An educational path generation system, method, device and electronic device

Abstract

The application discloses an education path generation system, method and device and electronic equipment, and relates to the technical field of education, and comprises a data acquisition module, a feature extraction module, a rule engine module, an information matching module and a path generation module; the data acquisition module is used for acquiring multi-dimensional student basic information and school education data of students; the feature extraction module is used for generating multi-dimensional learning ability feature information; the rule engine module is used for obtaining multi-dimensional education information corresponding to the school education data and a set of education rule information corresponding to a plurality of schools respectively; the information matching module is used for determining a target school from the plurality of schools, in which the education rule information matches the multi-dimensional student basic information and the multi-dimensional learning ability feature information; and the path generation module is used for generating an education path of the student based on the target school. The application can realize the structured processing of the education data, improve the matching accuracy of the education path, and meet the personalized education planning needs of students.

Description

Technical Field

[0001] This application relates to the field of educational technology, and in particular to a system, method, apparatus, and electronic device for generating pathways to higher education. Background Technology

[0002] In high school education, college application planning is a crucial aspect that influences students' future development. Students can choose from various pathways, such as general admissions, specialized admissions, and admissions based on artistic or athletic talents, and can apply to multiple schools and corresponding majors, provided they meet the application requirements.

[0003] Currently, college application pathway planning technology uses information such as students' scores, subject selections, and student status to filter out eligible schools and corresponding majors from the admission information released by schools, and then generates a college application pathway.

[0004] However, this method filters schools and corresponding majors based on students' scores and subject selections, without considering students' interests and other personalized characteristics. This results in a mismatch between the selected schools and majors and students' interests, abilities, and strengths. The sheer volume and complexity of school admissions information, coupled with the current lack of technology for categorizing and filtering this information, leads to outdated or irrelevant information interfering with the student's suitability. Consequently, the generated pathways do not match the student's needs. Furthermore, school admissions information is manually extracted and updated periodically from websites and other channels. Delays in this process result in information lag, preventing the pathways from being dynamically adjusted based on updated information, thus leading to low accuracy. Even if students meet the score requirements and apply to relevant schools and majors, a lack of interest or mismatch between their abilities and the requirements may hinder their ability to fully utilize their talents, potentially leading to aversion to school or changing majors. This results in low utilization rates of the generated pathways, failing to meet students' personalized academic planning needs. Summary of the Invention

[0005] In view of this, this application provides a system, method, apparatus and electronic device for generating college entrance pathways. The main purpose is to improve the technical problem of the current technology that selects schools and corresponding majors based on students' scores, subject selection and other conditions, without taking into account students' interests and other personalized characteristics. This results in the selected schools and corresponding majors not matching students' interests, abilities and strengths, and thus the low accuracy of the generated college entrance pathways.

[0006] Firstly, this application provides a system for generating pathways to higher education, including: The module includes a data acquisition module, a feature extraction module, a rule engine module, an information matching module, and a path generation module. The data acquisition module is connected to the feature extraction module and the rule engine module respectively; the information matching module is connected to the rule engine module and the feature extraction module and the path generation module respectively. The data acquisition module is used to obtain multi-dimensional basic student information and school admission data; The feature extraction module is used to perform learning ability feature analysis on the multi-dimensional student basic information sent by the data acquisition module, and generate multi-dimensional learning ability feature information, which includes the student's learning interest feature information, learning ability feature information, and subject proficiency information. The rule engine module is used to extract school admission information from the school admission data sent by the data collection module, obtain multi-dimensional admission information corresponding to the school admission data, generate admission rules from the multi-dimensional admission information, and obtain a set of admission rule information corresponding to multiple schools respectively. The information matching module is used to determine the target school from the multiple schools that matches the admission rule information with the multi-dimensional student basic information and the multi-dimensional learning ability feature information, based on the set of admission rule information of the multiple schools sent by the rule engine module. The path generation module is used to generate the student's college entrance path based on the target school sent by the information matching module.

[0007] Optionally, the feature extraction module is used to perform learning ability feature analysis on the multi-dimensional student basic information, generate the student's learning ability profile, and extract ability information based on the learning ability profile to obtain the multi-dimensional learning ability feature information.

[0008] Optionally, the information matching module is used for: The multi-dimensional student basic information sent by the data acquisition module is matched with the college entrance examination rule information in the set of college entrance examination rule information sent by the rule engine module to obtain candidate college entrance examination rule information that meets the matching conditions in the set of college entrance examination rule information. The school corresponding to the candidate college entrance examination rule information is determined as the candidate school. The college entrance examination rule information includes enrollment rule information and college entrance examination experience rule information. Based on the multi-dimensional learning ability characteristic information, the candidate schools are analyzed, and based on the analysis results, they are prioritized and ranked to determine the target school corresponding to the student from the candidate schools.

[0009] Optionally, the data acquisition module includes a student information acquisition module and a college entrance examination data acquisition module; The student information collection module is connected to the feature extraction module, and the college entrance examination data collection module is connected to the rule engine module. The student information collection module is used to obtain multi-dimensional basic student information through a network interface and send the multi-dimensional basic student information to the feature extraction module. The school admission data acquisition module is used to obtain the school's admission data through web crawling technology and send the school's admission data to the rule engine module.

[0010] Optionally, the rule engine module includes an enrollment rule module and a college admission experience rule module; The enrollment rules module is connected to the student information collection module and the information matching module, and the college entrance experience rules module is connected to the college entrance rules information collection module and the information matching module; The enrollment rules module is used to determine the first confidence level of the school enrollment data based on the data source of the school enrollment data in the school admission data; in response to the first confidence level meeting the confidence level condition, the module extracts enrollment information from the school enrollment data to obtain the enrollment information corresponding to the school enrollment data, and generates enrollment rules from the enrollment information to obtain the enrollment rule information; The college entrance examination experience rule module is used to determine the second confidence level of the historical admission data based on the data source of the historical admission data in the school's college entrance examination data; in response to the second confidence level meeting the confidence level condition, the module extracts college entrance examination experience information from the historical admission data to obtain the college entrance examination experience information corresponding to the historical admission data, and generates college entrance examination experience rules from the college entrance examination experience information to obtain the college entrance examination experience rule information.

[0011] Optionally, the enrollment rule module is used to respond to the update of the school's enrollment data by obtaining the updated enrollment data and the third confidence level of the updated enrollment data; extracting enrollment update information from the updated school enrollment data to obtain the corresponding updated enrollment information; generating enrollment update rules from the updated enrollment information to obtain updated enrollment rule information; and updating the enrollment rule information when the third confidence level meets the confidence level condition. The college admission experience rule module is used to respond to the update of the historical admission data, obtain the updated historical admission data and the fourth confidence level of the updated historical admission data; extract the updated historical admission information from the updated historical admission data to obtain the updated historical admission information corresponding to the updated historical admission data; generate updated historical admission rules from the updated historical admission information to obtain college admission experience update rule information; and update the college admission rule information when the fourth confidence level meets the confidence level condition.

[0012] Optionally, the rule engine module stores the updated school admission rule information, and the updated school admission rule information and the original school admission rule information together form the school admission rule information set.

[0013] Secondly, this application provides a method for generating pathways to higher education, including: Obtain multi-dimensional basic student information and school admission data; The learning ability characteristics of the multi-dimensional student basic information are analyzed to generate multi-dimensional learning ability characteristic information, which includes the student's learning interest characteristics, learning ability characteristics, and subject proficiency information. The school admission data is used to extract admission information to obtain multi-dimensional admission information corresponding to the school admission data. Admission rules are generated from the multi-dimensional admission information to obtain a set of admission rule information corresponding to multiple schools. Based on the set of admission rules information of the multiple schools, target schools that match the admission rules information with the multi-dimensional student basic information and the multi-dimensional learning ability characteristic information are determined from the multiple schools; Based on the target school, generate the student's pathway to higher education.

[0014] Thirdly, this application provides an educational pathway generation device, comprising: The acquisition module is configured to acquire multi-dimensional basic student information and school admission data. The analysis module is configured to perform learning ability feature analysis on the multi-dimensional student basic information and generate multi-dimensional learning ability feature information, which includes the student's learning interest feature information, learning ability feature information, and subject proficiency information. The extraction module is configured to extract admission information from the school admission data to obtain multi-dimensional admission information corresponding to the school admission data, generate admission rules from the multi-dimensional admission information, and obtain a set of admission rule information corresponding to multiple schools respectively. The determination module is configured to determine a target school from the multiple schools that matches the admission rule information with the multi-dimensional student basic information and the multi-dimensional learning ability characteristic information, based on the set of admission rule information of the multiple schools. The generation module is configured to generate the student's college entrance path based on the target school.

[0015] Fourthly, this application provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor executes the computer program to implement the college entrance path generation system described in the first aspect.

[0016] Based on the above technical solution, this application provides a system, method, apparatus, and electronic device for generating college entrance pathways, comprising: a data acquisition module, a feature extraction module, a rule engine module, an information matching module, and a pathway generation module; the data acquisition module is connected to the feature extraction module and the rule engine module respectively; the information matching module is connected to the rule engine module, the feature extraction module, and the pathway generation module respectively; the data acquisition module is used to acquire multi-dimensional student basic information and school entrance data; the feature extraction module is used to perform learning ability feature analysis on the multi-dimensional student basic information sent by the data acquisition module to generate multi-dimensional learning ability feature information; the rule engine module is used to extract entrance information from the school entrance data to obtain multi-dimensional entrance information corresponding to the school entrance data, and generate entrance rules from the multi-dimensional entrance information to obtain a set of entrance rule information corresponding to multiple schools respectively; the information matching module is used to determine the target school from multiple schools that matches the entrance rule information with the multi-dimensional student basic information and multi-dimensional learning ability feature information based on the set of entrance rule information from multiple schools; the pathway generation module is used to generate the student's college entrance pathway based on the target school. Compared with existing technologies, this application uses a feature extraction module to analyze the learning ability characteristics of multi-dimensional student basic information, generating multi-dimensional learning ability feature information to extract personalized characteristics such as students' interests, hobbies, and strengths; it uses a rule engine module to generate a set of college entrance rules information, realizing the structured processing of college entrance data and improving the matching degree between college entrance paths and students; and it uses an information matching module to first determine candidate schools based on multi-dimensional student basic information, and then filter target schools that match the multi-dimensional learning ability feature information, improving the matching accuracy of college entrance paths and meeting students' personalized college entrance planning needs. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This paper shows a schematic diagram of the structure of an educational pathway generation system provided in an embodiment of this application; Figure 2 A flowchart illustrating a method for generating pathways to higher education provided in an embodiment of this application is shown. Figure 3 This illustration shows a schematic diagram of a pathway generation device provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown.

[0018] exist Figure 1 middle: 1-Data Acquisition Module; 11-Student Information Acquisition Module; 12-College Admission Data Acquisition Module; 2-Feature extraction module; 3-Rules Engine Module; 31-Admissions Rules Module; 32-College Admissions Experience Rules Module; 4-Information matching module; 5-Path generation module. Detailed Implementation

[0019] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0020] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0021] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0022] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0023] The following is combined Figure 1 This application describes an educational pathway generation system according to some embodiments.

[0024] This application provides an embodiment of an educational pathway generation system, such as... Figure 1As shown, it includes: a data acquisition module 1, a feature extraction module 2, a rule engine module 3, an information matching module 4, and a path generation module 5; the data acquisition module 1 is connected to the feature extraction module 2 and the rule engine module 3 respectively; the information matching module 4 is connected to the rule engine module 3, the feature extraction module 2, and the path generation module 5 respectively; the data acquisition module 1 is used to acquire multi-dimensional basic student information and school admission data; the feature extraction module 2 is used to perform learning ability feature analysis on the multi-dimensional basic student information sent by the data acquisition module 1, and generate multi-dimensional learning ability feature information, which includes students' learning interest feature information, learning ability ... The data collection module 1 extracts school admission information and its students' academic strengths and weaknesses. The rule engine module 3 extracts admission information from the school admission data sent by the data collection module 1, obtaining multi-dimensional admission information corresponding to the school admission data. It then generates admission rules based on this multi-dimensional information, resulting in a set of admission rule information for each school. The information matching module 4, based on the admission rule information set from multiple schools sent by the rule engine module 3, determines the target school from among these schools that matches the admission rule information with the multi-dimensional student basic information and multi-dimensional learning ability characteristics. The path generation module 5 generates the student's admission path based on the target school sent by the information matching module 4.

[0025] In this embodiment, multi-dimensional student basic information can be data reflecting an individual student's situation. Specifically, multi-dimensional student basic information can include student basic data, student academic data, and student personalized data. Among them, student basic data can specifically include the province where the school is located, the current grade level, ethnicity, household registration type / place of residence, height / vision, etc. Different provinces have different multiple college entrance paths, and different grade levels face different college entrance goals and plans. Ethnicity and household registration type / place of residence correspond to different special enrollment information. Height / vision is related to some college entrance paths that have physical fitness requirements. Student academic data can specifically include past major exam scores, subject selection, academic proficiency test grade, competition / honors, etc. Past major exam scores can be used for initial screening of college entrance paths. Subject selection needs to match the subject selection requirements of different college entrance paths. Some college entrance paths require academic proficiency test grade. Competition / honors are related to college entrance paths.

[0026] In this embodiment, the school's admission data can be data related to school enrollment and admission. Specifically, the school's admission data can include enrollment data and historical admission data. Enrollment data can come from relevant department websites, university admission websites, etc., and can include admission regulations, subject selection requirements, bonus point information, geographical restrictions, and admission score lines. Historical admission data can be generated based on the school's historical admission data, and can include historical admission score ranges, matching of admitted students' characteristics, and cases of matching between the university's professional training direction and student development.

[0027] In this embodiment of the application, multi-dimensional learning ability characteristic information can be information reflecting the personalized characteristics of students, and can be used to match higher education paths that match students' abilities and interests. For example, the multi-dimensional learning ability characteristic information in this embodiment can specifically include learning interest characteristic information, learning ability characteristic information, and subject proficiency information; wherein, learning interest characteristic information can be information about students' interests in fields such as engineering, humanities, arts, and scientific research; learning ability characteristic information can be assessment information about students' logical thinking ability, language expression ability, and hands-on practical ability; and subject proficiency information can be advantageous subjects determined based on students' academic data, such as mathematics, physics, and chemistry.

[0028] In this embodiment, the rule engine module 3 receives school admission data sent by the data acquisition module 1, calls an entity recognition model (such as a named entity recognition model) to extract key entities from the admission information, filters out entities such as university name, major category, subject requirements, score range, and policy type, and establishes the association relationship between the entities and the admission data (i.e., admission information); the extracted association information is combined with a predefined rule template library in a text parsing pipeline, and a rule generator automatically generates structured condition-conclusion rules (i.e., admission rule information).

[0029] In the embodiments of this application, the set of school admission rule information can be a collection of integrated school admission rule information. Specifically, the set of school admission rule information can be a rule base. The rule base can be used to store various structured rules related to school admission. Specifically, it can include hard rules generated based on the admission information of multiple schools, and soft expert experience rules with confidence weights generated based on admission experience information. The rule base can achieve the coexistence of updated rules and original rules through version control. That is, after the new rules corresponding to the updated admission information are added to the database, they can be stored synchronously with the old rules corresponding to the original admission information.

[0030] In this embodiment of the application, the candidate schools can be schools that meet the basic requirements of the students after preliminary screening. For example, the candidate schools in this embodiment of the application can specifically be schools whose admission information matches the students' multi-dimensional basic information, such as universities that meet the basic requirements of students' student status, scores, and subject selection.

[0031] In this embodiment of the application, the target school can be a school selected from candidate schools that matches the student's personalized characteristics. For example, the target school in this embodiment of the application can specifically be a school selected from candidate schools that matches the student's learning interests, learning abilities, and strengths in specific subjects, such as a top-tier engineering university for a student who excels in physics and is interested in engineering.

[0032] In this embodiment of the application, the data acquisition module 1 sends multi-dimensional student basic information to the feature extraction module 2, and the data acquisition module 1 sends the school admission data to the rule engine module 3; the rule engine module 3 sends the school admission rule information set to the information matching module 4; the feature extraction module 2 sends multi-dimensional learning ability feature information and multi-dimensional student basic information to the information matching module 4; and the information matching module 4 sends the target school to the path generation module 5.

[0033] Compared with existing technologies, the embodiments of this application analyze the learning ability features of multi-dimensional student basic information through a feature extraction module, generating multi-dimensional learning ability feature information to extract personalized features such as students' interests, hobbies, and strengths; generate a set of college entrance rules information through a rule engine module to achieve structured processing of college entrance data and improve the matching degree between college entrance paths and students; and first determine candidate schools based on multi-dimensional student basic information through an information matching module, and then filter target schools that match multi-dimensional learning ability feature information to improve the matching accuracy of college entrance paths and meet students' personalized college entrance planning needs.

[0034] As an optional approach, feature extraction module 2 is used to perform learning ability feature analysis on multi-dimensional student basic information, generate a student learning ability profile, and extract ability information based on the learning ability profile to obtain multi-dimensional learning ability feature information.

[0035] In this embodiment of the application, the learning ability profile can be a comprehensive descriptive profile that includes basic student information and learning ability characteristic information, which can provide a comprehensive individual basis for information matching. For example, the student profile in this embodiment of the application may specifically include basic information such as the province where the student's school is located, ethnicity, and household registration type; academic information such as past exam scores and subject selection; and characteristic information such as learning interests, abilities, strengths, and subjects they excel in.

[0036] Optionally, the information matching module 4 is used to: match the multi-dimensional student basic information sent by the data collection module 1 with the college entrance examination rule information in the set of college entrance examination rule information sent by the rule engine module 3, to obtain candidate college entrance examination rule information that meets the matching conditions in the set of college entrance examination rule information, and to determine the schools corresponding to the candidate college entrance examination rule information as candidate schools. The college entrance examination rule information includes enrollment rule information and college entrance examination experience rule information. Based on the multi-dimensional learning ability characteristic information, the candidate schools are analyzed, and priority ranking is performed based on the analysis results to determine the target school corresponding to the student from the candidate schools.

[0037] In this embodiment, the matching conditions can be conditions used to filter candidate admission rules information. For example, the matching conditions in this embodiment can specifically include basic hard matching conditions, such as school registration / household registration matching conditions, score attainment conditions, subject selection matching conditions, and admission type matching conditions. Specifically, the school registration / household registration matching condition can be that the student's school registration location and household registration type meet the school's admission geographical restrictions; the score attainment condition can be that the student's scores reach the school's admission score line or admission score range; the subject selection matching condition can be that the student's subject selection combination meets the school's major subject selection requirements; and the admission type matching condition can be that the student's chosen admission path is consistent with the school's admission type.

[0038] In this embodiment of the application, the information matching module 4 can obtain various types of college entrance examination information in the college entrance examination rule information set, including the admission rule information and historical admission rule data of multiple schools, match the student's multi-dimensional basic student information with the admission rule information, filter out candidate college entrance examination information that meets the basic requirements based on the matching conditions, and determine the school corresponding to the candidate college entrance examination rule information as the candidate school.

[0039] In this embodiment of the application, the information matching module 4 can obtain multi-dimensional learning ability feature information generated by the feature extraction module 2 and input it into the information analysis model. The information analysis model can combine the admission information of candidate schools to analyze the suitability of each candidate school with the student's learning interests, learning abilities, and proficient subjects. Based on the analysis results, the candidate schools are prioritized and ranked, with the candidate schools with higher suitability ranking higher. A preset number of schools are selected from the ranking results as the target schools corresponding to the students, ensuring that the target schools not only meet the basic application requirements but also suit the students' personalized development needs. The information matching module 4 can load structured hard admission information rules and soft expert experience rules with confidence weights to accurately verify the matching process. The large model can provide in-depth suitability analysis to achieve a unity of accuracy and personalization.

[0040] In the embodiments of this application, the information analysis model can be a model used to analyze the fit between candidate schools and students' personalized characteristics. For example, the information analysis model in the embodiments of this application may specifically include a collaborative model of a large model and a rule engine, including but not limited to an analysis model based on similarity calculation, an evaluation model combined with expert experience rules, etc., which can comprehensively evaluate the degree of fit between the candidate school's training direction, core courses, ability requirements and students' learning ability characteristics.

[0041] Optionally, the data acquisition module 1 includes a student information acquisition module 11 and a college entrance examination data acquisition module 12. The student information acquisition module 11 is connected to the feature extraction module 2, and the college entrance examination data acquisition module 12 is connected to the rule engine module 3. The student information acquisition module 11 is used to obtain multi-dimensional basic student information through a network interface and send the multi-dimensional basic student information to the feature extraction module 2. The college entrance examination data acquisition module 12 is used to obtain school college entrance examination data through web crawling technology and send the school college entrance examination data to the rule engine module 3.

[0042] In this embodiment, the student information collection module 11 can be a functional module for acquiring student-related data. The student information collection module 11 can achieve automated and accurate collection of student data. For example, in this embodiment, the student information collection module 11 can specifically be a module with data synchronization and transmission functions, capable of establishing connections with multiple student data source platforms to acquire multi-dimensional basic student information.

[0043] In this embodiment, the school admission data acquisition module 12 can be a functional module specifically used to acquire school admission-related data, and the school admission information acquisition module 12 can realize real-time dynamic acquisition of school admission information. For example, the school admission information acquisition module 12 in this embodiment can specifically be a module with data acquisition, parsing and updating functions, capable of acquiring various types of school admission information from authoritative information sources and processing them accordingly.

[0044] In this embodiment of the application, the network interface can be an interface for data transmission, enabling the student information collection module 11 to connect with the data source platform. For example, the network interface in this embodiment may specifically include a standardized API interface that supports secure authentication methods such as OAuth / Token authentication. After authorization, it can establish a stable connection with the school's academic affairs system, standardized examination platform, student activity record platform, etc., ensuring the security and reliability of data acquisition.

[0045] In this embodiment of the application, the student information collection module 11 can establish a connection with the school's academic affairs system, standardized examination platform, student activity record platform, etc. through a standardized network interface, and regularly and automatically synchronize dynamic data such as students' academic performance, examination results, participation in activities, and basic information. After cleaning and standardization, the data is transmitted to the feature extraction module 2 to provide data support for student profile generation and learning ability feature analysis. The college entrance examination data collection module 12 can obtain college entrance examination data such as admission data and historical admission data from authoritative sources such as the official websites of relevant departments and the admission websites of target universities through various methods such as targeted crawling and standardized API interfaces. After parsing and integration, the data is sent to the rule engine module 3.

[0046] Optionally, the rule engine module 3 includes an enrollment rule module 31 and an academic experience rule module 32. The enrollment rule module 31 is connected to the student information collection module 11 and the information matching module 4, and the academic experience rule module 32 is connected to the academic data collection module 12 and the information matching module 4, respectively. The enrollment rule module 31 is used to determine the first confidence level of the school enrollment data based on the data source of the school enrollment data in the school academic data. In response to the first confidence level meeting the confidence level condition, the enrollment information is extracted from the school enrollment data to obtain the enrollment information corresponding to the school enrollment data, and enrollment rules are generated from the enrollment information to obtain enrollment rule information. The academic experience rule module 32 is used to determine the second confidence level of the historical admission data based on the data source of the historical admission data in the school academic data. In response to the second confidence level meeting the confidence level condition, academic experience information is extracted from the historical admission data to obtain the academic experience information corresponding to the historical admission data, and academic experience rules are generated from the academic experience information to obtain academic experience rule information.

[0047] In this embodiment of the application, school enrollment data can be raw data related to enrollment published by the school. For example, the school enrollment data in this embodiment of the application may specifically include text data such as the school's enrollment regulations, subject selection requirements, bonus point information, admission score lines, and enrollment geographical restrictions.

[0048] For the embodiments of this application, historical admission data can be the school's past admission records. For example, the historical admission data in this embodiment can specifically include data such as the school's academic performance, subject combinations, ethnicity, household registration type, and competition honors of students admitted in previous years.

[0049] In this embodiment, the first confidence level can be a confidence level assigned based on the authority of the data source, and can be used to reflect the reliability of the enrollment data. For example, in this embodiment, the first confidence level can be a value between 0 and 1. Enrollment data from authoritative platforms such as school websites and education examination authorities are assigned a higher confidence level (e.g., 0.8-1.0), while enrollment data from non-authoritative third-party platforms are assigned a lower confidence level (e.g., 0.3-0.7).

[0050] In this embodiment, the second confidence level can be a confidence level assigned based on the authority of the data source, and the second confidence level can be used to reflect the reliability of historical admission data. For example, in this embodiment, the second confidence level can be a value between 0 and 1, with a higher confidence level (e.g., 0.8-1.0) assigned to data sourced from the historical experience data of college admission experts.

[0051] In the embodiments of this application, the confidence level condition can be a condition for judging whether the school's admission data is reliable based on the data source. For example, the confidence level condition in the embodiments of this application can specifically be that the confidence level of the admission data is greater than a preset confidence threshold (such as 0.8), which can be calculated based on factors such as the authority of the data source and the accuracy of the analysis.

[0052] In this embodiment, the information parsing model can be a model used to transform unstructured college entrance examination data into structured college entrance examination rule information. For example, the information parsing model in this embodiment may specifically include a text parsing pipeline, which may include a Named Entity Recognition (NER) model, a rule template library, a rule generator, a natural language processing-based text parsing model, etc., capable of extracting key entities and logical relationships from unstructured college entrance examination data text.

[0053] In this embodiment of the application, the enrollment information collection module can obtain school admission data through targeted web crawling and other methods. Based on the source of the admission data, a first confidence level and a second confidence level are determined. If the first confidence level and the second confidence level meet the confidence level conditions, the admission data is input into the information parsing model of the rule engine module 3. The information parsing model can first perform text preprocessing on the admission data, and then extract key entities such as universities, majors, subjects, and score requirements through the Named Entity Recognition (NER) model. Combined with a predefined rule template library, structured condition-conclusion rules are generated, thereby obtaining standardized admission rule information.

[0054] Optionally, the enrollment rules module 31 is used to respond to updates in school enrollment data, obtain updated enrollment data and a third confidence level of the updated enrollment data; if the third confidence level meets the confidence level conditions, it extracts updated enrollment information from the updated school enrollment data to obtain the updated enrollment information corresponding to the school enrollment data, generates updated enrollment rules from the updated enrollment information, and obtains updated enrollment rule information; and updates the admission rules information based on the updated enrollment rule information. The admission experience rules module 32 is used to respond to updates in historical admission data, obtain updated historical admission data and a fourth confidence level of the updated historical admission data; if the fourth confidence level meets the confidence level conditions, it extracts updated historical admission information from the updated historical admission data to obtain the updated historical admission information corresponding to the updated historical admission data, generates updated historical admission rules from the updated historical admission information, and obtains updated admission experience rules information; and updates the admission rules information based on the updated admission experience rules information.

[0055] In this embodiment of the application, the updated school admissions data can be updated data after changes have occurred in the school's admissions data. For example, the updated school admissions data in this embodiment of the application may specifically include data such as the school's revised admission regulations, updated subject selection requirements, and changed admission score lines.

[0056] In this embodiment, the admission update rule information can be structured rule information obtained by generating rules from the school's admission update information. For example, the admission update rule information in this embodiment may specifically include updated admission rules, admission requirements, admission criteria, and other structured rule information.

[0057] In this embodiment of the application, the updated historical admission data can be updated data after supplementation or correction of historical admission data. For example, the updated historical admission data in this embodiment of the application may specifically include supplemented previous years' admission data, corrected admission score ranges, updated student characteristic data, etc.

[0058] In this embodiment, the updated rules for college admission experience can be updated rules generated based on historical admission update data. For example, the updated rules for college admission experience in this embodiment may specifically include updated school admission preferences, newly added professional matching cases, and revised admission probability assessment rules.

[0059] In this embodiment of the application, the enrollment information collection module can monitor changes in school enrollment data through a scheduled task manager. In response to updates to school enrollment data, the enrollment information collection module can automatically acquire updated school enrollment data and send it to the enrollment rule module 31. The enrollment rule module 31 can determine the third confidence level of the updated enrollment data. If the third confidence level meets the confidence level condition, it generates rules for the updated enrollment rule information through an information parsing model. The updated enrollment rule information is then incorporated into the college entrance examination rule information set to update the original enrollment rule information. If the confidence level condition is not met, the updated enrollment rule information is temporarily not updated and can be marked for manual review.

[0060] In this embodiment, the college admission data acquisition module can respond to updates in historical admission data by automatically acquiring updated historical admission data and sending it to the college admission experience rule module 32. The college admission experience rule module 32 can determine the fourth confidence level of the updated historical admission data. If the fourth confidence level meets the confidence level condition, the college admission experience rule module 32 generates rules for the updated historical admission data to obtain college admission experience update rule information. The college admission experience update rule information is then incorporated into the college admission rule information set to update the original college admission experience update rule information. If the confidence level condition is not met, the update is temporarily suspended and the college admission experience update rule information is marked for manual review.

[0061] Optionally, this application embodiment also provides a rule base update example, which collects multi-dimensional student basic information by calling school system API, examination platform API, and activity platform API. After data cleaning and formatting, the collected data is updated to the student profile database. Admission information is collected by targeted web crawling, and admission information web pages / documents are downloaded from the authoritative source whitelist. The updated web pages or documents are stored in the original document library. The process of identifying the updated content may include: preprocessing the newly stored document and loading historical versions, and comprehensively judging the degree of change by executing text comparison algorithms and large model-generated summary comparison. If an update is required, the updated document content is output to the NER model for key entity extraction, and new rules are generated and stored based on the matching rule base template.

[0062] Optionally, the rules engine module 3 stores the updated admission rules information, and the updated admission rules information and the original admission rules information form an admission rules information set.

[0063] In this embodiment, after updating the admission rule information, the rule engine module 3 can store the updated admission rule information while retaining the original admission rule information. This allows the updated and original admission rule information to form a set of admission rule information, with both old and new rules (corresponding to the old and new admission rule information) coexisting, thus achieving version control of the admission rule information. The system can switch the version of admission rule information used according to actual needs, time, or scenario, ensuring the continuity of the admission path planning logic.

[0064] Optionally, this application embodiment also provides a rule base (i.e., the set of college admission rule information in this application embodiment) configuration example. The input sources include an existing rule base (historical version), structured admission information, and college admission expert experience (text / interview / case). The structured admission information is parsed by the parsing module based on a predefined parsing template library and a large model-assisted extractor. The college admission expert experience is identified by the experience encoding module based on a domain-specific language (DSL), a rule configuration interface, and a confidence labeling tool. The structured admission information and college admission expert experience undergo rule syntax checking, rule conflict detection, and rule optimization in the rule generator. The generated rules are stored in the rule storage layer. The rule storage repository includes a hard rule base (admission information rules), a soft rule base (experience rules), rule metadata (version / source / effective time), and a rule relationship graph (dependency / conflict / priority).

[0065] Optionally, the rule base can be managed through a management tool layer, which may include a rule knowledge base (query / search), a rule testing platform, an impact analysis tool, and an audit log system. The rule base can also be managed through a version management layer, which includes a version controller (Git-like management), a rule distribution system, rollback management, and an effective timeline management. Versions can be automatically switched during off-peak usage periods or manually switched by the administrator, and the rule base will be reloaded after the switch.

[0066] Optionally, the rule engine interface uses a rule loader, rule compiler, fact matcher, and inference engine to match multi-dimensional student basic information and multi-dimensional student feature information with rules in the rule base, determine rules suitable for students, and output the rules to the planning process.

[0067] Compared with existing technologies, the embodiments of this application generate learning ability profiles and extract multi-dimensional learning ability feature information through a feature extraction module, thereby improving the accuracy of learning ability feature information; determine candidate schools by matching multi-dimensional student basic information with college entrance examination rules information through an information matching module, and determine target schools by analyzing and ranking multi-dimensional learning ability feature information, thereby achieving precise screening of candidate schools and improving the fit between target schools and students; obtain multi-dimensional student basic information through network interfaces and obtain school college entrance examination data through web crawling technology, thereby achieving automated acquisition of student information and college entrance examination data; generate standardized rules through a rule engine module, thereby achieving accurate college entrance examination path generation; update college entrance examination rule information by responding to data updates and filtering by confidence conditions, thereby achieving dynamic updating of college entrance examination rule information; and improve the accuracy of college entrance examination path by combining enrollment rule information and college entrance examination experience rule information.

[0068] This embodiment provides a method for generating pathways to higher education, such as... Figure 2 As shown, the method includes: Step 201: Obtain multi-dimensional basic student information and school admission data.

[0069] In this embodiment of the application, obtaining multi-dimensional student basic information can be achieved by establishing standardized API interfaces with school academic affairs systems, standardized examination platforms, student activity record platforms, etc., and regularly and automatically synchronizing dynamic data such as students' academic performance, examination results, participation in activities, and basic information. After the data is cleaned and standardized, multi-dimensional student basic information is formed.

[0070] In this embodiment, school admission information is obtained by deploying a high-priority, trusted targeted crawler to periodically monitor specific sections of authoritative official information sources such as the official websites of relevant departments and the admission websites of target universities, and to collect admission information, admission brochures, historical admission data, etc.

[0071] Step 202: Analyze the learning ability characteristics of students' basic information in multiple dimensions to generate multi-dimensional learning ability characteristic information.

[0072] Among them, the multi-dimensional learning ability characteristic information includes students' learning interest characteristics, learning ability characteristics, and subject proficiency information.

[0073] In this embodiment of the application, a learning ability feature analysis is performed on multi-dimensional student basic information by a profile generation model to generate a student's learning ability profile. The learning ability profile can clean, standardize and extract features from multi-dimensional student basic information, and generate multi-dimensional learning ability feature information by deeply analyzing and mining students' learning interest features, learning ability features and subjects they are good at.

[0074] In the embodiments of this application, the profile generation model can be a model used to analyze student data and generate student profiles. For example, the profile generation model in the embodiments of this application may include, but is not limited to, a natural language processing model fine-tuned with data from the education field, which has the ability to deeply understand and analyze multi-dimensional student basic information, and can extract key features from students' academic data and personalized data to generate comprehensive student profiles.

[0075] For example, based on students' participation in extracurricular activities and career interest preferences, we can analyze and derive information on students' learning interest characteristics (such as a preference for engineering or proficiency in humanities); based on students' exam score distribution and competition participation results, we can analyze and derive information on students' learning ability characteristics (such as outstanding logical thinking ability or strong hands-on practical ability); based on students' subject scores and academic performance in previous major exams, we can determine students' proficiency in certain subjects (such as proficiency in mathematics or physics).

[0076] Step 203: Extract admission information from school admission data to obtain multi-dimensional admission information corresponding to the school admission data. Generate admission rules from the multi-dimensional admission information to obtain a set of admission rule information corresponding to multiple schools.

[0077] In this embodiment, key entities (such as schools, majors, scores, etc.) are extracted from the college admission information using an entity recognition model (such as a named entity recognition model). Entities such as university name, major category, subject requirements, score range, and policy type are filtered out, and the association between entities and college admission data (i.e., college admission information) is established. The extracted association information is then combined with a predefined rule template library to improve the text parsing pipeline, and a rule generator automatically generates structured condition-conclusion rules (i.e., college admission rule information).

[0078] Step 204: Based on the information set of admission rules of multiple schools, determine the target school from multiple schools that matches the admission rule information with the multi-dimensional student basic information and multi-dimensional learning ability characteristic information.

[0079] In this embodiment, the student's multi-dimensional basic information is matched with the admission information of various schools in the admission rules information set. Schools meeting the requirements are then selected based on preset matching conditions. These conditions may include matching of student status / household registration, score attainment, subject selection matching, and admission type matching. For example, if a student's household registration type meets the requirements of a school's special admission program, the student's college entrance examination score reaches the school's admission cut-off score, the student's subject selection combination meets the subject selection requirements of a certain major, or the student's chosen arts and sports specialty admission type matches the school's admission type, schools meeting these matching conditions can be identified as candidate schools. During this process, the rule engine can load structured, rigid admission information rules to accurately verify the matching process, ensuring that all candidate schools meet the basic application requirements.

[0080] In this embodiment of the application, determining the target school that meets the multi-dimensional learning ability characteristic information from multiple candidate schools can be achieved by inputting the multi-dimensional learning ability characteristic information into an information analysis model. The information analysis model can combine the admission rule information of the candidate schools in the admission rule information set to comprehensively evaluate the suitability of each candidate school with the student. Based on the suitability evaluation results, the candidate schools are prioritized, with the candidate schools with higher suitability ranking higher. A predetermined number of schools are selected as target schools from the ranking results. In this process, a large model can be used to combine general knowledge, historical cases, and soft expert experience rules to conduct in-depth suitability analysis, ensuring that the target schools not only meet the basic requirements but also adapt to the student's personalized development needs.

[0081] Step 205: Generate the student's pathway to higher education based on the target school.

[0082] In this embodiment, generating a pathway to higher education can specifically involve generating pathway information and learning suggestion information. The pathway information may include target schools and corresponding majors, pathway type (e.g., general admission, special admission, arts / sports talent admission), application deadlines, and required application materials. The learning suggestion information can be supplementary advice provided to students to achieve their higher education goals, helping them improve their competitiveness in the college entrance examination. For example, the learning suggestion information in this embodiment may specifically include targeted reinforcement directions for strong subjects, improvement plans for weak subjects, suggestions for competition participation, and supplementary extracurricular activities, among other specific action suggestions for each stage.

[0083] Compared with existing technologies, this embodiment analyzes the learning ability characteristics of students' basic information from multiple dimensions to generate multi-dimensional learning ability characteristic information, thereby extracting personalized characteristics such as students' interests, hobbies, and strengths. By generating a set of college entrance examination rules information, it achieves structured processing of college entrance examination data, improving the matching degree between college entrance examination paths and students. By determining candidate schools based on multi-dimensional student basic information and then screening target schools that match the multi-dimensional learning ability characteristic information, it improves the matching accuracy of college entrance examination paths and meets students' personalized college entrance examination planning needs.

[0084] Optionally, this application embodiment also provides a data collection example. The data sources are divided into enrollment information data sources and student data sources. The enrollment information data sources cover official admission channels, education websites, education examination authorities, and target university channels. The student data sources cover school academic affairs systems, standardized examination platforms, and student activity record platforms. The two types of data are aggregated through combined platform data sources and data API interfaces (OAuth / Token). After the enrollment information data is aggregated, an original enrollment information text library is formed. After the student data is aggregated, it enters the student data preparation stage. The enrollment information data is compared through text comparison (including Hash / Difference). (Separate comparison and large model summary comparison) to determine whether to update. If not, it enters the waiting for the next scheduling. After the student data is standardized, the change recognition engine identifies the changes. The enrollment information data that meets the update conditions enters the enrollment information text parsing pipeline, and passes through the named entity recognition model, rule extraction, rule storage, and then enters the structured rule management module. The process is set up with a manual review interface. The rules are reviewed in conjunction with system notification reminders to determine whether they are consistent / pass. If they are consistent, the rules are published to the rule library. If not, the rules are discarded / marked. Finally, the rules that pass the review are entered into the rule engine release version library.

[0085] As an optional approach, this application embodiment also provides a rule base configuration example. The specific process of rule configuration may include: receiving unstructured enrollment information, preprocessing and classifying the enrollment information, using a large model to assist in the extraction of key information, and generating condition-conclusion rules as hard enrollment rules; receiving expert experience descriptions, using natural language understanding to identify key elements and logic in the expert experience, encoding the experience into a DSL or rule language and adding confidence weights as soft experience rules; and manually opening the rule configuration interface to select the rule type, defining the rule using a DSL or form, setting conditions and conclusions, and configuring weights and priorities to achieve manual rule configuration.

[0086] Optionally, conflict detection and format verification can be performed on hard admission rules, soft experience rules, and manually configured rules. A unique identifier and version number can be assigned to each rule and stored in the rule version repository. If it is the currently effective version, the rule engine can be activated and the rule repository index can be updated to complete the rule configuration. Historical versions can be temporarily stored and the rule version can be switched according to the transition time or scenario.

[0087] Compared with existing technologies, this embodiment improves the accuracy of learning ability feature information by generating learning ability profiles and extracting multi-dimensional learning ability feature information; it determines candidate schools by matching multi-dimensional student basic information with college entrance examination rules, and determines target schools by analyzing and ranking multi-dimensional learning ability feature information, thus achieving precise screening of candidate schools and improving the fit between target schools and students; it automates the acquisition of student information and college entrance examination data by obtaining multi-dimensional student basic information through network interfaces and by obtaining school college entrance examination data through web crawling technology; it ensures the accuracy of college entrance examination path generation by generating standardized rules; it dynamically updates college entrance examination rules by responding to data updates and updating the college entrance examination rules information after filtering by confidence conditions; and it improves the accuracy of college entrance examination paths by combining enrollment rule information and college entrance examination experience rule information.

[0088] Furthermore, as Figure 2 The specific implementation of the method shown in this embodiment provides an educational pathway generation device, such as... Figure 3 As shown, the device includes: an acquisition module 31, an analysis module 32, an extraction module 33, a determination module 34, and a generation module 35.

[0089] Module 31 is configured to acquire multi-dimensional basic student information and school admission data. Analysis module 32 is configured to perform learning ability feature analysis on the multi-dimensional student basic information sent by the data acquisition module, and generate multi-dimensional learning ability feature information, which includes students' learning interest feature information, learning ability feature information and subject proficiency information. The extraction module 33 is configured to extract school admission information from school admission data, obtain multi-dimensional admission information corresponding to the school admission data, generate admission rules from the multi-dimensional admission information, and obtain a set of admission rule information corresponding to multiple schools respectively. The determination module 34 is configured to determine the target school that matches the admission rule information with the multi-dimensional student basic information and multi-dimensional learning ability characteristic information from multiple schools based on the admission rule information set of multiple schools. The generation module 35 is configured to generate the student's college entrance path based on the target school sent by the information matching module.

[0090] It should be noted that other corresponding descriptions of the functional units involved in the page resource loading device based on teaching equipment provided in this embodiment can be found in the following references. Figure 2 The corresponding descriptions in [the document] will not be repeated here.

[0091] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0092] like Figure 4 The diagram shown is a hardware structure schematic of an electronic device according to the present invention, comprising: At least one processor 401; and, Memory 402 is communicatively connected to at least one processor 401; wherein, The memory 402 stores instructions that can be executed by at least one processor, such that the at least one processor can execute the aforementioned pathway generation system.

[0093] Figure 4 Take a processor 401 as an example.

[0094] The electronic device may also include an input device 403 and an output device 404.

[0095] The processor 401, memory 402, input device 403, and output device 404 can be connected via a bus or other means. Figure 4 Taking the example of a connection between China and Israel via a bus.

[0096] Memory 402, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the school admission path generation system in this application embodiment, for example, Figure 1 The system shown. The processor 401 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules stored in the memory 402, thereby realizing the college entrance path generation system in the above embodiment.

[0097] Memory 402 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the pathway generation system, etc. Furthermore, memory 402 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 402 may optionally include memory remotely located relative to processor 401, and these remote memories may be connected via a network to the apparatus executing the pathway generation system. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0098] Input device 403 can receive user clicks and generate signal inputs related to user settings and function control of the college entrance path generation system. Output device 404 may include display devices such as a display screen.

[0099] One or more modules are stored in memory 402, and when run by one or more processors 401, the school admission path generation system in any of the above method embodiments is executed.

[0100] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0101] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0102] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0103] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms, or it can be implemented by hardware. By applying the solution of this embodiment, compared with the existing technology, this embodiment uses a feature extraction module to analyze the learning ability features of multi-dimensional student basic information, generating multi-dimensional learning ability feature information, and realizing the extraction of personalized features such as students' interests, hobbies, and strengths; it uses a rule engine module to generate a set of college entrance examination rule information, realizing the structured processing of college entrance examination data and improving the matching degree between college entrance examination paths and students; it uses an information matching module to first determine candidate schools based on multi-dimensional student basic information, and then screen target schools that match the multi-dimensional learning ability feature information, improving the matching accuracy of college entrance examination paths and meeting students' personalized college entrance examination planning needs; and it uses a feature extraction module to generate a learning ability profile and extract multi-dimensional learning ability feature information, improving... The system ensures the accuracy of learning ability characteristic information; it determines candidate schools by matching multi-dimensional student basic information with college entrance examination rules through an information matching module, and determines target schools by analyzing and ranking multi-dimensional learning ability characteristic information, thereby achieving precise screening of candidate schools and improving the fit between target schools and students; it automates the acquisition of student information and college entrance examination data by obtaining multi-dimensional student basic information through network interfaces and school college entrance examination data through web crawling technology; it generates standardized rules through a rule engine module to ensure the accuracy of college entrance examination path generation; it dynamically updates college entrance examination rules by responding to data updates and filtering them with confidence conditions; and it improves the accuracy of college entrance examination paths by combining admission rules information and college entrance examination experience rules information.

[0104] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0105] The above are merely specific embodiments of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to these embodiments, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0106] It should be noted that the technical solutions in this application are not limited to use in the system and method for generating pathways to higher education, but can also be extended to related applications of the same type that require control. All of these should fall within the protection scope of this application. No specific limitations are made here regarding the related applications that require control.

[0107] All articles and references disclosed above, including patent applications and publications, are incorporated herein by reference for various purposes. The term “substantially constitutes…” used to describe a combination should include the identified elements, components, parts, or steps, as well as other elements, components, parts, or steps that do not substantially affect the essential novelty of the combination. The use of the terms “comprising” or “including” to describe combinations of elements, components, parts, or steps herein also contemplates embodiments substantially constituted by such elements, components, parts, or steps. The use of the term “may” herein is intended to indicate that any described attribute included by “may” is optional.

[0108] Multiple elements, components, parts, or steps can be provided by a single integrated element, component, part, or step. Alternatively, a single integrated element, component, part, or step can be divided into multiple separate elements, components, parts, or steps. The use of "a" or "an" to describe an element, component, part, or step does not imply the exclusion of other elements, components, parts, or steps.

[0109] It should be understood that the above description is for illustrative purposes and not for limitation. Many embodiments and applications beyond the provided examples will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this teaching should not be determined by reference to the above description, but rather by reference to the foregoing claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and publications, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the foregoing claims is not intended as a waiver of that subject matter, nor should it be considered as a failure of the applicant to consider that subject matter as part of the disclosed subject matter. It is evident that various modifications and variations can be made to this application by those skilled in the art without departing from the spirit and scope of this application. Thus, this application is also intended to include such modifications and variations if they fall within the scope of the claims and their equivalents.

Claims

1. A system for generating pathways to higher education, characterized in that, include: The module includes a data acquisition module, a feature extraction module, a rule engine module, an information matching module, and a path generation module. The data acquisition module is connected to the feature extraction module and the rule engine module respectively; the information matching module is connected to the rule engine module and the feature extraction module and the path generation module respectively. The data acquisition module is used to obtain multi-dimensional basic student information and school admission data; The feature extraction module is used to perform learning ability feature analysis on the multi-dimensional student basic information sent by the data acquisition module, and generate multi-dimensional learning ability feature information, which includes the student's learning interest feature information, learning ability feature information, and subject proficiency information. The rule engine module is used to extract school admission information from the school admission data sent by the data collection module, obtain multi-dimensional admission information corresponding to the school admission data, generate admission rules from the multi-dimensional admission information, and obtain a set of admission rule information corresponding to multiple schools respectively. The information matching module is used to determine the target school from the multiple schools that matches the admission rule information with the multi-dimensional student basic information and the multi-dimensional learning ability feature information, based on the set of admission rule information of the multiple schools sent by the rule engine module. The path generation module is used to generate the student's college entrance path based on the target school sent by the information matching module.

2. The system according to claim 1, characterized in that, The feature extraction module is used to perform learning ability feature analysis on the multi-dimensional student basic information, generate the student's learning ability profile, and extract ability information based on the learning ability profile to obtain the multi-dimensional learning ability feature information.

3. The system according to claim 1, characterized in that, The information matching module is used for: The multi-dimensional student basic information sent by the data acquisition module is matched with the college entrance examination rule information in the set of college entrance examination rule information sent by the rule engine module to obtain candidate college entrance examination rule information that meets the matching conditions in the set of college entrance examination rule information. The school corresponding to the candidate college entrance examination rule information is determined as the candidate school. The college entrance examination rule information includes enrollment rule information and college entrance examination experience rule information. Based on the multi-dimensional learning ability characteristic information, the candidate schools are analyzed, and based on the analysis results, they are prioritized and the target school corresponding to the student is determined from the candidate schools.

4. The system according to claim 1, characterized in that, The data acquisition module includes a student information acquisition module and a college entrance examination data acquisition module; The student information collection module is connected to the feature extraction module, and the college entrance examination data collection module is connected to the rule engine module. The student information collection module is used to obtain multi-dimensional basic student information through a network interface and send the multi-dimensional basic student information to the feature extraction module. The school admission data acquisition module is used to obtain the school's admission data through web crawling technology and send the school's admission data to the rule engine module.

5. The system according to claim 4, characterized in that, The rule engine module includes an admissions rule module and a college entrance experience rule module; The enrollment rules module is connected to the student information collection module and the information matching module, and the college entrance examination experience rules module is connected to the college entrance examination data collection module and the information matching module respectively; The admission rules module is used to determine the first confidence level of the school admission data based on the data source of the school admission data in the school's college entrance examination data; In response to the first confidence level meeting the confidence level condition, the school enrollment data is used to extract enrollment information to obtain the enrollment information corresponding to the school enrollment data, and enrollment rules are generated from the enrollment information to obtain the enrollment rule information; The college entrance examination experience rule module is used to determine the second confidence level of the historical admission data based on the data source of the historical admission data in the school's college entrance examination data; in response to the second confidence level meeting the confidence level condition, the module extracts college entrance examination experience information from the historical admission data to obtain the college entrance examination experience information corresponding to the historical admission data, and generates college entrance examination experience rules from the college entrance examination experience information to obtain the college entrance examination experience rule information.

6. The system according to claim 5, characterized in that, The enrollment rules module is used to respond to the update of the school's enrollment data, obtain the updated enrollment data and the third confidence level of the updated enrollment data; when the third confidence level meets the confidence level condition, the module extracts the updated enrollment information from the updated school's enrollment data to obtain the updated enrollment information corresponding to the school's enrollment data, and generates enrollment update rules from the updated enrollment information to obtain the updated enrollment rule information. The admission rules information is updated according to the aforementioned admission update rules information; The college admission experience rule module is used to respond to the update of the historical admission data, obtain the updated historical admission data and the fourth confidence level of the updated historical admission data; when the fourth confidence level meets the confidence level condition, extract the updated historical admission information from the updated historical admission data to obtain the updated historical admission information corresponding to the updated historical admission data, generate the updated historical admission rules from the updated historical admission information to obtain the college admission experience update rule information; and update the college admission rule information according to the updated college admission experience update rule information.

7. The system according to claim 5 or 6, characterized in that, The rule engine module stores the updated college entrance examination rule information, and the updated college entrance examination rule information and the original college entrance examination rule information together form the college entrance examination rule information set.

8. A method for generating pathways to higher education, characterized in that, include: Obtain multi-dimensional basic student information and school admission data; The learning ability characteristics of the multi-dimensional student basic information are analyzed to generate multi-dimensional learning ability characteristic information, which includes the student's learning interest characteristics, learning ability characteristics, and subject proficiency information. The school admission data is used to extract admission information to obtain multi-dimensional admission information corresponding to the school admission data. Admission rules are generated from the multi-dimensional admission information to obtain a set of admission rule information corresponding to multiple schools. Based on the set of admission rules information of the multiple schools, target schools that match the admission rules information with the multi-dimensional student basic information and the multi-dimensional learning ability characteristic information are determined from the multiple schools; Based on the target school, generate the student's pathway to higher education.

9. A device for generating pathways to higher education, characterized in that, include: The acquisition module is configured to acquire multi-dimensional basic student information and school admission data. The analysis module is configured to perform learning ability feature analysis on the multi-dimensional student basic information and generate multi-dimensional learning ability feature information, which includes the student's learning interest feature information, learning ability feature information, and subject proficiency information. The extraction module is configured to extract admission information from the school admission data to obtain multi-dimensional admission information corresponding to the school admission data, generate admission rules from the multi-dimensional admission information, and obtain a set of admission rule information corresponding to multiple schools respectively. The determination module is configured to determine a target school from the multiple schools that matches the admission rule information with the multi-dimensional student basic information and the multi-dimensional learning ability characteristic information, based on the set of admission rule information of the multiple schools. The generation module is configured to generate the student's college entrance path based on the target school.

10. An electronic device, characterized in that, The system includes the pathway generation system according to any one of claims 1 to 7.

Images