Multi-variable-based college entrance examination application recommendation method and related device

Abstract

The invention discloses a multi-variable-based college entrance examination volunteer recommendation method and a related device, and relates to the technical field of volunteer recommendation, and the method comprises the steps: obtaining college entrance examination basic information inputted by an examinee, and determining an examinee adaptive specialty according to an evaluation result obtained through the online character interest ability evaluation of the examinee; constructing portraits of different majors of each college according to the enrollment plans of different majors of each college and public information in previous years, and determining the total score of the portraits of different majors of each college from multiple dimensions; then, using a pre-trained AI large model to extract and obtain application limit conditions of different majors of each college; and finally, integrating the input basic information of the college entrance examination, the specialties adapted to the examinees, the application limiting conditions of different specialties of the colleges and the total score of the portraits, and carrying out multi-gear application recommendation. According to the application, the score, character, interest and ability characteristics of the examinees, multi-dimensional characteristics of college specialties and application limitation conditions of some specialties are comprehensively considered, and a comprehensive and accurate volunteer recommendation scheme can be provided for the examinees.

Description

Technical Field

[0001] This application relates to the technical field of volunteer recommendation, and particularly to a college entrance examination volunteer recommendation method and related device based on multiple variables. Background Art

[0002] Filling in college entrance examination volunteers is a crucial step for candidates to enter their ideal universities and majors. It not only concerns the candidates' personal interests and career plans but also involves a careful plan for future education and career paths. With the continuous improvement of the informatization level of the college entrance examination, a large amount of data is stored in networks and business information systems. These data contain rich college entrance examination information and potential value. How to quickly and accurately construct an analysis model and generate intuitive and easy-to-understand analysis results is the challenge faced by current college entrance examination volunteer filling.

[0003] Although traditional methods such as the line difference method and ranking method can make certain predictions based on historical data, due to the uncertainties of factors such as college entrance examination policies, enrollment plans, and candidate distributions, these methods do not consider these changing factors, which may lead to inaccurate prediction results, and thus the recommended colleges and majors are not precise enough. In addition, traditional filling methods do not fully consider information such as candidates' personal wishes, interests, abilities, career plans, as well as employment, further education, and admission restrictions for each major, resulting in a low adaptability between the recommended colleges and majors and the candidates. These methods fail to accurately match the personalized characteristics of each candidate, resulting in a large deviation between the recommended results and the candidates' interests, career plans, etc., and unable to provide a comprehensive and accurate volunteer recommendation plan for candidates. Summary of the Invention

[0004] The purpose of this application is to provide a college entrance examination volunteer recommendation method and related device based on multiple variables, which can provide a comprehensive and accurate volunteer recommendation plan for candidates.

[0005] To achieve the above purpose, this application provides the following solutions:

[0006] In the first aspect, this application provides a college entrance examination volunteer recommendation method based on multiple variables, including the following steps:

[0007] Obtain the basic college entrance examination information input by the candidate; the basic college entrance examination information includes basic physical conditions, subjects applied for, scores of each subject, intended application regions, and intended application majors.

[0008] Obtain the evaluation results of the candidate's online personality, interest, and ability assessment, and determine the majors suitable for the candidate; the majors suitable for the candidate are majors that suit the candidate's personality, interest, and ability characteristics, and are used as reference conditions for volunteer recommendation in combination with the intended application majors.

[0009] Construct portraits of different majors in each institution based on the enrollment plans of different majors in each institution and publicly available information from previous years, and determine the total portrait scores of different majors in each institution from multiple dimensions; the total portrait scores of different majors in each institution are used to rank different majors in each institution.

[0010] Using a pre-trained large AI model, extract the admission special requirements noted for different majors in each institution to obtain the admission restriction conditions for different majors in each institution; the admission restriction conditions are used to screen each major in each institution in combination with the basic physical conditions of the candidates, and eliminate the majors of institutions that do not meet the admission special requirements.

[0011] Based on the comprehensive college entrance examination basic information, candidates' suitable majors, the admission restriction conditions of different majors in each institution, and the total portrait scores, provide multi-level volunteer recommendations for candidates; the multi-level volunteer recommendations are to determine several volunteer recommendation levels according to the total college entrance examination scores of the candidates, and under any volunteer recommendation level, recommend the majors with higher rankings and suitable for the candidates among the majors sorted in descending order of the total portrait scores to the candidates.

[0012] Optionally, construct portraits of different majors in each institution based on the enrollment plans of different majors in each institution and publicly available information from previous years, and determine the total portrait scores of different majors in each institution from multiple dimensions, specifically including the following steps:

[0013] Construct portraits of different majors in each institution based on the enrollment plans of different majors in each institution and publicly available information from previous years; the characteristic dimensions of the portraits include school type, school nature, school location, school ranking, characteristic majors, major ranking, enrollment plan, employment prospects, further education prospects, whether it is a newly added institution, and whether it is a newly added major.

[0014] For the portrait of any major in a certain institution, calculate the portrait scores of each dimension of the major based on the publicly available information of the major in previous years.

[0015] Calculate the total portrait score of the major based on the portrait scores of each characteristic dimension of the major and the weight of each characteristic dimension of the major; for candidates in different score segments, calculate the total portrait scores of different majors in each institution using different weight combinations.

[0016] Optionally, based on the comprehensive college entrance examination basic information, candidates' suitable majors, the admission restriction conditions of different majors in each institution, and the total portrait scores, provide multi-level volunteer recommendations for candidates, specifically including the following steps:

[0017] Conduct a preliminary screening of each major in each institution according to the examination subjects of the candidates in the college entrance examination basic information to obtain the set of institution majors after preliminary screening.

[0018] According to the basic physical conditions of the candidates in the college entrance examination basic information and the application restrictions of different majors in each college in the set of colleges and majors after the initial screening, the application restrictions of each college and major are screened to obtain a set of colleges and majors that meet the hard conditions.

[0019] Determine several volunteer recommendation levels according to the total college entrance examination scores of the candidates.

[0020] For any volunteer recommendation level, based on the set of colleges and majors that meet the hard conditions, the majors suitable for the candidates, the intended application regions, and the intended application majors, volunteer recommendations are made for the candidates; when making volunteer recommendations for the candidates, they are sorted according to the total portrait scores of each college and major and then output in descending order.

[0021] Optionally, determine several volunteer recommendation levels according to the total college entrance examination scores of the candidates, which specifically include the following steps:

[0022] Determine the total college entrance examination scores of the candidates according to the scores of each subject of the candidates in the college entrance examination basic information.

[0023] Divide the scores within the preset numerical range above and below the total college entrance examination scores of the candidates into several volunteer recommendation levels; the volunteer recommendation levels include the sprint volunteer recommendation level, the secure volunteer recommendation level, the bottom-guarantee volunteer recommendation level, and the bottom-rank volunteer recommendation level.

[0024] Optionally, when making multi-level volunteer recommendations for the candidates, for any major, it is necessary to display the admission probability of the major for the candidates; the method for recommending college entrance examination volunteers based on multiple variables further includes the following steps:

[0025] Estimate the predicted admission scores of each college and major according to the enrollment plans of each college and major and the previous college entrance examination admission data.

[0026] Calculate the admission probability of the candidates according to the predicted admission scores of each college and major and the total college entrance examination scores of the candidates. Calculate the admission probability of the candidates according to the following formula:

[0027] f(x) = 100 * (1 / (1 + exp((x - the total college entrance examination scores of the candidates) / 10))).

[0028] Among them, f(x) is the admission probability of any major with a predicted admission score of x for the candidates, x is the predicted admission score of any major, and exp() is the natural exponential function.

[0029] Optionally, the online personality interest and ability assessment participated by the candidates includes the Holland vocational interest assessment, the MBTI personality assessment, the multiple intelligence assessment, the values assessment, and the career orientation assessment.

[0030] In a second aspect, the present application provides a college entrance examination volunteer recommendation system based on multiple variables, including:

[0031] The college entrance examination basic information acquisition module is used to acquire the basic information of the college entrance examination input by the examinee; the basic information of the college entrance examination includes basic physical conditions, subjects applied for, scores of each subject, intended regions of application, and intended majors of application.

[0032] The online personality interest and ability evaluation module is used to obtain the evaluation results obtained by the examinee in the online personality interest and ability evaluation, and determine the majors suitable for the examinee; the majors suitable for the examinee are majors that suit the characteristics of the examinee's personality interest and ability, and are used as reference conditions for volunteer recommendation in combination with the intended majors of application.

[0033] The college and major portrait construction module is used to construct portraits of different majors in each college according to the enrollment plans and past public information of different majors in each college, and determine the total portrait scores of different majors in each college from multiple dimensions; the total portrait scores of different majors in each college are used to rank different majors in each college.

[0034] The application restriction condition extraction module is used to use a pre-trained large AI model to extract the application restriction conditions of different majors in each college according to the special admission requirements noted in different majors in each college; the application restriction conditions are used to screen each major in each college in combination with the examinee's basic physical conditions, and eliminate the majors of colleges that do not meet the special admission requirements.

[0035] The multi-gear volunteer recommendation module is used to comprehensively consider the college entrance examination basic information, majors suitable for the examinee, application restriction conditions and total portrait scores of different majors in each college, and recommend volunteers for the examinee in multiple gears; the multi-gear volunteer recommendation is to determine several volunteer recommendation gears according to the total college entrance examination score of the examinee, and under any volunteer recommendation gear, recommend the majors that rank high and are suitable for the examinee among the majors sorted in descending order of the total portrait score to the examinee.

[0036] Thirdly, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the steps of the college entrance examination volunteer recommendation method based on multiple variables described above.

[0037] Fourthly, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the college entrance examination volunteer recommendation method based on multiple variables described above.

[0038] Fifthly, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the college entrance examination volunteer recommendation method based on multiple variables described above.

[0039] According to the specific embodiments provided in this application, the following technical effects are disclosed in this application:

[0040] This application provides a college entrance examination volunteer recommendation method and related device based on multiple variables. In this method, the basic college entrance examination information input by the candidate is obtained, and the majors suitable for the candidate are determined according to the evaluation results obtained from the candidate's participation in the online personality, interest, and ability assessment. Subsequently, according to the enrollment plans and past public information of different majors in each college, portraits of different majors in each college are constructed, and the total scores of the portraits of different majors in each college are determined from multiple dimensions. Then, using a pre-trained large AI model, according to the special admission requirements noted for different majors in each college, the admission restriction conditions for different majors in each college are extracted. Finally, by comprehensively considering the input basic college entrance examination information, the majors suitable for the candidate, the admission restriction conditions for different majors in each college, and the total portrait scores, several volunteer recommendation levels are determined according to the candidate's total college entrance examination score. At any volunteer recommendation level, among the majors sorted in descending order of the total portrait score, the majors with higher rankings and suitable for the candidate are recommended to the candidate. The above solution of this application analyzes the multi-dimensional portraits of the candidate's intentions and college majors, comprehensively considers the candidate's score, personality, interest, and ability characteristics, the multi-dimensional characteristics of college majors, and the admission restriction conditions for some special majors. On the basis of ensuring admission to the greatest extent, a personalized volunteer filling plan is provided for the candidate, avoiding the problems of single and similar recommendations of traditional volunteer filling software, as well as the phenomenon of slipping gears caused by the candidate's score meeting the requirements, but other conditions not meeting the special requirements of the major, and improving the candidate's satisfaction with the volunteer recommendation plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the following described drawings are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a flowchart of a college entrance examination volunteer recommendation method based on multiple variables provided by an embodiment of this application.

[0043] Figure 2 It is a flowchart of step A3 in a college entrance examination volunteer recommendation method based on multiple variables provided by an embodiment of this application.

[0044] Figure 3 It is a flowchart of step A5 in a college entrance examination volunteer recommendation method based on multiple variables provided by an embodiment of this application.

[0045] Figure 4 It is a schematic diagram of the functional modules of a college entrance examination volunteer recommendation system provided by an embodiment of this application.

[0046] Figure 5 The structural schematic diagram of a computer device provided by an embodiment of the present application. Specific implementation manners

[0047] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0048] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0049] A method for recommending college entrance examination volunteers based on multiple variables provided by an embodiment of the present application. In an exemplary embodiment, as Figure 1 shown, it includes the following steps:

[0050] A1. Obtain the basic college entrance examination information input by the candidate; the basic college entrance examination information includes basic physical conditions, subjects to apply for, scores of each subject, intended regions to apply for, and intended majors to apply for.

[0051] For example, the basic college entrance examination information input by the candidate includes the candidate's province (such as Beijing, Shanghai, Anhui, etc.), selected examination subjects (liberal arts / science, physics / chemistry / biology, etc.), candidate scores (total score, scores of each subject), gender (male / female), height (such as 165 cm), vision (E chart), whether color blind, whether color weak, physical conditions (such as stuttering, scars on exposed parts of the body, whether left-handed, whether strabismus, etc.), intended schools to apply for (such as Peking University, Tsinghua University, etc.), intended regions to apply for (such as Beijing, Shanghai, Guangzhou, Shenzhen, etc.), and intended majors to apply for (such as computer science and technology, electronic information engineering, etc.).

[0052] A2. Obtain the evaluation results obtained by the candidate participating in the online personality interest ability evaluation, and determine the majors suitable for the candidate; the majors suitable for the candidate are majors that suit the characteristics of the candidate's personality interest ability and are used as reference conditions for volunteer recommendation in combination with the intended majors to apply for. Specifically, the online personality interest ability evaluation participated by the candidate includes Holland vocational interest evaluation, MBTI personality evaluation, multiple intelligence evaluation, values evaluation, and career tendency evaluation.

[0053] Specifically, in this embodiment, the standard Holland interest assessment, MBTI personality assessment, multiple intelligence assessment, values assessment, and career tendency assessment questionnaires are localized to conform to the language habits of high school students. Candidates answer questions online, and based on the assessment results, the scores of candidates in each dimension are calculated. According to the score situation of the candidates, majors suitable for the candidates are associated.

[0054] A3. According to the enrollment plans of different majors in each institution and the publicly available information in previous years, construct portraits of different majors in each institution, and determine the total portrait scores of different majors in each institution from multiple dimensions; the total portrait scores of different majors in each institution are used to rank different majors in each institution. In this embodiment, as Figure 2 shown, step A3 specifically includes the following steps:

[0055] A31. According to the enrollment plans of different majors in each institution and the publicly available information in previous years, construct portraits of different majors in each institution; the characteristic dimensions of the portraits include school type, school nature, school location, school ranking, characteristic majors, major ranking, enrollment plan, employment prospects, further education prospects, whether it is a newly added institution, and whether it is a newly added major.

[0056] A32. For the portrait of any major in a certain institution, calculate the portrait scores of each dimension of the major according to the publicly available information of the major in previous years.

[0057] A33. Calculate the total portrait score of the major according to the portrait scores of each characteristic dimension of the major and the weight of each characteristic dimension of the major; for candidates in different score segments, different weight combinations are used to calculate the total portrait scores of different majors in each institution.

[0058] Judge the scores input by the candidates in step A1 to determine whether the total college entrance examination score of the candidates is greater than the special admission score line or near the batch line. The recommended solutions for candidates with different scores are different. Specifically, as shown in Table 1 and Table 2, they are the weight designs of different characteristic dimensions in the portraits of each institution and each major when making volunteer recommendations for high-score candidates and low-score candidates.

[0059] Table 1 Weight Design of Different Characteristic Dimensions of the Portrait of Colleges and Majors in High Score Segments

[0060]

[0061]

[0062]

[0063] Table 1 Weight Design of Different Characteristic Dimensions of the Portrait of Colleges and Majors in High Score Segments

[0064]

[0065]

[0066]

[0067] When constructing the portraits of institutions and majors, calculate the scores of each major in each institution on different feature dimensions, and finally obtain the total portrait scores of each major in each institution through weighted calculation, which are used as reference factors for ranking each major when recommending college application plans. The calculation formula for the total portrait score of each major:

[0068]

[0069] Among them: image refers to the total portrait score of each major, K i refers to the weight value of each of the above-mentioned feature dimensions, and S i refers to the score value of each of the above-mentioned feature dimensions.

[0070] A4. Use a pre-trained large AI model to extract the admission special requirements noted for different majors in each institution, and obtain the application restrictions for different majors in each institution; the application restrictions are used to screen each major in each institution in combination with the candidate's basic physical conditions, and eliminate the majors of institutions that do not meet the admission special requirements.

[0071] In an alternative implementation, by using a self-developed large AI model, train it based on the previous enrollment plan data of each major in each institution. After training, give each piece of major note information to the large AI model to extract specified information, such as single-subject score requirements, gender requirements, foreign language language requirements, vision requirements, physical condition requirements, etc.

[0072] In an embodiment, when the large AI model is being trained, taking 5 training samples and 3 feature dimensions as an example, the sample data matrix is expressed as:

[0073]

[0074] If only the true value label y 12 is empty, it means that there is no true value label for the second feature dimension in the training sample x 1 . Then, for the second feature dimension, the label missing ratio = 1 / 5. If the true value labels y 12 and y 32 are empty, it means that there are no true value labels for the second feature dimension in the training samples x 1 and x 3 . Then, for the second feature dimension, the label missing ratio = 2 / 5. The larger the label missing ratio, the more serious the label missing in the corresponding dimension.

[0075] To solve the problem of severe label loss in some feature dimensions, the following weight assignment method based on information entropy and mutual information is adopted to enhance the model's processing ability for data with label loss and improve the accuracy and robustness of the model. Among them, entropy is an index representing the amount of information. The higher the entropy, the greater the information content, the higher the uncertainty, and the more difficult it is to predict. Mutual information is a statistic used to measure the closeness of the relationship between two true value labels, showing the correlation between true value labels. The higher the information entropy of the label, the lower the reliability of the label data, and the greater the mutual information, the higher the correlation between the labels. The calculation formula for the information entropy of the label is expressed as:

[0076]

[0077] In the formula, E j represents the information entropy of the j-th true value label, and p ij represents the probability that the value of the i-th training sample appears on the j-th true value label, and n represents the total number of training samples.

[0078] The calculation formula for mutual information is expressed as:

[0079]

[0080] In the formula, I(Y j ; Y k ) represents the mutual information between labels Y j and Y k , p(y j , y k ) represents the joint probability mass function of labels Y j and Y k , and p(y j ) and p(y k ) respectively represent the marginal probability mass functions of labels Y j and Y k .

[0081] According to the information entropy, mutual information, and label loss ratio, determine the second weight value, using the following formula:

[0082]

[0083] In the formula, w j represents the second weight value of the j-th true value label, m represents the total number of true value labels in any dimension, E j represents the information entropy of the j-th true value label, E k represents the information entropy of the k-th true value label, I(Y j ; Y k ) represents the mutual information between labels Y j and Y kThe mutual information between k ; Y l ) indicates label Y k and Y l The mutual information between them, α represents the label missing ratio in any dimension.

[0084] The weight distribution according to the above formula is more objective and reasonable, ensuring the balance of the importance of each label in different dimensions. It further improves the generalization ability of the model, enables the model to achieve good prediction results on different data sets, and improves the performance and stability of the target prediction model.

[0085] A5. Comprehensively consider the basic college entrance examination information, the candidate's suitable major, the application restrictions of different majors in various colleges and universities, and the total score of the portrait, and make multiple volunteer recommendations for the candidate; multiple volunteer recommendations are to determine several volunteer recommendation levels according to the candidate's total college entrance examination score, and in any volunteer recommendation level, recommend the candidate to the major that is ranked high and suitable for the candidate among the majors sorted in descending order according to the total score of the portrait. In this embodiment, if Figure 3 As shown, step A5 specifically includes the following steps:

[0086] A51. Based on the candidates' application subjects in the basic information of the college entrance examination, the majors of each college are preliminarily screened to obtain the set of college majors after the preliminarily screening. For example, if the candidate's elective subjects are physics, chemistry and biology, then if a certain major in a school requires physics or chemistry as the elective subject, then the major is selected; if another major in a school requires history as the elective subject, then the major does not meet the candidate's elective subject requirements and is not selected.

[0087] A52. According to the basic physical conditions of the examinees in the basic information of the college entrance examination and the application restrictions of different majors in each college in the college major set after the initial screening, the restriction conditions of each college and major are screened to obtain a set of college majors that meet the hard conditions. For example, the information entered by the examinee includes: scores in each subject, gender (male / female), height (such as 165cm), vision (how many in the E-letter table), whether color blind, color weak, physical conditions (such as stuttering, whether there are scars on exposed parts of the body, whether left-handed, strabismus, etc.), etc., combined with the special information of the professional notes in the enrollment plan of each college extracted by AI in step A4, college majors that meet the examinee's conditions are screened; for example: the intelligent medical engineering major of Anhui Medical University, the requirement in the professional notes is: no color blind or color weak examinees are recruited; at the same time, the examinee selected color blindness in "whether color blind" in step A1, so the intelligent medical engineering major of Anhui Medical University is not selected; similarly, the notes in all college majors are checked, and only the majors that meet the physical condition restrictions of the examinee are selected.

[0088] A53. Determine several volunteer recommendation levels according to the total college entrance examination score of the candidate. Specifically, first, determine the total college entrance examination score of the candidate according to the scores of each subject of the candidate in the basic college entrance examination information. Subsequently, divide the scores within a preset numerical range above and below the candidate's total college entrance examination score into several volunteer recommendation levels; the volunteer recommendation levels include the sprint volunteer recommendation level, the secure volunteer recommendation level, the guaranteed volunteer recommendation level, and the bottom volunteer recommendation level. For example, define the school majors with admission scores greater than the candidate's score by 3 - 15 points as sprint volunteers; define the school majors with admission scores greater than the candidate's score by 2 points and within - less than 10 points below the candidate's score as secure volunteers; define the school majors with admission scores less than the candidate's score by 11 - 20 points as guaranteed volunteers; define the school majors with admission scores less than the candidate's score by 21 - 30 points as bottom volunteers; set the number of sprint, secure, guaranteed, and bottom volunteers in different score segments (for example, for 80 volunteers in Zhejiang, the number of sprint volunteers is 16, the number of secure volunteers is 40, the number of guaranteed volunteers is 16, and the number of bottom volunteers is 8, for a total of 80 volunteers).

[0089] A54. For any volunteer recommendation level, conduct volunteer recommendations for the candidate according to the set of college majors that meet the hard conditions, the candidate's suitable majors, the intended application region, and the intended application major; when conducting volunteer recommendations for the candidate, sort according to the total portrait scores of each college major and output in descending order. For example, if the candidate's intended region is Beijing, then give priority to recommending college majors in Beijing; for another example, according to the evaluation results in step A2, this candidate is suitable for studying majors such as computer science and technology, electronic information engineering, etc., then give priority to recommending colleges that recruit majors such as computer science and technology, electronic information engineering, etc.). Among the majors that meet the candidate's target intention, recommend according to the scores of each college major in the college major portrait in step A3, from high to low. Taking Zhejiang as an example, recommend until 16 sprint volunteers are filled.

[0090] As an improved embodiment, when conducting multi - level volunteer recommendations for the candidate in step A5, for any major, it is necessary to display the admission probability of this major for the candidate; arrange them in ascending order of the admission probability of each college major, which is the final volunteer plan for this candidate. Therefore, the method for recommending college entrance examination volunteers based on multiple variables provided by this embodiment further includes the following steps:

[0091] B1. Estimate the predicted admission scores of each college major according to the enrollment plans of each college major and the previous years' college entrance examination admission data.

[0092] Specifically, based on the college entrance examination admission data of previous years matched with the enrollment plan, the institutions and majors of the latest enrollment plan are sorted. The sorting principle is as follows: First, match the college entrance examination admission score data of previous years according to the enrollment plan. Taking the 2024 enrollment plan as an example, match the professional admission scores of each school in 2023 with the enrollment plan of each school in 2024. After the matching, then sort them in descending order according to the admission scores in 2023.

[0093] Among the optional methods, convert the admission scores of each major in the past three years into equivalent scores based on the most recent year (for example, for the major of Computer Science and Technology at Nanjing University, the minimum admission score in 2024 is 690 points, and the minimum ranking is 998; the minimum score in 2023 is 687 points, and the minimum ranking is 1059; the minimum score in 2022 is 676 points, and the minimum ranking is 1165 points; then, based on 2024 as the benchmark, the converted equivalent scores are: 688 points, 689 points, and 690 points respectively for 2022 - 2024).

[0094] Comprehensively consider relevant factors such as the admission scores of each institution's major in the past three years, the enrollment plans of two years, the one - point - one - segment table, the rankings of institutions and majors, employment, and admission rules, etc., to estimate the predicted admission scores of each institution's major. The scores and weights of each dimension index are shown in Table 3.

[0095] Table 3 Score Table of Each Dimension for the Predicted Admission Scores of Institution Majors

[0096]

[0097]

[0098] In Table 3, ME is the enrollment number of this major, ZE is the enrollment number above this major, SE is the number of candidates above this score, and CE is the number of candidates corresponding to this score.

[0099] According to the characteristic dimensions of the above table, calculate the scores of each institution's major in different dimensions. After weighted averaging, obtain a final score for each institution's major as the predicted admission score of each institution's major. The calculation formula for the predicted admission score:

[0100]

[0101] Among them, P_score refers to the predicted score of each institution's major, λ i refers to the weight value of each of the above - mentioned characteristic dimensions, and f i refers to the score value of each of the above - mentioned characteristic dimensions.

[0102] B2. Calculate the admission probability of candidates based on the predicted admission scores of each institution's major and the total college entrance examination scores of candidates. Calculate the admission probability of candidates according to the following formula:

[0103] f(x) = 100 * (1 / (1 + exp((x - the total college entrance examination score of the candidate) / 10))).

[0104] Among them, f(x) is the admission probability of any major with a predicted admission score of x for the candidate, x is the predicted admission score of any major, and exp() is the natural exponential function.

[0105] For the above method of this application, by obtaining the online assessment data of the candidate, it is possible to better understand the candidate's interest, personality, and ability characteristics, and match the professional direction suitable for the candidate's specialties. Compared with the traditional method based on historical admission data, personalized recommendation can more accurately recommend according to the characteristics and needs of the candidate, improving the accuracy and practicality of the recommendation. Secondly, through the enrollment plan, match the college entrance examination admission data of previous years, rank the colleges and majors, and comprehensively consider relevant factors such as the admission scores of each college and major in the past three years, the enrollment plans in the past two years, the one-point-one-section table, colleges, major rankings, employment, and admission rules, etc., to predict the admission probability. It can effectively reduce the impact of factors such as changes in the enrollment plans in the past two years (such as enrollment reduction, enrollment expansion), changes in the application popularity of colleges and majors, etc. on the application, more accurately predict the admission probability of colleges and majors, and improve the accuracy of the recommendation. In addition, by associating information such as the rankings, employment, further education, and special requirements of each major extracted by AI for each college and major, more comprehensive information and more accurate recommendation plans can be provided for the candidate.

[0106] Traditional recommendation methods often only focus on the candidate's scores and the admission situations of previous years' colleges, while ignoring the strength of each college and major, as well as information on employment, further education, and special limited application conditions for majors. However, this recommendation method comprehensively considers multiple factors and can provide more practical recommendation results for candidates. Through the information on employment, candidates can understand the future employment direction and prospects, enabling candidates to more accurately assess the risks of applying to that college and major, and reducing the risks brought by information asymmetry; through the information on special application restrictions for each major extracted by AI, it is ensured that the candidate's physical conditions and other aspects can meet the admission conditions of the major, avoiding the situation in the traditional application system where only the candidate's scores are concerned, resulting in the candidate having sufficient scores but slipping due to some special conditions (such as physical conditions, single-subject scores, etc.) not meeting the major admission requirements.

[0107] Based on the same inventive concept, the embodiments of this application also provide a system for implementing the above-mentioned college entrance examination volunteer recommendation method based on multiple variables. The solution provided by this system to solve the problem is similar to the solution described in the above method. In an exemplary embodiment, as Figure 4 shown, a college entrance examination volunteer recommendation system based on multiple variables is provided, including the following modules:

[0108] The college entrance examination basic information acquisition module is used to acquire the basic information of the college entrance examination input by the candidate; the basic information of the college entrance examination includes basic physical conditions, subjects to apply for, scores of each subject, intended regions to apply for, and intended majors to apply for.

[0109] The online personality interest and ability assessment module is used to obtain the assessment results of the candidate's participation in the online personality interest and ability assessment and determine the majors suitable for the candidate; the majors suitable for the candidate are majors that suit the characteristics of the candidate's personality interest and ability and are used as reference conditions for volunteer recommendation together with the intended majors to apply for.

[0110] The college and major portrait construction module is used to construct portraits of different majors in each college according to the enrollment plans and publicly available information of previous years of different majors in each college, and determine the total scores of the portraits of different majors in each college from multiple dimensions; the total scores of the portraits of different majors in each college are used to rank different majors in each college.

[0111] The application restriction condition extraction module is used to use a pre-trained large AI model to extract the application restriction conditions of different majors in each college according to the special admission requirements noted in different majors in each college; the application restriction conditions are used to screen different majors in each college in combination with the candidate's basic physical conditions, and eliminate the majors of colleges that do not meet the special admission requirements.

[0112] The multi-level volunteer recommendation module is used to comprehensively consider the basic information of the college entrance examination, the majors suitable for the candidate, the application restriction conditions and the total scores of the portraits of different majors in each college, and provide multi-level volunteer recommendations for the candidate; the multi-level volunteer recommendations are to determine several volunteer recommendation levels according to the total score of the candidate's college entrance examination, and under any volunteer recommendation level, recommend the majors that rank among the top and are suitable for the candidate from the majors sorted in descending order of the total scores of the portraits to the candidate.

[0113] Of course, Figure 4 the architecture shown is only exemplary, and when implementing different functions, one or at least two components in the Figure 4 shown system can be omitted according to actual needs.

[0114] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it can implement the college entrance examination volunteer recommendation method based on multiple variables provided in the above embodiments.

[0115] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0116] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0117] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0118] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0119] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0120] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAMs), magnetoresistive random access memories (MRAMs), ferroelectric random access memories (FRAMs), phase change memories (PCMs), graphene memories, etc. Volatile memories can include random access memories (RAMs) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0121] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchains, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0122] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0123] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the present application; at the same time, for those of ordinary skill in the art, according to the ideas of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for recommending college entrance examination volunteers based on multiple variables, characterized in that: include: Obtaining basic college entrance examination information input by the examinee; the basic college entrance examination information includes basic physical condition, examination subjects, scores of each subject, intended examination region, and intended examination major; Obtain the assessment results of the candidate's online personality, interest and ability assessment to determine the candidate's suitable major; the candidate's suitable major is a major that is suitable for the candidate's personality, interest and ability characteristics, and is used in combination with the intended application major as a reference condition for volunteer recommendation; Based on the enrollment plans of different majors in various colleges and universities and the public information of previous years, we build the portraits of different majors in various colleges and universities, and determine the total scores of the portraits of different majors in various colleges and universities from multiple dimensions; The total score of the portraits of different majors in each college is used to rank the different majors in each college; Using the pre-trained AI big model, according to the special admission requirements of different majors in each college, the application restriction conditions of different majors in each college are extracted; the application restriction conditions are used to screen the majors of each college in combination with the basic physical conditions of the candidates, and eliminate the majors of colleges that do not meet the special admission requirements; Based on the basic information of the college entrance examination, the candidate's suitable major, the application restrictions of different majors in various colleges and the total portrait score, multiple levels of volunteer recommendations are made to the candidate; the multiple levels of volunteer recommendation are to determine several volunteer recommendation levels according to the candidate's total college entrance examination score, and under any volunteer recommendation level, the majors that are ranked high and suitable for the candidate will be recommended to the candidate among the majors sorted in descending order according to the total portrait score.

2. The method for recommending college entrance examination volunteers based on multiple variables according to claim 1, characterized in that: Based on the enrollment plans of different majors in various colleges and universities and the public information of previous years, we build the portraits of different majors in various colleges and universities, and determine the total scores of the portraits of different majors in various colleges and universities from multiple dimensions, including: Based on the enrollment plans of different majors in various colleges and universities and public information from previous years, a portrait of different majors in various colleges and universities is constructed; the characteristic dimensions of the portrait include school type, school nature, school region, school ranking, featured majors, major ranking, enrollment plan, employment prospects, prospects for further study, whether new colleges and new majors are added; For the portrait of any major in a certain college, the portrait score of each dimension of the major is calculated based on the public information of the major in previous years; The total portrait score of the major is calculated based on the portrait scores of each characteristic dimension of the major and the weights of each characteristic dimension of the major; for candidates in different score ranges, different weight combinations are used to calculate the total portrait scores of different majors in each college.

3. The method for recommending college entrance examination volunteers based on multiple variables according to claim 2 is characterized in that: Based on the basic college entrance examination information, the candidate's suitable major, the application restrictions of different majors in various colleges and universities, and the total score of the portrait, multiple volunteer recommendations are made for the candidate, including: According to the subjects applied for by the examinees in the basic information of the college entrance examination, preliminary screening is performed on various colleges and majors to obtain a set of colleges and majors after the preliminary screening; According to the basic physical conditions of the examinees in the college entrance examination basic information and the application restriction conditions of different majors in each college in the college major set after the initial screening, the restriction conditions of each major in each college are screened to obtain a set of college majors that meet the hard conditions; According to the total scores of the candidates in the college entrance examination, several volunteer recommendation levels are determined; For any volunteer recommendation level, volunteer recommendations are made for candidates based on the set of colleges and majors that meet the hard conditions, the candidate's suitable major, the intended application area, and the intended application major; when making volunteer recommendations for candidates, they are sorted according to the total portrait scores of each college and major, and then output in descending order.

4. The method for recommending college entrance examination volunteers based on multiple variables according to claim 3 is characterized in that: According to the total score of the candidates in the college entrance examination, several volunteer recommendation levels are determined, including: Determine the total score of the college entrance examination of the examinee according to the scores of each subject of the examinee in the basic information of the college entrance examination; The scores of the candidates' total college entrance examination scores within a preset numerical range are divided into several volunteer recommendation levels; the volunteer recommendation levels include sprint volunteer recommendation levels, safe volunteer recommendation levels, backup volunteer recommendation levels and bottom volunteer recommendation levels.

5. The method for recommending college entrance examination volunteers based on multiple variables according to claim 1, characterized in that: When recommending multiple levels of volunteers to candidates, for any major, it is necessary to display the admission probability of the major to the candidate; the college entrance examination volunteer recommendation method based on multiple variables also includes: According to the enrollment plan of each college and major and the college entrance examination admission data of previous years, the predicted score line of each college and major is estimated; The admission probability of candidates is calculated based on the predicted scores of each major in each college and the total scores of candidates in the college entrance examination; the admission probability of candidates is calculated according to the following formula: f(x)=100*(1 / (1+exp((x-candidate's total college entrance examination score) / 10))); Among them, f(x) is the admission probability of a candidate for any major with a predicted score of x, x is the predicted score of any major, and exp() is the natural exponential function.

6. The method for recommending college entrance examination volunteers based on multiple variables according to claim 5 is characterized in that: The online personality, interest and ability assessments that candidates take include the Holland Vocational Interest Assessment, MBTI Personality Assessment, Multiple Intelligence Assessment, Value Assessment and Career Preference Assessment.

7. A college entrance examination volunteer recommendation system based on multiple variables, characterized in that: include: The college entrance examination basic information acquisition module is used to obtain the college entrance examination basic information input by the examinee; the college entrance examination basic information includes basic physical conditions, application subjects, scores of each subject, intended application area and intended application major; The online personality, interest and ability assessment module is used to obtain the assessment results of the candidates' online personality, interest and ability assessment and determine the candidates' suitable majors; the candidates' suitable majors are majors that are suitable for the candidates' personality, interest and ability characteristics, and are used together with the intended majors as reference conditions for volunteer recommendation; The school major portrait construction module is used to construct portraits of different majors in each school based on the enrollment plans of different majors in each school and the public information of previous years, and determine the total scores of the portraits of different majors in each school from multiple dimensions; The total score of the portraits of different majors in each college is used to rank the different majors in each college; The application restriction extraction module is used to use the pre-trained AI large model to extract the application restriction of different majors in each college according to the special admission requirements of different majors in each college. The application restriction is used to screen the majors of each college in combination with the basic physical conditions of the candidates, and eliminate the majors of colleges that do not meet the special admission requirements. The multi-level volunteer recommendation module is used to make multi-level volunteer recommendations for candidates based on the basic information of the college entrance examination, the candidate's suitable major, the application restrictions of different majors in various colleges and universities, and the total portrait score; the multi-level volunteer recommendation is to determine several volunteer recommendation levels based on the candidate's total college entrance examination score, and under any volunteer recommendation level, the major that is ranked high and suitable for the candidate will be recommended to the candidate among the majors sorted in descending order according to the total portrait score.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the college entrance examination volunteer recommendation method based on multiple variables as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the college entrance examination volunteer recommendation method based on multiple variables as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the college entrance examination volunteer recommendation method based on multiple variables as described in any one of claims 1 to 6.

Images