Ear-nose-throat specialized clinical teaching effect evaluation system based on artificial intelligence

Abstract

The invention provides an artificial intelligence-based ear-nose-throat specialized clinical teaching effect evaluation system. The system comprises a natural language processing module, a computer vision analysis module, a virtual patient evaluation module, an otoscope image acquisition device, an image recognition module, an intelligent scoring and feedback module, a literature retrieval scoring module, a data management module and a visual presentation module. According to the system, multi-modal data of students in the processes of voice answering, skill operation, virtual inquiry, otoscope image recognition and literature retrieval are collected, automatic analysis and scoring are carried out, an ability evaluation report and personalized feedback are generated, standardization and intelligence of teaching evaluation are achieved, and the teaching efficiency is improved. The comprehensive ability evaluation device is suitable for comprehensive ability evaluation in the ear-nose-throat specialized medical teaching process. The system has the advantages of objective scoring, efficient processing, visual feedback and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of medical education and artificial intelligence technology, in particular, to an ear-nose-throat specialized clinical teaching effect evaluation system based on artificial intelligence. BACKGROUND

[0002] In medical education, clinical teaching evaluation is an important means to ensure teaching quality and improve the comprehensive ability of medical students. Especially in standardized training of resident physicians and specialized teaching, how to accurately and comprehensively evaluate the ability of students in basic knowledge, operation skills, clinical thinking, communication skills and information retrieval has become the core problem of medical teaching reform. In recent years, with the development of artificial intelligence, big data analysis and other technologies, more and more medical education institutions have tried to introduce intelligent technology into teaching management and evaluation system to improve teaching efficiency and objectivity.

[0003] Most of the existing clinical teaching evaluation systems rely on manual scoring. Teachers make subjective judgments by observing the operation process, question and answer performance or case analysis results of students. Under the condition of heavy teaching task and evaluation pressure, this traditional method is prone to problems such as non-uniform evaluation criteria, insufficient objectivity of results and excessive burden on teachers. At the same time, for the evaluation needs of ear-nose-throat and other technology-intensive specialties, the existing systems generally lack the ability to integrate and analyze multi-modal data such as voice, image, operation trajectory and interactive behavior, making it difficult to fully reflect the comprehensive ability development of students. In addition, the emerging teaching links such as virtual case simulation, medical image recognition and retrieval training have limited support in the existing system, and there is a lack of effective automatic evaluation mechanism.

[0004] Therefore, an intelligent evaluation system for multi-modal teaching data is urgently needed in current ear-nose-throat specialized teaching, which can collect, process and analyze the multi-dimensional performance of students in real or simulated teaching tasks, so as to realize objective and consistent comprehensive evaluation, reduce the evaluation pressure of teachers and improve the accuracy and efficiency of teaching evaluation. SUMMARY

[0005] In order to solve the problems of the prior art, the embodiments of the present application provide an ear-nose-throat specialized clinical teaching effect evaluation system based on artificial intelligence. The technical solution is as follows:

[0006] An ear-nose-throat specialized clinical teaching effect evaluation system based on artificial intelligence is provided, comprising:

[0007] A natural language processing module is configured to recognize and analyze the semantic analysis of the written or spoken answers of students, and generate basic knowledge score results;

[0008] A computer vision analysis module is configured to collect operation images of students in ear-nose-throat skill training and analyze operation standardization;

[0009] a virtual patient evaluation module for constructing a virtual diagnosis environment, collecting the interactive behaviors of the trainee in the simulated diagnosis process, and evaluating the clinical decision-making ability and diagnosis logic;

[0010] an otoscope image acquisition device and an image recognition module, the device comprising an optical probe, a handle control module, and an image processing module, and the image recognition module being configured to analyze the ear canal image and output structured preliminary diagnosis information;

[0011] an intelligent scoring and feedback module for fusing the scoring data of multiple analysis modules to generate a capability radar chart and personalized learning suggestions;

[0012] a literature retrieval scoring module for evaluating the keyword setting, retrieval strategy, and literature relevance of the trainee in the information retrieval task;

[0013] a data management module for storing and desensitizing the images, voice, behavior records, and scoring results generated in the teaching process;

[0014] a visual presentation module for displaying the scoring results, capability growth trajectory chart, and recommended feedback content.

[0015] Further, the natural language processing module comprises a speech recognition unit and a semantic analysis unit, the speech recognition unit being configured to convert the voice content into text data, and the semantic analysis unit being configured to perform semantic matching between the text and the preset answer, calculate the answer point coverage rate, and generate a score.

[0016] Further, the computer vision analysis module comprises an image acquisition unit and a motion recognition unit, the motion recognition unit being configured to output operation standardization score and image feedback results based on key point tracking and standard process comparison algorithm.

[0017] Further, the virtual patient evaluation module comprises a virtual case generation unit and a behavior interaction collection unit, the virtual case generation unit being configured to generate a case scenario with specific complaints, signs, and intervention needs, and the behavior interaction collection unit being configured to record the diagnosis order, judgment path, and diagnosis decision of the trainee.

[0018] Further, the optical probe of the otoscope image acquisition device adopts a flexible structure to adapt to the curvature of the ear canal, and the image processing module comprises an image preprocessing unit, a feature extraction unit, and an image recognition unit, the image recognition unit being configured to classify and identify the lesion area in the image and generate a structured diagnosis suggestion.

[0019] Further, the intelligent scoring and feedback module comprises a data fusion unit, a capability evaluation unit and a feedback generation unit, the capability evaluation unit is used for constructing a multi-dimensional capability vector and performing cluster scoring, and the feedback generation unit is used for pushing a capability atlas and personalized recommended resources.

[0020] Further, the literature retrieval scoring module comprises a retrieval analysis unit and a relevance scoring unit, the retrieval analysis unit extracts keywords and retrieval paths set by the student, and the relevance scoring unit scores the theme matching degree and literature timeliness of the retrieval result.

[0021] Further, the data management module comprises a data acquisition unit, a data storage unit and a data security unit, the data security unit performs desensitization processing on data related to identity information, and sets an access permission control mechanism.

[0022] Further, the visualization presentation module comprises a graph generation unit and an interface display unit, the graph generation unit is used for generating column charts, radar charts, growth curve charts and other graphical results, and the interface display unit is used for pushing the evaluation result to the student end and the teacher end.

[0023] Further, the handle control module of the otoscope image acquisition device is internally provided with a wireless transmission module and a pressure sensor, and the pressure sensor is used for detecting the force change in the process of inserting into the ear canal to prevent damage caused by deep operation.

[0024] The technical scheme provided by the embodiment of the present application has the following beneficial effects:

[0025] The present application provides an otolaryngology clinical teaching effect evaluation system based on artificial intelligence, by constructing a natural language processing module, a computer vision analysis module, a virtual patient evaluation module, an otoscope image recognition module, an intelligent scoring and feedback module, a literature retrieval scoring module, a data management module and a visualization presentation module, the automatic acquisition, intelligent analysis and graphical feedback of multi-modal behavior data in the whole process of otolaryngology teaching are realized, and the objectivity, accuracy and practicability of evaluation are improved.

[0026] The natural language processing module in the system of the present application can realize semantic recognition and scoring of student speech answers and written expression contents, the computer vision analysis module can recognize the action standardization in skill operation, the virtual patient evaluation module can carry out dynamic case simulation and emergency response training, the otoscope image recognition module has the lesion analysis capability for ear canal images, and the literature retrieval scoring module can quantitatively evaluate the information retrieval strategy and result quality of the student. The modules are cooperatively operated, fused and analyzed by the intelligent scoring and feedback module, a structured capability evaluation report and personalized learning suggestions are generated, and output to the visualization module for unified display.

[0027] Through the above-mentioned multi-module integration and intelligent analysis mechanism, this invention not only improves the efficiency of clinical teaching assessment and reduces the subjective scoring burden of teachers, but also realizes the quantitative tracking and growth prediction of trainees' knowledge, skills and thinking abilities. It has good prospects for promotion and application, and is particularly suitable for standardized training of resident physicians and digital teaching reform in otolaryngology. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a schematic diagram of a module of an artificial intelligence-based clinical teaching effectiveness evaluation system for otolaryngology, according to an embodiment of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0031] like Figure 1 As shown, the present invention provides an artificial intelligence-based clinical teaching effect evaluation system for otolaryngology, which is divided into three layers according to its functional architecture: user interaction layer, intelligent processing layer and data presentation layer. Each layer undertakes different functions such as information collection, intelligent analysis and result output.

[0032] At the user interaction layer, the system is equipped with a voice input acquisition module, an image acquisition device, and a virtual operation and consultation interface, which are used to collect raw operation data of trainees in the clinical teaching process, including voice, image, and behavioral data in oral answers, skill demonstrations, and simulated consultations.

[0033] At the intelligent processing layer, the system relies on multiple artificial intelligence analysis modules to process the collected data, including a natural language processing module, a computer vision analysis module, an otoscopy image recognition module, and a virtual patient assessment module, corresponding to core tasks such as knowledge quiz scoring, operational standardization analysis, image diagnosis recognition, and simulated case assessment, respectively. The results output from these modules are further aggregated into the intelligent scoring and feedback module, which completes the multi-dimensional capability fusion assessment and personalized feedback generation.

[0034] In the data presentation layer, the intelligent scoring results are transmitted to the data management module, the visual presentation module, and the literature retrieval scoring module respectively. Among them, the data management module archives the evaluation records and constructs the student growth trajectory; the visual presentation module outputs graphical reports to support multi-dimensional viewing on the student and teacher ends; the literature retrieval scoring module is used to evaluate the student's ability in medical information acquisition and outputs the relevance score combined with the task theme. At the same time, the system also includes the ability growth trajectory analysis and graphical report output function to support comprehensive teaching evaluation and tracking analysis.

[0035] The overall system structure is clear in logic and smooth in data flow, which can realize the closed-loop evaluation process from input collection, intelligent processing to result feedback, and has good implementability and promotion value.

[0036] Based on the overall system structure, the structure composition and technical implementation of each functional module are described in detail as follows.

[0037] I. Implementation of natural language processing module

[0038] The natural language processing module is deployed between the user interaction layer and the intelligent processing layer, which is used to automatically score the student's written answers and voice answers. The module includes a speech recognition unit and a semantic analysis unit:

[0039] The speech recognition unit receives the student's voice input in the basic knowledge evaluation link, uses a speech recognition model specialized in the medical field to transcribe the speech, and generates structured text;

[0040] The semantic analysis unit calls the medical knowledge graph and the reference answer library, scores the text content according to the preset knowledge points and semantic matching rules, and outputs the score and coverage report of each question.

[0041] This module supports the recognition and correction of common medical terminology and synonymous expressions to ensure the accuracy and fairness of the scoring results.

[0042] II. Implementation of computer vision analysis module

[0043] The computer vision analysis module mainly faces the skill training evaluation of ear-nose-throat routine examination operation, and uses image recognition and posture analysis technology to score the operation process. The module is composed of an image acquisition unit and a motion recognition unit:

[0044] The image acquisition unit accesses the video acquisition device of the classroom or skill training table to record the whole process of the student's operation;

[0045] The action recognition unit adopts a skeleton point extraction and trajectory analysis algorithm to recognize a hand action path, an instrument use mode, and an operation sequence, and compare them with a standard operation database to calculate an operation standardization score.

[0046] The system can identify common errors such as "inappropriate tongue pressing", "missing operation sequence", and "deviation of mirror angle" in items such as nasal mirror insertion and pharyngeal examination, and provide image feedback prompts.

[0047] III. Embodiment of virtual patient evaluation module

[0048] The virtual patient evaluation module is based on virtual reality (VR) or augmented reality (AR) technology, simulates common ear-nose-throat clinical conditions, and constructs a diagnostic operation environment. The module includes a virtual case generation unit and a behavior interaction acquisition unit:

[0049] The virtual case generation unit dynamically generates a case with specific complaints, signs, and diagnosis and treatment intervention requirements according to the training target and student level;

[0050] The behavior interaction acquisition unit acquires and analyzes the inquiry sequence, decision logic, and response process of the student in the virtual scene.

[0051] The module can simulate sudden deafness, acute laryngeal obstruction, etc. to realize comprehensive evaluation of emergency response, communication skills and logical judgment ability.

[0052] IV. Embodiment of otoscope image acquisition device and image recognition module

[0053] The otoscope image acquisition device is a portable medical examination tool with intelligent image processing and local analysis capabilities, suitable for ear canal image acquisition and lesion analysis. The device structure includes:

[0054] Optical probe: The front end integrates a high-resolution miniature camera and a multi-angle cold light source. After image acquisition, the image is sent to the processing module in real time;

[0055] Handle control module: integrated with microprocessor, photographing button and wireless transmission component;

[0056] Image recognition module: including image preprocessing unit, feature extraction unit and lesion recognition unit. Image preprocessing improves image quality through image enhancement and correction algorithm, feature extraction identifies information such as tympanic membrane shape, perforation edge and blood vessel distribution, and the recognition module uses multi-label classification algorithm to output preliminary diagnosis results and generate structured reports.

[0057] At the same time, the device structure has a flexible snake bone tube design and a pressure sensor, which realizes the adaptation to the physiological morphology of the ear canal and the real-time monitoring of the insertion force, and improves the operation safety.

[0058] V. Implementation of the Intelligent Scoring and Feedback Module

[0059] The intelligent scoring and feedback module is located in the intelligent processing layer of the system, and is used for fusion processing of the scoring results of each analysis module, and outputs a comprehensive ability evaluation and personalized learning suggestion. The module includes the following three functional units:

[0060] The data fusion unit receives the scoring data of the natural language processing module, the computer vision analysis module, the otoscope image recognition module, and the virtual patient evaluation module, standardizes the data using a unified dimension standard, and constructs a multi-dimensional ability vector of the student.

[0061] The ability evaluation unit calls an evaluation model based on machine learning to cluster analyze and grade the student's knowledge mastery, operation standardization, clinical thinking ability, and information integration ability, and generates a comprehensive score.

[0062] The feedback generation unit outputs an ability radar chart, a stage growth curve, and a weak skill point prompt based on the score results, and automatically matches and recommends learning resources such as special video courses and modular training question sets, to guide the personalized teaching path.

[0063] The module keeps synchronization with the teaching task process during system operation, and realizes a real-time scoring and stage feedback dual mechanism.

[0064] VI. Implementation of the Literature Retrieval Scoring Module

[0065] The literature retrieval scoring module is deployed in the data presentation layer, and is used for evaluating the performance of the student in information acquisition ability, and is suitable for teaching task scenarios such as course assignments and theme reading. The module includes a retrieval analysis unit and a relevance scoring unit:

[0066] The retrieval analysis unit records the search keywords, logical expressions, selected database types, and search paths set by the student.

[0067] The relevance scoring unit uses an AI semantic analysis model to perform semantic comparison on the literature title, abstract, and task theme submitted by the student, and calculates the score according to the keyword coverage, literature timeliness, and type matching degree.

[0068] For example, in the "non-surgical treatment plan for chronic sinusitis" theme task, the system can identify that the keywords do not cover points such as "nasal irrigation" and "glucocorticoids", and the scoring result will be adjusted downward accordingly, and keyword optimization suggestions will be provided.

[0069] VII. Implementation of the Data Management Module

[0070] The data management module is responsible for the unified archiving and security management of all scoring data and behavior records in the system, meeting the compliance and traceability requirements of the teaching process. Its functional structure includes:

[0071] Data acquisition unit: interconnected with each module, real-time acquisition of scoring data, raw speech, image sequence and inquiry interaction records;

[0072] Data storage unit: using distributed storage architecture to classify and store different types of data into databases and file systems, supporting cross-platform access;

[0073] Data security unit: anonymization processing of sensitive data involving facial images, speech content and identity information, including image coding, ID encryption, metadata cleaning, etc., and setting a hierarchical permission control mechanism to protect user privacy.

[0074] This module supports course grouping management, task version record and historical trajectory comparison functions, facilitating teaching quality analysis and teaching strategy adjustment.

[0075] Eight, implementation of the visualization presentation module

[0076] The visualization presentation module is used to feed back the system evaluation results to the student and teacher ends in various graphical forms, facilitating real-time monitoring of teaching status and evaluation progress. Its main components include a graph generation unit and an interface display unit:

[0077] Graph generation unit: generating ability radar chart, score column chart, growth trend line chart, operation heat map and inquiry process path diagram according to scoring data;

[0078] Interface display unit: build a double-end interactive interface, show individual ability performance and improvement suggestions to students, and show overall performance of the class, weak link analysis and individual early warning information to teachers.

[0079] The system supports displaying evaluation data by course, stage and skill classification, and the chart results can be exported as a report document or pushed to the teaching management platform for end-of-term summary, stage evaluation or teaching improvement meeting.

[0080] In summary, the artificial intelligence-based otolaryngology clinical teaching effect evaluation system provided by the application integrates natural language processing, computer vision, virtual reality, image recognition and machine learning and other intelligent technologies, and constructs a full-process intelligent evaluation framework covering knowledge questions and answers, skill operation, clinical thinking, image diagnosis and information retrieval. The system realizes the collection, intelligent analysis, real-time feedback and visual presentation of multi-modal data through modular design, not only improves the objectivity and accuracy of teaching evaluation, but also helps to realize personalized teaching path planning and process teaching quality management, and is suitable for medical student internship training, resident physician examination and specialized teaching digital reform and other application scenarios, and has good implementation foundation and popularization prospect.

[0081] Application example

[0082] In the hospital otolaryngology clinical teaching training base, in order to improve the teaching evaluation quality of resident physician standardized training, the teaching management team deploys the artificial intelligence-based otolaryngology clinical teaching effect evaluation system provided by the application, and organizes students to complete a multi-dimensional comprehensive ability evaluation task.

[0083] This evaluation task is issued by the system platform, including basic knowledge fast question and answer, nasal mirror operation skill test, virtual patient inquiry training, ear mirror image recognition task and theme literature retrieval five sub-modules. Each student completes each content in turn, and the system automatically collects data and outputs analysis results.

[0084] Step one: basic knowledge fast question and answer (application of NLP module)

[0085] The system extracts 10 questions related to ear-nose-throat anatomy and pathology from the question bank, starts the natural language processing module for voice question and answer evaluation. The students answer one by one, the system automatically converts the voice content into text, and calls the semantic analysis unit and the reference answer for comparison. For example, in the question of "physiological function of eustachian tube", the reference answer sets 5 points, the student answers 3 points, and the system judges the score as 6 points, and prompts "suggest adding 'pressure regulation function'".

[0086] Step two: nasal mirror examination skill evaluation (application of CV module)

[0087] The students use standard operating instruments to complete nasal mirror examination simulation operation in the training classroom, and the camera records the whole process. The computer vision module of the system extracts the action key point track, identifies the mirror holding method, insertion angle and examination path. After AI comparison with the standard process, it prompts: "the operation sequence is complete, the angle deviation is less than 10%, and the lower nasal cavity area is missed", the score is 92 points, and the operation omission point is marked with a red box in the image.

[0088] Step three: virtual patient simulation inquiry (application of VR / AR module)

[0089] The system loads the "sudden deafness" virtual case, and the student wears the VR device to enter the simulated examination room to ask questions and make a preliminary diagnosis of the patient. The virtual patient has symptoms such as sudden hearing loss, no dizziness, and ear congestion. The system records the student's questioning order and diagnosis path, and evaluates the logicality and coverage. This student did not rule out Meniere's disease, and was judged by the system as "incomplete differential diagnosis", with a comprehensive score of 75 points, and was recommended to review "sudden deafness differential process".

[0090] Step four: otoscope image recognition task (application of intelligent otoscope and image recognition module)

[0091] The student uses the intelligent otoscope device to examine the ear canal model at the skill station, and the image is collected by the cold light source and transmitted to the AI analysis module. The image recognition unit completes image correction and lesion feature extraction, and judges that "the left eardrum has a perforation about 2mm in diameter". The system generates a structured report: "it is recommended to further conduct pure tone audiometry", and evaluates the image clarity and operation standardization, outputting an operation score of 95 points.

[0092] Step five: subject literature retrieval task (application of literature scoring module)

[0093] The system sets the retrieval task: "non-surgical treatment strategies for chronic sinusitis", the student enters the AI literature engine built in the system, sets the keywords "sinusitis" "conservative treatment" "hormone nasal spray", selects PubMed database and submits 5 core literatures. The system analyzes the keyword coverage and literature abstract relevance, and suggests: "it is recommended to add the keyword 'nasal irrigation' to improve the recall rate", with a score of 88 points.

[0094] Final feedback

[0095] After the evaluation, the system automatically integrates the scores of the five modules to generate the student's ability radar chart and personalized growth curve. The intelligent scoring and feedback module pushes the following suggestions: "the virtual interview part needs to strengthen the diagnosis logic training of sudden illness, and recommends the learning module: ear deafness diagnosis classification path simulation; it is recommended to review the keyword expansion method in the literature retrieval part, and recommends the practice task: keyword transformation group training."

[0096] The teacher end synchronously receives the comprehensive report, views the statistical data distribution and weak item aggregation trend of the whole class of students, and provides data support for subsequent personalized teaching grouping and teaching strategy optimization.

[0097] The above is only a preferred embodiment of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An artificial intelligence-based otolaryngology clinical teaching effectiveness evaluation system, characterized in that, The system comprises: a natural language processing module for recognizing and analyzing the semantic of the written or spoken answers of the students to generate basic knowledge score results; a computer vision analysis module for collecting operation images of the students in the ear-nose-throat skill training and analyzing the operation standardization; a virtual patient evaluation module for constructing a virtual diagnosis and treatment environment, collecting the interactive behaviors of the students in the simulated diagnosis process, and evaluating the clinical decision-making ability and diagnosis logic; an otoscope image collection device and an image recognition module, the device comprising an optical probe, a handle control module and an image processing module, the image recognition module being used for analyzing the ear canal images and outputting structured preliminary diagnosis information; an intelligent scoring and feedback module for fusing the scoring data of multiple analysis modules to generate a capability radar chart and personalized learning suggestions; a literature retrieval scoring module for evaluating the keyword setting, retrieval strategy and literature relevance of the students in the information retrieval task; a data management module for storing and desensitizing the images, voices, behavior records and scoring results generated in the teaching process; a visualization presentation module for displaying the scoring results, capability growth trajectory chart and recommended feedback content.

2. The system of claim 1, wherein, The natural language processing module comprises a speech recognition unit and a semantic analysis unit, the speech recognition unit being used for converting the speech content into text data, and the semantic analysis unit being used for performing semantic matching between the text and the preset answer, calculating the answer point coverage rate and generating the score.

3. The system of claim 1, wherein, The computer vision analysis module comprises an image collection unit and a motion recognition unit, the motion recognition unit outputting operation standardization score and image feedback results based on key point tracking and standard process comparison algorithm.

4. The system of claim 1, wherein, The virtual patient evaluation module comprises a virtual case generation unit and a behavior interaction collection unit, the virtual case generation unit generating a case scenario with specific complaints, signs and intervention needs, and the behavior interaction collection unit recording the diagnosis order, judgment path and diagnosis decision of the students.

5. The system of claim 1, wherein, The optical probe of the otoscope image collection device adopts a flexible structure to adapt to the curvature of the ear canal, the image processing module comprises an image preprocessing unit, a feature extraction unit and an image recognition unit, and the image recognition unit is used for classifying and identifying the lesion area in the image and generating structured diagnosis suggestions.

6. The system of claim 1, wherein, The intelligent scoring and feedback module comprises a data fusion unit, a capability evaluation unit and a feedback generation unit, the capability evaluation unit being used for constructing a multi-dimensional capability vector and performing cluster scoring, and the feedback generation unit being used for pushing the capability atlas and personalized recommended resources.

7. The system of claim 1, wherein, The literature retrieval scoring module comprises a retrieval analysis unit and a relevance scoring unit, the retrieval analysis unit extracting the keywords and retrieval path set by the students, and the relevance scoring unit scoring the theme matching degree and literature timeliness of the retrieval results.

8. The system of claim 1, wherein, The data management module comprises a data collection unit, a data storage unit and a data security unit, the data security unit performing desensitization processing on the data involving identity information and setting an access permission control mechanism.

9. The system of claim 1, wherein, The visualization presentation module comprises a graph generation unit and an interface display unit, the graph generation unit is used for generating column chart, radar chart, growth curve chart and other graph results, and the interface display unit is used for pushing the evaluation results to the student end and the teacher end.

10. The system of claim 1, wherein, The handle control module of the otoscope image acquisition device is internally provided with a wireless transmission module and a pressure sensor, the pressure sensor is used for detecting the force change in the process of inserting into the ear canal, and damage caused by excessive operation is prevented.

Images