choice", adds 5 points to the score for "stable choice", and subtracts 10 points to the score for "safe choice". The system will automatically lock the matching universities and majors corresponding to "ambitious choice", "stable choice" and "safe choice" based on the admission scores of each university in previous years.

[0024] The "major priority" refers to prioritizing the applicant's interest in and career plans when recommending majors. The system will prioritize recommending majors that meet the applicant's eligibility criteria, and then consider factors such as the university and location. The specific calculation method is as follows: The system calculates the average score of the equivalent scores and the scores of the same rank over the previous 3 years or more. It adds 5-15 points to the score for "ambitious choice", adds 5 points to the score for "stable choice", and subtracts 10 points to the score for "safe choice". The system will automatically lock the corresponding majors and universities for "ambitious choice", "stable choice" and "safe choice" based on the admission scores of each university in previous years.

[0025] The "regional priority" refers to the system prioritizing the city or region where universities are located when recommending universities, giving preference to institutions and majors within the applicant's preferred region. The specific calculation method is as follows: The system calculates the average score of the equivalent scores for the previous 3 years or more, adds 5-15 points to the score for "ambitious choices", adds 5 points to the score for "stable choices", and subtracts 10 points to the score for "safe choices". The system will automatically lock the list of universities and majors corresponding to "ambitious choices", "stable choices" and "safe choices" based on the admission scores of each university or major in previous years. If a region is selected, the system will further lock all universities or majors in that region that meet the candidate's conditions.

[0026] The volunteer application display module includes: displaying the above-mentioned multi-dimensional recommended volunteer applications based on big data and artificial intelligence, such as equivalent ranking, equivalent score, university priority, major priority and region priority, and displaying the "ambitious, stable and safe" three-tier recommended volunteer applications, including outputting the final recommended universities, majors, regions and their admission probabilities.

[0027] Compared with the prior art, the beneficial effects of the present invention are:

[0028] (1) The core of this invention lies in providing a new multi-dimensional recommendation system and method for college entrance examination applications based on big data and artificial intelligence. The multi-dimensional recommendation method includes personalized recommendations for majors based on multiple dimensions such as career personality test, career interest test, career ability assessment, and career positioning assessment. The multi-dimensional application recommendation system includes: a database module of past college entrance examinations, a multi-dimensional assessment module, an intelligent data processing module, a multi-dimensional application recommendation module, and an application scheme display module. The multi-dimensional application recommendation module includes precise recommendations for applications based on multiple dimensions such as equivalent ranking, equivalent score, university priority, major priority, and region priority, based on big data and artificial intelligence. The recommendation results are divided into three tiers of "ambitious, stable, and safe" based on the risk level for personalized and precise recommendations, and are displayed in the application scheme display module.

[0029] (2) This invention provides a scientific basis for college entrance examination students' college application choices through multi-dimensional personalized assessment and AI multi-dimensional college application recommendations, solving the subjectivity and blindness of students' college application choices and improving the scientific nature, accuracy and success rate of the application. This invention is applicable to high school students in all provinces with the new college entrance examination system, including the 3+1+2 type, 3+3 type, and Zhejiang 3+3 type (including technology subjects). Attached Figure Description

[0030] Figure 1 This is a schematic diagram of the overall system and method for multi-dimensional recommendation of college entrance examination application based on big data and artificial intelligence proposed in this invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0032] like Figure 1 As shown, this invention provides a new multi-dimensional recommendation system and method for college entrance examination applications based on big data and artificial intelligence. The multi-dimensional recommendation system includes: a database module of past college entrance examinations, a multi-dimensional assessment module, an intelligent data processing module, a multi-dimensional application recommendation module, and an application scheme display module.

[0033] The database module for past college entrance examinations includes: data fields for university introductions, major introductions, admission batches, early admission batches, cut-off scores, major scores, enrollment plans, score distribution, tie-breaking arrangements, special admissions, and admission restrictions.

[0034] The multi-dimensional assessment module includes test scales and type codes for occupational personality tests, occupational interest tests, occupational ability assessments, and occupational positioning assessments.

[0035] (1) Career personality test: After the MBTI career personality test, the type code is combined with the subject selection type and AI machine learning and deep learning are used to accurately match and recommend majors. The content includes the characteristics of career personality type, suitable majors and reasons, major coverage, career development direction, etc.

[0036] (2) Career interest test: After the Holland career interest test, the type code is combined with the subject selection type and AI machine learning and deep learning are used to accurately match and recommend majors. The content includes the characteristics of career interest type, suitable majors and reasons, major coverage, career development direction, etc.

[0037] (3) Career ability assessment: After the multiple intelligences test, the type code is combined with the subject selection type and AI machine learning and deep learning are used to accurately match and recommend majors. The content includes the characteristics of career ability type, suitable majors and reasons, major coverage, career development direction, etc.

[0038] (4) Career positioning assessment: After the career anchor assessment, the type code will be combined with the subject selection type to accurately match and recommend majors using AI machine learning and deep learning. The content includes the characteristics of career positioning type, suitable majors and reasons, major coverage, career development direction, etc.

[0039] The intelligent data processing module includes: after receiving the above data, it uses a college application recommendation AI algorithm to analyze historical college entrance examination data and assessment results.

[0040] The multi-dimensional college application recommendation module includes: precise recommendations based on big data and artificial intelligence, such as equivalent ranking, equivalent score, priority of universities, priority of majors, and priority of regions. The recommendation results are divided into three tiers of "ambitious, stable, and safe" based on the level of risk for personalized and precise recommendations.

[0041] (1) Equivalent ranking = the ranking of the college entrance examination in the current year × [the number of candidates who chose this subject in previous years / the number of candidates who chose this subject in the current year] × [the number of undergraduate (or junior college) students admitted to this subject in previous years / the number of undergraduate (or junior college) students admitted to this subject in the current year]. Candidates directly fill in their ranking of the college entrance examination in the "equivalent ranking" field in the system. The system will automatically match the equivalent ranking scores in previous years according to the "one-point-one-section table". It will calculate the average equivalent scores in the previous 3 years or more. Add 5-15 points to the "high-end" score, add 5 points to the "stable" score and subtract 10 points to the "safe" score, and subtract 10-30 points to the "guaranteed" score. The system will automatically lock the matching colleges or majors corresponding to the "high-end", "stable", and "guaranteed" scores according to the admission scores of each university or major in previous years.

[0042] (2) Equivalent score = score of the current year + (previous provincial control line - current provincial control line). Candidates should directly fill in their college entrance examination score of the current year in the "equivalent score" field of the system. The system will automatically match the equivalent scores of previous years and calculate the average equivalent score of the previous 3 years or more. Add 5-15 points to the score as "ambitious choice", add 5 points to the score and subtract 10 points as "stable choice", and subtract 10-30 points as "safe choice". The system will automatically lock the matching colleges or majors corresponding to "ambitious choice", "stable choice" and "safe choice" according to the admission scores of each university or major in previous years.

[0043] (3) Priority for universities: Calculate the average score of the equivalent scores of the same position in the previous 3 years or more, add 5-15 points to the "reaching" university, add 5 points to the "stable" university and subtract 10 points to the "safe" university, and subtract 10-30 points to the "guaranteed" university. The system will automatically lock the matching universities and majors corresponding to "reaching", "stable" and "safe" universities based on the university admission scores of each university in previous years.

[0044] (4) Major priority: Calculate the average score of the equivalent scores of the same position in the previous 3 years or more, add 5-15 points to the "reaching choice", add 5 points to the "stable choice" and subtract 10 points to the "safe choice", and subtract 10-30 points to the "guaranteed choice". The system will automatically lock the majors and universities corresponding to the "reaching choice", "stable choice" and "safe choice" according to the admission scores of each university in previous years.

[0045] (5) Regional priority: Calculate the average score of the equivalent scores of the same position in the previous 3 years or more, add 5-15 points to the "reaching choice", add 5 points to the "stable choice" and subtract 10 points to the "safe choice", and subtract 10-30 points to the "guaranteed choice". The system will automatically lock the list of majors and colleges corresponding to "reaching choice", "stable choice" and "safe choice" based on the admission scores of colleges or majors of each university in previous years. Select the region, and the system will further lock all colleges or majors in the region that meet the candidate's conditions.

[0046] The volunteer application display module includes: displaying the above-mentioned multi-dimensional recommended volunteer applications based on big data and artificial intelligence, such as equivalent ranking, equivalent score, university priority, major priority, and region priority, and displaying the "ambitious, stable, and safe" three-tier recommended volunteer applications, including outputting the final recommended universities, majors, regions, and their admission probabilities.

[0047] The above process will be illustrated with a case study below.

[0048] Zhao is a student from a certain region. Under the new college entrance examination system, the subject selection type is 3+1+2, which is Physics + Chemistry + Geography. In the 2025 college entrance examination, his score was 509 points, ranking 48901.

[0049] Based on the multi-dimensional assessment modules, namely career personality test, career interest test, career ability assessment, and career positioning assessment, Zhao was recommended to apply for majors such as computer science, design, economics, geographic information science, and environmental science.

[0050] Calculated by the intelligent data processing module, Zhao's equivalent average score for the first three years was approximately 501 points, and the average score of his equivalent ranking for the first three years was approximately 503 points.

[0051] Zhao is interested in majors such as "Big Data Science", "Internet of Things Engineering" or "Network Engineering", so based on the admission scores of these majors in previous years, we recommend majors and universities with "major priority".

[0052] Because of his father's poor health, Zhao did not want to attend university in another province and hoped to stay in his local area to take care of his father. Therefore, based on the "regional priority" approach, local universities were recommended. The average score of the equivalent scores from the previous three years was taken as 502 points. 5-15 points were added above as "ambitious choice", 5 points were added above and 10 points were subtracted below as "stable choice", and 10-30 points were subtracted below as "safe choice". The system will automatically lock the corresponding majors and universities for "ambitious choice", "stable choice" and "safe choice" according to the admission scores of universities or majors in previous years.

[0053] Through the "high-stakes, stable, and guaranteed" three-tiered recommendation system, the final application choices are as follows:

[0054] (1) Top choices: Group A102 of universities: “Data Science and Big Data”, “Internet of Things Engineering”, “Intelligent Science and Engineering” and Group A101 of universities: “New Energy Science and Engineering”, “Intelligent Manufacturing Engineering”, “New Energy Materials and Devices”, “Safety Engineering”, “Vehicle Engineering”.

[0055] (2) Stable choices: College B (Big Data Management and Application, Apparel Design and Engineering, Materials Science, Environmental Engineering), College C (New Energy Science and Engineering, Energy and Power Engineering, Environmental Engineering, etc.), College D, etc.

[0056] (3) Guarantee the choice of college: College E, College F, College G.

[0057] Zhao was ultimately admitted to her first choice and first major, Big Data Management and Application, through her "stable application" program.

[0058] It should be understood that the application of the present invention is not limited to the examples above. For those skilled in the art, any improvements or modifications made based on the above description should fall within the protection scope of the appended claims.

Claims

1. A new multi-dimensional recommendation system and method for college entrance examination applications based on big data and artificial intelligence, characterized in that, The new college entrance examination application multi-dimensional recommendation method includes: career personality test, career interest test, career ability assessment, career positioning assessment, etc.

2. The multi-dimensional recommendation method for new college entrance examination applications according to claim 1, characterized in that: The career personality test involves students filling out a career personality test form in the system. Based on the test results, the Myers-Briggs (MBTI) algorithm is used to obtain a career personality type code. The career personality type code is then combined with the subject selection type to accurately match and recommend majors using AI machine learning and deep learning. The content includes the characteristics of the career personality type, suitable majors and reasons, major coverage, career development direction, etc., for students to refer to when choosing a major.

3. The multi-dimensional recommendation method for new college entrance examination applications according to claim 1, characterized in that: The career interest test involves students filling out a career interest test form in the system. Based on the test results, the system uses John Holland's personality-career matching theory to obtain a career interest type code. This code is then combined with the student's chosen subject type and AI machine learning and deep learning to accurately match and recommend majors. The recommendations include the characteristics of the career interest type, suitable majors and reasons, major coverage, career development directions, etc., for students to refer to when choosing a major.

4. The multi-dimensional recommendation method for new college entrance examination applications according to claim 1, characterized in that: The career ability assessment involves students filling out a career ability assessment form in the system. Based on the assessment results, the system uses Howard Gardner's theory of multiple intelligences to obtain career ability type codes. These codes are then combined with the student's chosen subject type and AI machine learning and deep learning are used to accurately match and recommend majors. The recommendations include the characteristics of the career ability type, suitable majors and reasons, major coverage, career development directions, etc., for students to refer to when choosing a major.

5. The multi-dimensional recommendation method for new college entrance examination applications according to claim 1, characterized in that: The career positioning assessment involves students filling out a career positioning assessment form in the system. Based on the assessment results, the system uses Edgar H. Schein's career anchor theory to obtain a career positioning type code. The career positioning type code is then combined with the subject selection type to accurately match and recommend majors using AI machine learning and deep learning. The content includes the characteristics of the career positioning type, suitable majors and reasons, major coverage, career development direction, etc., for students to refer to when choosing a major.

6. A new multi-dimensional recommendation system and method for college entrance examination applications based on big data and artificial intelligence, characterized in that... The new college entrance examination application multi-dimensional recommendation system includes: a historical college entrance examination database module, a multi-dimensional assessment module, an intelligent data processing module, a multi-dimensional application recommendation module, and an application plan display module. Among them: The database module for past college entrance examinations includes: data fields for university introductions, major introductions, admission batches, early admission batches, cut-off scores, major scores, enrollment plans, score distribution, tie-breaking arrangements, special admissions, and admission restrictions. The multi-dimensional assessment module includes: test scales and their type codes for occupational personality tests, occupational interest tests, occupational ability assessments, and occupational positioning assessments; The intelligent data processing module includes: after receiving the above data, it uses a college application recommendation AI algorithm to analyze historical college entrance examination data and assessment results.

7. The new college entrance examination application multi-dimensional recommendation system according to claim 6, characterized in that, The multi-dimensional college application recommendation module includes: precise recommendations based on big data and artificial intelligence, considering equivalent ranking, equivalent score, university priority, major priority, and region priority. Furthermore, it categorizes the recommendations into three tiers—"ambitious," "stable," and "safe"—based on risk level for personalized and precise recommendations. Equivalent ranking = Current year's college entrance examination ranking × [Number of candidates who chose this subject in previous years / Number of candidates who chose this subject in this year] × [Number of undergraduate (or junior college) students admitted to this subject in previous years / Number of undergraduate (or junior college) students admitted to this subject in this year]. Candidates can directly fill in their current year's college entrance examination ranking in the "Equivalent Ranking" field of the system. The system will automatically match the equivalent ranking scores from previous years based on the "One Point One Section Table". It will calculate the average equivalent scores from the previous 3 years or more, add 5-15 points for "Aiming for Top Choice", add 5 points and subtract 10 points for "Stable Choice", and subtract 10-30 points for "Guaranteed Choice". The system will automatically lock the matching universities or majors corresponding to "Aiming for Top Choice", "Stable Choice", and "Guaranteed Choice" based on the admission scores of various universities or majors in previous years. Equivalent score = Current year's score + (Previous year's provincial control line - Current year's provincial control line). Candidates directly fill in their current year's college entrance examination score in the "Equivalent Score" field of the system. The system will automatically match the equivalent scores from previous years and calculate the average equivalent score from the previous 3 years or more. Add 5-15 points to the score for "ambitious choice", add 5 points to the score for "stable choice", and subtract 10 points to the score for "safe choice". Subtract 10-30 points to the score for "guaranteed choice". The system will automatically lock the matching universities or majors corresponding to "ambitious choice", "stable choice", and "safe choice" based on the admission scores of various universities or majors in previous years. University Priority: Calculate the average score of the equivalent scores and equivalent scores of the same rank over the previous 3 years or more, add 5-15 points to the "ambitious choice", add 5 points to the "stable choice" and subtract 10 points to the "safe choice", and subtract 10-30 points to the "guaranteed choice". The system will automatically lock the matching universities and majors corresponding to the "ambitious choice", "stable choice" and "safe choice" based on the university admission scores of each university in previous years. Major Priority: Calculate the average score of the equivalent scores and equivalent scores of the same rank over the past 3 years or more, add 5-15 points to the "ambitious choice", add 5 points to the "stable choice" and subtract 10 points to the "safe choice", and subtract 10-30 points to the "guaranteed choice". The system will automatically lock the majors and universities corresponding to the "ambitious choice", "stable choice" and "safe choice" based on the admission scores of each university in previous years. Region Priority: Calculate the average score of the equivalent scores and equivalent scores of the same rank over the previous 3 years or more. Add 5-15 points to the "ambitious choice", add 5 points to the "stable choice" and subtract 10 points to the "safe choice", and subtract 10-30 points to the "guaranteed choice". The system will automatically lock the corresponding majors and universities for "ambitious choice", "stable choice" and "safe choice" based on the admission scores of each university or major in previous years. Select the region, and the system will further lock all universities or majors in that region that meet the candidate's conditions.

8. The new college entrance examination application multi-dimensional recommendation system according to claim 6, characterized in that: The volunteer application display module showcases the above-mentioned multi-dimensional recommended volunteer applications based on big data and artificial intelligence, including equivalent ranking, equivalent score, university priority, major priority, and region priority. It also displays the "ambitious, stable, and safe" three-tier recommended volunteer applications, including recommended universities, majors, regions, and admission probabilities.

Images