Artificial intelligence empowered college nursing of obstetrics and gynecology major course evaluation method and system

Abstract

The application is suitable for the technical field of medical education, and provides an AI-enabled college gynecology and obstetrics nursing major course evaluation method and system, which comprises the following steps: collecting multi-source learning data of students; based on a natural language processing model, a learning behavior analysis engine and a virtual operation evaluation model, AI analysis is performed on text data, learning behavior data and virtual operation data to obtain an AI analysis report; based on a preset PDCA cycle engine, teaching optimization suggestions are generated to a teacher end and an adaptive learning path is triggered to a student end according to the AI analysis report to perform a PDCA cycle; and a multi-dimensional evaluation report is generated according to data of each link in the PDCA cycle. The application deeply integrates artificial intelligence and college education, converts a gynecology and obstetrics clinical guideline into a technical path of a calculable evaluation index, realizes medical rule digitization, can be applied to college gynecology and obstetrics teaching, and brings a multi-dimensional and quantifiable significant effect.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of medical education, and particularly relates to an AI-enabled college obstetrics and gynecology nursing major course evaluation method and system. BACKGROUND

[0002] The rapid development of artificial intelligence (AI) technology brings new opportunities and challenges to the field of education. Obstetrics and gynecology nursing is an important branch of medical education, and nursing professional teaching must focus on job competence to improve the quality of nursing talent cultivation and provide high-quality nursing for the clinic. The college obstetrics and gynecology nursing major course system needs to keep pace with the times and cultivate nursing talents that meet the needs of the times. The mechanism of delivery is an important core content of obstetrics and gynecology nursing. At present, the traditional teaching method is to research and analyze the current situation of the college obstetrics and gynecology nursing course evaluation system, and to improve the teaching results while also presenting problems such as single evaluation method, lack of individualization, and untimely feedback. Therefore, effective measures must be taken to improve the quality of talent cultivation to meet the needs of economic and social development for high-quality innovative medical talents.

[0003] AI technology is convenient and efficient, and can make the teaching scene more diverse: publishing intelligent question banks, learning analysis, virtual simulation, etc. AI technology can be applied to the feasible scheme of delivery mechanism course evaluation, using natural language processing technology to develop an intelligent question and answer system to evaluate students' understanding of the delivery mechanism; using virtual reality technology to build a virtual delivery scene to evaluate students' clinical operation skills and adaptability; using learning analysis technology to track students' learning process and provide personalized learning suggestions and feedback.

[0004] Formative evaluation is a student-centered evaluation that is immediate, dynamic, and multiple in the teaching process, with diagnostic, motivating, feedback, and guiding functions, which can effectively guide teaching strategies, promote student learning, and improve teaching effectiveness. Based on AI technology, a delivery mechanism course evaluation model is constructed, including evaluation indicators, evaluation methods, and implementation of the evaluation model. In the course assessment, the proportion of assessment is reset, with 70% of process assessment and 30% of final assessment. Process assessment includes (attendance-AI intelligent homework / test-practical teaching-course mind map design-AI practical case reproduction-group case analysis); final assessment adopts closed-book examination, and the score is in percentage. Through score analysis, the achievement degree of course objectives is calculated.

[0005] However, the particularity of the nursing profession is to take human life and health as the object, and there is no room for error. This not only requires students to master basic theoretical knowledge and operational skills, but also to have good professional quality. In the traditional teaching mode of gynecological and obstetric nursing, there is a cramming teaching, that is, a one-way infusion type of teaching, students passively memorize theories, lack of active thinking and critical thinking training; Theory is light and practice is heavy: the proportion of classroom theory teaching is too high, and the opportunity for clinical operation is insufficient, students are prone to problems such as awkward operation and poor problem-solving ability when facing real cases. The gap between simulation and real scene is large: traditional model practice (such as dummy mold) cannot completely simulate complex clinical situations (such as changes in maternal emotions, emergency rescue, etc.).

[0006] Clinical work and learning should have good professional ethics, professional consciousness, professional style and professional attitude. Students rarely think about what kind of professional quality they should have to meet the needs of the workplace in the future, and professional course teachers need to interpret the professional quality of nurses in the right way while teaching knowledge and skills combined with the background of nursing profession; At present, the cultivation of humanistic care and communication ability is insufficient, the tendency of technology supremacy is too much emphasis on operation skills, and the cultivation of humanistic quality such as maternal psychological support, family communication and cultural sensitivity is ignored. The lack of doctor-patient communication training, students lack simulation training to deal with scenes such as maternal anxiety and family conflicts.

[0007] In summary, the current traditional professional course evaluation system is single, score-oriented, dependent on written examination, and ignores the evaluation of comprehensive quality such as clinical operation ability, team cooperation and emergency handling; And the feedback mechanism is weak, lacking dynamic evaluation and personalized guidance of students' learning process; The application of digital means is insufficient, and modern technologies such as virtual simulation (VR) and online learning platform have not been fully integrated into teaching. Therefore, how to build an intelligent evaluation system that can evaluate theoretical cognition, operational skills and professional quality at the same time, and provide real-time feedback and personalized teaching intervention, is still a technical problem to be solved in the field of higher education. SUMMARY

[0008] The purpose of the present application is to provide an AI-enabled college gynecological and obstetric nursing professional course evaluation method, which aims to solve the above technical problems.

[0009] The present application is realized in the following way: an AI-enabled college gynecological and obstetric nursing professional course evaluation method, comprising the following steps:

[0010] Collecting multi-source learning data of students; the multi-source learning data includes text data, learning behavior data and virtual operation data;

[0011] Based on natural language processing model, learning behavior analysis engine and virtual operation evaluation model, AI analysis is performed on text data, learning behavior data and virtual operation data to obtain AI analysis report;

[0012] Based on the preset PDCA cycle engine, according to the AI analysis report, the teaching optimization suggestions are generated to the teacher end, and the adaptive learning path is triggered to the student end, and the PDCA cycle is carried out;

[0013] According to the data of each link in the PDCA cycle, a multi-dimensional evaluation report is generated.

[0014] Further, the text data includes student attendance records, online homework, stage test scores, theoretical test results, case analysis, short answer questions; the learning behavior data includes homework submission time, classroom interaction data, online learning time, learning video viewing progress; the virtual operation data includes virtual operation video, virtual simulation operation log.

[0015] Further, the natural language processing model includes a BERT model and / or a GPT model; the learning behavior analysis engine includes a time series model; and the virtual operation evaluation model includes a computer vision algorithm.

[0016] Further, based on the natural language processing model, the learning behavior analysis engine and the virtual operation evaluation model, the step of AI analyzing the text data, the learning behavior data and the virtual operation data, specifically includes:

[0017] Based on the BERT model and / or the GPT model, the text data is AI analyzed to automatically evaluate the knowledge mastery of the students;

[0018] Based on the time series model, the learning trajectory of the students is analyzed according to the learning behavior data and the virtual operation data, the learning mode is identified, and the weak link of the students is predicted;

[0019] Based on the computer vision algorithm, the virtual operation data is AI analyzed, the operation steps, methods and paths of the students are compared with the standard operation process frame by frame, and the deviation score is calculated.

[0020] Further, the preset PDCA cycle engine includes:

[0021] Planning: generating class and / or individual learning plans according to AI analysis reports, and dynamically adjusting the priority of the teaching resource library;

[0022] Execution: push personalized learning plans to students, and collect learning data through real-time classroom interaction tools;

[0023] Checking: comparing preset targets, outputting gap reports according to student learning data, and detecting virtual simulation operation standardization through a virtual operation evaluation model;

[0024] Processing: according to the inspection result, generating teaching optimization suggestions to the teacher end, triggering adaptive learning path to the student end.

[0025] Another object of the present application is to provide an AI-enabled college obstetrics and gynecology nursing major course evaluation system for realizing the AI-enabled college obstetrics and gynecology nursing major course evaluation method.

[0026] A data acquisition module is configured to acquire multi-source learning data of students, wherein the multi-source learning data includes text data, learning behavior data and virtual operation data.

[0027] An AI analysis module is configured to perform AI analysis on the text data, learning behavior data and virtual operation data based on a natural language processing model, a learning behavior analysis engine and a virtual operation evaluation model, and obtain an AI analysis report.

[0028] A PDCA cycle module is configured to generate teaching optimization suggestions to the teacher end and trigger adaptive learning path to the student end based on a preset PDCA cycle engine and the AI analysis report, and perform PDCA cycle.

[0029] An evaluation report generation module is configured to generate a multi-dimensional evaluation report based on data of each link in the PDCA cycle.

[0030] Further, the PDCA cycle module comprises:

[0031] A planning unit is configured to generate class and / or individual learning plans based on the AI analysis report, and dynamically adjust the priority of the teaching resource library.

[0032] An execution unit is configured to push personalized learning plans to students and collect learning data through real-time classroom interaction tools.

[0033] An inspection unit is configured to compare preset targets, output a gap report based on the learning data of students, and detect the normativity of virtual simulation operations through a virtual operation evaluation model.

[0034] A processing unit is configured to generate teaching optimization suggestions to the teacher end and trigger adaptive learning path to the student end based on the inspection result.

[0035] Further, the AI-enabled college obstetrics and gynecology nursing major course evaluation system further comprises:

[0036] A virtual simulation module is configured to construct a high-fidelity obstetrics and gynecology nursing scene, and perform normativity evaluation on the operations of students based on motion capture technology.

[0037] The AI-enabled college obstetrics and gynecology nursing major course evaluation method provided by the application deeply integrates artificial intelligence and college education, converts obstetrics and gynecology clinical guidelines into a technical path of a calculable evaluation index, realizes the digitization of medical rules, can be applied to college obstetrics and gynecology teaching, and brings a multi-dimensional and quantifiable significant effect, not only improves the skill qualification rate in the 'point', but also reconstructs the teaching process in the 'line', optimizes the education ecology in the'surface', and finally realizes the fundamental purpose of cultivating high-quality and high-adaptability nursing talents. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 The flowchart of the AI-enabled college obstetrics and gynecology nursing major course evaluation method provided by the embodiment of the application.

[0039] Figure 2 The flowchart of AI analysis on text data provided by the embodiment of the application.

[0040] Figure 3 The flowchart of AI analysis on virtual operation data provided by the embodiment of the application.

[0041] Figure 4 The flowchart of the evaluation framework provided by the embodiment of the application.

[0042] Figure 5 The structure block diagram of the AI-enabled college obstetrics and gynecology nursing major course evaluation system provided by the embodiment of the application.

[0043] Figure 6 The structure block diagram of the PDCA cycle module provided by the embodiment of the application. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical scheme and advantages of the application clearer, further detailed description will be made to the application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the application and do not limit the application.

[0045] As shown in the drawings, Figure 1 In another embodiment of the application, an AI-enabled college obstetrics and gynecology nursing major course evaluation method is provided, comprising the following steps:

[0046] S100, collecting multi-source learning data of students; the multi-source learning data includes text data, learning behavior data and virtual operation data;

[0047] S200, based on a natural language processing model, a learning behavior analysis engine and a virtual operation evaluation model, AI analysis is performed on the text data, the learning behavior data and the virtual operation data to obtain an AI analysis report;

[0048] S300, based on the preset PDCA cycle engine, generating teaching optimization suggestions to the teacher end and triggering adaptive learning paths to the student end according to the AI analysis report, and performing PDCA cycle;

[0049] S400, generating a multi-dimensional evaluation report according to the data of each link in the PDCA cycle.

[0050] It should be noted that the method provided by the embodiments of the application can be applied to the evaluation of obstetric nursing professional course system, and the following embodiments are described by taking childbirth professional courses as an example, but are not limited thereto.

[0051] Specifically, the text data includes but is not limited to student attendance records, online homework, stage test scores, theoretical test results, case analysis, short answer questions, etc.; the learning behavior data includes but is not limited to homework submission time, classroom interaction data, online learning time, learning video viewing progress, etc.; the virtual operation data includes but is not limited to virtual operation video, virtual simulation operation log, etc. In actual application, the above step S100 can be realized by a data collection layer; multi-source data input is adopted: integrating student attendance records, online homework, stage test scores, virtual simulation operation logs, classroom interaction data (such as questions and answers, discussions); based on sensors and interfaces, virtual operation data is collected through virtual simulation devices (such as VR gloves, motion capture cameras); learning management system (LMS) application programming interface (API) can be connected to obtain learning data such as theoretical test results.

[0052] In a preferred embodiment of the application, the natural language processing model (NLP) includes a BERT model and / or a GPT model; the learning behavior analysis engine includes a time series model; and the virtual operation evaluation model includes a computer vision algorithm.

[0053] In a preferred embodiment of the application, based on the natural language processing model, the learning behavior analysis engine and the virtual operation evaluation model, the step of AI analyzing the text data, the learning behavior data and the virtual operation data specifically includes:

[0054] Based on the BERT model and / or the GPT model, the text data is AI analyzed to automatically evaluate the knowledge mastery level of the student;

[0055] Based on the time series model, the learning trajectory of the student is analyzed according to the learning behavior data and the virtual operation data, the learning mode is identified, and the weak link of the student is predicted;

[0056] Based on the computer vision algorithm, the virtual operation data is AI analyzed, the operation steps, techniques and paths of the student are compared with the standard operation process frame by frame, and the deviation score is calculated.

[0057] Specifically, such as Figure 2 As shown in the AI-enabled evaluation method for obstetrics and gynecology nursing courses in universities provided in this embodiment of the invention, the core task of the natural language processing (NLP) model is to analyze students' textual answers (such as case analysis and short answer questions) and automatically assess their knowledge mastery. BERT and GPT are currently the most advanced NLP models. By using BERT (precise understanding and scoring of student answers) or GPT (generating parsing and interactive feedback) models to analyze students' textual answers (such as case analysis questions), assess the depth of knowledge mastery, and automatically generate labels for incorrect answers (such as "incorrect differential diagnosis of placental abruption").

[0058] In addition, the learning behavior analysis engine analyzes learning trajectories based on time series models (LSTM, which records student learning behaviors in chronological order), including theoretical learning trajectories, weekly test scores, homework submission times, and online learning durations; and practical operation records: the time sequence of completing the delivery steps in virtual simulation (such as the time consumed in each stage of "cervical dilation → fetal head descent → delivery"), thereby predicting weak points.

[0059] like Figure 3 As shown, virtual operation data such as practical actions collected by VR devices, including time-series data, can be preprocessed using the methods described above. Then, it can be compared with standard operation sequences to generate deviation scores, which can be used to assess students' mastery of virtual simulation operations.

[0060] In a preferred embodiment of the present invention, the preset PDCA cycle engine includes:

[0061] Plan: Generate class and / or individual learning plans based on AI analysis reports (such as "focusing on strengthening teaching of labor stages next week"), and dynamically adjust the priority of teaching resource library (such as pinning micro-lessons related to frequently missed knowledge points).

[0062] Do: Push personalized learning plans to students (e.g., assign extra virtual training to students who are weak in "breech delivery"), and collect learning data through real-time classroom interaction tools (e.g., timed quiz machines);

[0063] Check: Compare with preset goals (e.g., "80% of students master uterine contraction monitoring"), output gap reports based on students' learning data; and check the standardization of virtual simulation operations through virtual operation evaluation models (e.g., "whether the fetal head flexion angle meets the standard").

[0064] Processing (Act): Based on the inspection results, generate teaching optimization suggestions to the teacher (such as "increase the case discussion class time for abnormal labor process") and trigger adaptive learning paths to the student (such as unlocking the basic theory review module when the error rate is >50%).

[0065] In the embodiment of the present application, structured data (test scores, etc.) and unstructured data (virtual operation video, etc.) are uniformly processed through multi-source learning data fusion, that is, text (homework), video (operation video), and numerical value (test score) are uniformly embedded in a vector space for AI joint analysis. The embodiment of the present application adopts a dynamic evaluation algorithm, constructs an intelligent question bank based on a BERT model, and automatically generates test questions with difficulty adaptation; specifically, the dynamic test question generation algorithm is as follows: the input is: student historical error knowledge points, current chapter (such as "Chapter 8 Complications of Pregnancy"). The processing process is: the difficulty of the question and the matching degree of the student's ability are calculated through Item Response Theory (IRT); preferentially push the questions with strong relevance and not up to standard (such as "Nursing Measures Selection Question of Preeclampsia"). The output is: personalized test paper (PDF / online form).

[0066] Virtual simulation practice evaluation can be scored by comparing the standard operation process through motion capture technology, and virtual simulation data can be processed by edge computing nodes to reduce cloud delay. The feedback loop design of the PDCA cycle engine: the teacher end receives the overall weak point report of the class in real time, and the student end obtains the personalized learning path suggestion. Specifically, the teaching feedback loop process is as follows: student operation / answering questions→data collection→AI analysis→generating diagnosis report→teacher adjusting teaching→student receiving new task.

[0067] The embodiment of the present application can also deploy a lightweight model (such as MobileNet) on the mobile end (student end and teacher end) to support instant feedback in the classroom.

[0068] In step S400, the evaluation framework as shown in Figure 4 Based on the double-channel explanation system, a multi-dimensional evaluation report is generated: the decision tree visualizes the scoring basis, for example, the deduction points: 3 seconds of fetal position judgment delay (standard ≤2 seconds); associated with medical guidelines, automatically generate improvement suggestions, for example, if the technique is adjusted 15 degrees in advance, the score can be improved by 12%.

[0069] Specifically, the double-channel explanation system includes channel one and channel two. Channel one is based on the explanation of the machine decision process, which explains the decision logic inside the AI analysis model; usually, SHAP value, LIME, etc. Model processing, output visual contribution analysis, make the scoring process transparent and traceable. Students and teachers can see the specific technical items of the score and loss. Channel two is based on the explanation of the clinical medical rules, which explains the medical principles and clinical guidelines behind the results, and improves according to the medical standards; for example, based on the knowledge graph, medical expert rule base (i.e. digitized clinical guidelines) for processing, output text-based, teaching meaningful improvement suggestions.

[0070] As Figure 5 Another object of the present application is to provide an AI-enabled college gynecological nursing major course evaluation system for realizing the AI-enabled college gynecological nursing major course evaluation method as described above, which comprises:

[0071] a data acquisition module 10 for acquiring multi-source learning data of students; the multi-source learning data includes text data, learning behavior data and virtual operation data;

[0072] an AI analysis module 20 for AI analyzing the text data, learning behavior data and virtual operation data based on a natural language processing model, a learning behavior analysis engine and a virtual operation evaluation model, to obtain an AI analysis report;

[0073] a PDCA cycle module 30 for generating teaching optimization suggestions to a teacher end and triggering an adaptive learning path to a student end according to the AI analysis report based on a preset PDCA cycle engine, to perform a PDCA cycle;

[0074] an evaluation report generation module 40 for generating a multi-dimensional evaluation report according to data of each link in the PDCA cycle.

[0075] As Figure 6 shown in the present application, in a preferred embodiment of the present application, the PDCA cycle module 30 comprises:

[0076] a planning unit 31 for generating a class and / or individual learning plan according to the AI analysis report and dynamically adjusting a teaching resource library priority;

[0077] an execution unit 32 for pushing a personalized learning plan to students and collecting learning data through a real-time classroom interaction tool;

[0078] an inspection unit 33 for comparing a preset target, outputting a gap report according to the learning data of the students, and detecting virtual simulation operation standardization through a virtual operation evaluation model;

[0079] a processing unit 34 for generating teaching optimization suggestions to the teacher end and triggering the adaptive learning path to the student end according to the inspection results.

[0080] In a preferred embodiment of the present application, the AI-enabled college obstetrical and gynecological nursing major course evaluation system further comprises a virtual simulation module for constructing a high-fidelity obstetrical and gynecological nursing scene and performing normative evaluation on the operation of students based on motion capture technology; mainly including the following: scene construction: Unity 3D / Unreal Engine is used to develop a high-fidelity delivery scene (including normal delivery, shoulder dystocia and other abnormal conditions); operation evaluation: motion capture technology is used to record the operation of students (such as "hand pressing position, force and timing"); scoring based on rule engine (such as "lose 10 points for not identifying umbilical cord prolapse within 30 seconds").

[0081] It should be noted that the above modules and units can be implemented in the form of a computer program, which can run on a computer device, and the computer program composed of the modules can be stored in the memory of the computer device to enable the processor to execute the steps of the above method.

[0082] It should be understood that although each step in the flowchart of each embodiment of the present application is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise stated herein, the execution of these steps has no strict order limitation, and these steps can be executed in other order. Moreover, at least part of the steps in each embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or sub-steps or stages of other steps.

[0083] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the program can be stored in a non-volatile computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of the method. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory.

[0084] The above embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it cannot be understood as a limitation on the scope of the patent of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of protection of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for evaluating obstetrics and gynecology nursing courses in colleges and universities using AI, characterized in that... Includes the following steps: Collect students' multi-source learning data; the multi-source learning data includes text data, learning behavior data, and virtual operation data; Based on natural language processing models, learning behavior analysis engines, and virtual operation evaluation models, AI analysis is performed on text data, learning behavior data, and virtual operation data to obtain AI analysis reports. Based on the preset PDCA cycle engine, and according to the AI ​​analysis report, teaching optimization suggestions are generated for teachers and adaptive learning paths are triggered for students to carry out the PDCA cycle. Generate a multi-dimensional evaluation report based on data from each stage of the PDCA cycle; The natural language processing model includes the BERT model and / or the GPT model; the learning behavior analysis engine includes a time series model; the virtual operation evaluation model includes a computer vision algorithm. The steps for AI analysis of text data, learning behavior data, and virtual operation data based on natural language processing models, learning behavior analysis engines, and virtual operation evaluation models include: Based on the BERT model and / or GPT model, AI analysis is performed on text data to automatically assess students' knowledge mastery. Based on time series models, students' learning trajectories are analyzed using learning behavior data and virtual operation data to identify learning patterns and predict students' weaknesses. Based on computer vision algorithms, AI analysis is performed on virtual operation data to compare students' operation steps, techniques, and paths with standard operation procedures frame by frame and calculate deviation scores.

2. The AI-enabled evaluation method for obstetrics and gynecology nursing courses in universities according to claim 1, characterized in that, The text data includes student attendance records, online assignments, stage test scores, theoretical test results, case analyses, and short answer questions; the learning behavior data includes assignment submission time, classroom interaction data, online learning duration, and learning video viewing progress; the virtual operation data includes virtual operation recordings and virtual simulation operation logs.

3. The AI-enabled evaluation method for obstetrics and gynecology nursing courses in universities according to claim 1, characterized in that, The preset PDCA cycle engine includes: Plan: Generate class and / or individual learning plans based on AI analysis reports, and dynamically adjust the priority of the teaching resource library; Implementation: Pushing personalized learning plans to students and collecting learning data through real-time classroom interaction tools; Inspection: Compare with preset goals, output gap reports based on students' learning data; and check the standardization of virtual simulation operations through a virtual operation evaluation model; Processing: Based on the inspection results, generate teaching optimization suggestions for teachers and trigger adaptive learning paths for students.

4. An AI-enabled evaluation system for obstetrics and gynecology nursing courses in universities, used to implement the AI-enabled evaluation method for obstetrics and gynecology nursing courses in universities as described in any one of claims 1-3, characterized in that, include: The data acquisition module is used to collect students' multi-source learning data; The multi-source learning data includes text data, learning behavior data, and virtual operation data; The AI ​​analysis module is used to perform AI analysis on text data, learning behavior data, and virtual operation data based on natural language processing models, learning behavior analysis engines, and virtual operation evaluation models, and to generate AI analysis reports. The PDCA cycle module is used to generate teaching optimization suggestions for teachers and trigger adaptive learning paths for students based on the preset PDCA cycle engine and AI analysis reports, and to carry out the PDCA cycle. The evaluation report generation module is used to generate multi-dimensional evaluation reports based on data from each stage of the PDCA cycle.

5. The AI-enabled evaluation system for obstetrics and gynecology nursing courses in universities according to claim 4, characterized in that, The PDCA cycle module includes: The planning unit is used to generate class and / or individual learning plans based on AI analysis reports and dynamically adjust the priority of the teaching resource library. The execution unit is used to push personalized learning plans to students and collect learning data through real-time classroom interaction tools; The inspection unit is used to compare with preset targets, output gap reports based on students' learning data, and check the standardization of virtual simulation operations through a virtual operation evaluation model. The processing unit is used to generate teaching optimization suggestions for teachers and trigger adaptive learning paths for students based on the inspection results.

6. The AI-enabled evaluation system for obstetrics and gynecology nursing courses in universities according to claim 4 or 5, characterized in that, Also includes: The virtual simulation module is used to construct high-fidelity obstetric and gynecological nursing scenarios and to conduct standardized evaluations of students' operations based on motion capture technology.

Images