Teaching and training institution intelligent enrollment method and system based on big data analysis

Abstract

The invention belongs to the technical field of data analysis, and discloses a teaching and training institution intelligent enrollment method and system based on big data analysis. The method comprises the steps that preprocessed education data is grouped according to schools and grades, any group is extracted, any student in any group is evaluated and analyzed based on a first data set, and an analysis result is obtained; extracting any subject, clustering the students in any group based on the first analysis result, generating a plurality of classification sets, generating a recommended course for the students in each classification set, extracting any student, and determining a recommended teacher based on the student basic information, the analysis result and the teacher information corresponding to the recommended course. And after traversing all the students in all the groups, recommending courses and teachers to generate personalized enrollment information for each student based on the analysis result corresponding to each student, and sending the personalized enrollment information to a contact terminal corresponding to each student. According to the technical scheme of the invention, intellectualization and precision of enrollment can be realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and specifically relates to an intelligent enrollment method and system for an education and training institution based on big data analysis. Background Art

[0002] As competition in the education industry becomes increasingly fierce, education and training institutions are faced with challenges such as how to accurately locate potential students, improve enrollment efficiency, and optimize resource allocation. Traditional enrollment methods often rely on advertising, word-of-mouth communication, and field promotion activities. These methods are not only costly and inefficient, but also difficult to achieve accurate positioning and personalized services.

[0003] Similar prior art includes a Chinese patent application with publication number CN111861398A, which discloses an online education enrollment and course system, an enrollment module for users to log in to the online education enrollment and course system and develop training institutions; a publicity module for regularly pushing activities, courses and articles to users; a management module for checking order status, interacting with students or parents, and checking parents' clues and enrollment status. There is also a Chinese patent application with publication number CN115840914A, which discloses an enrollment system, in which the user end prepares enrollment information; the publishing end publishes enrollment information and collects customer feature information; and the service end is used to input the customer feature information collected by the publishing end into a preset machine learning model to predict the customer's intention to register. The customer's intention to register refers to the degree of the customer's intention to register for a course published in the enrollment information.

[0004] The above two methods only send uniformly prepared enrollment information to users during enrollment, and cannot accurately push information according to user needs. Therefore, it is an urgent problem to provide an intelligent enrollment method and system for educational institutions based on big data analysis, so as to realize the intelligence, precision and efficiency of the enrollment process through big data analysis technology. Summary of the invention

[0005] In response to the technical problems raised above, the present invention provides an intelligent enrollment method and system for educational institutions based on big data analysis.

[0006] In a first aspect, the present invention provides an intelligent enrollment method for an education and training institution based on big data analysis, the method comprising the following steps:

[0007] Step 1: Obtain students’ educational data through online and / or offline methods;

[0008] Step 2: pre-process the educational data to obtain the data to be analyzed, wherein the data to be analyzed includes basic information of students and academic data of students;

[0009] Step 3: extract student identifiers from the data to be analyzed, group the students according to school and grade based on the student identifiers, and then divide the data to be analyzed into multiple data sets based on the groups;

[0010] Step 4: extract any group, and evaluate and analyze any student in any group based on the first data set to obtain an analysis result, wherein the first data set is the data set corresponding to any group;

[0011] Step 5: extract any subject, cluster the students in any group based on the first analysis result, generate multiple classification sets, and generate recommended courses for students in each classification set, wherein the first analysis result is the analysis result corresponding to any subject;

[0012] Step 6: Extract any student, determine the recommended teacher based on the student's basic information, analysis results and teacher information of the teacher corresponding to the recommended course, and sort all the recommended teachers;

[0013] Step 7: After traversing all groups, all subjects, and all students, generate personalized enrollment information for each student based on the analysis results, recommended courses, and recommended teachers corresponding to each student;

[0014] Step 8: Send personalized enrollment information to the contact terminal corresponding to each student.

[0015] Specifically, the student academic data includes the test paper data of all subjects in each test of the student within a preset time. Step 4 includes:

[0016] Step 41: for any subject, extract the first test paper data of any student in any test;

[0017] Step 42: obtaining the test score of any student in any test based on the first test paper data;

[0018] Step 43: After traversing all students in any group, calculate the first eigenvalue of the nth student in any subject in any exam based on the test scores. The first eigenvalue P1 of the nth student n The calculation formula is:

[0019]

[0020] Among them, S n is the test score of the nth student, is the average score of any subject in any examination, n is a positive integer from 1 to N, and N is the total number of students in any group;

[0021] Step 44: After traversing all the exams of any subject within the preset time, calculate the second eigenvalue of any subject of the nth student. The calculation formula is:

[0022]

[0023] Among them, P2 n is the second eigenvalue of any subject of the nth student, P1 n,m is the first eigenvalue of any subject of the nth student in the mth examination, where m is a positive integer from 1 to M, and M is the total number of examinations within a preset time;

[0024] Step 45, extract the second test paper data of the nth student in the most recent test, identify the wrongly answered questions in the second test paper data, and define them as the first type of questions;

[0025] Step 46: determine the evaluation value of each question in the first category of questions, and adjust the first test score and first ranking of the nth student in the most recent test based on the second characteristic value of any subject of the nth student and the evaluation value of each first category of questions to obtain an adjustment result;

[0026] Step 47, identifying the knowledge point corresponding to each first-category question, and generating a subject analysis result for any subject of the nth student based on the first eigenvalue, the second eigenvalue, the knowledge point, the first test score, the first ranking, and the adjustment result;

[0027] Step 48: After traversing all students in any group, return to step 41;

[0028] Step 49: After traversing all subjects, generate analysis results based on the subject analysis results corresponding to all subjects of any student.

[0029] Specifically, step 46 includes:

[0030] Extract any question from the first category of questions, determine whether the second characteristic value is greater than or equal to the evaluation value corresponding to any question, and if so, obtain the score of any question, and add the score to the first test score to generate a new first test score;

[0031] After traversing all the first category questions, the nth student is re-ranked based on the new first test score, and the new first test score and the new ranking are defined as the adjustment result.

[0032] Specifically, step 5 includes:

[0033] Step 51, extract any student, and identify the first knowledge point corresponding to the first type of question of any student;

[0034] Step 52: Generate a feature sequence based on the first feature value, the second feature value, and the first knowledge point of any student;

[0035] Step 53: After traversing all students, cluster all students corresponding to any subject based on the feature sequence;

[0036] Step 54: extract any classification set, and obtain the first characteristic sequence of the student with the highest first characteristic value in any classification set;

[0037] Step 55: Match recommended courses for students in any classification set based on the first feature sequence.

[0038] Specifically, step 55 includes:

[0039] Step 551: extracting the second feature sequence of all students enrolled in any subject from the first storage module, wherein the second feature sequence is the feature sequence of the students enrolled when they enter the institution;

[0040] Step 552: Calculate the similarity between the first feature sequence and any second feature sequence, and define the enrolled students corresponding to the second feature sequence whose similarity is greater than a first preset value as the objects to be compared;

[0041] Step 553: Obtain the improvement value of each object to be compared, and use the course corresponding to the student with the largest improvement value as the recommended course.

[0042] Specifically, the student basic information includes personality and hobbies, and the teacher information includes personality, hobbies, and expertise. Step 6 includes:

[0043] Based on the subject analysis results, analyze the knowledge points mastered by any student to obtain the first-category knowledge points that any student has not mastered and the second-category knowledge points that are weak;

[0044] Compare the student information with the teacher information. If the i-th data in the student information matches the data in the teacher information, the comparison result is set to 1, otherwise the comparison result is set to 0. The student information includes the student basic information, the first category of knowledge points and the second category of knowledge points.

[0045] After the comparison is completed, the recommendation degree of any teacher is calculated using the following formula:

[0046]

[0047] Among them, R j is the recommendation degree of the jth teacher, V i is the comparison result of the i-th data in the student information, α i is the parameter weight coefficient, i is a positive integer from 1 to I, and I is the total number of all data in the student information;

[0048] Teachers whose recommendation degrees are greater than a second preset value are regarded as recommended teachers, and all recommended teachers are sorted from large to small based on the recommendation degrees.

[0049] Specifically, in step 6, the campus to be promoted is determined based on the location of the school corresponding to any group, and the in-service teachers of the campus to be promoted are further selected as teachers corresponding to the recommended courses.

[0050] Specifically, personalized enrollment information is sent via email, text message, and / or social software.

[0051] In a second aspect, the present invention also provides an intelligent enrollment system for an education and training institution based on big data analysis, the system comprising: a data acquisition module, a data processing module, a data division module, a data analysis module, a course recommendation module, a teacher recommendation module, an information production module and a data sending module;

[0052] A data acquisition module, used to acquire students' educational data through online and / or offline methods;

[0053] The data processing module is used to pre-process the educational data and obtain the data to be analyzed, wherein the data to be analyzed includes the basic information of the students and the academic data of the students;

[0054] A data partitioning module is used to extract student identifiers from the data to be analyzed, group the students according to school and grade based on the student identifiers, and then divide the data to be analyzed into multiple data sets based on the groups;

[0055] A data analysis module, used to extract any group, evaluate and analyze any student in any group based on a first data set, and obtain an analysis result, wherein the first data set is a data set corresponding to any group;

[0056] A course recommendation module is used to extract any subject, cluster students in any group based on the first analysis result, generate multiple classification sets, and generate recommended courses for students in each classification set, wherein the first analysis result is the analysis result corresponding to any subject;

[0057] The teacher recommendation module is used to extract any student, determine the recommended teacher based on the student's basic information, analysis results and teacher information of the teacher corresponding to the recommended course, and sort all the recommended teachers;

[0058] The information production module is used to generate personalized enrollment information for each student based on the analysis results, recommended courses and recommended teachers corresponding to each student after traversing all groups, all subjects and all students;

[0059] The data sending module is used to send personalized enrollment information to the contact terminal corresponding to each student.

[0060] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0061] 1. Through automated data collection, processing and analysis, educational institutions can obtain comprehensive information about students more quickly and generate personalized enrollment information based on it, thus reducing the time and cost of manual operations and subjective judgments and improving the efficiency of enrollment work.

[0062] 2. Use big data analysis technology to deeply explore students' academic data, basic information, interests and hobbies and other multi-dimensional information, so as to more accurately assess students' learning abilities and needs. Based on these assessment results, education and training institutions can provide students with course recommendations and teacher matching that are more in line with their actual needs, meet the specific needs of different students, and enhance the accuracy of admissions.

[0063] 3. By automatically producing personalized enrollment information that responds to the needs of students and parents, the attractiveness of enrollment information can be enhanced, user satisfaction and trust can be improved, and the market competitiveness of educational institutions can be enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0065] Figure 1 This is a flow chart of the intelligent enrollment method for educational institutions based on big data analysis of the present invention;

[0066] Figure 2 This is a modular schematic diagram of the intelligent enrollment system for educational institutions based on big data analysis of the present invention. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. Obviously, the specific embodiments described herein are only used to explain the present invention and are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0068] It should be noted that if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0069] Figure 1 The figure is a flow chart of an embodiment of an intelligent enrollment method for an education and training institution based on big data analysis provided by the present invention, and the flow chart specifically includes the following steps:

[0070] Step 1: Obtain students’ educational data through online and / or offline methods.

[0071] Exemplarily, educational data is obtained through social media, official websites, search engines, online course platforms, third-party data service providers, marketing channels or third-party platforms, etc.

[0072] Step 2: Preprocess the educational data to obtain the data to be analyzed, where the data to be analyzed includes students' basic information and students' academic data.

[0073] The above preprocessing includes data cleaning, deduplication, conversion, normalization, integration, etc. The data to be analyzed is obtained through preprocessing to ensure the accuracy and consistency of educational data and improve data quality.

[0074] Students’ basic information includes name, gender, age, contact information, family background, personality, mental state, hobbies, specialties, etc.

[0075] Academic data includes classroom performance, participation in extracurricular activities, teacher evaluations, test papers, test scores, etc.

[0076] Step 3: extract student identifiers from the data to be analyzed, group students according to school and grade based on the student identifiers, and then divide the data to be analyzed into multiple data sets based on the groups.

[0077] Students in different grades have different learning contents and knowledge points to master, and students in different schools have different learning situations. Students are grouped finely based on school and grade, and the data to be analyzed is divided into data sets corresponding to the student groups. Analysis is performed on specific groups to improve the accuracy of the analysis results.

[0078] The number of data sets is related to the number of schools and the number of grades in the schools.

[0079] Step 4: extract any group, and evaluate and analyze any student in any group based on the first data set to obtain the analysis result, wherein the first data set is the data set corresponding to any group.

[0080] For any group, the learning situation of each student in each subject in the group is analyzed separately, and courses and teachers can be recommended based on the students' learning situation in any subject.

[0081] Specifically, the student academic data includes the test paper data of all subjects in each test of the student within a preset time. Step 4 includes:

[0082] Step 41: For any subject, extract the first test paper data of any student in any test.

[0083] Step 42: Obtain the test score of any student in any test based on the first test paper data.

[0084] Step 43: After traversing all students in any group, calculate the first eigenvalue of the nth student in any subject in any exam based on the test scores. The first eigenvalue P1 of the nth student n The calculation formula is:

[0085]

[0086] Among them, S n is the test score of the nth student, is the average score of any subject in any examination, n is a positive integer from 1 to N, and N is the total number of students in any group.

[0087] Step 44: After traversing all the exams of any subject within the preset time, calculate the second eigenvalue of any subject of the nth student. The calculation formula is:

[0088]

[0089] Among them, P2 n is the second eigenvalue of any subject of the nth student, P1 n,m It is the first eigenvalue of any subject of the nth student in the mth examination, m is a positive integer from 1 to M, and M is the total number of examinations within the preset time.

[0090] Step 45: extract the second test paper data of the nth student in the most recent test, identify the wrongly answered questions in the second test paper data, and define them as the first type of questions.

[0091] Step 46: determine the evaluation value of each question in the first category of questions, and adjust the first test score and first ranking of the nth student in the most recent test based on the second eigenvalue of any subject of the nth student and the evaluation value of each first category of questions to obtain the adjustment result.

[0092] Step 47, identifying the knowledge point corresponding to each first-category question, and generating a subject analysis result for any subject of the nth student based on the first eigenvalue, the second eigenvalue, the knowledge point, the first test score, the first ranking and the adjustment result.

[0093] Step 48: After traversing all students in any group, return to step 41.

[0094] Step 49: After traversing all subjects, generate analysis results based on the subject analysis results corresponding to all subjects of any student.

[0095] The preset time is set according to the experience of those skilled in the art or according to the actual application scenario, and the embodiments of the present application do not limit this. For example, the preset time is one school year or one semester.

[0096] Examinations within the preset time include monthly exams, midterm exams and final exams.

[0097] The first eigenvalue can be used to intuitively display the relative situation of students in the subjects to be analyzed in an exam, helping educational institutions and students understand the performance and positioning of individuals in the overall score in an exam. One exam cannot reflect the true level of students. The second eigenvalue is calculated based on the first eigenvalue of multiple exams within a preset time, and the second eigenvalue is used to quantitatively analyze the comprehensive level of students' knowledge, skills, and abilities in the subjects to be analyzed. Automatically conduct quantitative analysis of students' knowledge levels, which is convenient for subsequent course recommendations and improves the scientific nature of personalized recommendations.

[0098] The above subject analysis results also include the knowledge points that students have mastered, weak knowledge points, knowledge points that students have not mastered, as well as the difference between the adjusted ranking and the first ranking (the ranking that students can improve), and the difference between the adjusted score and the first test score (the score that students can improve).

[0099] Specifically, step 46 includes:

[0100] Extract any question from the first category of questions, determine whether the second characteristic value is greater than or equal to the evaluation value corresponding to any question, and if so, obtain the score of any question, and add the score to the first test score to generate a new first test score;

[0101] After traversing all the first category questions, the nth student is re-ranked based on the new first test score, and the new first test score and the new ranking are defined as the adjustment result.

[0102] For example, the evaluation value of a question is the difficulty coefficient, degree of difficulty, etc. of the question. When the second eigenvalue is greater than or equal to the evaluation value corresponding to the question, it means that theoretically the student can answer the question based on the comprehensive level of the analyzed subject, but due to carelessness or other non-ability factors, the error caused by the question can be understood as the student's weak knowledge point. When the second eigenvalue is less than the evaluation value corresponding to the question, it means that theoretically the student's comprehensive level cannot answer the question, and the knowledge point corresponding to the question can be understood as the knowledge point that the student has not mastered.

[0103] Adjust the students' test scores and rankings according to their overall level to more accurately reflect their learning level, provide students with personalized learning feedback, and help them understand their strengths and weaknesses. Make conservative estimates of the rankings and grades that students can improve, and provide students with course recommendations that meet their needs for areas that need improvement, improve adaptability, increase publicity credibility, and improve enrollment efficiency.

[0104] Step 5: extract any subject, cluster the students in any group based on the first analysis result, generate multiple classification sets, and generate recommended courses for students in each classification set, wherein the first analysis result is the analysis result corresponding to any subject.

[0105] For any subject, students are clustered based on the subject analysis results of all students in any subject, and students with similar learning needs and characteristics are grouped into the same classification set, so as to recommend training courses to students in each classification set in batches. While generating personalized enrollment information for each student, courses are recommended in batches for students with similar comprehensive levels to improve data processing efficiency.

[0106] Specifically, step 5 includes:

[0107] Step 51, extract any student, and identify the first knowledge point corresponding to the first type of question of any student.

[0108] Step 52: Generate a feature sequence based on the first feature value, the second feature value, and the first knowledge point of any student.

[0109] Step 53: After traversing all students, cluster all students corresponding to any subject based on the feature sequence.

[0110] Step 54: extract any classification set and obtain the first feature sequence of the student with the highest first feature value in any classification set.

[0111] Step 55: Match recommended courses for students in any classification set based on the first feature sequence.

[0112] The first knowledge point is the knowledge point that students are weak in or have not mastered. It is the knowledge point that needs to be strengthened and improved. There can be one or more.

[0113] Exemplarily, the feature sequence of the student corresponding to the first feature value located at the middle position in any classification set may also be used for matching and recommending courses.

[0114] Specifically, step 55 includes:

[0115] Step 551: extract the second feature sequence of all students enrolled in any subject corresponding to the first storage module, wherein the second feature sequence is the feature sequence of the students when they enter the institution.

[0116] Step 552: Calculate the similarity between the first feature sequence and any second feature sequence, and define the enrolled students corresponding to the second feature sequence whose similarity is greater than a first preset value as objects to be compared.

[0117] Step 553: Obtain the improvement value of each object to be compared, and use the course corresponding to the student with the largest improvement value as the recommended course.

[0118] The first preset value is set according to the experience of those skilled in the art or according to an actual application scenario, and the embodiments of the present application are not limited to this.

[0119] Compare the students with the highest first eigenvalue with the current students, use the existing successful cases to guide and optimize the course recommendations for other students, and improve the personalization and effectiveness of educational services. In previous registrations, students with the same comprehensive level may have registered for courses of different levels (basic classes, consolidation classes, advanced classes, etc.). Students studying in different courses will have different degrees of progress due to different course content, etc. Recommending courses that have been proven to be effective to students can enhance students' confidence in their learning outcomes.

[0120] By analyzing the characteristic sequences of students, we can more accurately match courses suitable for students' current learning levels and needs, so that the recommended courses are more in line with students' learning characteristics, which helps to improve learning efficiency and can help students make greater progress in weak links.

[0121] Step 6: Extract any student, determine the recommended teacher based on the student's basic information, analysis results, and teacher information of the teacher corresponding to the recommended course, and sort all recommended teachers.

[0122] Recommending teachers to students based on their basic information, analysis results, and teacher information can match students with suitable teachers, which helps improve learning outcomes.

[0123] Specifically, the student basic information includes personality and hobbies, and the teacher information includes personality, hobbies, and expertise. Step 6 includes:

[0124] Based on the subject analysis results, analyze the knowledge points mastered by any student to obtain the first-category knowledge points that any student has not mastered and the second-category knowledge points that are weak;

[0125] Compare the student information with the teacher information. If the i-th data in the student information matches the data in the teacher information, the comparison result is set to 1, otherwise the comparison result is set to 0. The student information includes the student basic information, the first category of knowledge points and the second category of knowledge points.

[0126] After the comparison is completed, the recommendation degree of any teacher is calculated using the following formula:

[0127]

[0128] Among them, R j is the recommendation degree of the jth teacher, V i is the comparison result of the i-th data in the student information, α i is the parameter weight coefficient, i is a positive integer from 1 to I, and I is the total number of all data in the student information;

[0129] Teachers whose recommendation degrees are greater than a second preset value are regarded as recommended teachers, and all recommended teachers are sorted from large to small based on the recommendation degrees.

[0130] The second preset value is set according to the experience of those skilled in the art or according to an actual application scenario, and the embodiment of the present application does not limit this.

[0131] When setting the weight coefficient of each parameter, a larger weight coefficient is set for the parameters related to the knowledge points, and a smaller weight coefficient is set for the parameters not related to the knowledge points. At the same time, different weight coefficients are set for the parameters corresponding to the knowledge points that have not been mastered and the parameters corresponding to the weak knowledge points. The specific setting is based on the experience of technical personnel in this field or according to the actual application scenario, and the embodiments of the present application are not limited to this.

[0132] Determining which teachers are most suitable for which students through scientific methods can help optimize the allocation of teacher resources and improve learning efficiency. For example, in English teaching, students' interests and hobbies are the same as teachers' interests and hobbies. When communicating, using interests and hobbies as topics can increase student participation and improve learning efficiency. For another example, student A's knowledge point a1 is relatively weak, and teacher B is good at knowledge point a1, has a unique teaching method, and has good teaching results. Student A learning in teacher B's class can help effectively improve learning efficiency.

[0133] By carefully matching the personalities, hobbies, and knowledge points between students and teachers, we can achieve accurate personalized teaching matching, recommend suitable teachers to students in need, improve the overall quality and effectiveness of educational services, and increase the attractiveness of enrollment promotion.

[0134] Specifically, in step 6, the campus to be promoted is determined based on the location of the school corresponding to any group, and the in-service teachers of the campus to be promoted are further selected as teachers corresponding to the recommended courses.

[0135] When an educational institution is large in scale, it will have multiple campuses. Recommending campuses and teachers with convenient geographical locations can increase the attractiveness and efficiency of enrollment and improve the effectiveness of promotion.

[0136] Step 7: After traversing all groups, all subjects, and all students, generate personalized enrollment information for each student based on the analysis results, recommended courses, and recommended teachers corresponding to each student.

[0137] Personalize your admissions information as a poster, link, and / or document, including information about your institution, fees, benefits, contact details, and more.

[0138] The recommended teachers are ranked and displayed, and each teacher’s teaching methods and strong knowledge points are displayed.

[0139] By providing personalized course and teacher recommendations and generating personalized admissions information, more potential students can be attracted. At the same time, by providing detailed reasons for course and teacher recommendations, communication between parents and schools can be promoted, and both parents and schools can focus on students' growth and improve admissions success rates.

[0140] Step 8: Send personalized enrollment information to the contact terminal corresponding to each student.

[0141] Specifically, personalized enrollment information is sent via email, text messages and / or social software to achieve precision marketing.

[0142] Figure 2 FIG. 1 is a schematic diagram of a structure of an embodiment of an intelligent enrollment system for an educational institution based on big data analysis provided by the present invention. Figure 2 As shown, the system includes: a data acquisition module 10, a data processing module 20, a data division module 30, a data analysis module 40, a course recommendation module 50, a teacher recommendation module 60, an information production module 70 and a data sending module 80.

[0143] The data acquisition module 10 is used to acquire the educational data of students online and / or offline.

[0144] The data processing module 20 is used to pre-process the educational data to obtain the data to be analyzed, wherein the data to be analyzed includes the basic information of the students and the academic data of the students.

[0145] The data partitioning module 30 is used to extract student identifiers from the data to be analyzed, group the students according to school and grade based on the student identifiers, and then divide the data to be analyzed into multiple data sets based on the groups.

[0146] The data analysis module 40 is used to extract any group, evaluate and analyze any student in any group based on the first data set, and obtain analysis results, wherein the first data set is the data set corresponding to any group.

[0147] The course recommendation module 50 is used to extract any subject, cluster the students in any group based on the first analysis result, generate multiple classification sets, and generate recommended courses for students in each classification set, wherein the first analysis result is the analysis result corresponding to any subject.

[0148] The teacher recommendation module 60 is used to extract any student, determine the recommended teacher based on the student's basic information, analysis results and teacher information of the teacher corresponding to the recommended course, and sort all the recommended teachers.

[0149] The information production module 70 is used to generate personalized enrollment information for each student based on the analysis results, recommended courses and recommended teachers corresponding to each student after traversing all groups, all subjects and all students.

[0150] The data sending module 80 is used to send personalized enrollment information to the contact terminal corresponding to each student.

[0151] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0152] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The above-mentioned program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0153] The above-mentioned embodiments only express the preferred implementation mode of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An intelligent enrollment method for educational institutions based on big data analysis, characterized in that: The steps include: Step 1: Obtain students’ educational data through online and / or offline methods; Step 2: pre-process the educational data to obtain data to be analyzed, wherein the data to be analyzed includes basic information of students and academic data of students; Step 3: extracting student identifiers from the data to be analyzed, grouping the students according to school and grade based on the student identifiers, and then dividing the data to be analyzed into multiple data sets based on the groups; Step 4: extract any group, and evaluate and analyze any student in any of the groups based on the first data set to obtain an analysis result, wherein the first data set is a data set corresponding to any of the groups; Step 5: extract any subject, cluster the students in any of the groups based on the first analysis result, generate multiple classification sets, and generate recommended courses for the students in each of the classification sets, wherein the first analysis result is the analysis result corresponding to any of the subjects; Step 6: extract any student, determine the recommended teacher based on the student's basic information, the analysis result and the teacher information of the teacher corresponding to the recommended course, and sort all the recommended teachers; Step 7: After traversing all groups, all subjects and all students, generate personalized enrollment information for each student based on the analysis results, the recommended courses and the recommended teachers corresponding to each student; Step 8: Send the personalized enrollment information to the contact terminal corresponding to each student.

2. The method according to claim 1, characterized in that The student academic data includes the test paper data of all subjects in each examination of the student within a preset time, and the step 4 includes: Step 41, for any of the subjects, extract the first test paper data of any student in any test; Step 42: obtaining the test score of any student in any test based on the first test paper data; Step 43: After traversing all students in any of the groups, the first characteristic value of the nth student in any of the subjects in any exam is calculated based on the test scores. The first characteristic value P1 of the nth student is n The calculation formula is: Among them, S n is the test score of the nth student, S is the average score of any subject in any test, n is a positive integer from 1 to N, and N is the total number of students in any group; Step 44, after traversing all the examinations of any of the subjects within the preset time, calculate the second characteristic value of any of the subjects of the nth student, and the calculation formula is: Among them, P2 n is the second characteristic value of any of the subjects of the nth student, P1 n,m is the first characteristic value of any of the subjects in the mth examination of the nth student, where m is a positive integer from 1 to M, and M is the total number of examinations within the preset time; Step 45, extracting the second test paper data of the nth student in the most recent test, identifying the wrongly answered questions in the second test paper data, and defining them as the first category of questions; Step 46: determining an evaluation value of each question in the first category of questions, and adjusting a first test score and a first ranking of the nth student in a most recent test based on the second characteristic value of any of the subjects of the nth student and the evaluation value of each of the first category of questions, to obtain an adjustment result; Step 47: Identify the knowledge point corresponding to each of the first-category questions, and generate a subject analysis result for any of the subjects of the nth student based on the first characteristic value, the second characteristic value, the knowledge point, the first test score, the first ranking, and the adjustment result; Step 48: After traversing all students in any of the groups, return to step 41; Step 49: After traversing all subjects, generate the analysis result based on the subject analysis results corresponding to all subjects of any student.

3. The method according to claim 2, characterized in that The step 46 comprises: Extract any question from the first category of questions, determine whether the second characteristic value is greater than or equal to the evaluation value corresponding to any of the questions, and if so, obtain the score of any of the questions, and add the score to the first test score to generate a new first test score; After traversing all the first category questions, the nth student is re-ranked based on the new first test score, and the new first test score and the new ranking are defined as the adjustment result.

4. The method according to claim 2, characterized in that: The step 5 comprises: Step 51, extract any student, and identify the first knowledge point corresponding to the first type of question of any student; Step 52: Generate a feature sequence based on the first feature value, the second feature value, and the first knowledge point of any student; Step 53: After traversing all students, cluster all students corresponding to any of the subjects based on the feature sequence; Step 54: extract any classification set, and obtain the first feature sequence of the student with the highest first feature value in any classification set; Step 55: Match the recommended courses for students in any of the classification sets based on the first feature sequence.

5. The method according to claim 4, characterized in that The step 55 comprises: Step 551: extracting from the first storage module a second feature sequence of all the students enrolled in any of the subjects, wherein the second feature sequence is the feature sequence of the students enrolled when they entered the institution; Step 552: Calculate the similarity between the first feature sequence and any second feature sequence, and define the enrolled students corresponding to the second feature sequence whose similarity is greater than a first preset value as objects to be compared; Step 553: Obtain the improvement degree value of each object to be compared, and use the course corresponding to the student with the largest improvement degree value as the recommended course.

6. The method according to claim 2, characterized in that The student basic information includes personality and hobbies, the teacher information includes personality, hobbies and expertise, and step 6 includes: Analyze the knowledge points mastered by any student based on the subject analysis results to obtain the first category of knowledge points that any student has not mastered and the second category of knowledge points that are weak; Compare the student information with the teacher information, and if the i-th data in the student information matches the data in the teacher information, set the comparison result to 1, otherwise set the comparison result to 0, wherein the student information includes the student basic information, the first category of knowledge points, and the second category of knowledge points; After the comparison is completed, the recommendation degree of any teacher is calculated, and the calculation formula is: Among them, R j is the recommendation degree of the jth teacher, V i is the comparison result of the i-th data in the student information, α i is the parameter weight coefficient, i is a positive integer from 1 to I, and I is the total number of all data in the student information; The teachers whose recommendation degree is greater than a second preset value are taken as the recommended teachers, and all the recommended teachers are sorted from large to small based on the recommendation degree.

7. The method according to claim 1, characterized in that In step 6, the campus to be promoted is determined based on the location of the school corresponding to any of the groups, and the in-service teachers of the campus to be promoted are further selected as teachers corresponding to the recommended courses.

8. The method according to claim 1, characterized in that Send said personalized enrollment information via email, text message and / or social software.

9. An intelligent enrollment system for educational institutions based on big data analysis, used to implement the method according to any one of claims 1 to 8, characterized in that: include: Data acquisition module, data processing module, data division module, data analysis module, course recommendation module, teacher recommendation module, information production module and data sending module; The data acquisition module is used to acquire the educational data of students online and / or offline; The data processing module is used to pre-process the educational data to obtain data to be analyzed, wherein the data to be analyzed includes basic information of students and academic data of students; The data partitioning module is used to extract student identifiers from the data to be analyzed, group students according to school and grade based on the student identifiers, and then divide the data to be analyzed into multiple data sets based on the groups; The data analysis module is used to extract any group, and to evaluate and analyze any student in any of the groups based on the first data set to obtain an analysis result, wherein the first data set is a data set corresponding to any of the groups; The course recommendation module is used to extract any subject, cluster the students in any of the groups based on the first analysis result, generate multiple classification sets, and generate recommended courses for students in each of the classification sets, wherein the first analysis result is the analysis result corresponding to any of the subjects; The teacher recommendation module is used to extract any student, determine the recommended teacher based on the student's basic information, the analysis result and the teacher information of the teacher corresponding to the recommended course, and sort all the recommended teachers; The information making module is used to generate personalized enrollment information for each student based on the analysis results, recommended courses and recommended teachers corresponding to each student after traversing all groups, all subjects and all students; The data sending module is used to send the personalized enrollment information to the contact terminal corresponding to each student.

Images