Labor education practice self-adaptive evaluation system and device based on multi-source perception

Abstract

The invention discloses a labor education practice self-adaptive evaluation system and device based on multi-source perception, and relates to the technical field of intelligent management, and the system comprises a perception terminal module which is used for collecting student labor data and environment change data in real time; the data processing module is used for carrying out deep integration analysis on the multi-source sensing data and establishing a labor behavior portrait of the student; the self-adaptive evaluation module is used for carrying out self-adaptive labor evaluation according to the labor behavior portrait of each student; and the feedback interaction module is used for performing periodic assessment summarization and multi-party information interaction according to the personalized labor assessment report. The technical problems that existing labor education evaluation depends on subjective judgment, interference factors are many, real-time feedback cannot be achieved, and the reliability of the evaluation result is poor are solved, comprehensive and real-time student labor performance evaluation and personalized feedback are achieved through a self-adaptive evaluation mechanism relying on multi-source perception and robustness artificial intelligence, and the evaluation efficiency is improved. And the reliability of the evaluation result is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to a labor education practice adaptive evaluation system and equipment based on multi-source perception. Background Art

[0002] With the continuous development of the education sector, personalized education and intelligent teaching have gradually become important directions of educational reform. Current labor education assessments mostly rely on teachers' subjective judgments, suffering from single evaluation criteria, incomplete data, and delayed feedback. This makes it difficult to monitor students' labor performance and health status in real time, and it is impossible to conduct personalized assessments based on individual students' differences. In addition, existing technologies lack effective real-time data collection and dynamic feedback mechanisms. Assessment accuracy is low, especially when students' status fluctuates greatly or when there are complex environmental interferences. This makes it impossible to adjust educational content in a timely manner and provide accurate guidance. Summary of the Invention

[0003] This application provides a labor education practice adaptive evaluation system and equipment based on multi-source perception, which is used to solve the technical problems of existing labor education evaluation that rely on subjective judgment, have many interference factors and cannot provide real-time feedback, and have poor reliability of evaluation results.

[0004] The first aspect of the present application provides an adaptive evaluation system for labor education practice based on multi-source perception, and the system includes: a perception terminal module, which is used to collect on-site student labor data and environmental change data in real time based on an intelligent perception terminal to obtain multi-source perception data, and the multi-source perception data is associated with student identity information; a data processing module, which is used to deeply integrate and analyze the multi-source perception data to establish a labor behavior portrait of each student; an adaptive evaluation module, which contains a standard indicator library and a behavioral feature weight adjustment mechanism, and is used to perform adaptive labor evaluation based on the labor behavior portrait of each student and generate a personalized labor evaluation report; a feedback interaction module, which is used to perform periodic evaluation and summary based on the personalized labor evaluation report, and feedback to the teacher side, student side, and parent side for a three-in-one information display.

[0005] According to a second aspect of the present application, an electronic device is provided, comprising: a processor, wherein the processor is coupled to a memory, wherein the memory is used to store a program, and when the program is executed by the processor, the system of the first aspect is implemented.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The labor education practice adaptive evaluation system and equipment based on multi-source perception provided by this application relate to the field of intelligent management technology. Students' labor data and environmental information are collected in real time through intelligent devices and associated with student identities. The data processing module integrates these data to construct students' labor behavior portraits. The adaptive evaluation module performs personalized evaluation based on the student portraits and generates evaluation reports. The feedback interaction module performs periodic summaries based on the evaluation reports and displays information through the teacher side, student side, and parent side to achieve three-party interaction. This solves the technical problems of the existing labor education evaluation relying on subjective judgment, many interference factors, and inability to provide real-time feedback, and poor reliability of evaluation results. It realizes a comprehensive and real-time student labor performance evaluation and personalized feedback through an adaptive evaluation mechanism based on multi-source perception and robust artificial intelligence, thereby improving the reliability of evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 Schematic diagram of the structure of the labor education practice adaptive evaluation system based on multi-source perception provided in the embodiment of the present application;

[0010] Figure 2 A schematic diagram of the structure of an adaptive evaluation module of a labor education practice adaptive evaluation system based on multi-source perception provided in an embodiment of the present application;

[0011] Figure 3 A structural diagram of an electronic device is provided for this application.

[0012] Explanation of the reference numerals: perception terminal module 10 , data processing module 20 , adaptive evaluation module 30 , feedback interaction module 40 , electronic device 300 , memory 301 , processor 302 , communication interface 303 , bus architecture 304 . DETAILED DESCRIPTION

[0013] This application provides a labor education practice adaptive evaluation system and equipment based on multi-source perception, which is used to solve the technical problems of existing labor education evaluation that rely on subjective judgment, have many interference factors and cannot provide real-time feedback, and have poor reliability of evaluation results.

[0014] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0016] Example 1, as Figure 1 As shown, the present application provides a labor education practice adaptive evaluation system based on multi-source perception, the system comprising:

[0017] The perception terminal module 10 is used to collect on-site student labor data and environmental change data in real time based on an intelligent perception terminal to obtain multi-source perception data, which is associated with student identity information.

[0018] Specifically, the core function of the perception terminal module 10 of this application is to collect student labor data and environmental change data on site in real time based on the intelligent perception terminal, thereby obtaining multi-source perception data. This data is closely associated with the student's identity information, ensuring the accuracy and pertinence of the data. Specifically, an intelligent perception terminal refers to a device with data collection, processing and transmission capabilities, such as a smart bracelet, smart tools, environmental sensors, etc.

[0019] The perception terminal module is deployed at the student labor activity site and uses multimodal intelligent hardware devices, including: wearable smart bracelets, which are used to collect students' physiological parameters such as heart rate (unit: bpm), cadence (steps / min), and skin temperature (°C), with a sampling period of 2 seconds; visual cameras and edge computing boxes, combined with human posture recognition algorithms (such as OpenPose), are used to analyze students' labor movements, task execution postures, and collaborative behaviors, triggering image feature extraction every 5 seconds; multi-parameter environmental sensors (DHT22, MQ series, noise meter modules) are used to obtain ambient temperature, humidity, air quality, and noise level, with a sampling period of 5 seconds; student identity identification uses RFID / QR code scanning and binding to ensure that multi-source data corresponds to individuals.

[0020] Multi-source perception data includes data from various sources and in various forms, including text, images, audio, and video. This data can reflect students' behaviors and environmental changes during the work process from multiple perspectives. Multi-source perception data is characterized by the coexistence of multi-source and multi-modal data, a complex external organizational structure, and different types of data expressing the same semantics from different perspectives. This data diversity provides the system with a rich source of information, facilitating a more comprehensive assessment of students' work behaviors and working environment.

[0021] In actual operation, the workflow of the perception terminal module 10 is as follows: First, the intelligent perception terminal collects student labor data and environmental change data in real time. These data are transmitted to the data processing module through the sensor network. The data processing module cleans and preprocesses the collected multi-source perception data to remove noise data and abnormal data. Subsequently, feature data related to labor behavior is extracted from the preprocessed data, such as labor skill performance, labor attitude, labor time distribution, etc. These feature data are correlated with the student's identity information to construct a labor behavior portrait of each student. The labor behavior portrait is a dynamic data window that is updated in real time and can reflect the student's behavior patterns and performance characteristics in different labor scenarios. In this way, the perception terminal module 10 can not only monitor students' labor behavior in real time, but also adjust the monitoring strategy in time according to changes in the labor environment to ensure the accuracy and timeliness of the data.

[0022] These multi-source perception data will be associated with the student's identity information to ensure that each piece of data can accurately correspond to a specific student. Through technologies such as RFID tags and QR code scanning, the system can identify the student's identity and ensure that the data collected by the perception terminal can be correctly bound to the student's personal information, thereby generating student performance data in different labor tasks. For example, each student is equipped with an RFID card or QR code bound to their identity information to ensure that the collected data corresponds one-to-one with the individual. The system sets the perception frequency as follows:

[0023] Physiological data (heart rate, cadence, skin temperature) is collected every 2 seconds; behavioral data (task posture and motion flow through image recognition) is continuously collected by the camera and feature extraction is triggered every 5 seconds; environmental data (temperature and humidity, air quality, noise, etc.) is collected every 5 seconds; every 5 minutes is a packaging cycle, and the data is uniformly uploaded to the edge computing node or main server. The data is described in a unified JSON structure. The collection device is wirelessly connected to the data processing module via Wi-Fi or Bluetooth Low Energy protocol (BLE) to achieve full-process tracking of each student.

[0024] This approach not only ensures data accuracy and personalization, but also provides a reliable basis for subsequent data analysis and evaluation. By comprehensively analyzing physiological, behavioral, and environmental data, the perception terminal module provides comprehensive and accurate information support for subsequent adaptive evaluation, effectively improving the accuracy and real-time performance of the entire labor education system.

[0025] The data processing module 20 is used to deeply integrate and analyze the multi-source perception data to establish a labor behavior portrait of each student.

[0026] Furthermore, the data processing module 20 of the embodiment of the present application is further configured to perform the following steps:

[0027] P21: After data cleaning and preprocessing of the multi-source perception data, feature data related to labor behavior is extracted from the multi-source perception data, and scene association clustering is performed to generate a multivariate feature array; P22: Based on the multivariate feature array, association analysis is performed in combination with student identity information to construct a labor behavior portrait of each student. The labor behavior portrait is a dynamic data window that is updated in real time, including students' behavior patterns and performance characteristics in different labor scenarios.

[0028] It should be understood that the core task of the data processing module 20 of the present application is to deeply integrate and analyze multi-source perception data collected from multiple perception terminals to construct a labor behavior portrait of each student.

[0029] For example, the data processing module uses Python scripts combined with NumPy and scikit-learn libraries to implement data cleaning, standardization, and behavioral profiling. The main technical paths are as follows:

[0030] 1. Data cleaning: We use the IQR method and the Z-score dual mechanism to identify abnormal data. We set a threshold: Z-scores > 3 or values outside the median ±1.5*IQR range are considered abnormal and removed. 2. Data normalization: All input features are uniformly scaled to the [0,1] interval using the following formula: X_norm = (X - X_min) / (X_max - X_min). 3. Feature extraction: We construct a feature vector S_i for each student:

[0031] S_i={HR_avg,HR_std,Task_completion_ratio,Coop_freq,Fatigue_flag,Env_stress_index}; where: HR_avg is the average heart rate during the period, Task_completion_ratio = actual completion amount / task target value, Env_stress_index = temperature impact coefficient × humidity index × noise level weighted value; 4. Cluster analysis: K-means clustering is performed on the characteristic vectors of the student group. The recommended K value is set to 4-6, which can be flexibly adjusted based on class size; 5. Behavioral profile maintenance: The profile data structure of each student is stored in a MongoDB database in real time, using the student ID as the key value to construct a dynamically updated data table.

[0032] Specifically, the data processing module first performs data cleaning and preprocessing, including removing noise, missing values, and erroneous data from the raw data. It also standardizes data from different sources to ensure consistency and usability. For example, it handles abnormal data caused by factors such as equipment failure and external environmental interference, and converts data of different dimensions to the same scale for effective comparison and analysis. Missing values are filled in using appropriate interpolation or estimation methods to ensure data integrity.

[0033] After cleaning and preprocessing, the data enters the feature extraction phase. The data processing module extracts characteristic data related to labor behavior from multi-source sensory data, including but not limited to students' physiological characteristics (such as heart rate, exercise volume, gait, etc.), behavioral characteristics (such as task completion, operational standards, and collaboration with others), and environmental characteristics (such as temperature, humidity, noise, and air quality). These characteristics can comprehensively reflect the various abilities demonstrated by students during the labor process and the impact of the labor environment on their performance. For example, by monitoring students' heart rates, their physical exertion and fatigue levels can be assessed; by analyzing behavioral characteristics, it can be determined whether students adhered to operational standards when performing tasks and whether they possess the necessary labor skills.

[0034] After feature data extraction is complete, scenario-related clustering is further performed. The purpose of this process is to cluster similar behavioral characteristics based on students' performance in different labor scenarios and identify students' behavioral patterns in specific tasks or environments. For example, in gardening tasks, students' labor behavior characteristics can be compared with preset task standards. Based on data such as students' task completion and operational standardization, one type of behavior pattern is formed. In cleaning tasks, another type of behavior pattern is identified based on students' interaction and efficiency during the labor process. In this way, students' labor performance is classified by scenario, generating a multivariate feature array.

[0035] Based on the generated multivariate feature array, the data processing module (20) performs association analysis in combination with the student identity information, thereby constructing a labor behavior profile for each student. The student's identity information can be associated through RFID tags or QR code scanning to ensure that each student's behavior data corresponds to their personal identity, thereby generating a unique and comprehensive labor behavior profile for each student. This labor behavior profile not only includes the student's behavior patterns and performance characteristics in different labor scenarios, but can also be updated dynamically in real time. Whenever a student participates in a new labor task, the system will update the profile based on the new data to reflect the student's performance in the new task. In this way, the system can capture changes in students' performance during the long-term labor process and provide continuous tracking records.

[0036] Through this series of processes, the data processing module successfully transforms the multi-source data collected from the sensing terminal module into a highly personalized and real-time profile of students' labor behavior. This labor behavior profile provides accurate and real-time data support for subsequent adaptive assessment and personalized feedback.

[0037] The adaptive assessment module 30 contains a standard indicator library and a behavioral feature weight adjustment mechanism, which is used to perform adaptive labor assessment based on the labor behavior portrait of each student and generate a personalized labor assessment report.

[0038] Further, such as Figure 2 As shown, the adaptive evaluation module 30 of the embodiment of the present application includes a basic completion evaluation unit, a high-intensity labor task protection evaluation unit and a team collaboration evaluation unit.

[0039] Specifically, the core function of the adaptive assessment module 30 of this application is to conduct an adaptive labor assessment based on the labor behavior portrait of each student and generate a personalized labor assessment report. This module contains a standard indicator library and a behavioral feature weight adjustment mechanism, which ensures the personalization and accuracy of the evaluation results by dynamically adjusting the evaluation criteria. Among them, the standard indicator library provides a multi-dimensional evaluation standard for the evaluation process, covering various behavioral characteristics that students may exhibit during the labor process, such as task completion, work efficiency, operational standardization, and collaborative spirit. These standards are quantitatively evaluated based on the performance of students in labor activities, providing a basic framework for subsequent adaptive evaluation.

[0040] The behavioral characteristic weight adjustment mechanism can dynamically adjust the evaluation strategy based on students' individual differences and labor behavior characteristics. For example, if a student excels in teamwork, the weight of this dimension can be automatically increased to better reflect their teamwork ability in the evaluation. Similarly, if a student performs poorly in physical labor tasks, the system can adjust the corresponding evaluation criteria based on their physiological status data (such as heart rate, exercise volume, etc.), reducing the strict assessment of physical completion. Therefore, the weight adjustment mechanism optimizes the evaluation strategy in real time based on the student's personalized performance, ensuring that each student's performance is evaluated fairly and accurately.

[0041] The core of this module is a configurable weighted rule engine. The scoring model uses the following technical structure:

[0042] The scores of all evaluation dimensions are derived from the standardized scores (0-10) after processing by the data processing module; the initial weights are configured by the experience of education experts, and the system supports a dynamic weight fine-tuning mechanism.

[0043] The Apache Drools rule engine is used to dynamically adjust weights based on behavioral profiling characteristics. For example, if Fatigue_flag=TRUE, the weight of "task completion" is automatically reduced from 0.4 to 0.3, and the weight of the "protection status" dimension is increased to 0.2; if Coop_freq is 10% higher than the class average, the weight of the collaboration dimension is increased by 10%.

[0044] Calculation example:

[0045] A student's scores for each dimension are: Task Completion = 7.5, Collaboration = 8, Fatigue = 6, and Environmental Adaptation = 7. After dynamic weight adjustment, W_task = 0.35, W_coop = 0.35, W_fatigue = 0.2, and W_env = 0.1. The total score is 0.35 × 7.5 + 0.35 × 8 + 0.2 × 6 + 0.1 × 7 = 7.325. A structured comment is also generated: "Possessing good collaboration and task completion skills, and pays attention to the balance between work and rest."

[0046] Specifically, the adaptive assessment module 30 includes a basic completion assessment unit, a high-intensity labor task protection assessment unit, and a teamwork assessment unit. These three units work together to complete a multi-dimensional assessment of students. The basic completion assessment unit is primarily responsible for evaluating students' completion of labor tasks, including the quality, efficiency, and standardization of task execution. This unit uses a multi-indicator quantitative assessment of students' performance in different tasks to generate a completion score for each task, and then scores it based on a standard indicator library to ultimately form an assessment result of the basic task completion.

[0047] The High-Intensity Labor Task Protection Assessment Unit focuses on monitoring students' physiological state and environmental adaptability during high-intensity labor tasks. By monitoring students' physiological data (such as heart rate and physical activity) and changes in the labor environment (such as temperature, humidity, and noise) in real time, this unit ensures that students are not overly fatigued or exposed to unsafe environments during the labor process, thereby safeguarding their health and safety.

[0048] The Teamwork Assessment Unit focuses on assessing students' performance in teamwork. By tracking and analyzing students' collaborative behaviors, the unit evaluates their collaborative abilities, communication skills, and teamwork efficiency in team tasks, providing students with personalized feedback on teamwork.

[0049] For example, the initial evaluation index weights are set as follows:

[0050] Task completion: 0.4 (dynamic adjustment range ±0.1); Collaboration performance: 0.3 (±0.1);

[0051] Fatigue protection: 0.2 (±0.1); Environmental adaptability: 0.1 (±0.05); Scoring model: ;in, is the dynamically adjusted weight, Score the corresponding dimension (out of 10 points).

[0052] Behavior weight automatic adjustment logic:

[0053] If Fatigue_flag is TRUE, the Task dimension weight is lowered and the Fatigue dimension weight is increased; if the student shows increased collaborative initiative in consecutive tasks (Coop_freq>threshold), the collaboration weight is increased.

[0054] Example: Student A's performance is Task=7.5, Coop=8.2, Fatigue=6, Env=7.

[0055] The adjusted weights are 0.35 / 0.35 / 0.2 / 0.1.

[0056] Calculated: 0.35*7.5+0.35*8.2+0.2*6+0.1*7=7.545.

[0057] Furthermore, the adaptive evaluation module 30 of the embodiment of the present application is further configured to perform the following steps:

[0058] P30: Receive and update the labor behavior portrait of each student in real time, and extract behavioral data from it for multi-dimensional evaluation, including: P31: Based on the basic completion evaluation unit, conduct routine labor evaluation and generate basic completion evaluation results; P32: According to the high-intensity labor task protection evaluation unit, conduct real-time high-intensity protection monitoring, and provide real-time protection feedback based on the monitoring results; P33: Through the team collaboration evaluation unit, conduct collaborative task tracking evaluation and generate team collaboration scoring results.

[0059] Optionally, the adaptive assessment module 30 of the present application can continuously track students' performance during the labor process by receiving and updating the labor behavior portrait of each student in real time, and conduct multi-dimensional assessments based on the students' actual conditions.

[0060] First, a routine labor assessment is conducted based on the Basic Completion Assessment Unit, generating a basic completion assessment result. This assessment unit focuses on students' completion of labor tasks, including the quality, efficiency, and compliance of task execution. Through a multi-metric quantitative assessment of tasks, a completion score is generated for each student in each labor task. Scoring is based on a standard indicator library to assess students' performance in specific tasks, resulting in a basic completion assessment result. This result reflects students' ability to execute routine labor tasks and serves as the fundamental basis for evaluating their labor capacity and achievements.

[0061] Next, based on the high-intensity labor task protection assessment unit, real-time high-intensity protection monitoring is carried out, and real-time protection feedback is provided based on the monitoring results. This assessment unit focuses on monitoring students' physiological and environmental adaptability during high-intensity labor tasks. By acquiring students' physiological data (such as heart rate, cadence, etc.) and environmental data (such as temperature, humidity, and noise), it is possible to detect in real time whether students are overly fatigued or facing unsafe working environments. If a student's physiological state is detected to be abnormal or the working environment changes beyond the safety threshold, an immediate safety reminder is issued and appropriate protective measures are implemented, such as recommending that students rest or adjust their work intensity. A reminder is also sent to the teacher to ensure the safety of students during high-intensity labor tasks.

[0062] Finally, the teamwork assessment unit tracks and evaluates collaborative tasks, generating a teamwork score. This unit tracks and analyzes students' behaviors during teamwork tasks to assess their performance within the team. Key evaluation indicators may include the student's role assignment within the team, the frequency of collaborative interactions, and the rationality of task division. This unit identifies students' collaborative enthusiasm, communication skills, and team efficiency during teamwork tasks, generating a corresponding teamwork score. This data allows for a better understanding of students' performance in teamwork and timely guidance and support.

[0063] Through the above steps, the adaptive assessment module 30 can comprehensively and in real time evaluate students' performance in labor education, ensure the dynamic, personalized and accurate evaluation results, and ensure that each student's labor performance can receive comprehensive feedback and guidance.

[0064] Furthermore, the adaptive assessment module 30 of the embodiment of the present application is further configured to perform the following steps when performing a conventional labor assessment based on the basic completion assessment unit:

[0065] P31-1: Based on the labor behavior portrait, extract the task completion data of multiple tasks; P31-2: Based on the task completion data of multiple tasks, conduct a multi-indicator quantitative evaluation of the students' completion status in various labor tasks, and generate basic task indicator quantitative values; P31-3: According to the preset standard indicator library, evaluate and score the basic task indicator quantitative values, and generate each student's completion score in different tasks; P31-4: Combine each student's completion score in different tasks to generate a basic completion evaluation result.

[0066] Specifically, when conducting routine labor assessments, this is performed through the basic completion assessment unit. First, based on the student's labor behavior profile, task completion data for multiple tasks is extracted. Each student's labor behavior profile includes their performance in different labor tasks, which may involve different types of labor activities, such as cleaning, gardening, assembly, etc. Through real-time monitoring and data analysis, the student's specific performance data for each task is extracted from the labor behavior profile, including information on multiple dimensions such as task execution time, task completion quality, and work efficiency.

[0067] Next, the task completion data for multiple tasks is analyzed to conduct a multi-indicator quantitative assessment of students' performance in various labor tasks. For example, based on indicators such as the length of time, efficiency, accuracy, and standardization of students' work in different tasks, the quality of students' execution of tasks and the degree to which they meet task requirements are evaluated. Quantified values for basic task indicators are generated for each task, such as the ratio of the number of tasks completed by students to the total number of tasks. The quality of labor results, such as the quality of agricultural products and the qualified rate of industrial products, is then evaluated to quantify the quality of students' task completion. The professional skills demonstrated by students during the labor process, such as proficiency in operating tools and problem-solving skills, are assessed. The time spent by students on each task is analyzed to assess their time management skills.

[0068] Next, based on the preset standard indicator library, the quantitative values of the basic task indicators of each student in different tasks are evaluated and scored. The standard indicator library contains a series of predefined evaluation criteria and scoring rules to determine whether the student's performance in each task has met the established standards. For example, for task completion rate, the system may set a completion rate of 90% and above as excellent, 80%-89% as good, and so on; at the same time, the library may also contain scoring weights adjusted according to the importance and difficulty of different labor tasks. After evaluating and scoring the quantitative values of the basic task indicators, a corresponding completion score is generated for each student's performance in different tasks.

[0069] For example, the system extracts task execution time, task completion rate, and matching degree of action behavior flow (DTW similarity with the standard action sequence); example fields include: task_duration = 32min, completion_ratio = 0.87, pose_similarity = 0.93;

[0070] Next, task completion data is quantitatively evaluated using multiple metrics to establish a scoring model: completion quality score = completion_ratio × 0.5 + pose_similarity × 0.5; time efficiency score = 1 - |actual time - standard task time| / standard task time; and completion score = (completion quality score + time efficiency score) / 2. Furthermore, a standardized scoring system is applied based on a standard metric library. The system compares the task completion data to the target ranges in the task standard library (e.g., a cleaning task should be completed within 30-40 minutes, with a completion rate > 0.85 and a performance standard > 0.9), assigning acceptable / excellent / fair grades. Finally, the scores of all tasks are combined to output a basic completion assessment result. If multiple tasks are performed simultaneously, the weighted sum is calculated based on the task weights (e.g., 0.7 for the primary task and 0.3 for the secondary task). For example, if the primary task score is 8.5 and the secondary task score is 7.2, then the total score is 8.5 × 0.7 + 7.2 × 0.3 = 8.01.

[0071] Generate the student labor task completion evaluation results as shown in the following table:

[0072] Form 1: Student Labor Task Completion Evaluation Form

[0073] Student Name Task Name Completion time (minutes) Task quality rating (0-10) Normative score (0-10) Task efficiency (task / time) Overall completion score Student A Cleaning tasks 30 8 9 0.5 8.5 Student B Gardening tasks 45 7 8 0.4 7.8 Student C Assembly tasks 40 9 10 0.6 9.5

[0074] Finally, by combining each student's completion scores across different tasks, a basic completion assessment is generated. This result summarizes the student's overall performance across all labor tasks. For example, the score for each task may be weighted averaged based on factors such as the nature, difficulty, and time required of the task, ultimately generating a comprehensive basic completion assessment that reflects the student's overall performance across various labor tasks.

[0075] Through these steps, the basic completion assessment unit can conduct accurate and detailed quantitative assessments of students' performance in various labor tasks, ensuring that each student's labor results receive comprehensive and objective feedback.

[0076] Furthermore, the adaptive assessment module 30 of the embodiment of the present application is further configured to perform the following steps when performing real-time high-intensity protection monitoring based on the high-intensity labor task protection assessment unit:

[0077] P32-1: Based on the labor behavior portrait, the physiological characteristics data of each student are extracted in real time according to the student identity code; P32-2: The high-intensity labor task protective assessment unit performs periodic fatigue abnormality monitoring based on the physiological characteristics data; P32-3: When the physiological characteristics data of any student is detected to be abnormal, the protection mechanism is immediately triggered and a real-time protection instruction is generated; P32-4: Based on the real-time protection instruction, real-time protection feedback is sent to the student end through the intelligent sensing terminal, and a protection reminder is sent to the teacher end.

[0078] It should be understood that when conducting real-time high-intensity protection monitoring, it is implemented through the high-intensity labor task protection assessment unit to ensure the safety and health of students during the labor process.

[0079] First, based on the student's labor behavior profile, physiological data, including key physiological indicators such as heart rate, body temperature, and blood oxygen saturation, are extracted in real time according to each student's identity code. Using smart bracelets or other wearable devices, each student's physiological data is collected and updated in real time, ensuring accurate association with their identity information. The use of identity codes ensures that each student's data is accurately matched to their personal information, providing a reliable foundation for subsequent analysis.

[0080] Next, the high-intensity labor task protective assessment unit performs periodic fatigue anomaly monitoring based on the extracted physiological characterization data. This monitoring process continuously tracks the student's physiological state through a set monitoring period (such as ten minutes / time), analyzes the student's fatigue level and identifies possible anomalies. Several physiological thresholds can be set. For example, when the student's heart rate is too high or too low, or the blood oxygen level is abnormal, an alarm will be triggered. For example, a heart rate exceeding 180 beats / minute and lasting for more than 5 minutes can be set as a fatigue anomaly threshold. Periodic monitoring ensures that the student's physiological changes during the labor process can be captured in a timely manner, especially when the student is in a state of fatigue or health risk, the system can respond quickly.

[0081] For example, the system first extracts student physiological data in real time from data uploaded by the wristband device: heart rate (HR), cadence, skin temperature, etc. The sampling period is 2 seconds, and the cache period is 5 minutes. The system takes the median, maximum value, and trend slope as input features. Next, periodic fatigue anomaly monitoring is performed to construct a fatigue risk scoring function: Fatigue_score = w1×(HR_max / HR_baseline)+w2×(cadence change rate)+w3×(skin temperature anomaly). If the score is greater than the set threshold (e.g., Fatigue_score>1.5), the system marks Fatigue_flag=true. The protection mechanism is triggered according to the anomaly, and a real-time protection instruction is generated. The protection mechanism includes: task pause, rest prompt, and teacher reminder push. The instruction format is:

[0082] {"student_id":"S007","action":"pause_task","reason":"fatigue_detected"}.

[0083] Push protection feedback to the student and teacher terminals. The student's device vibrates or displays a break prompt, and the teacher's device displays a pop-up window stating "Student S007's current status is abnormal. Please confirm and resolve." Examples are as follows:

[0084] Form 2: Student Physiological Data Monitoring and Fatigue Assessment Form

[0085] Student Name Task Name Initial heart rate (bpm) Current heart rate (bpm) Maximum heart rate (bpm) Blood oxygen saturation (%) Fatigue status assessment Protection Recommendations Student A Cleaning tasks 75 110 140 95 Moderate fatigue Rest for 15 minutes Student B Gardening tasks 80 130 150 92 High fatigue Rest for 30 minutes Student C Assembly tasks 70 100 130 96 Mild fatigue Rest for 10 minutes

[0086] When the system detects an abnormality in a student's physiological data, the protection mechanism is immediately triggered and real-time protection instructions are generated. These instructions include but are not limited to reminding students to rest, adjust their work intensity, stop the current task, etc., to prevent students from continuing to work under excessive fatigue or unsafe conditions. The generation of protection instructions can be based on the student's current health status and determine whether protective measures are needed based on preset safety standards. For example, if the system detects that a student's heart rate continues to be too fast and has not returned to normal, it can trigger instructions requiring the student to rest or make adjustments to avoid potential health risks.

[0087] Finally, based on the generated real-time protection instructions, the intelligent sensing terminal sends real-time protection feedback to the student, informing them of their current physical condition and any necessary adjustments. Simultaneously, protection reminders are sent to the teacher, helping them understand the student's health status in real time and take further action as needed, such as assisting them with rest breaks or adjusting their work tasks. This two-way feedback mechanism not only ensures that students can adjust their work status in a timely manner, but also provides teachers with real-time monitoring and intervention capabilities, further safeguarding student health and safety.

[0088] Through these steps, the protective assessment unit for high-intensity labor tasks can monitor students' physiological status in real time, detect abnormalities in a timely manner and take protective measures, thereby effectively preventing unsafe accidents caused by excessive fatigue or health risks, and ensuring the physical health and safety of students during the labor process.

[0089] Furthermore, the adaptive assessment module 30 of the embodiment of the present application is further configured to perform the following steps when performing real-time high-intensity protection monitoring based on the high-intensity labor task protection assessment unit:

[0090] P32-5: Monitor students' environmental data during labor tasks in real time to obtain real-time labor environment data; P32-6: Perform periodic environmental anomaly monitoring based on the real-time labor environment data; P32-7: When any environmental indicator is detected to exceed the safety environment threshold, an environmental anomaly warning is issued to the teacher through the intelligent sensing terminal.

[0091] In a possible embodiment of the present application, when performing real-time high-intensity protection monitoring, the high-intensity labor task protection assessment unit of the adaptive assessment module 30 also needs to simultaneously perform environmental safety monitoring to further ensure the safety of students during the labor process.

[0092] First, the environmental data of students during their labor tasks are monitored in real time to obtain real-time labor environment data. Specifically, the environmental parameters of the labor site are collected in real time through intelligent sensing terminals (such as portable environmental sensors). These data include but are not limited to temperature, humidity, noise level, light intensity, etc., which can reflect the real-time environmental conditions of the labor site. For example, working in a high temperature or high humidity environment may cause students to be physically exhausted or suffer from heatstroke, while working in an environment with excessive noise may affect students' hearing health. By monitoring these environmental data in real time, the immediate status of the students' environment can be obtained, and factors that may affect students' health and labor efficiency can be understood in a timely manner. For example, the following table is shown:

[0093] Form 3: Student labor environment data monitoring form

[0094] Student Name Task Name Ambient temperature (℃) Ambient humidity (%) Noise level (dB) Environmental Safety Assessment Environmental impact score (0-10) Student A Cleaning tasks 28 70 65 Safety 7 Student B Gardening tasks 30 75 80 Unsafe 5 Student C Assembly tasks 24 60 60 Safety 8

[0095] Next, periodic environmental anomaly monitoring is performed based on the real-time working environment data. This monitoring process involves the continuous tracking and analysis of environmental parameters such as temperature, humidity, air quality, and noise. Safety thresholds are set for each environmental indicator. When environmental data exceeds these safety standards, they are immediately identified and an alarm is triggered. For example, the system can set environmental anomaly thresholds for temperatures exceeding 35°C, humidity exceeding 80%, or noise levels exceeding 85 decibels. This periodic monitoring ensures that potential safety hazards are promptly identified at the early stages of environmental changes, preventing students from continuing to work in unsuitable environments.

[0096] If any monitored environmental indicator exceeds the safety threshold, an environmental anomaly warning will be sent to the teacher via the intelligent sensing terminal. Specifically, if the system detects an environmental anomaly such as excessive temperature, humidity, or noise, it will immediately send a warning message to the teacher. This warning information helps teachers adjust work tasks, arrange student breaks, or make appropriate environmental adjustments (such as improving ventilation and adjusting work areas), ensuring that students' work environment remains within a safe range. This mechanism can effectively prevent health problems or labor accidents caused by environmental factors, further enhancing student labor safety.

[0097] Through the above steps, various parameters of the students' working environment can be monitored comprehensively and in real time to ensure that students can work in an environment that meets safety standards at any time, thereby improving the safety and effectiveness of the overall labor education process.

[0098] Furthermore, the adaptive assessment module 30 of the embodiment of the present application is further configured to perform the following steps when performing real-time high-intensity protection monitoring based on the high-intensity labor task protection assessment unit:

[0099] P32-1a: Collect students' physiological indicator monitoring data in high-intensity labor tasks and environmental monitoring data in various tasks; P32-2a: Based on the students' physiological indicator monitoring data, redistribute the evaluation weights of high-intensity labor tasks through the behavioral characteristic weight adjustment mechanism; P32-3a: Based on the environmental monitoring data, conduct periodic task safety assessments, and optimize labor tasks based on the assessment results.

[0100] Optionally, during real-time high-intensity protection monitoring, the High-Intensity Labor Task Protection Assessment Unit can further rationalize labor tasks. If the fatigue_flag is true or the environmental anomaly flag is true, the assessment module uses the behavioral weight adjustment mechanism to reduce the task completion weight from 0.4 to 0.25, increasing the weight of the fatigue / environmental dimension. The Safety Optimization Module recommends alternative tasks (e.g., switching from physical labor to static finishing tasks).

[0101] First, we collect physiological monitoring data from students during high-intensity labor tasks, as well as environmental monitoring data from each task. Using intelligent sensing terminals (such as smart bracelets and environmental sensors), we obtain real-time physiological data (such as heart rate, body temperature, and blood oxygen saturation) while students are performing high-intensity labor tasks, as well as environmental data (such as temperature, humidity, and noise level) at the task site. Physiological monitoring data can reflect students' physical condition, particularly fatigue, physical exertion, and potential health risks. Environmental monitoring data, on the other hand, indicates whether the students' work environment is suitable for high-intensity labor, thus providing the system with a comprehensive understanding of students' physical condition and the working environment.

[0102] Next, based on the students' physiological indicator monitoring data, the evaluation weights of high-intensity labor tasks are redistributed through the behavioral characteristic weight adjustment mechanism. Specifically, the evaluation weights can be dynamically adjusted according to the students' physiological status (such as high heart rate, physical overdraft, etc.). If the system detects that the student is in a state of high fatigue or abnormal physiological data, the evaluation criteria will be automatically adjusted, and the weight related to task completion can be reduced, while increasing the recommended weight for the adjusted task, such as reducing the weight of the task in the overall evaluation. In this way, the system can adapt to the students' real-time physiological conditions more flexibly, ensuring that the evaluation results are more in line with the students' actual abilities and health status, thereby avoiding evaluation deviations and health losses caused by excessive labor intensity.

[0103] Furthermore, based on environmental monitoring data, periodic task safety assessments are conducted, and labor tasks are optimized based on the assessment results. By real-time monitoring of environmental data such as temperature, humidity, noise, etc., it is assessed whether the labor environment is suitable for high-intensity labor. If it is detected that the environmental conditions do not meet safety standards (for example, the temperature is too high or the humidity is too high), the system will re-evaluate the current labor task and give priority to recommending tasks with higher safety or adjust the task arrangement. For example, if in a high temperature environment, students may be advised to move to a cooler area or adjust the content of the labor task to avoid health risks such as overwork or heat stroke. Through this task optimization mechanism, the system can optimize labor tasks in real time to ensure that students experience labor in an environment that meets safety standards.

[0104] Through the above steps, the protective assessment unit for high-intensity labor tasks can comprehensively consider students' physiological status and labor environment to ensure data accuracy and task safety in high-intensity labor tasks.

[0105] Furthermore, the adaptive evaluation module 30 of the embodiment of the present application is further configured to perform the following steps when performing collaborative task tracking evaluation through the team collaboration evaluation unit:

[0106] P33-1: Based on the labor behavior portrait, cluster the student information of the same collaborative task to generate multiple collaborative portrait groups; P33-2: For each collaborative portrait group, obtain the team role type of each student, and track the performance characteristics of the students in the team collaborative task in real time according to the team role type to obtain multiple team collaboration indicators; P33-3: Based on the multiple team collaboration indicators, perform a collaboration degree assessment to generate a team collaboration score result for each student.

[0107] Specifically, the adaptive evaluation module 30 performs collaborative task tracking evaluation through the team collaboration evaluation unit.

[0108] First, based on students' work behavior profiles, student information within the same collaborative task is clustered and multiple collaborative profile groups are generated. Each student's work behavior profile includes their performance characteristics and behavioral data across different tasks. Using a clustering algorithm, the system is able to divide students participating in the same collaborative task into multiple collaborative profile groups based on the similarity of their performance within the team task. Each group represents a group of students collaborating on the same task. The system categorizes students based on their behavioral characteristics (such as task division and frequency of collaborative interaction), ensuring that students' collaborative behaviors can be compared and analyzed within the same group, providing a more accurate basis for evaluation.

[0109] Next, for each collaborative portrait group, the team role type of each student is obtained, and the performance characteristics of the students in the team collaboration task are tracked in real time according to the team role type. Team role type refers to the different roles played by students in team tasks, such as leader, executor, coordinator, etc. The system identifies and determines the team role of each student based on the students' interactive behavior, task division and cooperation methods in the collaborative task. Subsequently, based on these role types, the specific performance characteristics of the students in the task will be tracked in real time. For example, a student who acts as a coordinator may mainly perform organizational communication and resource allocation, while a student who acts as an executor may focus more on the completion of the actual task. Based on the tracked performance characteristics, multiple team collaboration indicators are generated. These indicators include multiple aspects such as the frequency of students' interactions in the task, the rationality of the division of labor, the efficiency of task completion, and communication skills.

[0110] Finally, based on the multiple team collaboration indicators obtained, a collaboration degree assessment is performed, and a team collaboration score result for each student is generated. For example, a weight is assigned to each team collaboration indicator based on a preset standard indicator library. The allocation of weights can be based on the characteristics and importance of the team task. For example, in tasks that require a high degree of communication, the weight of communication efficiency may be higher. Then, multiple team collaboration indicators are integrated through weighted averaging or other comprehensive evaluation methods to generate a team collaboration score result for each student. The generated team collaboration score result not only reflects the student's performance in the team collaboration task, but also provides educators with targeted feedback and improvement suggestions. For example, for students with low team collaboration scores, the system can recommend that they strengthen their communication skills or improve their teamwork awareness.

[0111] For example, students in the same group are first clustered to generate collaborative portrait groups. Temporary groups are then constructed based on clock-in sign-ins, spatial location data (image recognition), and task binding relationships in collaborative tasks. Next, role types are identified and behavioral characteristics are tracked. Team roles are identified using indicators such as task initiation frequency, speaking frequency, and feedback response time.

[0112] Leaders: high task allocation rate and quick response; Coordinators: high communication frequency and many mediation records; Executors: high completion volume and many independent tasks.

[0113] Next, the degree of collaboration is quantitatively evaluated and a collaboration score is generated. The collaboration score is calculated as follows:

[0114] Cooperation_score = α × normalized interaction frequency + β × role contribution + γ × task joint completion rate; example parameters: α = 0.4, β = 0.3, γ = 0.3.

[0115] Finally, the collaboration dimension of each student’s labor behavior portrait is updated according to their collaboration score and included in the overall assessment.

[0116] For example, the following table shows:

[0117] Form 4: Teamwork Performance Evaluation Form

[0118] Student Name Task Name Team Roles Collaboration performance score (0-10) Communication skills rating (0-10) Task division score (0-10) Overall collaboration rating Student A Cleaning tasks Executor 8 7 9 8 Student B Gardening tasks Coordinator 9 8 8 8.5 Student C Assembly tasks Leader 10 9 9 9.5

[0119] Through the above steps, the Teamwork Assessment Unit of the Adaptive Assessment Module provides a comprehensive assessment of students' performance in teamwork tasks. This process not only ensures the accuracy and scientific nature of the assessment results but also provides important support for personalized feedback and improvements to the system. Through real-time tracking and comprehensive evaluation, the system can promptly identify and intervene in students' teamwork issues, effectively improving the scientific nature and effectiveness of labor education.

[0120] The feedback interaction module 40 is used to perform periodic evaluation and summary based on the personalized labor evaluation report, and provide feedback to the teacher side, the student side, and the parent side for a three-in-one information display.

[0121] It should be understood that the main function of the feedback interaction module 40 of this application is to conduct periodic evaluation summaries based on the students' personalized labor evaluation reports, and to feed back the evaluation results to the teacher side, the student side, and the parent side, forming a three-in-one information display to assist educators, students, and parents in fully understanding the students' performance and progress in labor education practice.

[0122] Feedback interaction module 40 builds a three-terminal system based on Vue+Echarts+WebSocket:

[0123] The teacher side provides a real-time assessment monitoring interface, report export (PDF) function and growth warning push; the student side displays personal behavior radar charts, task trajectories, and assessment logs; the parent side provides concise report summaries and suggestions (adapted to mobile devices).

[0124] Specifically, the front-end interactive interface of the feedback interaction module 40 is built based on the Vue framework, and all student data is displayed in real-time in the form of charts. The following visualization content is drawn using the Echarts component:

[0125] Student behavior radar chart (6-dimensional behavioral characteristics); labor progress curve (task completion rate changes over time); physiological state heat map (heart rate + ambient temperature dual-axis display);

[0126] The backend service is powered by Node.js and works with MongoDB for data caching and asynchronous report generation. Teachers can export assessment reports in PDF format, while students can track their progress. Parents can also display concise charts and summary recommendations.

[0127] After each labor task is completed, the system automatically generates an evaluation report with the following structure:

[0128] {"student_id":"S001","task_name":"Garden Cleanup","completion_score":8.2,"cooperation_score":7.6,"fatigue_risk":"Mild","env_adapt":6.8,"overall_score":7.9,"suggestion":"Improve task persistence and maintain good collaboration."}

[0129] In addition, the module also has an abnormal fluctuation detection mechanism: if a student's task score fluctuates by more than ±2 points for three consecutive times, the system triggers a "growth warning" and automatically pushes it to teachers and parents to assist in precise intervention.

[0130] Specifically, first, a periodic evaluation summary is generated based on the student's personalized labor evaluation report. For example, the following table is shown:

[0131] Form 5: Student Personalized Labor Evaluation Form

[0132] Student Name Task Type Basic completion score Collaborative Grading Fatigue score Environmental adaptation score Overall assessment score Evaluation Recommendations Student A Cleaning tasks 8.5 8 7 7 8 Enhance physical strength training Student B Gardening tasks 7.8 9 6 5 7 Improve working environment and take rest Student C Assembly tasks 9.5 9.5 8 8 9.3 Keep going, increase the challenge

[0133] Personalized labor assessment reports integrate student performance data from the labor process, including task completion, teamwork, safety status, and other dimensions. Through periodic analysis of this data, the feedback and interaction module summarizes a student's progress, strengths, and areas for improvement over a specific time period. This assessment not only includes the student's performance on each labor task but also combines long-term performance to provide a comprehensive assessment of their labor literacy and skill mastery.

[0134] Next, the feedback interaction module will feed back these evaluation summary information to different ports. The teacher side can view the students' detailed labor evaluation reports and periodic summaries to help teachers fully understand each student's performance and progress. Teachers can use this information to adjust the direction of students' labor education and provide personalized guidance and improvement suggestions. The student side can view their own labor evaluation results and periodic summaries through mobile devices or computers to help students identify their strengths and weaknesses and motivate them to continue to improve in their labor tasks. The parent side provides parents with a channel to view students' performance, enabling parents to understand their children's growth trajectory in labor education, and provides parents with a way to communicate with teachers, forming a good interaction between home and school to jointly support student development.

[0135] The feedback interaction module also displays student assessment results to teachers, students, and parents through visual means such as charts and progress bars, making the assessment information more intuitive and easy to understand. Real-time feedback and regular assessment summaries not only promote the coordination and consistency of education, but also provide important support for personalized education, helping to improve the overall effectiveness and quality of labor education.

[0136] In summary, the embodiments of the present application have at least the following technical effects:

[0137] This application collects data through the perception terminal module, conducts in-depth analysis and constructs a labor behavior portrait through the data processing module, and uses the adaptive evaluation module to conduct multi-dimensional evaluations such as task completion, fatigue protection, and collaborative performance. Finally, the evaluation results are provided in real-time feedback and periodic summary through the teacher, student, and parent ends to ensure that students' labor performance can be comprehensively and accurately monitored and optimized.

[0138] The technical effect of achieving comprehensive and real-time student labor performance evaluation and personalized feedback, and improving the reliability of evaluation results, has been achieved through an adaptive evaluation mechanism relying on multi-source perception and robust artificial intelligence.

[0139] Example 2: Exemplary electronic device

[0140] Reference below Figure 3 To describe the electronic device of the embodiment of the present application.

[0141] Based on the same inventive concept as the labor education practice adaptive evaluation system based on multi-source perception in the aforementioned embodiment, the present application also provides an electronic device, including: a processor, the processor is coupled to a memory, the memory is used to store a program, and when the program is executed by the processor, the system of embodiment one is implemented.

[0142] The electronic device 300 includes: a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may further include a bus architecture 304. The communication interface 303, the processor 302, and the memory 301 may be interconnected via the bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0143] The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0144] The communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), wired access network, etc.

[0145] The memory 301 can be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory can exist independently and be connected to the processor via the bus architecture 304. The memory can also be integrated with the processor.

[0146] The memory 301 is used to store computer-executable instructions for executing the solution of the present application, and the execution is controlled by the processor 302. The processor 302 is used to execute the computer-executable instructions stored in the memory 301, thereby realizing the labor education practice adaptive evaluation system based on multi-source perception provided by the above embodiment of the present application.

[0147] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0148] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0149] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. The adaptive evaluation system for labor education practice based on multi-source perception is characterized by: The system comprises: A perception terminal module is used to collect student labor data and environmental change data on site in real time based on an intelligent perception terminal to obtain multi-source perception data, which is associated with student identity information; A data processing module is used to deeply integrate and analyze the multi-source perception data to establish a labor behavior profile of each student; The adaptive assessment module includes a standard indicator library and a behavioral feature weight adjustment mechanism. It is used to conduct adaptive labor assessment based on each student's labor behavior profile and generate a personalized labor assessment report. The feedback interaction module is used to conduct periodic evaluation summaries based on the personalized labor evaluation report, and provide feedback to the teacher side, student side, and parent side for a three-in-one information display.

2. The labor education practice adaptive evaluation system based on multi-source perception according to claim 1 is characterized in that: When the data processing module performs in-depth integration and analysis of the multi-source perception data to establish a labor behavior portrait of each student, it is also used to: After cleaning and preprocessing the multi-source perception data, extracting feature data related to labor behavior from the multi-source perception data, and performing scene association clustering to generate a multivariate feature array; Based on the multivariate feature array and combined with student identity information, association analysis is performed to construct a labor behavior portrait of each student. The labor behavior portrait is a dynamic data window that is updated in real time and includes the student's behavior patterns and performance characteristics in different labor scenarios.

3. The labor education practice adaptive evaluation system based on multi-source perception according to claim 1 is characterized in that: The adaptive assessment module includes a basic completion assessment unit, a high-intensity labor task protection assessment unit and a team collaboration assessment unit.

4. The labor education practice adaptive evaluation system based on multi-source perception as claimed in claim 3 is characterized in that: The adaptive evaluation module is further configured to: Receive and update each student's labor behavior portrait in real time, and extract behavioral data from it for multi-dimensional evaluation, including: Based on the basic completion evaluation unit, a routine labor evaluation is performed to generate a basic completion evaluation result; Conduct real-time high-intensity protection monitoring according to the high-intensity labor task protection assessment unit, and provide real-time protection feedback based on the monitoring results; The team collaboration assessment unit is used to track and assess the collaborative tasks and generate a team collaboration scoring result.

5. The labor education practice adaptive evaluation system based on multi-source perception according to claim 4 is characterized in that: The adaptive assessment module performs a routine labor assessment based on the basic completion assessment unit to generate a basic completion assessment result, and is further configured to: Extracting task completion data for multiple tasks based on the labor behavior profile; Based on the task completion data of multiple tasks, a multi-indicator quantitative evaluation is conducted on the completion of students in various labor tasks to generate quantitative values of basic task indicators; According to the preset standard indicator library, the quantitative values of the basic task indicators are evaluated and scored to generate the completion score of each student in different tasks; The completion scores of each student in different tasks are combined to generate basic completion assessment results.

6. The labor education practice adaptive evaluation system based on multi-source perception according to claim 4 is characterized in that: When the adaptive assessment module performs real-time high-intensity protection monitoring based on the high-intensity labor task protection assessment unit, it is also used to: Based on the labor behavior portrait, physiological characteristics data of each student are extracted in real time according to the student identity code; The high-intensity labor task protection assessment unit performs periodic fatigue abnormality monitoring based on the physiological characterization data; When any student's physiological data is detected to be abnormal, the protection mechanism is immediately triggered and a real-time protection instruction is generated; Based on the real-time protection instruction, real-time protection feedback is sent to the student terminal through the intelligent sensing terminal, and a protection reminder is sent to the teacher terminal.

7. The labor education practice adaptive evaluation system based on multi-source perception according to claim 6 is characterized in that: When the adaptive assessment module performs real-time high-intensity protection monitoring based on the high-intensity labor task protection assessment unit, it is also used to: Monitor students' environmental data during their labor tasks in real time and obtain real-time labor environment data; Conduct periodic environmental anomaly monitoring based on the real-time working environment data; When any environmental indicator is detected to exceed the safety environment threshold, an environmental abnormality warning will be sent to the teacher through the intelligent sensing terminal.

8. The labor education practice adaptive evaluation system based on multi-source perception according to claim 7 is characterized in that: When the adaptive assessment module performs real-time high-intensity protection monitoring based on the high-intensity labor task protection assessment unit, it is also used to: Collect data on students' physiological indicators during high-intensity labor tasks and environmental monitoring data during various tasks; Based on the student physiological indicator monitoring data, the evaluation weights of high-intensity labor tasks are redistributed through the behavioral characteristic weight adjustment mechanism; Based on the environmental monitoring data, a periodic task safety assessment is performed, and labor tasks are optimized according to the assessment results.

9. The labor education practice adaptive evaluation system based on multi-source perception according to claim 4 is characterized in that: When the adaptive assessment module performs collaborative task tracking assessment through the team collaboration assessment unit, it is further used to: Based on the labor behavior portrait, cluster the student information of the same collaborative task to generate multiple collaborative portrait groups; For each collaborative portrait group, obtain the team role type of each student, and track the student's performance characteristics in team collaboration tasks in real time according to the team role type to obtain multiple team collaboration indicators; A collaboration degree assessment is performed based on the multiple team collaboration indicators to generate a team collaboration score result for each student.

10. An electronic device, characterized in that: include: A processor is coupled to a memory, and the memory is used to store a program. When the program is executed by the processor, the labor education practice adaptive evaluation system based on multi-source perception as described in any one of claims 1 to 9 is implemented.

Images