A system and method for evaluating the effectiveness of labor education practices

Abstract

This invention relates to the field of labor education evaluation technology, specifically disclosing a system and method for evaluating the effectiveness of labor education practices. The system includes a data acquisition module, a blockchain evidence storage module, an AI behavior analysis module, a closed-loop control module, and a central database. The data acquisition module collects multi-source data, including IoT check-in data, videos, multi-subject evaluations, and results. The blockchain evidence storage module encrypts and distributes the data using the SHA-256 algorithm. The AI ​​behavior analysis module uses the YOLOv8 model to identify labor behaviors and quantify parameters. The closed-loop control module generates evaluation results and outputs task adjustment and teaching optimization instructions, forming a periodic closed loop. This invention solves the problems of difficulty in ensuring the authenticity of existing labor education evaluation data, lack of process evaluation, and disconnect between evaluation and teaching, achieving full-chain traceability of evaluation, intelligent analysis, and integrated teaching.

Description

Technical Field

[0001] This invention relates to the field of labor education evaluation technology, specifically to a system and method for evaluating the effectiveness of labor education practices. Background Technology

[0002] Labor education is an important vehicle for cultivating morality and character, and a core approach to improving students' labor skills, fostering labor attitudes, and accumulating labor literacy. The evaluation of its practical effects serves as a "command stick" for the implementation of labor education, directly impacting the quality of achieving its goals and acting as a key criterion for education departments, schools, and parents to measure its effectiveness. Currently, labor education practices are widely implemented in schools at all levels across my country, but the corresponding evaluation work still faces multiple bottlenecks in terms of technology and methodology.

[0003] The existing methods for evaluating the effectiveness of labor education practices mainly include two categories: traditional manual evaluation and basic digital-assisted evaluation. Traditional methods mainly rely on paper records, manual scoring, and Excel statistics, depending on teachers' subjective judgment to record information such as students' labor time and task completion. Basic digital methods mostly use online forms, simple check-in tools, or modules embedded in the teaching affairs system to achieve preliminary online collection and statistics of evaluation data.

[0004] However, the aforementioned existing technologies have significant drawbacks: First, the authenticity and traceability of data are insufficient; labor data is easily tampered with and forged, lacking effective evidence preservation and verification mechanisms, making it difficult to avoid problems such as "formalized labor" and "fake labor." Second, process evaluation is lacking; existing methods focus on quantifying labor results and explicit skills, lacking effective identification and quantification methods for implicit manifestations such as collaborative behavior, adherence to safety regulations, and innovative operations during the labor process, resulting in an imbalance in evaluation dimensions. Third, evaluation data is fragmented; multi-source data (check-in data, evaluation data, and outcome data) are scattered across different tools, forming "data silos" that cannot achieve comprehensive correlation analysis. Fourth, evaluation is disconnected from teaching; it can only output static evaluation results, lacking a dynamic task adjustment and teaching strategy optimization mechanism based on evaluation data, making it difficult to guide the continuous improvement of labor education. Fifth, evaluation weights are fixed; a dynamic update mechanism based on actual evaluation results has not been established, making it unable to adapt to the evaluation needs of different labor scenarios and student development stages.

[0005] The aforementioned shortcomings result in existing evaluation results that are highly subjective, lack comprehensiveness, and are weak in guidance, failing to meet the evaluation goals of labor education that emphasize both process and outcome, and skills and qualities, thus hindering the improvement of labor education quality. Therefore, there is an urgent need for a labor education practice effectiveness evaluation system and method that can achieve reliable data storage, intelligent process analysis, and a closed-loop linkage between evaluation and teaching, in order to solve the pain points of existing technologies. Summary of the Invention

[0006] In view of the above-mentioned problems in the prior art, the present invention provides a system and method for evaluating the effectiveness of labor education practice, which solves the problems of strong subjectivity, insufficient comprehensiveness and weak guidance of existing evaluation results, and improves the credibility of data.

[0007] To achieve the above objectives, this invention proposes a labor education practice effectiveness evaluation system, comprising: Data acquisition module, blockchain evidence storage module, AI behavior analysis module, closed-loop control module, and central database; The data acquisition module is used to collect multi-source data during the labor practice process. The multi-source data includes IoT check-in data, labor scene video data, multi-subject evaluation data, and labor result data. The multi-subject evaluation data comes from the teacher's end, the student's end, the parent's end, and the practice base end. The blockchain evidence storage module is deployed on a distributed node consisting of the school server, the practice base server, and the education department server, and is used to perform hash encryption processing on the multi-source data and then store it in a distributed manner. The AI ​​behavior analysis module is used to extract and identify features from video data of labor scenes and output quantitative parameters of labor behavior. The central database is used to store standardized multi-source data and AI behavior analysis results; The closed-loop control module is used to generate evaluation results based on the data stored in the central database, and output labor task adjustment instructions and teaching strategy optimization instructions according to the evaluation results.

[0008] Preferably, the data acquisition module includes a GPS positioning unit, a high-definition camera unit, a multi-terminal interaction unit, and a results uploading unit; the GPS positioning unit is used to collect location data of the labor practice, the high-definition camera unit is used to collect video data of the labor scene at a frame rate of not less than 25fps, the multi-terminal interaction unit provides a standardized electronic evaluation form, and the results uploading unit supports uploading labor results in image, document, and video formats.

[0009] Preferably, the hash encryption processing of the blockchain evidence storage module adopts the SHA-256 algorithm, and the encryption formula is as follows: ; Where H is the hash value, M is the original multi-source data to be encrypted, and the encrypted data is synchronized to each distributed node through a consensus mechanism, ensuring that the data copies stored on each node maintain consistency.

[0010] Preferably, the AI ​​behavior analysis module includes a behavior recognition model and a parameter quantization unit; the behavior recognition model uses a YOLOv8 deep learning model to recognize collaborative actions, tool operation actions, and safety compliance actions in video data; the parameter quantization unit converts the recognized actions into quantified parameters, including the duration of action completion. Standard of movement and frequency of collaboration .

[0011] Preferably, the closed-loop control module includes an evaluation generation unit, a task matching unit, and a teaching adjustment unit; the evaluation generation unit calculates a comprehensive evaluation score based on multi-source data and AI behavior quantification parameters according to preset weights; the task matching unit selects suitable tasks from the labor task library according to the comprehensive evaluation score; and the teaching adjustment unit outputs instructions for adjusting class time allocation and instructions for key guidance points.

[0012] A method for evaluating the effectiveness of labor education practices is also proposed, employing any one of the labor education practice effectiveness evaluation systems described above, including: S1. Collect multi-source data from the labor practice process through the data acquisition module, and perform format standardization processing on the multi-source data to obtain standardized data; S2. The standardized data is hashed and encrypted using the blockchain notarization module, and the encrypted data is synchronized to the distributed nodes for storage. S3. The AI ​​behavior analysis module performs behavior recognition on video data in the standardized data and outputs quantitative parameters of labor behavior. S4. The central database stores standardized data and quantitative parameters of labor behavior, and the closed-loop control module generates comprehensive evaluation results based on the stored data. S5. The closed-loop control module outputs labor task adjustment instructions and teaching strategy optimization instructions based on the comprehensive evaluation results, completing one evaluation-adjustment closed loop. S6. Repeat steps S1-S5 to form a periodic evaluation-adjustment closed loop. After each closed loop, update the preset weights and labor task library.

[0013] Preferably, in S1, the format standardization process includes converting GPS positioning data into WGS-84 coordinate system coordinates, encoding video data into H.265 format, and converting multi-subject evaluation data into standardized scores of 0-10.

[0014] Preferably, in S4, the comprehensive evaluation score is calculated using a weighted summation formula: ; in, To evaluate the overall score, For the first Preset weights for class data For the first Standardized scores for class data Number the data type, with values ​​ranging from 1 to... , This represents the total number of data types from multiple sources.

[0015] Preferably, in S5, the labor task adjustment instructions include task difficulty adjustment parameters, task duration adjustment parameters, and task type matching parameters; the teaching strategy optimization instructions include instructor allocation instructions, class hour increase / decrease instructions, and key instruction for instruction content.

[0016] Preferably, in S6, the preset weights for updating are determined using the analytic hierarchy process (AHP), and the update formula is as follows: ; in, This is the weighting adjustment coefficient, with a value ranging from -0.2 to 0.2.

[0017] Therefore, this invention proposes a system and method for evaluating the effectiveness of labor education practices, the beneficial effects of which are as follows: (1) By using the SHA-256 encryption and distributed storage of the blockchain evidence storage module, the labor data is made immutable and traceable throughout the entire chain. Combined with multi-source data collection and standardized processing, the problem of data authenticity verification is solved. At the same time, the implicit behavioral quantitative parameters in the labor process are extracted by using the YOLOv8 model, which makes up for the shortcomings of traditional evaluation that emphasizes results over process, and realizes comprehensive quantitative evaluation of skills, attitudes and qualities in multiple dimensions.

[0018] (2) By constructing a periodic linkage mechanism of evaluation-task adjustment-teaching optimization through a closed-loop control module, and dynamically updating the preset weights with the analytic hierarchy process, the evaluation results are accurately aligned with labor teaching, and can adapt to the needs of different labor scenarios and students' developmental stages. This solves the problems of evaluation and teaching being disconnected and weights being fixed, and improves the pertinence and adaptability of labor education evaluation.

[0019] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the overall process of a labor education practice effectiveness evaluation system and method according to the present invention; Figure 2 This is a schematic diagram of the system module architecture of a labor education practice effectiveness evaluation system and method according to the present invention; Figure 3 This is a data processing and evaluation logic diagram of a labor education practice effectiveness evaluation system and method according to the present invention; Figure 4 This is a comprehensive evaluation and weight update diagram of a labor education practice effectiveness evaluation system and method according to the present invention. Detailed Implementation

[0021] To make the technical solutions, advantages, and objectives of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below. The described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention without creative effort are within the protection scope of this application.

[0022] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0023] like Figures 1-4 As shown, the present invention provides a system and method for evaluating the effectiveness of labor education practices.

[0024] A system for evaluating the effectiveness of labor education practices, comprising: Data acquisition module, blockchain evidence storage module, AI behavior analysis module, closed-loop control module, and central database; The data acquisition module is used to collect multi-source data during the labor practice process. The multi-source data includes IoT check-in data, labor scene video data, multi-subject evaluation data, and labor result data. The multi-subject evaluation data comes from the teacher's end, the student's end, the parent's end, and the practice base end. The data acquisition module includes a GPS positioning unit, a high-definition camera unit, a multi-terminal interaction unit, and a results upload unit. The GPS positioning unit is used to collect location data of labor practices, the high-definition camera unit is used to collect video data of labor scenes at a frame rate of not less than 25fps, the multi-terminal interaction unit provides standardized electronic evaluation forms, and the results upload unit supports uploading labor results in image, document, and video formats.

[0025] The blockchain evidence storage module is deployed on a distributed node consisting of the school server, the practice base server, and the education department server. It is used to perform hash encryption processing on multi-source data and then store it in a distributed manner. The hash encryption processing of the blockchain evidence storage module uses the SHA-256 algorithm, and the encryption formula is as follows: ; Where H is the hash value, M is the original multi-source data to be encrypted, and the encrypted data is synchronized to each distributed node through a consensus mechanism, ensuring that the data copies stored on each node maintain consistency.

[0026] The AI ​​behavior analysis module is used to extract and identify features from video data of labor scenes and output quantitative parameters of labor behavior. The AI ​​behavior analysis module includes a behavior recognition model and a parameter quantization unit. The behavior recognition model uses a YOLOv8 deep learning model to identify collaborative actions, tool operation actions, and safety compliance actions in video data. The parameter quantization unit converts the identified actions into quantified parameters, including the duration of the action. Standard of movement and frequency of collaboration .

[0027] A central database is used to store standardized multi-source data and AI behavior analysis results. The closed-loop control module is used to generate evaluation results based on data stored in the central database, and output labor task adjustment instructions and teaching strategy optimization instructions based on the evaluation results.

[0028] The closed-loop control module includes an evaluation generation unit, a task matching unit, and a teaching adjustment unit. The evaluation generation unit calculates a comprehensive evaluation score based on multi-source data and AI behavior quantification parameters, according to preset weights. The task matching unit selects suitable tasks from the labor task library based on the comprehensive evaluation score. The teaching adjustment unit outputs instructions for adjusting class time allocation and instructions for key guidance points.

[0029] A method for evaluating the effectiveness of labor education practices is also proposed, which adopts any of the above-mentioned labor education practice effectiveness evaluation systems, including: S1. Collect multi-source data from the labor practice process through the data acquisition module, and perform format standardization processing on the multi-source data to obtain standardized data; The format standardization process includes converting GPS positioning data into WGS-84 coordinate system coordinates, encoding video data into H.265 format, and converting multi-subject evaluation data into standardized scores of 0-10.

[0030] S2. The standardized data is hashed and encrypted using the blockchain notarization module, and the encrypted data is synchronized to the distributed nodes for storage. S3. The AI ​​behavior analysis module performs behavior recognition on video data in the standardized data and outputs quantitative parameters of labor behavior. S4. The central database stores standardized data and quantitative parameters of labor behavior, and the closed-loop control module generates comprehensive evaluation results based on the stored data. The overall evaluation score is calculated using a weighted summation formula: ; in, To evaluate the overall score, For the first Preset weights for class data For the first Standardized scores for class data Number the data type, with values ​​ranging from 1 to... , This represents the total number of data types from multiple sources.

[0031] S5. The closed-loop control module outputs labor task adjustment instructions and teaching strategy optimization instructions based on the comprehensive evaluation results, completing one evaluation-adjustment closed loop. Labor task adjustment instructions include parameters for adjusting task difficulty, adjusting task duration, and matching task type; teaching strategy optimization instructions include instructions for assigning instructors, instructions for increasing or decreasing class hours, and instructions for focusing on key teaching content.

[0032] S6. Repeat steps S1-S5 to form a periodic evaluation-adjustment closed loop. After each closed loop, update the preset weights and labor task library.

[0033] The updated preset weights are determined using the analytic hierarchy process (AHP), and the update formula is as follows: ; in, This is the weighting adjustment coefficient, with a value ranging from -0.2 to 0.2.

[0034] This invention takes a university-enterprise joint labor practice project on "Ecological Agriculture and Sustainable Development" for third-year environmental science students at a university (12 weeks in length, 20 groups of 4 students each, practice site being the university's industry-university-research ecological farm + cooperative agricultural technology enterprise training base) as an example, and uses the system and method of this invention to evaluate the effectiveness of labor education practice. The specific implementation process is as follows: The school's ecological farm and partner company training bases are equipped with IoT check-in terminals integrated with GPS positioning units (supporting both outdoor and indoor dual-scene positioning) and six high-definition cameras with a frame rate of 30fps (covering three major scenes: field operation area, laboratory analysis area, and company production workshop). A multi-terminal interactive platform has been built, including five types of interactive entry points: student APP, teacher management system, parent connection module, farm mentor end, and company mentor end. The company mentor end has added a professional skills evaluation module and a practical task progress tracking function. The blockchain evidence storage module is deployed in a distributed network consisting of the school server, partner company server, local education department server, and industry regulatory nodes. The central database achieves two-way data exchange with the school's academic affairs system and the company's training management system, supporting the linkage between practical data and professional credit recognition.

[0035] The IoT attendance tracking device collects students' daily practice attendance time, cross-site (farm or enterprise) movement trajectory (converted to WGS-84 coordinate system coordinates), and usage time and operation records of professional equipment (such as soil testers, irrigation control systems, and drone plant protection equipment); High-definition camera equipment captures real-time video of scenes such as field planting management, laboratory data analysis, and enterprise production process operation, and automatically encodes it into H.265 format; Multi-subject evaluations are submitted through an interactive platform: teacher evaluations focus on theoretical application ability, corporate mentor evaluations focus on professional skills and professional qualities, peer evaluations within groups focus on collaborative contributions, and parent evaluations focus on practical attitude and sense of responsibility. The system automatically converts all types of evaluation data into standardized scores of 0-10. Students submit various types of data through the results upload unit, including field management logs, soil or crop monitoring data analysis reports, ecological planting scheme designs, enterprise training summaries, innovation and entrepreneurship plans (optional), and visualization posters or short videos of practical results.

[0036] The blockchain evidence storage module uses the SHA-256 algorithm to encrypt the aforementioned standardized data (including newly added data types such as professional equipment operation logs and enterprise mentor evaluation records). Through a node consensus mechanism, it is synchronized to four distributed nodes: the school, the enterprise, the education department, and the industry regulator, ensuring that the practical data is traceable and tamper-proof throughout the entire process, providing a reliable basis for subsequent professional credit recognition and enterprise internship assessment.

[0037] The AI ​​behavior analysis module uses the YOLOv8 model to professionally analyze videos of work scenes, focusing on identifying three core behaviors: Professional operational practices (such as soil sample collection procedures, instrument calibration, and drone plant protection parameter settings). Cross-scenario collaborative behaviors (such as data docking between field practice and laboratory analysis within a group, and problem communication and collaboration with enterprise technical personnel, etc.); Occupational safety regulations (such as the wearing of laboratory protective equipment, safe operation of agricultural machinery, and standardized use of chemical reagents).

[0038] The parameter quantification unit outputs targeted quantification parameters: professional operation proficiency (scored from 0 to 10 points according to industry standards), cross-role collaboration response efficiency (average time from initiation to completion of collaboration request), problem-solving closed-loop time (cycle from discovering a practical problem to proposing a solution and verifying it), and professional standard compliance rate (percentage of times that safe operation or standard process execution is in compliance).

[0039] The central database stores standardized data and behavioral quantification parameters. The evaluation generation unit of the closed-loop control module optimizes the preset weights to calculate the comprehensive evaluation score according to the characteristics of college students' labor practice. The weight allocation is as follows: IoT check-in data (including professional equipment usage records) 0.15, behavioral quantification parameters (focusing on professional operation and collaboration) 0.4, multi-subject evaluation data (including enterprise mentor evaluation) 0.25, and achievement data (including professional reports and innovative solutions) 0.2. The calculation uses the following formula: (in To evaluate the overall score, For the first Preset weights for class data For the first Standardized scores for class data The data type is numbered, with values ​​from 1 to 4. =4 represents the total number of data types from multiple sources), ultimately generating a two-dimensional evaluation result consisting of the group's overall score and the individual's contribution score.

[0040] For groups or individuals with an overall evaluation score below 7, the task matching unit selects suitable tasks from the labor task database: those with weak professional skills are assigned one-on-one specialized training tasks by enterprise mentors (such as hands-on debugging of precision irrigation systems); groups with insufficient collaboration efficiency are given new cross-group joint research tasks (such as comparative experiments on ecological technologies in different planting areas). The teaching adjustment unit outputs personalized optimization instructions: for students with weak professional skills, add 4 enterprise training hours and push online professional skills course resources; for groups with insufficient innovation ability, arrange innovation and entrepreneurship mentors to provide guidance on refining the plan; for those with low compliance rate of professional norms, organize 1 special training on industry safety norms, and complete the first evaluation-adjustment closed loop.

[0041] Steps S1-S5 are repeated every 3 weeks, forming 4 cyclical closed loops. After the second closed loop, the preset weights are updated using the analytic hierarchy process (AHP) in conjunction with the professional training objectives: the weight of the quantitative parameters of professional operations for science and engineering students is increased by 0.05 (adjustment coefficient is 0.05), and the weight of collaborative behavior in humanities practical projects is increased by 0.08; at the same time, the labor task library is optimized, and new tasks such as "commercial design of ecological agricultural technology" and "cross-disciplinary collaborative farmland ecological monitoring project" are added to adapt to the ability advancement of college students and to meet the development needs of different professional directions and students.

[0042] After the 12-week practical project, the system generates a multi-dimensional comprehensive evaluation result based on the cumulative data from four closed-loop cycles, including: Three-dimensional radar chart (professional skills proficiency, collaborative innovation ability, and professional ethics compliance rate). Individual or group practice growth curve (trend of core indicators at each closed-loop stage). Personalized improvement suggestions (combining feedback from corporate mentors and professional development directions, such as suggestions for strengthening experimental skills for research-oriented studies and optimization plans for career practice for employment-oriented studies). The practical achievement certification report (connected to the school's credit recognition system and the enterprise internship evaluation system) automatically synchronizes the evaluation results to the student's comprehensive quality file and the enterprise's talent reserve database.

[0043] After the 12-week university-enterprise joint practice project concluded, the comprehensive evaluation results output by the system showed that the labor practice achievements of university students achieved a professional and progressive improvement: their professional operation proficiency increased by an average of 40% compared to the beginning of the project, their cross-role collaboration response efficiency was shortened by 35%, their professional standard compliance rate reached 96%, and their problem-solving closure time was reduced by an average of 28%; 90% of the groups adapted to their own ability shortcomings through dynamic task adjustments, and 30% of the practice results (such as ecological planting optimization plans and data analysis reports) were adopted by partner companies or transformed into the prototype of innovation and entrepreneurship projects; the deep integration of multi-subject evaluation and AI behavioral quantitative data improved the objectivity and comprehensiveness of the evaluation results by 50% compared to traditional evaluation, and the credible data stored on the blockchain was successfully connected to the school's credit recognition system and the enterprise's internship appraisal system, realizing an integrated closed loop of "practice-evaluation-certification".

[0044] This embodiment verifies that the system and method can effectively solve the pain points in the evaluation of college students' labor practice, such as the lack of professional dimensions, the separation of school and enterprise data, the insufficient quantification of the process, and the disconnect between evaluation and career development. It provides a scientific, intelligent, and practical evaluation solution for the deep integration of labor education and professional training in colleges and universities and the collaborative education between schools and enterprises.

[0045] Therefore, this invention provides a system and method for evaluating the effectiveness of labor education practices. It integrates IoT check-in data, video data, multi-subject evaluation data, and outcome data through a multi-source data acquisition module. After standardization processing, a blockchain-based notarization module encrypts and distributes the data using the SHA-256 algorithm. Then, an AI behavior analysis module extracts quantitative parameters of labor behavior using a YOLOv8 model. Finally, a closed-loop control module generates a comprehensive evaluation result based on a weighted summation formula and outputs task adjustment and teaching optimization instructions, forming a periodic closed loop with dynamically updated weights and task libraries. This system and method integrate reliable data notarization, intelligent process quantification, and evaluation-teaching linkage, comprehensively covering the entire process of labor education evaluation and providing a standardized, intelligent, and traceable solution for evaluating the effectiveness of labor education.

[0046] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A system for evaluating the effectiveness of labor education practices, characterized in that, include: Data acquisition module, blockchain evidence storage module, AI behavior analysis module, closed-loop control module, and central database; The data acquisition module is used to collect multi-source data during the labor practice process. The multi-source data includes IoT check-in data, labor scene video data, multi-subject evaluation data, and labor result data. The multi-subject evaluation data comes from the teacher's end, the student's end, the parent's end, and the practice base end. The blockchain evidence storage module is deployed on a distributed node consisting of the school server, the practice base server, and the education department server, and is used to perform hash encryption processing on the multi-source data and then store it in a distributed manner. The AI ​​behavior analysis module is used to extract and identify features from video data of labor scenes and output quantitative parameters of labor behavior. The central database is used to store standardized multi-source data and AI behavior analysis results. The closed-loop control module is used to generate evaluation results based on the data stored in the central database, and output labor task adjustment instructions and teaching strategy optimization instructions according to the evaluation results.

2. The evaluation system for the effectiveness of labor education practice according to claim 1, characterized in that, The data acquisition module includes a GPS positioning unit, a high-definition camera unit, a multi-terminal interaction unit, and a results uploading unit. The GPS positioning unit is used to collect location data of the labor practice, the high-definition camera unit is used to collect video data of the labor scene at a frame rate of not less than 25fps, the multi-terminal interaction unit provides standardized electronic evaluation forms, and the results uploading unit supports uploading labor results in image, document, and video formats.

3. The evaluation system for the effectiveness of labor education practice according to claim 1, characterized in that, The hash encryption process of the blockchain evidence storage module uses the SHA-256 algorithm, and the encryption formula is as follows: ； Where H is the hash value, M is the original multi-source data to be encrypted, and the encrypted data is synchronized to each distributed node through a consensus mechanism, ensuring that the data copies stored on each node maintain consistency.

4. The evaluation system for the effectiveness of labor education practice according to claim 1, characterized in that, The AI ​​behavior analysis module includes a behavior recognition model and a parameter quantization unit. The behavior recognition model uses a YOLOv8 deep learning model to identify collaborative actions, tool operation actions, and safety compliance actions in video data. The parameter quantization unit converts the identified actions into quantified parameters, including the duration of the action. Standard of movement and frequency of collaboration .

5. The evaluation system for the effectiveness of labor education practice according to claim 1, characterized in that, The closed-loop control module includes an evaluation generation unit, a task matching unit, and a teaching adjustment unit. The evaluation generation unit calculates a comprehensive evaluation score based on multi-source data and AI behavior quantification parameters, according to preset weights. The task matching unit selects suitable tasks from the labor task library based on the comprehensive evaluation score. The teaching adjustment unit outputs instructions for adjusting class time allocation and instructions for highlighting key points.

6. A method for evaluating the effectiveness of labor education practices, characterized in that, The labor education practice effectiveness evaluation system according to any one of claims 1-5 includes: S1. Collect multi-source data from the labor practice process through the data acquisition module, and perform format standardization processing on the multi-source data to obtain standardized data; S2. The standardized data is hashed and encrypted using the blockchain notarization module, and the encrypted data is synchronized to the distributed nodes for storage. S3. The AI ​​behavior analysis module performs behavior recognition on video data in the standardized data and outputs quantitative parameters of labor behavior. S4. The central database stores standardized data and quantitative parameters of labor behavior, and the closed-loop control module generates comprehensive evaluation results based on the stored data. S5. The closed-loop control module outputs labor task adjustment instructions and teaching strategy optimization instructions based on the comprehensive evaluation results, completing one evaluation-adjustment closed loop. S6. Repeat steps S1-S5 to form a periodic evaluation-adjustment closed loop. After each closed loop, update the preset weights and labor task library.

7. The method for evaluating the effectiveness of labor education practice according to claim 6, characterized in that, In S1, the format standardization process includes converting GPS positioning data into WGS-84 coordinate system coordinates, encoding video data into H.265 format, and converting multi-subject evaluation data into standardized scores of 0-10.

8. The method for evaluating the effectiveness of labor education practice according to claim 6, characterized in that, In S4, the comprehensive evaluation score is calculated using a weighted summation formula: ； in, To evaluate the overall score, For the first Preset weights for class data For the first Standardized scores for class data Number the data type, with values ​​ranging from 1 to... , This represents the total number of data types from multiple sources.

9. The method for evaluating the effectiveness of labor education practice according to claim 6, characterized in that, In S5, the labor task adjustment instructions include task difficulty adjustment parameters, task duration adjustment parameters, and task type matching parameters; the teaching strategy optimization instructions include instructor allocation instructions, class hour increase / decrease instructions, and key instruction instructions for instruction content.

10. A method for evaluating the effectiveness of labor education practice according to claim 6, characterized in that, In S6, the updated preset weights are determined using the analytic hierarchy process (AHP), and the update formula is as follows: ； in, This is the weighting adjustment coefficient, with a value ranging from -0.2 to 0.2.

Images