Homework correction and teaching auxiliary system based on intelligent terminal

Abstract

The invention relates to the technical field of education, in particular to a homework correction and teaching assistance system based on an intelligent terminal, which comprises a homework collection module, a multi-modal homework analysis module, an intelligent correction module, a personalized learning evaluation module, a dynamic feedback module, a teacher assistance module and a data storage and analysis module, the homework collection module is used for collecting homework submitted by students, the multi-mode homework analysis module is used for automatically identifying, classifying and analyzing homework content submitted by the students, the intelligent correction module is used for correcting the homework of the students and generating a correction report, and the personalized learning evaluation module is used for evaluating the homework of the students according to historical homework performance of the students. A personalized learning evaluation report is generated, a dynamic feedback module dynamically adjusts a learning plan, a teacher auxiliary module combines personalized learning evaluation and recommends teaching improvement measures, and a data storage and analysis module is used for long-term storage and dynamic analysis of learning evaluation data. According to the invention, informatization and intelligent management of the whole teaching process is realized.

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and in particular to a homework marking and teaching assistance system based on an intelligent terminal. Background Art

[0002] Most existing educational assistance systems focus on a single function, such as automatic homework grading or student performance tracking, and lack a comprehensive solution to fully integrate all aspects of the teaching and learning process. In addition, many existing systems are inefficient in processing diverse student assignments (such as text, images, audio and video data), and are unable to provide immediate and specific feedback. It is also difficult to provide customized learning suggestions based on students' personal performance and historical data. These limitations reduce the personalization and interactivity of teaching and also affect the improvement of education quality. Summary of the invention

[0003] The invention provides a homework marking and teaching auxiliary system based on an intelligent terminal.

[0004] The homework grading and teaching assistance system based on intelligent terminals includes a homework collection module, a multimodal homework analysis module, an intelligent grading module, a personalized learning evaluation module, a dynamic feedback module, a teacher assistance module, and a data storage and analysis module.

[0005] The homework collection module is used to collect the homework submitted by students in real time through the intelligent terminal, and uniformly format the text, picture, audio or video data of the homework;

[0006] The multimodal homework parsing module automatically identifies, classifies and parses the homework content submitted by students through image recognition, natural language processing and speech recognition technology, and generates a corresponding homework data structure;

[0007] The intelligent grading module automatically grades students' homework based on the preset standard answer library and problem-solving model, and generates a detailed grading report for each homework based on the homework analysis results and historical homework data;

[0008] The personalized learning assessment module analyzes students' knowledge mastery and learning progress based on their historical homework performance, generates personalized learning assessment reports, and puts forward targeted improvement suggestions;

[0009] The dynamic feedback module is used to push the correction results and learning suggestions to students in real time through the intelligent terminal, and receive students' feedback information to dynamically adjust the learning plan and homework requirements;

[0010] The teacher assistance module is used to provide teachers with statistical analysis of the whole class's homework situation, combine personalized learning assessment, recommend teaching improvement measures, and support teachers in adjusting personalized teaching plans;

[0011] The data storage and analysis module is used for long-term storage and dynamic analysis of students' homework data, correction data and learning evaluation data to facilitate subsequent adjustment of teaching strategies and system optimization.

[0012] Optionally, the homework collection module collects homework submitted by students in real time through smart terminals. The supported file formats include PDF, DOCX, JPG, PNG, MP3 and MP4. The module adopts efficient data compression algorithms (such as Huffman coding) to reduce bandwidth requirements during data transmission. After the homework data is uniformly formatted, it is sent to a preset central server through secure encrypted transmission for further processing.

[0013] Optionally, the multimodal job parsing module includes image recognition, natural language processing and speech recognition technologies. Image recognition uses convolutional neural networks, natural language processing uses a Transformer-based BERT model, and speech recognition is achieved through a long short-term memory network. The job data structures generated by each technology are fused with each other and unified into a structured job data through a weighted fusion algorithm (weights are determined by expert experience).

[0014] Optionally, the intelligent correction module includes:

[0015] Adaptive grading model selection: The intelligent grading module automatically selects the most appropriate grading model based on the type of homework submitted by the student. The system has multiple built-in models, including rule-based logical reasoning algorithms and statistical-based scoring systems;

[0016] Application of the grading model: For each grading model selected, implement a specific grading process;

[0017] Data integration and analysis: Combining the results of homework analysis with students' historical homework data, the intelligent grading module analyzes the degree of match between students' answers and the answers in the standard answer library. The system will consider students' error patterns and improvement trajectories in historical data and adjust the grading standards and the depth of feedback;

[0018] Generation of detailed grading reports: Based on the grading results of the above model, a detailed grading report is generated for each assignment, including the score, specific errors, improvement suggestions, and problem-solving analysis. The report will include a comprehensive evaluation of the student's performance and personalized improvement suggestions based on historical performance;

[0019] Feedback on grading results: Grading reports are automatically sent to students’ and teachers’ smart terminals through the system. Teachers can use these reports to adjust teaching strategies and content, and students can learn and improve themselves based on the feedback.

[0020] Optionally, the personalized learning assessment module uses a decision tree algorithm to analyze knowledge mastery based on students' historical homework performance. The module calculates the probability of each student mastering a knowledge point and generates a personalized learning assessment report based on the probability.

[0021] Optionally, the dynamic feedback module uses real-time messaging technology to push grading results and learning suggestions, and receives feedback information submitted by students through smart terminals, and dynamically adjusts the learning plan according to the students' feedback.

[0022] Optionally, the teacher assistance module provides a comprehensive statistical analysis platform that uses principal component analysis and cluster analysis to identify key influencing factors in teaching. The statistical reports provided by this module help teachers gain in-depth understanding of the learning status of the class as a whole and individual students, and provide teachers with customized teaching improvement suggestions.

[0023] Optionally, the data storage and analysis module adopts efficient data warehouse technology and combines real-time data stream processing and big data analysis technology to achieve efficient storage and dynamic analysis of student homework data, correction data and learning assessment data.

[0024] Beneficial effects of the present invention:

[0025] The present invention analyzes the homework content through multimodal technology, realizes automatic grading and dynamic feedback, greatly improves the grading efficiency and accuracy, and automatically generates personalized learning evaluation reports and improvement suggestions based on students' homework performance and historical data, which helps teachers to achieve targeted teaching. Through the dynamic feedback module, the system can interact with students in real time, receive their feedback and adjust the learning plan according to the feedback, thereby enhancing the flexibility and adaptability of the system. Through long-term data storage and analysis, the system can continuously optimize the grading algorithm and teaching suggestions, making teaching more accurate and efficient. The system covers the entire process from homework collection, grading, feedback to teaching improvement, and realizes the information and intelligent management of the entire teaching process. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0027] Figure 1 Schematic diagram of a system flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0029] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0030] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0031] like Figure 1 As shown, the homework grading and teaching assistance system based on the intelligent terminal includes a homework collection module, a multimodal homework analysis module, an intelligent grading module, a personalized learning evaluation module, a dynamic feedback module, a teacher assistance module and a data storage and analysis module, wherein:

[0032] The homework collection module is used to collect the homework submitted by students in real time through the intelligent terminal, and uniformly format the text, picture, audio or video data of the homework;

[0033] The multimodal homework analysis module automatically identifies, classifies and analyzes the homework content submitted by students through image recognition, natural language processing and speech recognition technology, and generates the corresponding homework data structure;

[0034] The intelligent grading module automatically grades students' homework based on the preset standard answer library and problem-solving model, and generates a detailed grading report for each homework based on the homework analysis results and historical homework data;

[0035] The personalized learning assessment module analyzes students’ knowledge mastery and learning progress based on their historical homework performance, generates personalized learning assessment reports, and puts forward targeted improvement suggestions;

[0036] The dynamic feedback module is used to push the correction results and learning suggestions to students in real time through smart terminals, receive students' feedback information, and dynamically adjust the learning plan and homework requirements;

[0037] The teacher assistance module is used to provide teachers with statistical analysis of the whole class's homework situation, combine personalized learning assessment, recommend teaching improvement measures, and support teachers in adjusting personalized teaching plans;

[0038] The data storage and analysis module is used for long-term storage and dynamic analysis of students' homework data, correction data and learning assessment data to facilitate subsequent adjustment of teaching strategies and system optimization.

[0039] The homework collection module collects homework submitted by students in real time through smart terminals. The supported file formats include PDF, DOCX, JPG, PNG, MP3 and MP4. The module uses efficient data compression algorithms (such as Huffman coding) to reduce the bandwidth requirements during data transmission. After the homework data is uniformly formatted, it is sent to the preset central server through secure encrypted transmission for further processing.

[0040] The multimodal job analysis module includes image recognition, natural language processing and speech recognition technologies. Image recognition uses convolutional neural networks, natural language processing uses the Transformer-based BERT model, and speech recognition is achieved through long short-term memory networks. The job data structures generated by each technology are integrated with each other and unified into a structured job data through a weighted fusion algorithm (weights are determined by expert experience).

[0041] The intelligent correction module includes:

[0042] Adaptive grading model selection: The intelligent grading module automatically selects the most appropriate grading model based on the type of homework submitted by the student. The system has multiple built-in models, including rule-based logical reasoning algorithms and statistical-based scoring systems;

[0043] Application of the grading model: For each grading model selected, a specific grading process is implemented. For example, for the selected scoring system, a logistic regression model is used for scoring. The model expression is:

[0044]

[0045] Among them, x represents the parsed feature vector received from the multimodal homework parsing module, and β is the model parameter. This model can quantify the score according to the characteristics of the student's homework;

[0046] Data integration and analysis: Combining the results of homework analysis with students' historical homework data, the intelligent grading module analyzes the degree of match between students' answers and the answers in the standard answer library. The system will consider students' error patterns and improvement trajectories in historical data and adjust the grading standards and the depth of feedback;

[0047] Generation of detailed grading reports: Based on the grading results of the above model, a detailed grading report is generated for each assignment, including the score, specific errors, improvement suggestions, and problem-solving analysis. The report will include a comprehensive evaluation of the student's performance and personalized improvement suggestions based on historical performance;

[0048] Feedback on grading results: Grading reports are automatically sent to students’ and teachers’ smart terminals through the system. Teachers can use these reports to adjust teaching strategies and content, and students can learn and improve themselves based on the feedback.

[0049] The personalized learning evaluation module uses a decision tree algorithm to analyze the knowledge mastery based on the student's historical homework performance. The module calculates the probability of each student mastering the knowledge point and generates a personalized learning evaluation report based on the probability. The evaluation algorithm expression is:

[0050]

[0051] Among them, α and β i are model parameters, x i is the feature vector of the student’s historical performance.

[0052] The dynamic feedback module uses real-time messaging technology to push grading results and learning suggestions. The module can also receive feedback information submitted by students through smart terminals and dynamically adjust the learning plan based on students' feedback. In addition, the module also combines user behavior analysis to optimize the timeliness and relevance of pushed content.

[0053] The teacher assistance module provides a comprehensive statistical analysis platform that uses principal component analysis and cluster analysis to identify key influencing factors in teaching. The statistical reports provided by this module help teachers gain an in-depth understanding of the learning status of the class as a whole and individual students, and provide teachers with customized teaching improvement suggestions.

[0054] The data storage and analysis module adopts efficient data warehouse technology and combines real-time data stream processing and big data analysis technology to achieve efficient storage and dynamic analysis of student homework data, correction data and learning assessment data.

[0055] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0056] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. The homework grading and teaching assistance system based on intelligent terminals is characterized by: It includes homework collection module, multimodal homework analysis module, intelligent correction module, personalized learning evaluation module, dynamic feedback module, teacher assistance module and data storage and analysis module, among which, The homework collection module is used to collect the homework submitted by students in real time through the intelligent terminal, and uniformly format the text, picture, audio or video data of the homework; The multimodal homework parsing module automatically identifies, classifies and parses the homework content submitted by students through image recognition, natural language processing and speech recognition technology, and generates a corresponding homework data structure; The intelligent grading module automatically grades students' homework based on a preset standard answer library and problem-solving model, and generates a grading report for each homework based on the homework analysis results and historical homework data; The personalized learning assessment module analyzes students' knowledge mastery and learning progress based on their historical homework performance, generates personalized learning assessment reports, and puts forward targeted improvement suggestions; The dynamic feedback module is used to push the correction results and learning suggestions to students in real time through the intelligent terminal, and receive students' feedback information to dynamically adjust the learning plan and homework requirements; The teacher assistance module is used to provide teachers with statistical analysis of the whole class's homework situation, combine personalized learning assessment, recommend teaching improvement measures, and support teachers in adjusting personalized teaching plans; The data storage and analysis module is used for long-term storage and dynamic analysis of students' homework data, correction data and learning assessment data.

2. The homework grading and teaching assistance system based on intelligent terminal according to claim 1 is characterized in that: The homework collection module collects homework submitted by students in real time through smart terminals, and supports file formats including PDF, DOCX, JPG, PNG, MP3 and MP4.

3. The homework grading and teaching assistance system based on intelligent terminal according to claim 2 is characterized in that: The multimodal job analysis module includes image recognition, natural language processing and speech recognition technologies. Image recognition uses convolutional neural networks, natural language processing uses the Transformer-based BERT model, and speech recognition is achieved through long short-term memory networks. The job data structures generated by each technology are fused with each other and unified into a structured job data through a weighted fusion algorithm.

4. The homework grading and teaching assistance system based on intelligent terminal according to claim 3 is characterized in that: The intelligent correction module includes: Adaptive grading model selection: The intelligent grading module automatically selects a grading model based on the type of homework submitted by the student. The system has multiple built-in models, including rule-based logical reasoning algorithms and statistical-based scoring systems. Application of the marking model: For each marking model selected, implement the marking process; Data integration and analysis: Combining the homework analysis results with the students’ historical homework data, the intelligent grading module analyzes the matching degree between the students’ answers and the answers in the standard answer library; Generation of detailed grading report: Based on the grading results, a grading report is generated for each assignment, including the score, errors, improvement suggestions and problem-solving analysis; Feedback on grading results: Grading reports are automatically sent to students’ and teachers’ smart terminals through the system. Teachers use the reports to adjust teaching strategies and content, and students conduct self-learning and improvement based on feedback.

5. The homework grading and teaching assistance system based on intelligent terminal according to claim 4 is characterized in that: The personalized learning assessment module uses a decision tree algorithm to analyze knowledge mastery based on students' historical homework performance, calculates the probability of each student mastering a knowledge point, and generates a personalized learning assessment report based on the probability.

6. The homework grading and teaching assistance system based on intelligent terminal according to claim 5 is characterized in that: The dynamic feedback module uses real-time messaging technology to push correction results and learning suggestions, and receives feedback information submitted by students through smart terminals, and dynamically adjusts the learning plan according to the students' feedback.

7. The homework grading and teaching assistance system based on intelligent terminal according to claim 6 is characterized in that: The teacher assistance module provides a statistical analysis platform, using principal component analysis and cluster analysis to identify influencing factors in teaching, helping teachers to gain an in-depth understanding of the learning status of the class as a whole and individual students, and providing teachers with customized teaching improvement suggestions.

8. The homework grading and teaching assistance system based on intelligent terminal according to claim 7 is characterized in that: The data storage and analysis module adopts data warehouse technology and combines real-time data stream processing and big data analysis technology to achieve the storage and dynamic analysis of student homework data, correction data and learning evaluation data.

Images