Labor education evaluation intelligent system

Abstract

The invention discloses a labor education evaluation intelligent system, and relates to the technical field of labor education intelligent evaluation. The system comprises an authority management unit, a labor education management unit, an integral service unit and a data monitoring unit. According to the labor education management unit provided by the invention, the labor education course data of the students are acquired, the labor education evaluation data are input according to the labor education intelligent evaluation authority and the labor education course data of the students, and the labor education semester evaluation result is generated from the labor education evaluation data by using a natural language processing method; the defect of strong subjectivity in a traditional evaluation mode is avoided, and the fairness and the accuracy of an evaluation result are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent evaluation of labor education, and in particular to an intelligent system for evaluating labor education. Background Art

[0002] With the continuous development of educational technology, the traditional labor education model can no longer meet the needs of modern education. In order to better cultivate students' labor concepts and practical abilities, labor education has gradually become an important part of modern education. At the same time, with the continuous development of artificial intelligence technology, it has become possible to apply it to the labor education evaluation system.

[0003] The existing labor education evaluation system mainly evaluates students' labor performance through teachers. This evaluation method has the disadvantage of strong subjectivity, which will affect the fairness and accuracy of the evaluation results. In addition, the existing labor education evaluation system also lacks a comprehensive evaluation of students' labor concepts and practical abilities, and cannot fully stimulate students' enthusiasm for labor. At the same time, the existing labor education evaluation system also lacks data-based management of students' labor performance, and cannot achieve dynamic tracking and management of students' labor performance. Therefore, the existing labor education evaluation system can no longer meet the needs of modern education, and a new labor education evaluation system is urgently needed to solve these problems. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides an intelligent system for evaluating labor education.

[0005] In order to achieve the above-mentioned object of the invention, the technical solution adopted by the present invention is: A labor education evaluation intelligent system, including an authority management unit, a labor education management unit, a points service unit and a data monitoring unit; The authority management unit is used to construct an authority management model based on a one-way left-biased tree, and use the authority management model to determine the authority of intelligent evaluation of labor education; The labor education management unit is used to set the labor education semester plan score of the students, obtain the labor education course data of the students, input the labor education evaluation data according to the labor education intelligent evaluation authority and the labor education course data of the students, and use the natural language processing method to generate the labor education semester evaluation results from the labor education evaluation data; The points service unit is used to generate the labor education points of students according to their labor education course data, and to generate the score achievement results of students according to their labor education semester plan scores and their labor education points; The data monitoring unit is used to visualize the evaluation results of the labor education semester and the students’ score achievement results for real-time viewing.

[0006] Furthermore, in the permission management unit, a permission management model is constructed according to a one-way left-biased tree, which is expressed as:

[0007] in: It is the constructor of the permission management model. is the node value of the current labor education intelligent evaluation authority, is the collection of all labor education intelligent evaluation authority node values, is an empty set, It is a function for generating the value of the authority node of labor education intelligent evaluation. is the left child node value of the labor education intelligent evaluation authority. It is the collection of all left child node values ​​of labor education intelligent evaluation authority.

[0008] Furthermore, the labor education management unit includes a labor education course module, a labor education plan module, and a labor education evaluation module; The labor education course module is used to obtain students' labor education course data; The labor education plan module is used to set the labor education semester plan score for students; The labor education evaluation module is used to input labor education evaluation data according to the labor education intelligent evaluation authority and the students' labor education course data, and generate labor education semester evaluation results using natural language processing based on the labor education semester plan scores and the labor education evaluation data.

[0009] Furthermore, in the labor education course module, the labor education course data of students is obtained, specifically: Render the course information to the student end in a waterfall flow to obtain the student end registration data. The course information includes course time, course location, course person in charge, course cover and detailed description; Set the registration conditions for labor education courses, and filter the student registration data based on the registration conditions for labor education courses; A sign-in code is issued to students who pass the registration screening to obtain the sign-in data on the student side, and the student's labor education course data is obtained based on the sign-in data on the student side.

[0010] Furthermore, the course information is rendered to the student end in a waterfall flow, specifically: Get the course browsing data of the student side, expressed as:

[0011] in: is the pixel difference of the distance the user scrolls the wheel during the time period. The number of milliseconds after the page is loaded. for The height pixel value of the pulley after milliseconds, The initial height pixel value of the scroll wheel; The course browsing data on the student side is derived to obtain the conditional data for course browsing, which is expressed as:

[0012] in: Conditional data for course browsing; When the conditional data of course browsing is equal to 0, let the number of milliseconds after the page is loaded be ,right Take the left and right limits:

[0013]

[0014] in: is the left limit value, is the right limit value, for Approaching from the left , for Approaching from the right ; When the left limit value is equal to the right limit value, the course information is requested from the backend based on the throttling limit and added to the waterfall queue; Set the throttling function, expressed as:

[0015] in: is the throttling value, for Throttling within a time period, for The number of times the left limit value is equal to the right limit value within the time period; Build a model to request course information from the backend, represented as:

[0016] in: is the number of backend data pages, is the number of data requests, For the Page No. courses; The model that requests course information from the backend is used to add the course information to the waterfall queue, and the throttling function is used to control the waterfall queue to render the course information to the student end.

[0017] Furthermore, in the labor education plan module, students' labor education semester plan scores include public service labor scores, labor theory learning scores, daily life labor scores, production on-the-job labor scores and social practice scores.

[0018] Furthermore, in the labor education evaluation module, the natural language processing method is used to generate the labor education semester evaluation results, specifically: Perform Chinese word segmentation on the labor education evaluation data to obtain the segmentation path with the highest probability, which is expressed as:

[0019] in: is the segmentation path with the largest conditional probability among the segmentation paths, is the conditional probability of the segmentation path, For all the paths of segmenting the labor education evaluation data, To provide evaluation data for labor education; The conditional probability of the segmentation path is calculated according to the Bayesian formula, which is expressed as:

[0020] in: is the normalized labor education evaluation data, is the probability model of the segmentation path, Always 1; The probability model of the segmentation path is constructed using the N-gram model, which is expressed as:

[0021] in: is the total number of segmentation paths, is the number of the segmentation path, For before given The first segmentation path The probability of a segmentation path appearing; Based on the Viterbi algorithm, the optimal part-of-speech tag sequence and its probability at each segmentation position are calculated to perform part-of-speech tagging on the evaluation words in the segmentation path, which is expressed as:

[0022] in: To evaluate the part-of-speech tag corresponding to the word, is the initial probability vector of the part-of-speech tag, Part-of-speech tags As the initial probability of the first word of the sentence, is the number of part-of-speech tags, is the transition probability matrix between part-of-speech tags, From the part-of-speech tag Move to part-of-speech tags The probability of is the emission probability matrix of part-of-speech tags to words, The segmentation path with the largest conditional probability among the segmentation paths Middle words; Standardization and feature extraction are performed based on part-of-speech tagging, and text generation is performed using the HMM model in natural language processing to generate the evaluation results of the labor education semester.

[0023] The present invention has the following beneficial effects: (1) The labor education management unit provided by the present invention obtains the labor education course data of the students, inputs the labor education evaluation data according to the labor education intelligent evaluation authority and the labor education course data of the students, and uses the natural language processing method to generate the labor education semester evaluation results from the labor education evaluation data, thereby avoiding the disadvantage of strong subjectivity in the traditional evaluation method and improving the fairness and accuracy of the evaluation results; (2) The present invention sets the students' labor education semester plan scores as public service labor scores, labor theory learning scores, daily life labor scores, production post labor scores and social practice scores in the labor education plan module, and then obtains the compliance status of each score. It can comprehensively focus on the comprehensive evaluation of students' public service labor, labor theory learning, daily life labor, production post labor and social practice, fully stimulate students' labor enthusiasm, and improve the quality and effect of labor education; (3) The present invention visualizes the evaluation results of the labor education semester and the students' score achievement results by setting up a data monitoring unit for real-time viewing, thereby realizing dynamic tracking and management of students' labor performance, making it easier for teachers and education managers to understand and grasp students' labor performance, and to identify problems and take measures in a timely manner; (4) The labor education evaluation intelligent system of the present invention utilizes natural language processing to generate labor education semester evaluation results from labor education evaluation data, thereby realizing the intelligence of the labor education evaluation process, improving evaluation efficiency, and reducing the workload of teachers and education administrators. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a schematic diagram of the structure of a labor education evaluation intelligent system. DETAILED DESCRIPTION

[0025] The specific implementation modes of the present invention are described below so that those skilled in the art can understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

[0026] like Figure 1 As shown, a labor education evaluation intelligent system includes an authority management unit, a labor education management unit, a points service unit and a data monitoring unit.

[0027] In an optional embodiment of the present invention, the permission management unit is used to construct a permission management model based on a one-way left-biased tree, and use the permission management model to determine the labor education intelligent evaluation permission.

[0028] In the rights management unit of the present invention, a rights management model is constructed according to a unidirectional left-biased tree, which is expressed as:

[0029] in: It is the constructor of the permission management model. is the node value of the current labor education intelligent evaluation authority, is the collection of all labor education intelligent evaluation authority node values, is an empty set, It is a function for generating the value of the authority node of labor education intelligent evaluation. is the left child node value of the labor education intelligent evaluation authority. It is the collection of all left child node values ​​of labor education intelligent evaluation authority.

[0030] In an optional embodiment of the present invention, the labor education management unit is used to set the student's labor education semester plan score, obtain the student's labor education course data, input the labor education evaluation data according to the labor education intelligent evaluation authority and the student's labor education course data, and use natural language processing to generate a labor education semester evaluation result from the labor education evaluation data.

[0031] The labor education management unit includes the labor education curriculum module, the labor education plan module and the labor education evaluation module.

[0032] The labor education course module is used to obtain the labor education course data of students. In the labor education course module, the present invention obtains the labor education course data of students, specifically: The course information is rendered to the student side in a waterfall flow to obtain the student registration data. The course information includes course time, course location, course person in charge, course cover and detailed description.

[0033] The present invention renders the course information to the student end in a waterfall flow manner, specifically: Get the course browsing data of the student side, expressed as:

[0034] in: is the pixel difference of the distance the user scrolls the wheel during the time period. The number of milliseconds after the page is loaded. for The height pixel value of the pulley after milliseconds, The initial height pixel value of the scroll wheel.

[0035] The course browsing data on the student side is derived to obtain the conditional data for course browsing, which is expressed as:

[0036] in: Conditional data browsed for the course.

[0037] When the conditional data of course browsing is equal to 0, let the number of milliseconds after the page is loaded be ,right Take the left and right limits:

[0038]

[0039] in: is the left limit value, is the right limit value, for Approaching from the left , for Approaching from the right .

[0040] When the monitored left limit value is equal to the right limit value, the course information is requested from the backend based on the throttling limit and added to the waterfall queue.

[0041] Set the throttling function, expressed as:

[0042] in: is the throttling value, for Throttling within a time period, for The number of times the left limit is equal to the right limit within the time period.

[0043] Build a model to request course information from the backend, represented as:

[0044] in: is the number of backend data pages, is the number of data requests, For the Page No. courses.

[0045] The model that requests course information from the backend is used to add the course information to the waterfall queue, and the throttling function is used to control the waterfall queue to render the course information to the student end.

[0046] Set the registration conditions for the labor education course, and filter the student-side registration data based on the registration conditions for the labor education course.

[0047] A sign-in code is issued to students who pass the registration screening to obtain the sign-in data on the student side, and the student's labor education course data is obtained based on the sign-in data on the student side.

[0048] The labor education plan module is used to set the labor education semester plan score of the students. In the labor education plan module of the present invention, the labor education semester plan score of the students includes public service labor score, labor theory learning score, daily life labor score, production post labor score and social practice score.

[0049] The labor education evaluation module is used to input labor education evaluation data according to the labor education intelligent evaluation authority and the students' labor education course data, and generate labor education semester evaluation results using natural language processing based on the labor education semester plan scores and the labor education evaluation data.

[0050] In the labor education evaluation module, the present invention uses natural language processing to generate the labor education semester evaluation results, specifically: Perform Chinese word segmentation on the labor education evaluation data to obtain the segmentation path with the highest probability, which is expressed as:

[0051] in: is the segmentation path with the largest conditional probability among the segmentation paths, is the conditional probability of the segmentation path, For all the paths of segmenting the labor education evaluation data, It is the evaluation data of labor education.

[0052] The conditional probability of the segmentation path is calculated according to the Bayesian formula, which is expressed as:

[0053] in: is the normalized labor education evaluation data, is the probability model of the segmentation path, Always 1.

[0054] The probability model of the segmentation path is constructed using the N-gram model, which is expressed as:

[0055] in: is the total number of segmentation paths, is the number of the segmentation path, For before given The first segmentation path The probability of a segmentation path appearing.

[0056] Based on the Viterbi algorithm, the optimal part-of-speech tag sequence and its probability at each segmentation position are calculated to perform part-of-speech tagging on the evaluation words in the segmentation path, which is expressed as:

[0057] in: To evaluate the part-of-speech tag corresponding to the word, is the initial probability vector of the part-of-speech tag, Part-of-speech tags As the initial probability of the first word of the sentence, is the number of part-of-speech tags, is the transition probability matrix between part-of-speech tags, From the part-of-speech tag Move to part-of-speech tags The probability of is the emission probability matrix of part-of-speech tags to words, The segmentation path with the largest conditional probability among the segmentation paths Middle words.

[0058] Standardization and feature extraction are performed based on part-of-speech tagging, and text generation is performed using the HMM (Hidden Markov Model) model in natural language processing to generate the evaluation results of the labor education semester.

[0059] In an optional embodiment of the present invention, the points service unit is used to generate the student's labor education points based on the student's labor education course data, and generate the student's score achievement result based on the student's labor education semester plan score and the student's labor education points.

[0060] In an optional embodiment of the present invention, the data monitoring unit is used to visualize the evaluation results of the labor education semester and the students' score achievement results for real-time viewing.

[0061] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0064] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0065] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A labor education evaluation intelligent system, characterized by: It includes the authority management unit, labor education management unit, points service unit and data monitoring unit; The authority management unit is used to construct an authority management model based on a one-way left-biased tree, and use the authority management model to determine the authority of intelligent evaluation of labor education; The labor education management unit is used to set the labor education semester plan score of the students, obtain the labor education course data of the students, input the labor education evaluation data according to the labor education intelligent evaluation authority and the labor education course data of the students, and use the natural language processing method to generate the labor education semester evaluation results from the labor education evaluation data; The points service unit is used to generate the labor education points of students according to their labor education course data, and to generate the score achievement results of students according to their labor education semester plan scores and their labor education points; The data monitoring unit is used to visualize the evaluation results of the labor education semester and the students’ score achievement results for real-time viewing.

2. The labor education evaluation intelligent system according to claim 1 is characterized in that: In the permission management unit, the permission management model is constructed according to the one-way left-biased tree, which is expressed as: in: It is the constructor of the permission management model. is the node value of the current labor education intelligent evaluation authority, is the collection of all labor education intelligent evaluation authority node values, is an empty set, It is a function for generating the value of the authority node of labor education intelligent evaluation. is the left child node value of the labor education intelligent evaluation authority. It is the collection of all left child node values ​​of labor education intelligent evaluation authority.

3. The labor education evaluation intelligent system according to claim 1 is characterized in that: The labor education management unit includes the labor education course module, the labor education plan module and the labor education evaluation module; The labor education course module is used to obtain students' labor education course data; The labor education plan module is used to set the labor education semester plan score for students; The labor education evaluation module is used to input labor education evaluation data according to the labor education intelligent evaluation authority and the students' labor education course data, and generate labor education semester evaluation results using natural language processing based on the labor education semester plan scores and the labor education evaluation data.

4. The labor education evaluation intelligent system according to claim 3 is characterized in that: In the labor education course module, obtain the students' labor education course data, specifically: Render the course information to the student end in a waterfall flow to obtain the student end registration data. The course information includes course time, course location, course person in charge, course cover and detailed description; Set the registration conditions for labor education courses, and filter the student registration data based on the registration conditions for labor education courses; A sign-in code is issued to students who pass the registration screening to obtain the sign-in data on the student side, and the student's labor education course data is obtained based on the sign-in data on the student side.

5. The labor education evaluation intelligent system according to claim 4 is characterized in that: Render the course information to the student end in a waterfall flow, specifically: Get the course browsing data of the student side, expressed as: in: is the pixel difference of the distance the user scrolls the wheel during the time period. The number of milliseconds after the page is loaded. for The height pixel value of the pulley after milliseconds, The initial height pixel value of the scroll wheel; The course browsing data on the student side is derived to obtain the conditional data for course browsing, which is expressed as: in: Conditional data for course browsing; When the conditional data of course browsing is equal to 0, let the number of milliseconds after the page is loaded be ,right Take the left and right limits: in: is the left limit value, is the right limit value, for Approaching from the left , for Approaching from the right ; When the left limit value is equal to the right limit value, the course information is requested from the backend based on the throttling limit and added to the waterfall queue; Set the throttling function, expressed as: in: is the throttling value, for Throttling within a time period, for The number of times the left limit value is equal to the right limit value within the time period; Build a model to request course information from the backend, represented as: in: is the number of backend data pages, is the number of data requests, For the Page No. courses; The model that requests course information from the backend is used to add the course information to the waterfall queue, and the throttling function is used to control the waterfall queue to render the course information to the student end.

6. The labor education evaluation intelligent system according to claim 3 is characterized in that: In the labor education plan module, students' labor education semester plan scores include public service labor scores, labor theory learning scores, daily life labor scores, production on-the-job labor scores and social practice scores.

7. The labor education evaluation intelligent system according to claim 3 is characterized in that: In the labor education evaluation module, the natural language processing method is used to generate the evaluation results of the labor education semester, specifically: Perform Chinese word segmentation on the labor education evaluation data to obtain the segmentation path with the highest probability, which is expressed as: in: is the segmentation path with the largest conditional probability among the segmentation paths, is the conditional probability of the segmentation path, For all the paths of segmenting the labor education evaluation data, To provide evaluation data for labor education; The conditional probability of the segmentation path is calculated according to the Bayesian formula, which is expressed as: in: is the normalized labor education evaluation data, is the probability model of the segmentation path, Always 1; The probability model of the segmentation path is constructed using the N-gram model, which is expressed as: in: is the total number of segmentation paths, is the number of the segmentation path, For before given The first segmentation path The probability of a segmentation path appearing; Based on the Viterbi algorithm, the optimal part-of-speech tag sequence and its probability at each segmentation position are calculated to perform part-of-speech tagging on the evaluation words in the segmentation path, which is expressed as: in: To evaluate the part-of-speech tag corresponding to the word, is the initial probability vector of the part-of-speech tag, Part-of-speech tags As the initial probability of the first word of the sentence, is the number of part-of-speech tags, is the transition probability matrix between part-of-speech tags, From the part-of-speech tag Move to part-of-speech tags The probability of is the emission probability matrix of part-of-speech tags to words, The segmentation path with the largest conditional probability among the segmentation paths Middle words; Standardization and feature extraction are performed based on part-of-speech tagging, and text generation is performed using the HMM model in natural language processing to generate the evaluation results of the labor education semester.

Images