A learning achievement detection method, system and device based on a WeChat applet

Abstract

The application discloses a learning achievement detection method, system and device based on a WeChat applet, and belongs to the technical fields of online intelligent evaluation and mobile internet.The application adopts a front-end and back-end separation architecture, builds a lightweight student operation terminal by relying on a WeChat applet, is matched with cloud service, a special database and a PC end management background, integrates eight core function modules of user hierarchical permission authentication, special structured question bank management, multi-mode intelligent paper setting, full-dimension examination anti-cheating monitoring, objective question real-time automatic marking, multi-dimension learning situation data visual analysis, personalized mistake review and relearning recommendation, organization management and preferential data linkage.The application can realize traceability of a college learning process, quantification of learning achievement and reusability of examination results, completely solves technical problems of strong subjectivity, low efficiency, scattered data and non-standard management of traditional examination, and improves examination work efficiency.

Description

Technical Field

[0001] This invention relates to the fields of smart education, smart management, mobile internet applications, and intelligent online assessment technologies, and particularly to a method, system, and device for detecting learning outcomes based on WeChat mini-programs. Background Technology

[0002] While a normalized learning mechanism has been fully implemented in Chinese universities, existing technologies and traditional assessment models have many substantial technical defects and management pain points in actual teaching management and outcome assessment, which seriously restrict the standardized, precise, and long-term development of higher education.

[0003] First, traditional learning outcomes cannot be quantified, and the assessment methods are highly subjective. Currently, most university learning assessments rely on traditional methods such as offline attendance checks, handwritten reflections, and class roll call. These methods can only verify students' learning participation and cannot quantify their actual mastery of theoretical knowledge. They are also difficult to objectively distinguish between students' learning effectiveness, resulting in highly subjective assessment results with insufficient credibility, and they cannot provide an objective basis for awarding honors, recommending students, or conducting point-based assessments.

[0004] Secondly, traditional assessment models are inefficient and extremely costly to manage. Current formal knowledge assessments mostly employ offline paper-based exams, involving a series of cumbersome processes such as printing exam papers, on-site organization, manual grading, manual score calculation, and manual data aggregation. This not only consumes significant human, material, and time resources, but also results in extremely low grading efficiency. Furthermore, the manual data collection process is prone to errors and omissions, making it difficult to efficiently aggregate, archive, and trace massive amounts of assessment data, thus failing to meet the needs of large-scale, routine assessments in universities.

[0005] Secondly, existing online learning platforms lack functionality and cannot form a closed-loop learning system. Most learning mini-programs and online examination systems currently on the market are general-purpose platforms, only suitable for general subject exams and ordinary online learning scenarios, without being customized for specific teaching and assessment scenarios. On the one hand, general-purpose platforms lack a dedicated knowledge point system and specialized assessment logic, failing to match the assessment characteristics of education; on the other hand, existing platforms generally suffer from the problem of "emphasizing learning while neglecting assessment," lacking dedicated functions such as anti-cheating exam mechanisms, intelligent test paper generation strategies, specific analysis of incorrect answers, differentiated student learning statistics, and organizational management. Student learning data is scattered and fragmented, failing to form a complete closed-loop system of learning, assessment, and review.

[0006] Meanwhile, existing technologies cannot achieve data linkage between learning outcomes and management work. Core tasks such as university recommendation and competency assessment all rely on students' learning outcomes as the core evaluation criteria. However, existing platforms cannot achieve digital linkage between learning data, exam results, and recommendation and evaluation work. Assessment data cannot be directly reused, resulting in the assessment work still relying on subjective human judgment, lacking objective and accurate data support, and making it difficult to ensure the fairness and standardization of recommendation and evaluation work.

[0007] Finally, existing general-purpose examination systems suffer from poor adaptability and high deployment costs. Traditional PC-based online examination systems have complex deployment processes, high maintenance costs, and limited usage scenarios. Students must rely on computer devices to participate in the assessment, resulting in extremely poor flexibility. Meanwhile, lightweight mobile platforms lack dedicated assessment logic and a multi-role organizational management system, making it impossible to achieve hierarchical learning management at the department and class levels. This makes it difficult to meet the standardized, accurate, lightweight, and routine needs of university learning outcome assessment.

[0008] In summary, the industry currently lacks a dedicated testing platform specifically designed for university settings that is lightweight, features intelligent assessment, anti-cheating testing, big data learning analysis, hierarchical organizational management, data linkage for recommendation, and closed-loop learning management. Therefore, this invention proposes a learning outcome testing method, system, and device based on WeChat mini-programs, which has significant practical implications and technological innovation value. Summary of the Invention

[0009] The purpose of this invention is to overcome the technical defects of existing technologies, such as the inability to quantify learning outcomes, low assessment efficiency, fragmented data, lack of a dedicated assessment system, missing anti-cheating mechanisms, imperfect learning loop, inability to link with the recommendation assessment, cumbersome platform deployment, and poor adaptability. This invention provides a learning outcome detection method, system, and device based on WeChat mini-programs, enabling traceability of the learning process in universities, quantification of learning outcomes, reusability of assessment data, and precision in learning management. It also constructs an intelligent, lightweight, and closed-loop digital assessment system to comprehensively improve the level of intelligent and information-based management in universities.

[0010] A learning outcome detection method based on WeChat Mini Programs includes the following steps: S1. User identity authentication and organization permission binding: Users initiate WeChat authorization login requests through WeChat mini programs. The backend service completes user identity verification and collects basic user information. Users independently select and authenticate their personal identity attributes and bind their department and organization information. The backend completes hierarchical permission allocation based on user identity attributes and organization affiliation, distinguishing between students' ordinary operation permissions and administrators' backend management permissions. S2. Dedicated Question Bank Structured Management and Intelligent Test Paper Generation: The backend pre-builds a dedicated question bank containing current affairs and meeting guidelines, binding each question with a unique knowledge point tag, difficulty level, and error type category tag; the system supports three test paper generation modes: fixed test paper generation, random test paper generation, and precise test paper generation by knowledge point. Administrators can customize the test paper question types, number of questions, difficulty, and knowledge point coverage according to teaching and assessment needs. S3. Online Examination and Comprehensive Anti-Cheating Monitoring: The student-side mini-program displays selectable test papers. After the user passes the second identity verification, they enter the examination interface. During the examination, the system activates multiple anti-cheating mechanisms, including time limit control for answering questions, randomization of test question options, real-time monitoring of browser screen switching times, full recording of abnormal operation behavior, prohibition of page copying and pasting, prohibition of background page switching, real-time interception of illegal examination behavior and retention of operation logs. S4. Automatic Scoring and Basic Learning Data Generation: After the user completes the questions and submits the test paper, the backend service calls the intelligent scoring algorithm to perform real-time fully automatic scoring of single-choice, multiple-choice, and true / false objective questions; the system automatically generates basic data such as the total test score, answer accuracy rate, and mastery rate of each knowledge point based on the answer data, and simultaneously builds personal answer records and wrong question datasets. S5. Multi-dimensional learning analysis and data visualization: Based on individual user answer data and overall organizational assessment data, it realizes two-dimensional learning analysis; at the individual level, it generates learning radar charts, error distribution statistics charts, and phased learning progress trend charts, and builds a personalized error notebook and list of weak knowledge points; at the organizational level, it statistically analyzes the exam participation rate, average score, excellent rate, and class ranking data of each department, and automatically generates standardized and exportable assessment reports. S6. Personalized Relearning Recommendation and Learning Loop Construction: The system accurately matches corresponding topic learning materials based on the user's wrong question data and weak knowledge point tags, and pushes personalized review learning content to the user; after completing the review learning, the user can initiate a special test again, forming a complete closed-loop learning mechanism of "learning-testing-data analysis-wrong question review-relearning-retesting"; S7. Data Synchronization and Recommendation Assessment Linkage: All user learning data, exam scores, and learning analysis reports are synchronized to the PC management backend in real time. Administrators can view, compile, and export the entire assessment data online. Based on the system data, the qualification screening and effectiveness evaluation for recommendation and points assessment are completed, realizing the digital linkage between learning outcomes and the evaluation and recommendation work.

[0011] Furthermore, in step S1, the hierarchical permission allocation specifically includes: for learning users, granting permissions to browse learning materials, take online exams, check grades, review incorrect answers, and view personal learning progress; for departments and administrators, granting permissions to manage question banks, publish exams, manage users, collect data, export reports, select outstanding students, and monitor overall learning progress, thereby achieving refined permission control for multiple roles.

[0012] Furthermore, in step S3, the anti-cheating monitoring specifically includes: the system presets a maximum allowed number of screen switching times, and automatically records abnormal exam behavior and marks the exam paper as abnormal when the threshold is exceeded; real-time monitoring of page operation status, and immediately pops up a warning when copying and pasting, page jumping, or background switching operations are detected, and automatically terminates the exam after multiple violations; the entire exam operation timeline is recorded, and all abnormal behavior logs are retained to achieve traceability of the exam process.

[0013] Furthermore, in step S5, the organizational dimension data statistics support custom statistical periods, and can generate statistical reports by single exam, week, month, and semester. It also supports multi-dimensional hierarchical filtering and statistics by department and grade, providing accurate data support for hierarchical management and assessment.

[0014] A learning outcome detection system based on WeChat Mini Program is used to implement the above detection method. The system adopts a lightweight architecture with front-end and back-end separation, including four major modules: front-end Mini Program, back-end server, database cluster, and PC management back-end. The aforementioned front-end mini-program is a student operating terminal that integrates functions such as user login, online learning, intelligent examination, grade inquiry, review of wrong questions, and personal center. It is adapted to the lightweight operation mode of WeChat mini-programs, which can be used and then left, without the need for separate download and installation. The backend server adopts a Node.js / Java service combined with a cloud function architecture, integrating an interface service module, a logic processing module, an anti-cheating monitoring module, an intelligent scoring module, a data statistical analysis module, and a security authentication module, which is responsible for the entire process of business logic processing, data calculation, permission verification, and security protection. The database cluster uses a MySQL database, which includes user information table, organizational structure table, question bank table, test paper configuration table, exam score table, answer record table, wrong question dataset table, learning record table, and statistical report data table, to realize the classified storage, related access and permanent retention of all business data; The PC-based management backend serves as the administrator's operating terminal, integrating functions such as question bank management, exam management, user organization management, score statistics, data visualization dashboards, report export, and recommendation qualification screening, thereby achieving digital control over the entire learning and assessment process.

[0015] Furthermore, the security service module of the backend server includes user identity encryption authentication, data transmission encryption, full recording of operation logs, and abnormal data early warning functions to prevent user information leakage, examination data tampering and unauthorized access, and to ensure system data security and operational compliance.

[0016] Furthermore, the question bank module is a dedicated structured question bank that strictly aligns with university teaching syllabi. It supports batch import of questions, online editing, categorized retrieval, difficulty adjustment, and knowledge point binding. It can also be updated in real time with current affairs questions to meet the needs of routine teaching and assessment.

[0017] A learning outcome detection device based on WeChat Mini Programs includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of the learning outcome detection method based on WeChat Mini Programs as described in any one of claims 1-4.

[0018] The beneficial effects of this invention are as follows: (1) Achieve precise quantification of learning outcomes and objective and fair assessment results. This invention breaks away from the traditional subjective assessment model. Through standardized test questions and intelligent data statistics, it accurately quantifies students' knowledge mastery and generates a visualized learning report and a list of weak knowledge points. Learning outcomes are detectable, quantifiable, and traceable, completely avoiding the subjective errors of manual assessment and providing objective data support for competency assessment and commendation.

[0019] (2) Significantly improve the efficiency of assessment management and reduce labor costs. This invention automates the entire process of exam release, test paper compilation, grading, statistics, and report generation without human intervention. Compared with the traditional offline paper-based assessment model, the efficiency of assessment work is increased by more than 60%, completely solving the problems of large workload and high error rate of manual grading and manual statistics, and significantly reducing the human, material, and time costs of teaching management in universities.

[0020] (3) Construct a dedicated assessment system to meet scenario-based needs. This invention has built a dedicated question bank for current affairs and meeting spirit, bound to knowledge points and difficulty tags, adapted to the dedicated assessment logic of education, and different from general examination platforms. It also supports multiple modes of test paper generation and can be flexibly adapted to different teaching scenarios such as daily in-class tests, periodic assessments, and final assessments.

[0021] (4) Improve the anti-cheating mechanism to ensure the authenticity of the assessment. This invention innovatively sets up multiple anti-cheating mechanisms such as timed answering, randomized option order, screen switching monitoring, abnormal behavior recording, and prohibition of copying and pasting. It monitors the examination behavior throughout the process and retains operation logs, effectively eliminating online examination cheating behavior and ensuring the authenticity and seriousness of online assessment.

[0022] (5) Realize big data learning analysis to support precision teaching. This invention relies on big data analysis and data visualization technology to realize learning statistics from both individual and organizational dimensions, accurately locate individual student learning weaknesses and class / department overall learning weaknesses, and provide data decision support for teachers to carry out targeted teaching and precise education.

[0023] (6) Construct a closed-loop learning mechanism to promote learning through testing. This invention guides students to conduct targeted review and learning through error analysis, weak knowledge point identification, and personalized learning recommendations, forming a complete learning closed loop. This completely solves the problem of traditional platforms emphasizing testing and neglecting review, and constructs a normalized and long-term learning improvement mechanism.

[0024] (7) Lightweight deployment, strong adaptability, and high security. This invention runs on WeChat mini-programs, requiring no download or installation, simple deployment, and can be used and discarded immediately, adapting to various mobile terminals; at the same time, it establishes a complete security system of permission control, data encryption, and log retention to ensure the security of user information and assessment data; the multi-role hierarchical permission management is adapted to the multi-level organizational management system of colleges, departments, and classes.

[0025] (8) Realize data linkage to empower management. This invention deeply links learning and assessment data with assessment, realizes the digital connection between educational achievements and evaluation work, and improves the level of smart digital construction in universities. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a simplified flowchart of the overall business process of this invention; Figure 2 This is a flowchart illustrating the system architecture hierarchy of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0029] This invention adopts a front-end and back-end separation architecture combined with a lightweight WeChat mini-program. Relying on mobile internet technology, big data analysis technology, artificial intelligence intelligent assessment technology, information security authentication technology, and data visualization technology, it builds a four-in-one personalized learning outcome detection system consisting of a student mini-program, a cloud server, a MySQL database, and a PC management backend. The core of this system covers eight key technology modules: user permission control, structured question bank management, intelligent test paper generation, anti-cheating examinations, automatic scoring, learning progress big data analysis, personalized review and learning, and organizational data linkage. This system fully realizes intelligent detection and management of learning outcomes throughout the entire process.

[0030] The system's overall architecture is clearly layered. The front end relies on WeChat mini-programs for lightweight user interaction, requiring no download or installation and allowing for immediate use, adapting to mobile learning and assessment scenarios anytime, anywhere. The back end uses Node.js / Java services combined with a cloud function architecture to ensure high-concurrency, low-latency business processing capabilities, adapting to the needs of large numbers of students taking exams online simultaneously in universities. The database uses a MySQL relational database to achieve structured storage and related calls for various types of business data. The PC management backend enables administrators to manage the entire domain, perform data statistics, and provide decision support.

[0031] The core technology process of this invention is implemented based on this testing method. Through seven core steps, namely identity authentication binding, exclusive question bank management, multi-mode intelligent test paper generation, all-dimensional anti-cheating monitoring, real-time automatic scoring, dual-dimensional learning analysis, closed-loop relearning recommendation, and data optimization linkage, it completely solves various pain points of existing technologies and realizes the standardization, intelligence, digitalization, and normalization of learning and assessment.

[0032] The present invention will now be described in further detail and in complete form with reference to specific embodiments.

[0033] 1. System Overall Architecture Implementation This invention adopts a lightweight architecture with front-end and back-end separation, consisting of a four-layer structure. Each layer operates independently, communicates with each other, and works collaboratively. The specific deployment is as follows: (1) Front-end interaction layer: The core is the WeChat Mini Program student client, developed based on the native WeChat Mini Program framework, adapted to iOS and Android mobile devices. No download or installation is required; users can quickly access and use it by scanning a QR code or searching via WeChat. The Mini Program client features a minimalist and lightweight design, runs smoothly, and is compatible with various network environments such as campus networks and mobile networks. The core functions include user login, organization binding, online learning, intelligent examination, grade inquiry, review of incorrect questions, and viewing of personal learning progress. At the same time, a strict permission differentiation mechanism is set up to adapt differentiated function displays according to student identity, catering to the learning and assessment needs of different student groups.

[0034] (2) Backend Service Layer: The system adopts a collaborative architecture combining Java backend services and WeChat cloud functions. The Java service is responsible for core business logic processing, data calculation, permission verification, and data statistical analysis, ensuring high concurrency and stability of the system and supporting thousands of students from a single school to take exams online simultaneously. The WeChat cloud functions are responsible for lightweight interface calls, login authorization verification, and real-time anti-cheating data monitoring, reducing server operating pressure. The backend integrates six core services: user authentication service, question bank management service, exam control service, intelligent scoring service, learning analysis service, and security protection service, providing comprehensive support for the entire business process.

[0035] (3) Data storage layer: A dedicated structured database cluster is built using MySQL 8.0 relational database, containing ten core data tables: user information table, organizational structure table, question bank resource table, test paper configuration table, examination record table, grade statistics table, wrong question dataset table, learning trajectory table, abnormal behavior log table, and report data table. All data tables are interconnected and stored in a structured manner, enabling permanent retention and rapid retrieval of user data, test question data, examination data, learning data, and log data, ensuring data integrity, consistency, and traceability.

[0036] (4) Backend management layer: The PC web management backend is developed based on the Vue framework, adapted to the full-domain management needs of the computer terminal, and opens differentiated permissions to university administrators, college counselors and other multi-level administrators, realizing full-process management functions such as batch management of question bank, release of examination tasks, user organization and management, full-domain grade statistics, visualization of learning data, one-click export of reports, and screening of recommendation qualifications.

[0037] 2. Specific Implementation Process of Core Methods Step 1: User authentication, permission allocation, and organization binding When a user opens the WeChat mini program for the first time, it triggers the official WeChat authorization login interface, obtains the user's publicly available WeChat information, and completes initial account registration and login. After successful login, the user must complete real-name authentication and identity classification, manually select their personal identity type, and accurately fill in their school, department, and grade information to complete organizational affiliation binding. After receiving user information, the backend service automatically verifies the legality of the information, synchronously enters it into the user information table and organizational structure table, and assigns corresponding operation permissions based on the user's identity and organizational attributes. Student users are only granted access to learning, exams, and personal data queries, while administrator users are granted full backend management permissions, achieving hierarchical and refined permission control to prevent unauthorized operations and unauthorized access.

[0038] Step Two: Structured Construction of a Dedicated Question Bank and Implementation of Intelligent Question Paper Generation Administrators build and maintain a dedicated question bank through a PC-based management backend, categorizing it into core categories such as current affairs and the spirit of important meetings to achieve full coverage of the knowledge system. Each entered question must be bound to three tags: first, a knowledge point tag, accurately corresponding to specific theoretical knowledge points; second, a difficulty tag, divided into three levels: easy, medium, and hard; and third, an error type tag, used for subsequent error classification and learning analysis.

[0039] The system has three built-in standardized test paper generation modes to adapt to different assessment scenarios: 1) Fixed test paper generation: the administrator manually selects specified test questions, question types, and number of questions to form a fixed test paper, which is suitable for unified standardized assessment; 2) Random test paper generation: the system randomly selects test questions from the question bank according to preset difficulty, question type, and number of questions to generate test papers, avoiding the risk of test question leakage; 3) Knowledge point test paper generation: test questions are selected in a targeted manner for specific weak knowledge points, which is suitable for special review and testing, and fully adapts to the needs of normalized teaching and assessment.

[0040] Step 3: Implementation of Online Examinations and Comprehensive Anti-Cheating Monitoring Administrators publish exam tasks through the backend, setting exam duration, participation scope, exam paper type, and anti-cheating parameters. Students receive exam notifications in real time. After selecting the corresponding exam paper, the system performs a second verification of user identity and organizational permissions; only those who pass the verification can enter the exam interface. During the exam, the system activates a comprehensive anti-cheating control mechanism: 1) Time limit control: the exam paper is automatically locked and submitted after the time limit expires; 2) Randomized question options: the order of options is completely different for different users and different exam sessions to prevent plagiarism; 3) Screen switching monitoring: the system monitors page switching behavior in real time, with a preset maximum threshold of 3 screen switchings; exceeding the threshold automatically records the anomaly and marks the exam paper; 4) Operation restrictions: copying, pasting, and saving screenshots of answers are prohibited, as is background page switching; 5) Full-process logging: every operation time, operation behavior, and abnormal information is accurately recorded, forming a complete exam log to ensure the exam process is traceable and verifiable.

[0041] Step 4: Intelligent Automatic Scoring and Basic Data Generation After completing all the questions, users click "Submit." The system automatically verifies the completeness of the answers; if no questions are left unsubmitted, the submission is complete. The backend intelligent scoring algorithm activates in real-time, performing millisecond-level automatic scoring for objective questions such as multiple choice, true / false, and multiple selection questions. It accurately matches the answers to the standard answers and automatically calculates core data such as the total score, overall accuracy rate, accuracy rate for each knowledge point category, and the number of incorrect answers. The system simultaneously stores this answer record in an answer record table, automatically categorizing incorrect answers into the user's personal error notebook, binding them to corresponding knowledge points, error types, and difficulty tags, generating a personalized error dataset. No manual statistics or grading are required; the entire process is automated.

[0042] Step 5: Multi-dimensional learning data analysis and visualization The system leverages big data analytics and data visualization technologies to achieve in-depth learning analysis from both individual and organizational perspectives. At the individual level: based on users' past exam data, it generates a radar chart of knowledge point mastery, intuitively displaying strengths and weaknesses in each module; it generates a statistical chart of incorrect answers, clearly showing frequently missed knowledge points; it generates a trend chart of learning progress at each stage, intuitively presenting changes in learning effectiveness; and it generates a personalized learning report to accurately pinpoint learning weaknesses. At the organizational level: the system automatically compiles exam participation rates, average scores, excellent rates, pass rates, and ranking data for each department, branch, and class, displaying the overall learning situation in a tiered manner. All statistical data is intuitively displayed through a visual dashboard, supporting administrators in real-time monitoring of overall teaching effectiveness.

[0043] Meanwhile, the system supports one-click export of data reports, which can generate standardized assessment reports in Excel and PDF formats. The reports contain complete data such as user information, exam scores, knowledge mastery, and participation, and can be directly used for university teaching archiving and evaluation filing.

[0044] Step Six: Personalized Review and Learning and the Construction of a Closed-Loop Mechanism Based on user error datasets and tags of weak knowledge points, the system uses a big data precision matching algorithm to automatically select corresponding thematic learning materials, knowledge point explanations, and specialized practice questions, pushing personalized review and learning content to users. Users can conduct specialized learning on weak knowledge points, and after completing the learning, they can initiate specialized mock tests on the corresponding knowledge points to further verify their learning effectiveness. Through a cyclical model of "daily learning - standardized testing - big data analysis - error review - precise relearning - secondary testing," a complete closed-loop learning system is constructed, completely solving the problems of fragmented, unreviewed, and unimproved traditional learning, and achieving learning through testing and improvement through assessment.

[0045] Step 7: Linking Data Synchronization with Recommendation and Evaluation All user learning progress, exam scores, learning analysis data, and abnormal exam records are synchronized in real time to the PC-based management backend, achieving seamless data exchange between the student and management ends. Administrators can filter assessment data for specified periods and organizations through the backend, quickly selecting candidates for excellence based on achievement, participation, and learning progress. Quantified learning outcomes serve as the core criterion for evaluation and recommendation, replacing traditional subjective assessment methods and achieving digitalization, objectivity, and standardization in the assessment process.

[0046] 3. Specific implementation details of system modules (1) Student Mini Program Functional Modules: Includes online learning module, intelligent examination module, grade query module, wrong question review module, and personal center module. The online learning module provides knowledge point text and video materials for learning; the intelligent examination module supports participation in unified examinations and special mock examinations; the grade query module displays past examination scores, rankings, and learning progress reports; the wrong question review module collects all wrong questions and supports redoing wrong questions and reviewing knowledge points; the personal center module supports information modification, organization binding, permission viewing, and learning record query.

[0047] (2) Backend service module: The interface service module is responsible for front-end and back-end data interaction and request response; the cloud function module is responsible for lightweight real-time calculation and anti-cheating monitoring; the logic processing module is responsible for core logic of test paper assembly, scoring, and data analysis; the security service module is responsible for data encryption, identity verification, log retention, and anomaly protection, ensuring the stable and secure operation of the system in all aspects.

[0048] (3) Database module: It achieves full business data coverage through ten core data tables. The data tables are linked and bound together, which can quickly realize data retrieval, statistics and updates, ensuring the real-time and accuracy of data, and providing data support for learning analysis, report generation and data linkage.

[0049] (4) PC management backend module: Question bank management supports batch import, editing, deletion and classification of test questions; Examination management supports examination release, parameter configuration and examination monitoring; User management supports organizational structure maintenance, user information review and permission allocation; Data management supports score statistics, visualization display and report export; Recommendation and screening supports custom conditions to screen candidates for awards, adapting to the needs of the entire process of university management.

[0050] Verified through multiple pilot applications, this invention simplifies the assessment process and reduces manual workload compared to traditional assessment models, thereby improving overall assessment management efficiency and completely resolving the problems of low efficiency, large errors, and statistical difficulties in offline assessments. Simultaneously, by quantifying assessment data, the objectivity and credibility of the selection and recommendation process are significantly enhanced, student learning initiative is markedly strengthened, and the closed-loop learning mechanism effectively improves students' mastery of theoretical knowledge. This achieves digital, refined, and routine management in universities, possessing extremely high value for widespread application.

[0051] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for detecting learning outcomes based on WeChat Mini Programs, characterized in that, Includes the following steps: S1. User identity authentication and organization permission binding: Users initiate WeChat authorization login requests through WeChat Mini Programs, and the backend service completes user identity verification and collects basic user information; users can independently select and authenticate their personal identity attributes. Users bind their department and organization information, and the backend completes hierarchical permission allocation based on user identity attributes and organization affiliation, distinguishing between students' ordinary operation permissions and administrators' backend management permissions. S2. Dedicated Question Bank Structured Management and Intelligent Test Paper Generation: The backend pre-builds a dedicated question bank containing current affairs and meeting guidelines, binding each question with a unique knowledge point tag, difficulty level, and error type category tag; the system supports three test paper generation modes: fixed test paper generation, random test paper generation, and precise test paper generation by knowledge point. Administrators can customize the test paper question types, number of questions, difficulty, and knowledge point coverage according to teaching and assessment needs. S3. Online Examination and Comprehensive Anti-Cheating Monitoring: The student-side mini-program displays selectable test papers. After the user passes the second identity verification, they enter the examination interface. During the examination, the system activates multiple anti-cheating mechanisms, including time limit control for answering questions, randomization of test question options, real-time monitoring of browser screen switching times, full recording of abnormal operation behavior, prohibition of page copying and pasting, prohibition of background page switching, real-time interception of illegal examination behavior and retention of operation logs. S4. Automatic Scoring and Basic Learning Data Generation: After the user completes the questions and submits the test paper, the backend service calls the intelligent scoring algorithm to perform real-time fully automatic scoring of single-choice, multiple-choice, and true / false objective questions; the system automatically generates basic data such as the total test score, answer accuracy rate, and mastery rate of each knowledge point based on the answer data, and simultaneously builds personal answer records and wrong question datasets. S5. Multi-dimensional learning analysis and data visualization: Based on individual user answer data and overall organizational assessment data, it realizes two-dimensional learning analysis; at the individual level, it generates learning radar charts, error distribution statistics charts, and phased learning progress trend charts, and builds a personal error notebook and a list of weak knowledge points; The organization collects statistics on exam participation rate, average score, pass rate, and class ranking data for each department, and automatically generates standardized, exportable assessment reports. S6. Personalized Relearning Recommendation and Learning Loop Construction: The system accurately matches corresponding topic learning materials based on the user's wrong question data and weak knowledge point tags, and pushes personalized review and learning content to the user. After completing the review and learning, users can initiate another targeted test, forming a complete closed-loop learning mechanism of "learning-testing-data analysis-reviewing wrong questions-relearning-retesting"; S7. Data Synchronization and Recommendation Assessment Linkage: All user learning data, exam scores, and learning analysis reports are synchronized to the PC management backend in real time. Administrators can view, compile, and export the entire assessment data online. Based on the system data, the qualification screening and effectiveness evaluation for recommendation and points assessment are completed, realizing the digital linkage between learning outcomes and the evaluation and recommendation work.

2. The learning outcome detection method based on WeChat Mini Programs according to claim 1, characterized in that, In step S1, the hierarchical permission allocation specifically includes: for learning users, granting permissions to browse learning materials, take online exams, check grades, review incorrect questions, and view personal learning progress; for departments and administrators, granting permissions to manage question banks, publish exams, manage users, collect data, export reports, select outstanding students, and monitor overall learning progress, thereby achieving refined permission control for multiple roles.

3. The learning outcome detection method based on WeChat Mini Programs according to claim 1, characterized in that, In step S3, the anti-cheating monitoring specifically includes: the system presets a maximum allowed number of screen switching times, and automatically records abnormal exam behavior and marks the exam paper as abnormal when the threshold is exceeded; real-time monitoring of page operation status, and immediately pop-up warnings when copying and pasting, page jumping, or background switching operations are detected, and the exam is automatically terminated after multiple violations; the entire exam operation timeline is recorded, and all abnormal behavior logs are retained to make the exam process traceable.

4. The learning outcome detection method based on WeChat Mini Programs according to claim 1, characterized in that, In step S5, the organizational dimension data statistics support custom statistical periods, and can generate statistical reports by single exam, week, month, and semester. It also supports multi-dimensional hierarchical filtering and statistics by department and grade, providing accurate data support for hierarchical management and assessment.

5. A learning outcome detection system based on WeChat Mini Programs, characterized in that, To implement the detection method according to any one of claims 1-4, the system adopts a lightweight architecture with front-end and back-end separation, including four major modules: front-end mini-program, back-end server, database cluster, and PC-end management backend. The aforementioned front-end mini-program is a student operating terminal that integrates functions such as user login, online learning, intelligent examination, grade inquiry, review of wrong questions, and personal center. It is adapted to the lightweight operation mode of WeChat mini-programs, which can be used and then left, without the need for separate download and installation. The backend server adopts a Node.js / Java service combined with a cloud function architecture, integrating an interface service module, a logic processing module, an anti-cheating monitoring module, an intelligent scoring module, a data statistical analysis module, and a security authentication module, which is responsible for the entire process of business logic processing, data calculation, permission verification, and security protection. The database cluster uses a MySQL database, which includes user information table, organizational structure table, question bank table, test paper configuration table, exam score table, answer record table, wrong question dataset table, learning record table, and statistical report data table, to realize the classified storage, related access and permanent retention of all business data; The PC-based management backend serves as the administrator's operating terminal, integrating functions such as question bank management, exam management, user organization management, score statistics, data visualization dashboards, report export, and recommendation qualification screening, thereby achieving digital control over the entire learning and assessment process.

6. The learning outcome detection system based on WeChat Mini Programs according to claim 5, characterized in that, The backend server's security service module includes user identity encryption authentication, data transmission encryption, full recording of operation logs, and abnormal data early warning functions to prevent user information leakage, exam data tampering, and unauthorized access, ensuring system data security and operational compliance.

7. The learning outcome detection system based on WeChat Mini Programs according to claim 5, characterized in that, The question bank module is a dedicated structured question bank that strictly aligns with university teaching syllabi. It supports batch import of questions, online editing, categorized retrieval, difficulty adjustment, and knowledge point binding. It can also be updated in real time with current affairs questions to meet the needs of routine teaching and assessment.

8. A learning outcome detection device based on WeChat mini-program, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the learning outcome detection method based on WeChat mini-program as described in any one of claims 1-4 are implemented.

Images