Medical experiment teaching closed-loop system based on AI

Abstract

The invention discloses a medical experiment teaching closed-loop system based on AI, and belongs to the technical field of medical education. Comprising an AI experiment preview auxiliary module, an AI experiment operation evaluation module, an AI experiment report marking module and a teaching data analysis and decision module, and when the system works, an experiment preview stage, an experiment operation stage, an experiment report writing stage and a teaching decision adjustment stage are included; in the experiment preview stage, the user is guided to preview according to the teaching strategy, the misoperation rate of the user in the experiment operation stage is reduced, the writing quality of the user in the experiment report writing stage is further improved, and in the teaching strategy adjustment stage, the teaching strategy is adjusted according to the experiment report, so that a teaching closed loop with mutual correlation promotion is formed. According to the invention, all teaching links are organically combined to form a complete teaching closed loop. All links are mutually associated and promoted, the teaching process is continuously optimized through analysis and feedback of AI on teaching data, and the teaching quality and efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical education, and particularly to a closed-loop system for medical experimental teaching based on AI. Background Art

[0002] In the field of medical education, experimental teaching is a key link in cultivating the practical ability and scientific research quality of medical professionals. However, there are many limitations in the traditional medical experimental teaching mode.

[0003] During the teaching process, the guidance of experimental operations mainly relies on on-site demonstrations and one-on-one guidance by teachers. Due to the limited energy of teachers, it is impossible to supervise and guide the operations of each student in real time and comprehensively, resulting in the errors made by students during the operations being difficult to correct in time, which affects the teaching effect. The marking of experimental reports is also mainly completed manually by teachers. This not only consumes a large amount of time and energy of teachers, but also due to the difficulty in completely unifying the evaluation criteria, the evaluation results have a certain degree of subjectivity and cannot accurately measure the learning achievements and scientific research capabilities of students.

[0004] With the development of educational informatization, although some auxiliary teaching tools have emerged, these tools often have single functions, lack systematicness and coherence, and cannot achieve effective connection and coordination of all teaching links. For example, some online learning platforms only provide course videos and simple test functions, and cannot provide real-time feedback and guidance on students' experimental operations; some auxiliary marking tools for experimental reports can only perform simple text duplication checking and are difficult to deeply analyze the scientificity, logic, etc. of experimental contents.

[0005] The rapid development of AI technology provides a new opportunity to solve these problems. However, at present, in medical experimental teaching, the application of AI technology is still in the exploration stage, and a complete and efficient closed-loop teaching system has not been formed, so the advantages of AI technology in improving teaching quality and efficiency cannot be fully utilized. Summary of the Invention

[0006] The object of the present invention is to overcome the deficiencies of the prior art, provide a closed-loop system for medical experiment teaching based on AI, and solve the problems existing in the process of medical experiment teaching, such as low efficiency, inaccurate evaluation, and disjointed teaching links. By using AI technology, the intelligentization of experiment teaching is realized, the teaching efficiency is improved, and the workload of teachers is reduced. The AI automatically evaluates the standardization of students' experimental operations, gives students feedback and guidance in a timely manner, so that students can correct mistakes in a timely manner and improve their experimental skills. The automatic and accurate grading of experimental reports is realized, and objective and comprehensive evaluation results are generated, accurately reflecting the learning situation and scientific research ability of students. Create a complete teaching closed-loop covering experimental preview, operation, report writing and evaluation, with each link closely connected and promoting each other. By analyzing the data of students in each link through AI, teaching decision support is provided for teachers, personalized teaching is realized, the learning needs of different students are met, and the quality of medical experiment teaching is comprehensively improved.

[0007] The object of the present invention is achieved through the following technical solutions: A closed-loop system for medical experiment teaching based on AI, including: An AI experimental preview assistance module, which is used to provide intelligent preview services for users using natural language processing methods and medical knowledge bases, and recommend personalized preview materials according to users' questions and learning progress; An AI experimental operation evaluation module, which is used to use computer vision recognition methods and machine learning algorithms to monitor and evaluate the experimental operation process of users in real time, and guide users in real time according to the evaluation results to correct incorrect operations; An AI experimental report grading module, which is used to grade the experimental reports submitted by users using natural speech processing methods and deep learning algorithms. First, the experimental reports are checked for plagiarism, then analyzed from multiple experimental dimensions, then an evaluation report is generated according to the grading results, and finally the administrator reviews and confirms; A teaching data analysis and decision-making module, which is used to collect and integrate the data generated by users in each link of the experiment, and use data analysis algorithms for in-depth mining and analysis. The administrator specifies personalized teaching strategies for each user according to the analysis results; When the system works, it includes an experimental preview stage, an experimental operation stage, an experimental report writing stage, and a teaching decision adjustment stage; in the experimental preview stage, users are guided to preview according to the teaching strategy, reducing the error operation rate of users in the experimental operation stage, thereby improving the writing quality of users in the experimental report writing stage. The teaching strategy adjustment stage adjusts the teaching strategy according to the experimental report, thus forming a mutually related and promoting teaching closed-loop.

[0008] Preferably, the experimental preview stage includes the following steps: The user logs in to the teaching system and enters the AI experiment preview assistance module. The user inputs experiment-related questions, and the AI experiment preview assistance module answers the questions and recommends preview materials. After the user studies the preview materials and completes the preview test, the AI experiment preview assistance module judges the user's preview situation based on the test results and synchronizes the data to the teaching data analysis and decision-making module.

[0009] Preferably, the experimental operation stage includes the following steps: The user conducts experimental operations in the laboratory. The AI experimental operation evaluation module collects operation videos through a camera and conducts real-time analysis and evaluation. During the operation process, the AI experimental operation evaluation module gives the user guidance in real time according to the evaluation results. After the experiment ends, the AI experimental operation evaluation module generates an operation score and uploads the operation data to the teaching data analysis and decision-making module.

[0010] Preferably, the experimental report writing stage includes the following steps: After the user completes the experimental report, it is submitted to the AI experimental report grading module for duplicate checking and grading to generate an evaluation report. The administrator logs in to the teaching system, reviews and adjusts the grading results, and feeds back the reviewed and adjusted evaluation report to the user. At the same time, the generated data is recorded in the teaching data analysis and decision-making module.

[0011] Preferably, the teaching decision-making adjustment stage includes the following steps: The teaching data analysis and decision-making module analyzes the user data collected. The administrator adjusts the teaching strategies for each user according to the analysis results.

[0012] Preferably, the experimental dimensions include experimental purpose, experimental method, experimental results, and experimental discussion.

[0013] The beneficial effects of the present invention are: 1) Improve teaching efficiency: The AI automatically completes tasks such as experimental operation evaluation and experimental report grading, greatly reducing the workload of teachers. Compared with the traditional teaching mode, teachers do not need to spend a lot of time on repeated operation guidance and report grading, and can invest more energy in the design of teaching content and personalized guidance for students. For example, in a class of 50 students, the traditional experimental report grading method requires teachers to spend several hours, while using this system, the AI grading only takes more than ten minutes, and teachers only need to conduct a simple review, greatly improving the teaching efficiency.

[0014] 2) Accurately evaluate students' learning outcomes: The AI evaluates students' experimental operations and reports based on objective algorithms and standards, avoiding the influence of teachers' subjective factors and making the evaluation results more accurate and objective. The AI can comprehensively evaluate students' learning outcomes from multiple dimensions, provide detailed feedback and improvement suggestions for students, help students better understand their learning situations, and clarify the direction of their efforts. For example, in the review of experimental reports, the AI can accurately point out the problems existing in aspects such as students' experimental method design, data processing, and result analysis, while traditional teacher reviews may miss some detailed problems.

[0015] 3) Implement personalized teaching: Through the teaching data analysis and decision-making module, teachers can formulate personalized teaching strategies according to the learning data of each student to meet the learning needs of different students. For students with a faster learning progress, teachers can provide more challenging learning tasks and extended materials; for students with learning difficulties, teachers can give more tutoring and support. This personalized teaching method can improve students' learning enthusiasm and learning effects, and promote the all-round development of students.

[0016] 4) Form a complete teaching closed-loop: This system organically combines teaching links such as experimental preview, operation, report writing, and evaluation to form a complete teaching closed-loop. Each link is interrelated and promotes each other. Through the analysis and feedback of teaching data by the AI, the teaching process is continuously optimized, and the teaching quality is improved. In the traditional teaching mode, each teaching link is relatively independent, lacking an effective data sharing and feedback mechanism, and it is difficult to achieve continuous improvement of teaching. Brief Description of the Drawings

[0017] Figure 1 is the system architecture diagram of the present invention; Figure 2 is the system working flow chart of the present invention. Detailed Embodiment

[0018] Next, the technical solution of the present invention will be clearly and completely described in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] Refer to Figure 1 - Figure 2 , the present invention provides a technical solution: An AI-based medical experiment teaching closed-loop system, including: An AI experimental preview assistance module, used to provide intelligent preview services for users using natural language processing methods and medical knowledge bases, and recommend personalized preview materials according to users' questions and learning progress; The AI experimental operation evaluation module is used to use computer vision recognition methods and machine learning algorithms to monitor and evaluate the user's experimental operation process in real time, and provide real-time guidance to the user according to the evaluation results to correct incorrect operations; The AI experimental report grading module is used to grade the experimental reports submitted by users using natural speech processing methods and deep learning algorithms. First, it checks the experimental reports for plagiarism, then analyzes them from multiple experimental dimensions, then generates an evaluation report according to the grading results, and finally the administrator reviews and confirms it; The teaching data analysis and decision-making module is used to collect and integrate the data generated by users in each link of the experiment, and use data analysis algorithms for in-depth mining and analysis. The administrator specifies personalized teaching strategies for each user according to the analysis results; When the system works, it includes the experimental preview stage, the experimental operation stage, the experimental report writing stage, and the teaching decision-making adjustment stage; in the experimental preview stage, it guides the user to preview according to the teaching strategy, reduces the error operation rate of the user in the experimental operation stage, and then improves the writing quality of the user in the experimental report writing stage. In the teaching strategy adjustment stage, the teaching strategy is adjusted according to the experimental report, thus forming a mutually related and promoting teaching closed loop.

[0020] In this embodiment, as Figure 1 shown, the data transmission and processing of the system include a user interaction layer, a data acquisition layer, an AI function module layer, and a data storage layer; the user interaction layer includes a student end and a teacher end. Students can preview experiments, perform experimental operations, and submit experimental reports through the student end. Teachers can conduct teaching management, view students' experimental data, and review experimental report grading through the teacher end; the data acquisition layer is used to collect experimental data, experimental operations, and experimental report data; the AI function module layer is used to provide functions such as digital human tutoring, teaching data analysis, experimental operation evaluation, and experimental report grading; the data storage layer is used to store data such as course content, experimental data, operation data, and report data.

[0021] The digital human tutoring function of the AI function module layer is realized by constructing an AI digital human based on the DeepSeek large model. The AI digital human analyzes the student's usual academic performance, the key points and teaching characteristics of this experimental course based on the DeepSeek large model, and automatically generates teaching ideas and content. Through the digital teacher image on the data fusion display terminal large screen, it vividly lectures to students. During the teaching process, students can interrupt and ask questions at any time. For example, calling "Teacher Xiaomeng" can wake up the classroom Q&A function. The virtual teacher simulates the behavior of a real teacher, expands and answers relevant questions, and can adjust the teaching idea in time according to the student's questions and return to the main topic to complete the teaching task.

[0022] The hardware of the system includes devices such as bio-signal acquisition systems, cameras, microphones, and computers distributed in the laboratory, which are used to collect data such as students' operation videos and audio. In terms of software, the AI experiment preview assistance module, the AI experiment operation evaluation module, the AI experiment report grading module, and the teaching data analysis and decision-making module all run based on the software system on the server side. This software system has powerful computing and storage capabilities, supporting the efficient operation of AI algorithms and the storage and management of a large amount of teaching data. At the same time, the system has also developed client applications for students and teachers, facilitating students to preview, submit reports, and teachers to conduct teaching management and grade reports, etc.

[0023] The AI experiment preview assistance module is based on natural language processing technology and medical knowledge bases, providing intelligent preview services for students. During the preview stage, students can input questions related to the experiment, such as the experiment purpose, experiment principle, experiment steps, etc. The AI automatically retrieves relevant information from the medical knowledge base and presents it to students in a concise and clear manner. At the same time, the AI can also recommend personalized preview materials for students according to their questions and learning progress, such as relevant experiment videos, literature, etc. For example, when students preview the "regulation of rabbit arterial blood pressure" experiment, the AI can not only explain the experiment principle in detail but also recommend some frontier research literature on cardiovascular physiological mechanisms to help students broaden their knowledge.

[0024] The AI experiment operation evaluation module uses computer vision technology and machine learning algorithms to monitor and evaluate students' experiment operation processes in real time. During the experiment, multiple cameras distributed in the laboratory collect students' operation videos. The AI analyzes the videos to identify the experimental instruments used by students, operation steps, and the standardization of operations. For example, for the operation step of "isolating the rabbit vagus nerve", the AI can accurately judge whether the student's operation method is correct and whether the nerve has been damaged. At the same time, the AI can also give students voice prompts and guidance in real time according to the evaluation results to help students correct incorrect operations in a timely manner. After the experiment, the AI comprehensively scores the entire experiment operation process to form a student's experiment operation file.

[0025] The AI experiment report grading module uses natural language processing technology and deep learning algorithms to comprehensively and meticulously grade the experiment reports submitted by students. The AI first checks the similarity of the experiment reports to detect whether there is any plagiarism in the report content. Then, it analyzes the reports from multiple dimensions such as the experiment purpose, experiment method, experiment results, and experiment discussion. For example, in the analysis of experiment results, the AI can judge whether the students' results are reasonable and consistent with the expectations based on the experiment data; in the experiment discussion section, the AI can evaluate whether the students' analysis of the experiment results is in-depth and whether they can elaborate in combination with relevant theoretical knowledge. The AI generates a detailed evaluation report based on the grading results, including scores, existing problems, and improvement suggestions, etc., and finally the teacher reviews and confirms it.

[0026] The teaching data analysis and decision-making module collects and integrates the data generated by students in various links such as experiment preview, operation, and report writing, and uses data analysis algorithms for in-depth mining and analysis. By analyzing the students' data, teachers can understand the learning characteristics, advantages, and disadvantages of each student, so as to formulate personalized teaching strategies. For example, if it is found that a certain student is not proficient in using instruments during the experiment operation, the teacher can arrange targeted intensive training for him; for students with relatively weak logical thinking ability in writing experiment reports, the teacher can recommend relevant writing guidance materials. At the same time, the teaching data analysis and decision-making module can also evaluate the teaching effect, provide a basis for teachers to adjust teaching content and methods, and continuously optimize the teaching process.

[0027] In some embodiments, the experiment preview stage includes the following steps: The user logs in to the teaching system, enters the AI experiment preview assistance module, the user inputs experiment-related questions, and the AI experiment preview assistance module answers and recommends preview materials; After the user studies the preview materials, completes the preview test, the AI experiment preview assistance module judges the user's preview situation according to the test results, and synchronizes the data to the teaching data analysis and decision-making module.

[0028] In this embodiment, the student logs in to the teaching system and enters the AI experiment preview assistance module. The student inputs experiment-related questions, and the AI answers and recommends preview materials. After the student studies the preview materials, completes the preview test, the AI understands the student's preview situation according to the test results, and synchronizes the data to the teaching data analysis and decision-making module.

[0029] In some embodiments, the experiment operation stage includes the following steps: The user conducts experimental operations in the laboratory. The AI experimental operation evaluation module collects the operation video through the camera and conducts real-time analysis and evaluation. During the operation process, the AI experimental operation evaluation module gives the user guidance in real time according to the evaluation results. After the experiment ends, the AI experimental operation evaluation module generates an operation score and uploads the operation data to the teaching data analysis and decision-making module.

[0030] In this embodiment, the student conducts experimental operations in the laboratory. The AI experimental operation evaluation module collects the operation video through the camera and conducts real-time analysis and evaluation. During the operation process, the AI gives the student guidance and prompts in a timely manner. After the experiment ends, the AI generates an operation score and uploads the operation data to the teaching data analysis and decision-making module.

[0031] In some embodiments, the experimental report writing stage includes the following steps: After the user completes the experimental report, it is submitted to the AI experimental report grading module for duplicate checking and grading to generate an evaluation report. The administrator logs in to the teaching system, reviews and adjusts the grading results, and feeds back the reviewed and adjusted evaluation report to the user. At the same time, the generated data is recorded in the teaching data analysis and decision-making module.

[0032] In this embodiment, after the student completes the experimental report, it is submitted to the AI experimental report grading module. The AI conducts duplicate checking and grading to generate an evaluation report. The teacher logs in to the system to review the grading results of the AI and can make manual adjustments if necessary. The reviewed evaluation report is fed back to the student, and at the same time, the relevant data is also recorded in the teaching data analysis and decision-making module.

[0033] In some embodiments, the teaching decision-making adjustment stage includes the following steps: The teaching data analysis and decision-making module analyzes the collected user data, and the administrator adjusts the teaching strategy for each user according to the analysis results.

[0034] In this embodiment, the teaching data analysis and decision-making module analyzes the collected student data to provide teaching decision-making support for teachers. The teacher adjusts the teaching strategy according to the analysis results, provides personalized tutoring for students, and realizes the optimization of the teaching process and the improvement of teaching quality.

[0035] In some embodiments, the experimental dimensions include experimental purpose, experimental method, experimental results, and experimental discussion.

[0036] The above are only the preferred embodiments of the present invention. It should be understood that the present invention is not limited to the forms disclosed herein, and should not be regarded as excluding other embodiments. Instead, it can be used in various other combinations, modifications, and environments, and can be changed within the scope of the concept described herein through the above teachings or the techniques or knowledge in related fields. Any changes and variations made by those skilled in the art without departing from the spirit and scope of the present invention shall fall within the protection scope of the appended claims of the present invention.

Claims

1. An AI-based closed-loop system for medical experiment teaching, characterized in that: Including: An AI experiment preview assistance module, which uses natural language processing methods and medical knowledge bases to provide intelligent preview services for users, and recommends personalized preview materials according to users' questions and learning progress; An AI experiment operation evaluation module, which uses computer vision recognition methods and machine learning algorithms to monitor and evaluate users' experiment operation processes in real time, and provides real-time guidance to users according to the evaluation results to correct incorrect operations; An AI experiment report grading module, which uses natural speech processing methods and deep learning algorithms to grade the experiment reports submitted by users. First, it checks the similarity of the experiment reports, then analyzes them from multiple experiment dimensions, then generates an evaluation report according to the grading results, and finally the administrator reviews and confirms it; A teaching data analysis and decision-making module, which collects and integrates the data generated by users in each link of the experiment, and uses data analysis algorithms for in-depth mining and analysis. The administrator formulates personalized teaching strategies for each user according to the analysis results; When the system works, it includes an experiment preview stage, an experiment operation stage, an experiment report writing stage, and a teaching decision-making adjustment stage; in the experiment preview stage, it guides users to preview according to the teaching strategy, reduces the error operation rate of users in the experiment operation stage, and then improves the writing quality of users in the experiment report writing stage. In the teaching strategy adjustment stage, the teaching strategy is adjusted according to the experiment report, thus forming a mutually related and promoting teaching closed-loop.

2. The AI-based closed-loop medical experiment teaching system according to claim 1, wherein: The said experiment preview stage Includes the following steps: The user logs in to the teaching system and enters the AI experiment preview assistance module. The user inputs experiment-related questions, and the AI experiment preview assistance module answers and recommends preview materials; After the user learns the preview materials, completes the preview test, and the AI experiment preview assistance module judges the user's preview situation according to the test results and synchronizes the data to the teaching data analysis and decision-making module.

3. The AI-based closed-loop system for medical experiment teaching according to claim 1, wherein: The said experiment operation stage includes the following steps: The user conducts experiment operations in the laboratory. The AI experiment operation evaluation module collects operation videos through the camera and conducts real-time analysis and evaluation. During the operation process, the AI experiment operation evaluation module gives real-time guidance to the user according to the evaluation results; after the experiment ends, the AI experiment operation evaluation module generates an operation score and uploads the operation data to the teaching data analysis and decision-making module.

4. The AI-based closed-loop medical experiment teaching system according to claim 1, wherein: The said experiment report writing stage includes the following steps: After the user completes the experiment report, submits it to the AI experiment report grading module for similarity check and grading to generate an evaluation report; The administrator logs in to the teaching system, reviews and adjusts the grading results, and feeds back the reviewed and adjusted evaluation report to the user, and at the same time records the generated data into the teaching data analysis and decision-making module.

5. The AI-based closed-loop medical experiment teaching system according to claim 1, wherein: The said teaching decision-making adjustment stage includes the following steps: The teaching data analysis and decision-making module analyzes the collected user data, and the administrator adjusts the teaching strategies of each user according to the analysis results.

6. The AI-based closed-loop medical experiment teaching system according to any one of claims 1-5, characterized in that: The said experiment dimensions include experiment purpose, experiment method, experiment result, and experiment discussion.

Images