College entrance examination voluntary reporting auxiliary system and method

Abstract

The invention discloses a college entrance examination voluntary reporting auxiliary system and method, and relates to the technical field of voluntary reporting, and the system comprises a data obtaining module which is used for obtaining user data and social industry demand data, evaluating strong subjects and vulnerable subjects of users based on the scores of the users, and marking the strong subjects and the vulnerable subjects; and the specialty recommendation module is used for carrying out character testing on the user, carrying out preliminary specialty recommendation based on character characteristics and subject strength conditions of the user, and further screening out specialties matched with industry development through social industry demand data. By collecting character test data and social industry demand data and combining user subject conditions, it is ensured that recommended professions not only accord with user interests and capabilities, but also coincide with future industry development trends, and by calculating admission probabilities of different schools, the risk of volunteer filling errors is reduced, and the experience of colleges is improved. The recommendation list is adjusted in real time according to the personal preference of the user, so that the personalized requirements of the user are met, and the accuracy and flexibility of the recommendation result are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of volunteer application, and in particular to an auxiliary system and method for filling out college entrance examination volunteer application. Background Art

[0002] In recent years, with the development of information technology and the widespread application of big data analysis, intelligent systems in the field of education have continued to emerge. Especially in the process of filling out college entrance examination applications, traditional manual experience guidance and static volunteer recommendation models are gradually unable to meet the increasingly diverse needs of modern users. Existing volunteer application systems usually rely on users' college entrance examination scores, admission scores over the years, school rankings and other information to provide users with relatively single volunteer suggestions. This traditional recommendation method often ignores the user's personalized needs, future career planning and the dynamic changes in social industry development. There is still room for further improvement in providing users with a comprehensive, personalized and forward-looking volunteer application plan. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing college entrance examination volunteer filling auxiliary system and method, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that the traditional volunteer application auxiliary system needs to be further improved in providing users with a comprehensive, personalized and forward-looking volunteer application plan.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a college entrance examination volunteer filling auxiliary system, which includes a data acquisition module for acquiring user data and social industry demand data, and evaluating the user's strong and weak subjects based on the user's grades and marking them;

[0006] The professional recommendation module is used to conduct personality tests on users, make preliminary professional recommendations based on the user's personality characteristics and subject strengths and weaknesses, and further screen out majors that match industry development through social industry demand data, and generate a professional recommendation list based on the screened majors;

[0007] The school recommendation module is used to select the corresponding school based on the major recommendation list, calculate the admission probability of different schools and generate a preliminary volunteer recommendation list;

[0008] The feedback improvement module is used to adjust the recommendation list in real time according to the user's personal preference data and store the final generated volunteer recommendation list.

[0009] As a preferred solution of the college entrance examination volunteer application auxiliary system of the present invention, wherein: the acquisition of user data and social industry demand data, and the evaluation of the user's strong and weak subjects based on the user's scores and marking them means that after the user enters the admission ticket number and ID number to log in to the system, the user's college entrance examination scores and provincial rankings are obtained from the education department database according to the user's admission ticket number, and the current enrollment policy and related college entrance examination rules are loaded at the same time, and the industry demand data of the entire society is obtained from multiple data sources;

[0010] Collect the user's previous test data, including mock test scores, regular test scores, and final test scores, and arrange the user's scores in chronological order, calculate the user's growth rate in each subject, and evaluate the user's learning progress in each subject:

[0011]

[0012] In the formula, represents the growth rate of the i-th subject, A i is the highest score in the history of the user, o is the learning rate, t0 is the turning point time of the user's learning progress, C i represents the user's initial score, T1 represents the time when the user took the first exam in the subject, and T n Indicates the user's latest exam time in this subject, T u is the time interval, N is the number of exams the user has taken in the subject, and W l,i is the user's latest test score in the subject, W k,i is the user's score in the kth exam, dt is a small time increment, and n represents the number of times the user takes the subject exam;

[0013] Compare the user's current score with the score distribution of users across the province, calculate the user's ranking percentile in the subject, and calculate the user's historical average growth rate. If the user's subject growth rate is higher than its own historical average growth rate, and the provincial ranking percentile corresponding to the user's current subject score is in the top 40% in the province, then mark the subject as a strong subject. If the user's subject growth rate is lower than its own historical average growth rate, and the provincial ranking percentile corresponding to the user's current subject score is in the bottom 40% in the province, then mark the subject as a weak subject.

[0014] As a preferred solution of the college entrance examination volunteer application auxiliary system of the present invention, wherein: the personality test of the user and the preliminary professional recommendation based on the personality characteristics and subject strengths of the user refer to guiding the user to use the MBTI personality assessment tool to take a personality test after the user logs into the system, and guiding the user to fill in the career planning information after the personality test, the user can select the target career field and personal career goals, and the personality test results of the user are combined with the filled-in career planning information to establish a mapping relationship between the career planning and the personality test results;

[0015] According to the user's personality type and career plan, matching major categories are screened out. If the user's personality type is INTP and the career plan is science and engineering, technical majors such as computer science, engineering, and data science are recommended first. If the user's personality type is ESFJ and the career plan is social services, social work, psychology, and education are recommended first.

[0016] In the matched professional categories, a mapping table is constructed according to the subject requirements of different majors to define the subjects required for each major. For each major, the matching degree is calculated based on the user's strong subjects, and the majors are sorted in descending order according to the matching scores to generate a preliminary professional recommendation list.

[0017] As a preferred solution of the college entrance examination volunteer filling auxiliary system of the present invention, wherein: the further screening of majors matching the industry development through social industry demand data, and generating a professional recommendation list based on the screened majors refers to using the LFA topic model to extract industry representative keywords from the industry classification standards and industry reports of the National Bureau of Statistics and market research to construct an industry label library, and the industry label library includes industry names, representative keywords and industry numbers;

[0018] After preprocessing the collected social industry demand data, the TF-IDF algorithm is used to extract high-frequency keywords related to industry demand from the collected social industry demand data, calculate the frequency of each keyword in various data sources, and use the frequency of occurrence as a preliminary indicator of discussion heat. The discussion heat of each data source is weighted averaged to generate the comprehensive discussion heat of each keyword;

[0019] Through the pre-trained BERT model, the keywords and keywords in the industry tag library are converted into context-aware vector representations. The cosine similarity is used to calculate the similarity between each keyword and all keywords in the industry tag library, and the maximum similarity value is taken as the matching degree between the keyword and the industry in the industry tag library.

[0020] Set a similarity judgment threshold Q, retain keywords that are higher than the similarity judgment threshold Q, and create a keyword-industry matching matrix, where each element represents the matching degree between a keyword and an industry;

[0021] For each industry, traverse the relevant keywords, calculate the contribution value of each keyword to the industry's demand index, add up the contribution values ​​of all keywords, and get the industry's comprehensive demand index;

[0022] Sort the industries in descending order according to the comprehensive demand index of each industry, and generate a preliminary list of high-demand industries including industry names and demand indexes;

[0023] Collect historical job demand data of high-demand industries, pre-process the collected historical job demand data, use the ARIMA model to predict the changing trend of future job demand, input the pre-processed historical data into the ARIMA model as a training set for model training, use the loss function and Adam optimizer to iteratively optimize the model parameters to obtain the optimized ARIMA model, and input the real-time job demand data into the ARIMA model to obtain the predicted data of future job demand;

[0024] Score each high-demand industry based on the predicted occupational demand data, calculate the job demand growth rate, and sort the industries in descending order based on the calculation results to form an industry trend score table. Use the Pearson correlation coefficient to evaluate the similarity of job demand growth trends in various industries, identify majors with similar demand in different industries, generate a list of cross-industry hot majors based on the analysis results, and sort the majors according to the job demand growth rate in different industries to generate a hot major recommendation list. Combined with the hot major recommendation list, screen the preliminary major recommendation list to generate the final major recommendation list.

[0025] As a preferred solution of the college entrance examination volunteer application auxiliary system of the present invention, wherein: the selecting corresponding schools based on the professional recommendation list, calculating the admission probability of different schools and generating a preliminary volunteer recommendation list refers to obtaining the professional admission data of colleges and universities throughout the country over the years, including the minimum admission score, admission ratio and number of admissions for the corresponding major of each school, and pre-processing the collected data, screening out colleges and universities offering corresponding majors according to the professional recommendation list and establishing a mapping relationship between majors and schools;

[0026] Use the Logistic regression model to predict the probability of a user being admitted to a school. Use the preprocessed college admission data of previous years as the training set to input into the Logistic regression model for model training. Define the loss function and Adam optimizer to iteratively optimize the model parameters. When the loss of the Logistic regression model no longer decreases significantly during the continuous iteration process, stop iterating and output the model parameters to update the Logistic regression model.

[0027] The user's real-time college entrance examination data is input into the Logistic regression model to obtain the probability value of being admitted to the school, and the schools are sorted in descending order according to the obtained admission probability values ​​to generate a preliminary volunteer recommendation list.

[0028] As a preferred solution of the college entrance examination volunteer application auxiliary system of the present invention, the real-time adjustment of the recommendation list according to the user's personal preference data refers to collecting the user's preference data, including geographical location, school level, major prospects and admission risk, and allowing the user to set priority weights for different preference types, using the features of the feature engineering privilege preliminary volunteer recommendation list and the user's preference features and comparing them, and calculating the preference matching degree M of each recommendation item:

[0029]

[0030] Where, T B is the feature matching value of the Bth item preference, w B is the weight set by the user, T max is the maximum matching value of the feature, and E is the number of user preferences;

[0031] According to the calculation results of the matching degree, all schools and majors are sorted in descending order, and schools and majors with high matching degrees are recommended to users first to generate the final volunteer recommendation list.

[0032] As a preferred solution of the college entrance examination volunteer application auxiliary system described in the present invention, the storage of the finally generated volunteer recommendation list refers to displaying the recommendation results to the user, and displaying the matching degree with the user's preferences and the specific matching reasons next to each school and major, and storing the final volunteer recommendation list locally and in the cloud in Excel format, encrypting the stored volunteer recommendation list file and implementing access control.

[0033] Another object of the present invention is to provide a method for assisting college entrance examination volunteer filling, which comprises:

[0034] Obtain user data and social industry demand data, evaluate the user's strong and weak subjects based on the user's performance and mark them;

[0035] Conduct personality tests on users, make preliminary professional recommendations based on their personality traits and subject strengths, further screen out majors that match industry development through social industry demand data, and generate a professional recommendation list based on the screened majors;

[0036] Select the corresponding school based on the professional recommendation list, calculate the admission probability of different schools and generate a preliminary volunteer recommendation list, adjust the recommendation list in real time according to the user's personal preference data and store the final volunteer recommendation list.

[0037] A computer device includes: a memory and a processor; the memory stores a computer program, and the processor implements the steps of a college entrance examination volunteer filling auxiliary system when executing the computer program.

[0038] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a college entrance examination volunteer filling auxiliary system.

[0039] The beneficial effects of the present invention are as follows: the present invention collects personality test data and social industry demand data and combines the user's subject situation to ensure that the recommended majors not only meet the user's interests and abilities, but also are consistent with future industry development trends. By calculating the admission probability of different schools, the risk of errors in volunteer applications is reduced. The recommendation list is adjusted in real time according to the user's personal preferences to meet the user's personalized needs and improve the accuracy and flexibility of the recommendation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0041] Figure 1 This is a structural diagram of the college entrance examination application assistance system.

[0042] Figure 2 Schematic diagram of the implementation process of the professional recommendation list generation process.

[0043] Figure 3 This is a flow chart of the auxiliary method for filling out college entrance examination applications. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0047] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a system for assisting college entrance examination volunteers, the system for assisting college entrance examination volunteers including:

[0048] S1, data acquisition module, used to obtain user data and social industry demand data, evaluate the user's strong and weak subjects based on the user's performance and mark them;

[0049] Specifically, user data and social industry demand data are obtained, and the user's strong and weak subjects are evaluated and marked based on the user's scores. After the user enters the admission ticket number and ID number to log in to the system, the user's college entrance examination score and provincial ranking are obtained from the education department database according to the user's admission ticket number, and the current enrollment policy and related college entrance examination rules are loaded at the same time, and the industry demand data of the entire society is obtained from multiple data sources (national policy releases, news media, social media);

[0050] Collect the user's previous test data, including mock test scores, regular test scores, and final test scores, and arrange the user's scores in chronological order, calculate the user's growth rate in each subject, and evaluate the user's learning progress in each subject:

[0051]

[0052] In the formula, represents the growth rate of the i-th subject, which is used to measure the learning growth rate of the user in the subject over a period of time. i (t) is the learning curve function of the i-th subject, which represents the learning progress of the user at different times t. i is the highest score in the history of the user, o is the learning rate, t0 is the turning point of the user's learning progress, that is, the time point when the user learns fastest. The time point of the learning curve growth fastest can be found by fitting the curve through the time points of multiple test scores. For example, if the user's score improves fastest in the third month, then t0 = 3, C i represents the user's initial score, T1 represents the time when the user took the first exam in the subject, and T n Indicates the user's latest exam time in this subject, T u is the time interval, N is the number of exams the user has taken in the subject, is the absolute difference between the user's latest test score and the previous test scores, which is used to measure the user's score fluctuation. l,i is the user's latest test score in the subject, W k,i is the user's score in the kth exam, dt is a small time increment, and n represents the number of times the user takes the subject exam;

[0053] The basic growth rate calculation formula is as follows:

[0054]

[0055] In the formula, a is the growth rate, b is the final value, which refers to the score of the latest exam, and c is the initial value, which refers to the score of the first exam;

[0056] In order to more accurately reflect the nonlinear changes in learning, the logarithmic growth model is introduced to describe the nonlinear changes in learning: By adjusting the parameters, it can be applied to the personalized learning curve of different users;

[0057] In order to accumulate the user’s learning progress over the entire time period, the learning is integrated and the user’s progress from T1 to T n The overall learning progress of quantifies the user's progress during the entire learning period. In order to eliminate the impact of learning time on the growth rate, the time normalization term T is introduced u ,Through time normalization, the average learning progress per unit time can be calculated;

[0058] In order to prevent an abnormal performance from having too great an impact on the growth rate, an exponential function is introduced for smoothing: By calculating the difference between the latest score and other test scores and processing it through an exponential function, the fluctuation of scores can be smoothed out, reducing the impact of a single test abnormality on the overall growth rate;

[0059] Compare the user's current score with the score distribution of users across the province, and calculate the user's ranking percentile P in the subject:

[0060]

[0061] In the formula, V1 is the total number of users in the province, and V2 is the specific ranking of the user, indicating the ranking of the user among the users in the province;

[0062] Calculate the user's historical average growth rate. If the user's subject growth rate is higher than its own historical average growth rate, and the provincial ranking percentile corresponding to the user's current subject score is in the top 40% in the province, then mark the subject as a strong subject. If the user's subject growth rate is lower than its own historical average growth rate, and the provincial ranking percentile corresponding to the user's current subject score is in the bottom 40% in the province, then mark the subject as a weak subject.

[0063] By collecting the user's mock exams, regular exams and final exam scores, the system can form a complete user academic performance profile. Compared with the method of focusing only on the one-time college entrance examination scores, the system analyzes the user's multiple exam scores to dynamically evaluate the user's learning progress in different time periods. By calculating the user's growth rate in different subjects, the system can more accurately identify the user's learning curve and find the potential and bottlenecks in the learning process. The calculation of the growth rate is not just a simple score difference, but a comprehensive analysis of multi-dimensional factors such as learning rate, number of exams and time intervals, so that the indicator can more carefully reflect the user's progress in the learning process. This refined analysis method can help users better understand their strong and weak subjects, and make targeted choices in subsequent volunteer recommendations. By calculating the user's growth rate and ranking percentile, the system can automatically mark the user's strong and weak subjects. Not only does it let users understand their strong subjects, but it also helps users recognize their shortcomings in weak subjects. This has important guiding significance for users to choose a major that suits their abilities when filling out their voluntary applications, avoiding the limitations of blindly choosing popular majors or relying too much on a single exam score.

[0064] S2, professional recommendation module, is used to conduct personality tests on users, make preliminary professional recommendations based on the user's personality characteristics and subject strengths, and further screen out majors that match industry development through social industry demand data, and generate a professional recommendation list based on the screened majors;

[0065] Specifically, a personality test is conducted on the user, and a preliminary professional recommendation is made based on the user's personality characteristics and subject strengths and weaknesses. After the user logs into the system, the user is guided to use the MBTI personality assessment tool to conduct a personality test, and after the personality test, the user is guided to fill in the career planning information. The user can choose the target career field (including science and engineering, medicine, art, and law, etc.), and can fill in personal career goals. The user's personality test results are combined with the filled-in career planning information to establish a mapping relationship between the career planning and personality test results: if the user's personality type is INTJ, and the filled-in career plan is science and engineering, the system will give priority to matching the user to technical majors such as engineering, computer science, and physics;

[0066] If the user's personality type is ESFJ and the career plan filled in is medical, the system will give priority to recommending the user related medical majors (such as nursing, public health, etc.);

[0067] According to the user's personality type and career plan, matching major categories are screened out. If the user's personality type is INTP and the career plan is science and engineering, technical majors such as computer science, engineering, and data science are recommended first. If the user's personality type is ESFJ and the career plan is social services, social work, psychology, and education are recommended first.

[0068] In the matched professional categories, a mapping table is constructed according to the subject requirements of different majors to define the subjects required for each major. For each major, the matching degree is calculated based on the user's strong subjects. J :

[0069]

[0070] In the formula, S I is the user's score in the Ith strong subject, R I is the requirement of major J for the Ith strong subject (e.g., recommended grades or minimum requirements), S is the set of strong subjects, i.e., the user’s strong subjects (determined based on the user’s historical performance, usually based on growth rate and ranking percentile);

[0071] According to the matching scores, the majors are sorted in descending order to generate a preliminary list of major recommendations.

[0072] By conducting personality tests on users, more accurate professional categories can be screened out through the correlation between the user's personality type and career planning. This not only improves the scientificity and personalization of the recommendation, but also avoids professional burnout or academic pressure caused by the mismatch between the user's personality and career in practical applications. This combination provides users with more valuable reference options for their long-term career development. According to the user's personality type and career planning, professional categories that are highly matched with the user's personal characteristics are screened out. For example, INTP type users tend to choose majors that require logical reasoning and are highly technical, while ESFJ type users tend to choose majors related to social services. This screening process greatly enhances the accuracy of volunteer recommendations and avoids the common drawback of "one template for all users" in traditional volunteer filling systems. After screening out suitable professional categories, the system further constructs a mapping table between subject requirements and strong subjects, and generates a personalized professional recommendation list by calculating the matching degree between the user's strong subjects and the requirements of each professional subject. It can ensure that the major selected by the user is both his or her interest and the field in which his or her academic ability is good. For example, if the user's strong subjects are physics and mathematics, and his career plan is engineering, the system will give priority to recommending majors that are highly related to these subjects, such as mechanical engineering or electrical engineering. This multi-dimensional matching algorithm greatly improves the accuracy and practicality of recommendations, ensuring that users can fully realize their potential in their future academic and professional careers.

[0073] Furthermore, through social industry demand data, we further screen out majors that match the industry development. Based on the screened majors, we generate a professional recommendation list, which means using the LFA topic model to extract industry representative keywords from the industry classification standards and industry reports of the National Bureau of Statistics and market research. Each industry, such as "artificial intelligence", "finance", "manufacturing", etc., will have multiple corresponding keywords (such as "deep learning", "data analysis", etc.), and build an industry label library, which includes industry names, representative keywords and industry numbers;

[0074] After preprocessing the collected social industry demand data (data cleaning, format standardization), the TF-IDF algorithm is used to extract high-frequency keywords related to industry demand (artificial intelligence, big data, new energy) from the collected social industry demand data, and the frequency of occurrence of each keyword in various data sources is calculated. The frequency of occurrence is used as a preliminary indicator of discussion heat. In order to avoid the influence of long-term accumulated data on the current heat evaluation, a time weight mechanism is introduced to give recent data a higher weight, including dividing the data into time segments with a weight of 1 for the most recent month, a weight of 0.5 for 1-3 months, and a weight of 0.2 for 3-6 months. The number of occurrences of each keyword in different time periods is multiplied by the corresponding weight, and then the sum is obtained to obtain the weighted frequency. The discussion heat of each data source is weighted averaged to generate the comprehensive discussion heat of each keyword.

[0075] Through the pre-trained BERT model, the keywords and keywords in the industry tag library are converted into context-aware vector representations. The cosine similarity is used to calculate the similarity between each keyword and all keywords in the industry tag library, and the maximum similarity value is taken as the matching degree between the keyword and the industry in the industry tag library.

[0076] The similarity judgment threshold Q is set through the cross-validation optimization algorithm, and the keywords above the similarity judgment threshold Q are retained to create a keyword-industry matching matrix, where each element represents the matching degree between a keyword and an industry;

[0077] For each industry, we traverse the relevant keywords, calculate the contribution value of each keyword to the industry's demand index, add up the contribution values ​​of all keywords, and get the industry's comprehensive demand index:

[0078]

[0079] In the formula, F f is the comprehensive demand index of industry f, indicating the demand intensity of the industry, H y is the discussion heat of keyword y, which indicates the attention of the keyword in various data sources (such as news, social media, and research reports). y,f is the matching degree between keyword y and industry f, indicating the relevance of the keyword to the industry, and x is the number of keywords related to industry x;

[0080] In this example, if we want to calculate the demand index of the "artificial intelligence" industry, the relevant keywords and their discussion popularity and matching degree are as follows:

[0081] Keyword 1: AI, discussion heat is 0.9, matching degree is 0.95;

[0082] Keyword 2: Machine learning, discussion heat is 0.8, matching degree is 0.85;

[0083] Keyword 3: Big data, discussion heat is 0.7, matching degree is 0.8;

[0084] Add up the contribution values ​​of these keywords to get the industry demand index:

[0085] F f =(0.9×0.95)+(0.8×0.85)+(0.7×0.8)=2.095,

[0086] Therefore, the demand index of the artificial intelligence industry is 2.095;

[0087] Sort industries in descending order according to the comprehensive demand index of each industry, generate a preliminary list of high-demand industries containing industry names and demand indexes (this list includes industries that are hotly discussed in society and highly matched with actual industry demand, such as "artificial intelligence", "new energy", "financial technology", etc.), collect the latest industry reports from McKinsey and IDC and job demand statistics on recruitment platforms, compare the preliminary list of high-demand industries with industry reports and recruitment data in terms of industry growth rate, salary level changes, and talent gap data, if an industry in the preliminary list of high-demand industries is also listed as an industry with a high growth rate in industry reports and recruitment data, confirm its position in the preliminary list, otherwise recalculate and sort;

[0088] Collect historical job demand data of high-demand industries, pre-process the collected historical job demand data, use the ARIMA model to predict the changing trend of future job demand, use the pre-processed historical data as a training set, input it into the ARIMA model for model training, use the loss function and Adam optimizer to iteratively optimize the model parameters to obtain the optimized ARIMA model, input the real-time job demand data into the ARIMA model to obtain the predicted data of future job demand;

[0089] Score each high-demand industry based on the predicted occupational demand data and calculate the job demand growth rate G L :

[0090]

[0091] Where D U+P D is the number of jobs in high-demand industries predicted by the ARIMA model in the future U+P years. U is the job demand of U in the current year;

[0092] Based on the calculation results, the industries are sorted in descending order to form an industry trend score table. The Pearson correlation coefficient is used to evaluate the similarity of the job demand growth trends in various industries, and the majors with similar demand in different industries are found. Based on the analysis results, a list of cross-industry hot majors is generated, and the majors are sorted according to the job demand growth rate in different industries to generate a hot major recommendation list. Combined with the hot major recommendation list, the preliminary major recommendation list is screened to generate the final major recommendation list.

[0093] The LFA topic model can extract representative keywords from the industry classification standards of the National Bureau of Statistics, industry reports, and market research data. By deeply analyzing the core factors of industry development, complex industry data is simplified into a set of keywords. This not only improves the system's understanding of industry characteristics, but also lays the foundation for subsequent professional matching. Compared with traditional keyword extraction methods, the LFA topic model pays more attention to implicit information in the text and can grasp the potential trends in the industry. This method enables the system to predict the future development direction of the industry and help users choose more forward-looking majors. The introduction of the TF-IDF algorithm adds quantitative analysis capabilities to the system for social industry demand data. By calculating the frequency of occurrence of keywords, the system can intuitively reflect the current social attention to certain industries. The discussion heat can not only help the system screen out industries with market potential, but also dynamically adjust the recommendation results to ensure that the majors selected by users can adapt to changes in social needs. The BERT model significantly improves the matching accuracy of keywords and industry labels through context-aware word vector representation. Compared with simple keyword matching, BERT can understand the meaning of words in different contexts, thereby ensuring that the recommendation results are closely related to industry needs. In addition, the introduction of cosine similarity further enhances the system's ability to quantitatively analyze the matching degree between keywords and industries. By setting the similarity judgment threshold Q, the system can automatically filter out the keywords that best meet industry needs, ensuring that the recommended majors are closely linked to industry development trends. The ARIMA model can accurately predict future job demand trends by analyzing historical job demand data and combining it with real-time data. Compared with traditional static analysis, the ARIMA model has the ability to process dynamic time series and can provide updated job demand forecast results in different time periods. By calculating the job demand growth rate and Pearson correlation coefficient, the system can identify cross-industry majors with similar demands and generate a list of cross-industry hot majors to help users identify those majors that have strong demands in multiple industries, ensuring that the recommended majors have strong competitiveness in the future. Compared with single-industry professional recommendations, cross-industry hot major recommendations can better help users expand their employment options.

[0094] S3, school recommendation module, used to select the corresponding school based on the major recommendation list, calculate the admission probability of different schools and generate a preliminary volunteer recommendation list;

[0095] Specifically, selecting the corresponding schools based on the professional recommendation list, calculating the admission probabilities of different schools and generating a preliminary volunteer recommendation list means obtaining the professional admission data of colleges and universities throughout the country, including the minimum admission score, admission ratio and number of admissions for the corresponding majors of each school, and pre-processing the collected data, screening out colleges and universities that offer corresponding majors according to the professional recommendation list and establishing a mapping relationship between majors and schools;

[0096] Use the Logistic regression model to predict the probability of a user being admitted to a school. Use the preprocessed college admission data of previous years as the training set to input into the Logistic regression model for model training. Define the loss function and Adam optimizer to iteratively optimize the model parameters. When the loss of the Logistic regression model no longer decreases significantly during the continuous iteration process, stop iterating and output the model parameters to update the Logistic regression model.

[0097] The user's real-time college entrance examination data is input into the Logistic regression model to obtain the probability value of being admitted to the school, and the schools are sorted in descending order according to the obtained admission probability values ​​to generate a preliminary volunteer recommendation list.

[0098] As a classic binary classification prediction algorithm, the Logistic regression model can combine the user's college entrance examination data with the school's admission data over the years, and output the probability of the user being admitted to the target school. Compared with the traditional prediction method based on the score line, Logistic regression can more accurately estimate the user's admission chance by learning the distribution and pattern of admissions over the years, especially when the school's admission scores fluctuate greatly or the admission ratio is small. This probability prediction method can not only help users avoid overestimating or underestimating their admission chances, but also effectively reduce the risk when filling out their applications, ensuring that users make more rational and scientific decisions. The system can make dynamic predictions based on the user's real scores, rather than simply relying on historical data. The introduction of this real-time data improves the immediacy of the prediction, making the recommendation results closer to the user's actual situation. Compared with the traditional method, the present invention can accurately calculate the admission probability of each school based on the user's current scores, and generate a scientific volunteer recommendation list for the user, greatly improving the accuracy of volunteer filling. A preliminary volunteer recommendation list is generated by sorting the admission probabilities of all schools in descending order. This recommendation list arranges schools according to the user's admission probability, helping users intuitively understand the possibility of being admitted to different schools. This probabilistic ranking method avoids the blind understanding of schools and majors when filling out traditional applications, and improves the scientificity and rationality of user choices.

[0099] S4, a feedback improvement module, used to adjust the recommendation list in real time according to the user's personal preference data and store the final generated volunteer recommendation list;

[0100] Specifically, adjusting the recommendation list in real time according to the user's personal preference data refers to collecting the user's preference data, including geographic location, school level, professional prospects and admission risk, and allowing the user to set priority weights for different preference types. For example, the user can set the weight of geographic location to the highest (such as 70%), and set the professional prospects to the secondary weight (such as 30%), using the features in the feature engineering privilege preliminary volunteer recommendation list and the user's preference features and comparing them, and calculating the preference matching degree M of each recommendation item:

[0101]

[0102] Where, T B is the feature matching value of the Bth item preference, w B is the weight set by the user, T max is the maximum matching value of the feature, and E is the number of user preferences;

[0103] According to the calculation results of the matching degree, all schools and majors are sorted in descending order, and schools and majors with high matching degrees are recommended to users first to generate the final volunteer recommendation list.

[0104] By allowing users to set priority weights for different preferences, the personalization of volunteer recommendations is maximized. Compared with traditional static recommendation systems, this system can dynamically respond to user needs and adapt to users' preference adjustments for different dimensions such as geographical location and school level during the volunteer application process. For example, a user initially pays more attention to the level of the school (such as 985 and 211 universities), but as the system recommendations are generated, the user can adjust the priority so that the school's geographical location or professional prospects become a new consideration. The system will recalculate the matching degree in real time to ensure that the recommendation results are more in line with the user's needs. This flexibility improves the user experience and allows users to independently control the recommendation process and avoid blind volunteer selection. Through feature engineering, the system can extract, convert and optimize a large amount of raw data to ensure that the matching analysis with user preferences is more accurate. Compared with traditional volunteer recommendation systems that only make recommendations based on a single dimension (such as the admission score), this system comprehensively processes multi-dimensional feature data, covering multiple key factors such as school level, geographical location, and professional prospects, greatly improving the accuracy of recommendation results. For example, a user wants to give priority to schools located in Beijing, but also requires a major with good employment prospects. The system can process these features simultaneously through feature engineering to ensure that the recommended schools and majors meet both geographical preferences and future employment needs. This multi-dimensional feature matching not only improves the relevance of the recommendation results, but also enhances the intelligence level of the system. By calculating the matching degree between each school and major and the user's preferences, the system can generate a volunteer recommendation list that best meets the user's preferences, centered on user needs.

[0105] Furthermore, storing the final volunteer recommendation list means displaying the recommendation results to the user, and displaying the degree of match with the user's preferences and the specific reasons for the match (geographic location priority, school level compliance) next to each school and major, storing the final volunteer recommendation list locally and in the cloud in Excel format, encrypting the stored volunteer recommendation list file and implementing access control.

[0106] The recommendation results are displayed to users, and the matching degree of each school and major with the user's preferences and the specific reasons for the matching are shown, which enhances the transparency and user trust of the recommendation system. The final volunteer recommendation list is stored in Excel format, which can bring great convenience to users. The application of cloud storage brings flexibility and security to users, solving the needs of users to access recommendation lists on different devices and in different locations. Through encryption, users' sensitive information is always protected during transmission and storage, ensuring that even if the data is intercepted during transmission, unauthorized users cannot interpret its content.

[0107] Example 2, reference Figure 3 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a method for assisting college entrance examination volunteer filling, which includes:

[0108] Obtain user data and social industry demand data, evaluate the user's strong and weak subjects based on the user's performance and mark them;

[0109] Conduct personality tests on users, make preliminary professional recommendations based on their personality traits and subject strengths, further screen out majors that match industry development through social industry demand data, and generate a professional recommendation list based on the screened majors;

[0110] Select the corresponding school based on the professional recommendation list, calculate the admission probability of different schools and generate a preliminary volunteer recommendation list, adjust the recommendation list in real time according to the user's personal preference data and store the final volunteer recommendation list.

[0111] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0112] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0113] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0114] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A system for assisting students to fill out college entrance examination applications, characterized in that: include, The data acquisition module is used to obtain user data and social industry demand data, evaluate the user's strong and weak subjects based on the user's performance and mark them; The professional recommendation module is used to conduct personality tests on users, make preliminary professional recommendations based on the user's personality characteristics and subject strengths and weaknesses, and further screen out majors that match industry development through social industry demand data, and generate a professional recommendation list based on the screened majors; The school recommendation module is used to select the corresponding school based on the major recommendation list, calculate the admission probability of different schools and generate a preliminary volunteer recommendation list; The feedback improvement module is used to adjust the recommendation list in real time according to the user's personal preference data and store the final generated volunteer recommendation list.

2. The college entrance examination volunteer filling auxiliary system as claimed in claim 1, characterized in that: The obtaining of user data and social industry demand data, and evaluating and marking the user's strong and weak subjects based on the user's scores means that after the user enters the admission ticket number and ID number to log into the system, the user's college entrance examination scores and provincial rankings are obtained from the education department database based on the user's admission ticket number, and the current enrollment policy and related college entrance examination rules are loaded at the same time, and the industry demand data of the entire society is obtained from multiple data sources; Collect the user's previous test data, including mock test scores, regular test scores, and final test scores, and arrange the user's scores in chronological order, calculate the user's growth rate in each subject, and evaluate the user's learning progress in each subject: In the formula, represents the growth rate of the i-th subject, A i is the highest score in the history of the user, o is the learning rate, t0 is the turning point time of the user's learning progress, C i represents the user's initial score, T1 represents the time when the user took the first exam in the subject, and T n Indicates the user's latest exam time in this subject, T u is the time interval, N is the number of exams the user has taken in the subject, and W l,i is the user's latest test score in the subject, W k,i is the user's score in the kth exam, dt is a small time increment, and n represents the number of times the user takes the subject exam; Compare the user's current score with the score distribution of users across the province, calculate the user's ranking percentile in the subject, and calculate the user's historical average growth rate. If the user's subject growth rate is higher than its own historical average growth rate, and the provincial ranking percentile corresponding to the user's current subject score is in the top 40% in the province, then mark the subject as a strong subject. If the user's subject growth rate is lower than its own historical average growth rate, and the provincial ranking percentile corresponding to the user's current subject score is in the bottom 40% in the province, then mark the subject as a weak subject.

3. The college entrance examination volunteer filling auxiliary system as claimed in claim 2, characterized in that: Conducting a personality test on the user and making preliminary professional recommendations based on the user's personality characteristics and subject strengths and weaknesses means that after the user logs into the system, the user is guided to use the MBTI personality assessment tool to conduct a personality test, and after the personality test, the user is guided to fill in career planning information. The user can select a target career field and personal career goals, and the user's personality test results are combined with the filled-in career planning information to establish a mapping relationship between the career plan and the personality test results; According to the user's personality type and career plan, matching major categories are screened out. If the user's personality type is INTP and the career plan is science and engineering, technical majors such as computer science, engineering, and data science are recommended first. If the user's personality type is ESFJ and the career plan is social services, social work, psychology, and education are recommended first. In the matched professional categories, a mapping table is constructed according to the subject requirements of different majors to define the subjects required for each major. For each major, the matching degree is calculated based on the user's strong subjects, and the majors are sorted in descending order according to the matching scores to generate a preliminary professional recommendation list.

4. The college entrance examination volunteer filling auxiliary system as claimed in claim 3, characterized in that: Further screening out the majors matching the industry development through the social industry demand data, and generating the major recommendation list based on the screened majors means using the LFA topic model to extract the industry representative keywords from the industry classification standards and industry reports of the National Bureau of Statistics and market research to build an industry tag library, and the industry tag library includes industry names, representative keywords and industry numbers; After preprocessing the collected social industry demand data, the TF-IDF algorithm is used to extract high-frequency keywords related to industry demand from the collected social industry demand data, calculate the frequency of each keyword in various data sources, and use the frequency of occurrence as a preliminary indicator of discussion heat. The discussion heat of each data source is weighted averaged to generate the comprehensive discussion heat of each keyword; Through the pre-trained BERT model, the keywords and keywords in the industry tag library are converted into context-aware vector representations. The cosine similarity is used to calculate the similarity between each keyword and all keywords in the industry tag library, and the maximum similarity value is taken as the matching degree between the keyword and the industry in the industry tag library. Set a similarity judgment threshold Q, retain keywords that are higher than the similarity judgment threshold Q, and create a keyword-industry matching matrix, where each element represents the matching degree between a keyword and an industry; For each industry, traverse the relevant keywords, calculate the contribution value of each keyword to the industry's demand index, add up the contribution values ​​of all keywords, and get the industry's comprehensive demand index; Sort the industries in descending order according to the comprehensive demand index of each industry, and generate a preliminary list of high-demand industries including industry names and demand indexes; Collect historical job demand data of high-demand industries, pre-process the collected historical job demand data, use the ARIMA model to predict the changing trend of future job demand, use the pre-processed historical data as a training set, input it into the ARIMA model for model training, use the loss function and Adam optimizer to iteratively optimize the model parameters to obtain the optimized ARIMA model, input the real-time job demand data into the ARIMA model to obtain the predicted data of future job demand; Score each high-demand industry based on the predicted occupational demand data, calculate the job demand growth rate, and sort the industries in descending order based on the calculation results to form an industry trend score table. Use the Pearson correlation coefficient to evaluate the similarity of job demand growth trends in various industries, identify majors with similar demand in different industries, generate a list of cross-industry hot majors based on the analysis results, and sort the majors according to the job demand growth rate in different industries to generate a hot major recommendation list. Combined with the hot major recommendation list, screen the preliminary major recommendation list to generate the final major recommendation list.

5. The college entrance examination volunteer filling auxiliary system as claimed in claim 4, characterized in that: The selecting corresponding schools based on the professional recommendation list, calculating the admission probabilities of different schools and generating a preliminary volunteer recommendation list refers to obtaining the professional admission data of colleges and universities throughout the country over the years, including the minimum admission score, admission ratio and number of admissions for the corresponding major of each school, and pre-processing the collected data, screening out colleges and universities that offer corresponding majors according to the professional recommendation list and establishing a mapping relationship between majors and schools; Use the Logistic regression model to predict the probability of a user being admitted to a school. Use the preprocessed college admission data of previous years as the training set to input into the Logistic regression model for model training. Define the loss function and Adam optimizer to iteratively optimize the model parameters. When the loss of the Logistic regression model no longer decreases significantly during the continuous iteration process, stop iterating and output the model parameters to update the Logistic regression model. The user's real-time college entrance examination data is input into the Logistic regression model to obtain the probability value of being admitted to the school, and the schools are sorted in descending order according to the obtained admission probability values ​​to generate a preliminary volunteer recommendation list.

6. The college entrance examination volunteer filling auxiliary system as claimed in claim 5, characterized in that: The real-time adjustment of the recommendation list according to the user's personal preference data refers to collecting the user's preference data, including geographic location, school level, major prospects and admission risk, and allowing the user to set priority weights for different preference types, using the features in the feature engineering privilege preliminary volunteer recommendation list and the user's preference features and comparing them, and calculating the preference matching degree M of each recommendation item: Where, T B is the feature matching value of the Bth item preference, w B is the weight set by the user, T max is the maximum matching value of the feature, and E is the number of user preferences; According to the calculation results of the matching degree, all schools and majors are sorted in descending order, and schools and majors with high matching degrees are recommended to users first to generate the final volunteer recommendation list.

7. The college entrance examination volunteer filling auxiliary system as claimed in claim 6, characterized in that: Storing the final volunteer recommendation list means displaying the recommendation results to the user, and displaying the degree of match with the user's preferences and the specific reasons for the match next to each school and major, storing the final volunteer recommendation list locally and in the cloud in Excel format, encrypting the stored volunteer recommendation list file and implementing access control.

8. A method for assisting college entrance examination volunteer filling based on the college entrance examination volunteer filling assisting system according to any one of claims 1 to 7, characterized in that: include, Obtain user data and social industry demand data, evaluate the user's strong and weak subjects based on the user's performance and mark them; Conduct personality tests on users, make preliminary professional recommendations based on their personality traits and subject strengths, further screen out majors that match industry development through social industry demand data, and generate a professional recommendation list based on the screened majors; Select the corresponding school based on the professional recommendation list, calculate the admission probability of different schools and generate a preliminary volunteer recommendation list, adjust the recommendation list in real time according to the user's personal preference data and store the final volunteer recommendation list.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the college entrance examination volunteer filling auxiliary system described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the college entrance examination volunteer filling auxiliary system described in any one of claims 1 to 7 are implemented.

Images