Midwifery practice teaching system based on scene simulation

Abstract

The invention discloses a midwifery practice teaching system based on scenario simulation, which relates to the technical field of medical teaching and is technically characterized by comprising a digital delivery model, a scenario simulation software system, a data acquisition and feedback module and an intelligent guidance module. The system simulates a real delivery process through a virtual environment, covers scenes such as uterine orifice dilation, baby delivery, placenta delivery, postpartum hemorrhage and the like, can generate physiological signals such as fetal heart sound and the like, and provides scene simulation of various delivery processes. And performing real-time analysis on student operation by using an artificial intelligence algorithm, and generating personalized feedback and a scoring report. In addition, the system supports simulation of emergency situations and customization of personalized learning paths, and ensures that students master diversified midwifery skills in a controllable and safe environment. Through the combination of VR and AR technologies, the system achieves immersive teaching, improves the learning efficiency and sense of participation, and remarkably improves the emergency response and standard operation capabilities of a midwife. The system is suitable for the field of medical education and has a wide application prospect.

Description

Technical Field

[0001] The invention relates to the technical field of medical teaching, and in particular to a midwifery practice teaching system based on scenario simulation. Background Art

[0002] Midwifery practice teaching is an important part of midwifery training and a key process to ensure that students have the necessary theoretical knowledge and operational skills. However, the traditional midwifery teaching model faces many challenges and limitations and is difficult to meet the needs of modern medical education. In the current educational environment, traditional midwifery practice teaching mainly relies on on-site clinical training, but due to the limited resources for midwifery clinical practice, it is difficult for students to obtain enough practical operation opportunities. In addition, there is a great deal of uncontrollability in the clinical environment, such as unpredictable development of the labor process, diverse patient conditions, and difficulty in simulating emergency situations. These increase the difficulty for students to master and cope with the complex delivery process during the learning process.

[0003] In recent years, with the rapid development of virtual reality (VR), augmented reality (AR), artificial intelligence and sensor technology, scenario simulation teaching has gradually become an effective means to solve these problems. Scenario simulation teaching aims to provide students with an immersive practical experience through a highly simulated virtual environment. The midwifery practice teaching system based on scenario simulation is a concrete manifestation of this trend. By constructing a virtual delivery scene and simulating various situations that may occur during the actual delivery process, it can make up for the shortcomings of the traditional teaching model and enable students to conduct systematic training in a more controllable and safe environment.

[0004] A significant problem with traditional midwifery teaching is the limited clinical cases. Many midwifery students may only be exposed to a small number of specific types of delivery cases during their internship, making it difficult to fully understand the diversity and complexity of the delivery process. In the actual midwifery process, various situations are ever-changing, from normal natural delivery to abnormal fetal malposition, postpartum hemorrhage and other emergencies. Each situation requires midwives to have rich theoretical knowledge and skilled operation skills. The midwifery practice teaching system based on scenario simulation can accurately simulate various delivery scenarios in a virtual environment through digital models and software control, allowing students to repeatedly practice and experience different delivery situations and improve their ability to respond to diverse clinical problems.

[0005] Another issue worth noting is that it is difficult to simulate emergency situations in traditional teaching. In real clinical environments, the occurrence of emergencies is unpredictable, which leads to students often lacking sufficient experience and emergency response capabilities when facing emergencies. The scenario simulation teaching system can effectively solve this problem. By using algorithm control and digital modeling, it simulates emergency situations such as fetal distress and postpartum hemorrhage, allowing students to conduct emergency operation training in a safe virtual environment. This not only reduces the potential risks to mothers and fetuses in real environments, but also improves students' emergency response and judgment capabilities under high-pressure situations.

[0006] Although some existing midwifery practice teaching systems have introduced simulation technology to a certain extent, they are often limited to static operation models and lack dynamic and interactive features. This teaching model lacks interaction and real-time feedback, which makes it difficult for students to master the actual operation details during childbirth. For example, traditional simulation models usually cannot be adjusted in real time according to students' operation behaviors, nor can they generate detailed operation feedback reports, making it difficult for students to discover and improve their own operation problems during the learning process.

[0007] In order to overcome the above shortcomings, we designed a midwifery practice teaching system based on scenario simulation to solve the above problems. Summary of the invention

[0008] The purpose of the present invention is to provide a midwifery practice teaching system based on scenario simulation in view of the deficiencies of the prior art, so as to solve the problems raised in the background technology.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] The midwifery practice teaching system based on scenario simulation includes a digital delivery model, a scenario simulation software system, a data collection and feedback module, and an intelligent guidance module. The digital delivery model uses virtual modeling technology to accurately simulate the physiological characteristics of the mother and fetus, including simulation elements such as the fetus, uterus, birth canal, placenta, and blood flow.

[0011] The scenario simulation software system can accurately control the delivery stage demonstration of the digital model through preset algorithms, such as fetal heart sound generation, cervical dilation, fetal delivery, placental delivery and postpartum hemorrhage.

[0012] The data collection and feedback module has built-in sensor data and operation log analysis functions to record the strength, direction, duration, etc. of students' operations;

[0013] The intelligent guidance module provides instant feedback on the accuracy of operations based on operation data analysis, including voice prompts, video guidance and real-time scoring.

[0014] As a preferred technical solution of the present invention, the scenario simulation software system uses a state machine control algorithm to simulate the delivery process in stages. The state machine is defined as follows:

[0015] State set: S = {preparation stage, early delivery stage, active stage, delivery stage, postpartum treatment};

[0016] State transition function: δ(s, a) = s′, where s is the current state, a is the operation input by the user, and s′ is the next state;

[0017] Through the state transfer function δ, the system automatically adjusts the delivery progress according to the user's operation.

[0018] As a preferred technical solution of the present invention, the fetal heart sound simulation module can generate a fetal heart sound signal in real time, and its signal generation formula is based on the Fourier series model:

[0019]

[0020] Among them, H(t) is the generated fetal heart sound signal, A n and B n is the coefficient of the Fourier series, T is the period, and the coefficient is adjusted to simulate the changes in fetal heart sounds under normal and abnormal conditions.

[0021] As a preferred technical solution of the present invention, the system includes a delivery process monitoring module, which uses a convolutional neural network (CNN) to perform real-time recognition and analysis of students' operation behaviors in a virtual environment. Its neural network architecture includes the following elements:

[0022] Input layer: video images of students’ gestures;

[0023] Hidden layers: convolutional layer, pooling layer and fully connected layer, used to extract gesture features;

[0024] Output layer: Classifies the accuracy of the student’s operation, such as “correct”, “deviant”, or “wrong”.

[0025] As a preferred technical solution of the present invention, the system includes an emergency situation simulation module, which can randomly generate or simulate emergency delivery situations according to preset conditions. The module uses a Markov chain probability model to describe the state transition of emergency situations:

[0026] P(X n+1 =j|X n =i) = p ij

[0027] Among them, X n is the current state, X n +1 is the next state, p i j is the transition probability from state i to state j. The system adjusts pij Simulate different types of emergency situations.

[0028] As a preferred technical solution of the present invention, the data collection and feedback module uses fuzzy logic algorithm to evaluate the student's operation behavior. The fuzzy evaluation rules are as follows:

[0029] Input variables: hand force F, operation speed V, posture angle θ;

[0030] Output variable: operation score S;

[0031] Rule set example: IF F is "moderate" AND V is "stable" AND θ is "correct", THENS is "high score":

[0032] The fuzzy scoring function is defined as follows:

[0033] S=w1·Linguistic(F)+w2·Linguistic(V)+w3·Linguistic(θ)

[0034] Among them, w i is the weight, which indicates the relative importance of each indicator.

[0035] As a preferred technical solution of the present invention, the intelligent guidance module generates feedback suggestions based on multivariate analysis of operation data.

[0036] The multivariate analysis formula is as follows:

[0037] Y=β0+β1X1+β2X2+β3X3+…+β n X n

[0038] Among them, Y is the final operation score, X i are the key indicators in the operation process, β i is the weight of the corresponding indicator. The system dynamically adjusts β according to the operation results. i To generate personalized guidance.

[0039] As a preferred technical solution of the present invention, the learning path optimization module designs a personalized learning plan based on a dynamic programming algorithm. The objective function of the path optimization is as follows:

[0040]

[0041] Among them, T i The time required for each learning module, C i The difficulty coefficient of each module. The system adjusts T i and C i Optimize learning paths to maximize students' learning efficiency.

[0042] As the preferred technical solution of the present invention, virtual reality (VR) and augmented reality (AR) modules provide an immersive experience of the delivery process. The VR / AR modules include: 3D visualization scene generation; real-time data sensors for tracking students' head and hand movements; and real-time feedback of operations to improve students' operation accuracy.

[0043] As a preferred technical solution of the present invention, the system supports remote collaborative teaching mode, allowing multiple users to simultaneously connect to the same virtual scene for group learning and collaborative discussion. The data synchronization of the remote collaboration module adopts the following time deviation adjustment formula:

[0044]

[0045] Where, ΔT i is the time deviation of the ith user, T i is the operation timestamp of the i-th user, and N is the total number of users. The system adjusts the data transmission time according to the deviation to ensure the synchronization of each user's operation.

[0046] Compared with the prior art, the beneficial effects of the present invention are: through the software system based on scenario simulation, midwifery practice teaching breaks through the limitation of insufficient actual cases in traditional teaching. The digital delivery model can simulate a variety of delivery situations, including normal delivery and emergency situations such as malposition of the fetus and postpartum hemorrhage. This flexibility enables students to repeatedly practice different types of delivery processes, fully master midwifery skills, and improve their ability to cope with actual clinical operations.

[0047] The scenario simulation system integrates data collection and feedback modules to monitor students' operating behaviors in real time and provide detailed evaluation reports. Through the intelligent guidance module, the system can immediately correct incorrect operations and give improvement suggestions. Such a feedback mechanism helps students discover problems during operation, adjust the operating methods in time, improve the accuracy and standardization of operations, and enhance learning effects.

[0048] The system uses artificial intelligence algorithms to analyze students' learning progress and operation data to generate a personalized learning path for each student. Based on the students' specific circumstances, the system will recommend appropriate practice content and difficulty to improve students' learning efficiency. Combined with the immersive experience of VR and AR technology, students can have a deeper understanding of the complex midwifery process and thus master the required skills more effectively. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a system block diagram of the midwifery practice teaching system based on scenario simulation proposed by the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] The following is combined with Figure 1 With reference to the accompanying drawings and a number of embodiments, specific embodiments of the present invention are described in detail.

[0052] Example 1: Simulation of normal delivery process

[0053] System initialization: Students select the "normal delivery process" mode, and the scenario simulation software system generates a standard delivery environment based on preset conditions, including virtual models of the mother's uterus, birth canal, and fetus.

[0054] Implementation steps:

[0055] Preparation stage: The system enters the "preparation stage". Students observe the virtual scene through VR equipment, and the system guides students to become familiar with the delivery environment and operation procedures.

[0056] The finite state machine control system switches from the "preparation stage" to the "early delivery stage". The state transfer function is as follows:

[0057] S(t+1)=f(S(t),A)

[0058] Among them, S(t) is the current delivery state, A is the student's operation action, and the system determines whether the delivery progress meets the standard based on the student's operation and decides whether to enter the next state.

[0059] Fetal heart sound simulation: As delivery progresses, the system starts the fetal heart sound simulation module, generates fetal heart sound signals in real time, and simulates the changes in the fetal heartbeat.

[0060] The formula for generating fetal heart sounds is based on the Fourier series model:

[0061]

[0062] Among them, H(t) is the generated fetal heart sound signal, A n and B n is the Fourier series coefficient, T is the fetal heart rate cycle. The coefficient is adjusted according to the progress of labor to simulate normal or abnormal fetal heart rate.

[0063] Active labor period: Students perform midwifery operations, and the system monitors the students' gestures, strength, and speed of operation. The convolutional neural network (CNN) algorithm analyzes the students' gestures to determine whether the operation meets the standards. The CNN architecture is as follows:

[0064] Input layer: video images of students’ gestures;

[0065] Hidden layer: multiple convolutional layers and pooling layers to extract gesture features;

[0066] Output layer: classifies student actions as “correct”, “deviant”, or “wrong”.

[0067] Delivery of the fetus: When students follow the correct steps, the system controls the fetus in the digital model to be delivered slowly, displaying the various physiological characteristics of the fetus.

[0068] Postpartum care: Students complete placental delivery and basic postpartum care operations. The system records the operation data and generates detailed scoring and feedback reports.

[0069] Feedback mechanism: During the whole process, the system records every detail of the operation through the data collection and feedback module, and generates the final score based on the fuzzy logic algorithm.

[0070] The scoring function of fuzzy logic is:

[0071] S=w1·Linguistic(F)+w2·Linguistic(V)+w3·Linguistic(θ)

[0072] Among them, S is the score, w i is the weight of each indicator, F is the hand strength, V is the operation speed, and θ is the operation angle.

[0073] Example 2: Emergency Simulation - Postpartum Hemorrhage

[0074] System initialization: The teacher selects the "postpartum hemorrhage" emergency simulation mode, and the scenario simulation software system generates a scenario, including a virtual model of the mother and the setting of the bleeding status.

[0075] Implementation steps:

[0076] Emergency scenario generation: The system enters normal delivery mode, but after the delivery process is completed, a postpartum hemorrhage scenario is randomly initiated.

[0077] The system controls the occurrence of bleeding through a Markov chain probability model, which is defined as follows:

[0078]

[0079] Where P(E) represents the probability of occurrence of emergency event E, λ is the expected event frequency, and k is the number of occurrences. The difficulty of emergency events can be controlled by adjusting λ.

[0080] Operation monitoring: Students need to quickly determine the cause of bleeding and take appropriate treatment measures, such as uterine massage, drug injection, etc. The data acquisition and feedback module uses fuzzy logic algorithms to evaluate students' emergency treatment operations and generate real-time feedback.

[0081] Scoring and feedback: The system generates scores based on students' emergency response speed and operation accuracy. The feedback report includes indicators such as processing time and effectiveness of measures.

[0082] Example 3: Delivery simulation of malposition of fetus

[0083] System initialization: Students select the "abnormal fetal position" scenario, and the system generates a digital model containing abnormal fetal positions, including transverse occipital position, posterior occipital position, and other abnormal fetal positions.

[0084] Implementation steps:

[0085] Fetal position detection: The system simulates a fetal examination before delivery and allows students to determine the fetal position through virtual palpation.

[0086] The state machine algorithm is used to simulate different postures of the fetus. The state transition function is as follows:

[0087] S(t+1)=δ(S(t),A)

[0088] Among them, S(t) is the current fetal position, A is the student's palpation operation, and the system determines whether it is correct based on the operation.

[0089] Midwifery operations: In the case of abnormal fetal position, the system requires students to implement specific corrective techniques, such as rotating the fetal head or changing the delivery posture.

[0090] The system uses the CNN algorithm to monitor the accuracy of the technique in real time. If the technique is inappropriate, the system will give immediate correction prompts.

[0091] Fetal delivery: After students complete the correct fetal position correction, the system simulates the fetal delivery process and displays the corrected delivery situation.

[0092] Result analysis: After the operation is completed, the system generates a detailed feedback report, which includes operation accuracy, error analysis and improvement suggestions.

[0093] The system also generates a personalized learning path and adjusts the learning order based on a dynamic programming algorithm:

[0094]

[0095] Among them, T i is the time students spend on each learning module, C i is the difficulty coefficient. The goal is to minimize students’ learning costs and improve learning efficiency.

[0096] Example 4: Personalized learning path generation

[0097] Implementation steps:

[0098] System initialization: Students select "personalized learning mode" according to their learning needs and operation conditions. The system starts the dynamic programming algorithm to generate the optimal learning path based on the students' historical operation data. Data collection: The system automatically summarizes the students' past operation data, including the score, error type and reaction time in each delivery scene.

[0099] The system calculates the student's performance in each operation link based on a multivariate regression equation:

[0100] Y=β0+β1X1+β2X2+β3X3+…+β n X n

[0101] Among them, Y is the total score of the operation, X i are various operation indicators, β i is the weight of the corresponding indicator.

[0102] Path optimization: Based on the objective function of dynamic programming, the system determines the learning modules that need to be reinforced and their order.

[0103] Feedback and adjustment: During the personalized learning process, the system will dynamically adjust the learning path based on the students' performance to ensure targeting and effectiveness.

[0104] Example 5: Multi-user collaborative learning in VR / AR immersive scenarios

[0105] System initialization: The teacher selects "multi-user collaboration mode", and the system generates a VR scene containing multiple virtual delivery rooms. Each student enters the virtual scene through a VR device.

[0106] Implementation steps:

[0107] Multi-user synchronization: Students enter the same delivery scene through a network connection, and the system synchronizes the operation data of each user through the time deviation adjustment formula:

[0108]

[0109] Where, ΔT i is the time deviation of the ith user, T i is the operation timestamp of the i-th user, and N is the total number of users. Operation consistency is ensured through synchronous adjustment.

[0110] Role assignment: The system automatically assigns roles according to the learning objectives of different students, such as main midwife, auxiliary midwife, etc. Each role is responsible for specific tasks.

[0111] Collaborative operation: In the scenario, students work together according to their assigned roles. The system monitors each student's performance through real-time data collection and provides operational suggestions and scores.

[0112] Team feedback: After the operation is completed, the system generates a team collaboration report, analyzes each student's performance and the overall score of team collaboration, and provides suggestions for improving team collaboration.

[0113] These embodiments demonstrate in detail the different application scenarios, operation details and practical applications of various algorithms of this patent, ensuring the high simulation and effectiveness of midwifery practice teaching in a virtual environment.

[0114] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in the field. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A midwifery practice teaching system based on scenario simulation, including a digital delivery model, a scenario simulation software system, a data collection and feedback module and an intelligent guidance module, characterized in that: The digital delivery model uses virtual modeling technology to accurately simulate the physiological characteristics of the mother and fetus, including fetal, uterus, birth canal, placenta and blood flow simulation elements; The scenario simulation software system uses a preset algorithm to accurately control the delivery stage demonstration of the digital model, including the fetal heart sound simulation module, cervical dilation, fetal delivery, placental delivery and postpartum hemorrhage process; The data collection and feedback module has built-in sensor data and operation log analysis functions to record the strength, direction, duration, etc. of students' operations; The intelligent guidance module provides instant feedback on the accuracy of operations based on operation data analysis, including voice prompts, video guidance and real-time scoring.

2. The midwifery practice teaching system based on scenario simulation according to claim 1 is characterized in that: The scenario simulation software system uses a state machine control algorithm to simulate the delivery process in stages. The state machine is defined as follows: State set: S = {preparation stage, early delivery stage, active stage, delivery stage, postpartum treatment}; State transition function: δ(s,a)=s′, where s is the current state, a is the operation input by the user, and s′ is the next state; Through the state transfer function δ, the system automatically adjusts the delivery progress according to the user's operation.

3. The midwifery practice teaching system based on scenario simulation according to claim 1 is characterized in that: The fetal heart sound simulation module generates a fetal heart sound signal in real time, and its signal generation formula is based on the Fourier series model: Among them, H(t) is the generated fetal heart sound signal, A n and B n is the coefficient of the Fourier series, T is the period, and the coefficient is adjusted to simulate the changes in fetal heart sounds under normal and abnormal conditions.

4. The midwifery practice teaching system based on scenario simulation according to claim 1 is characterized in that: The system includes a delivery process monitoring module, which uses a convolutional neural network to perform real-time recognition and analysis of students' operation behaviors in a virtual environment. The neural network architecture includes the following elements: Input layer: video images of students’ gestures; Hidden layers: convolutional layer, pooling layer and fully connected layer, used to extract gesture features; Output layer: classifies the accuracy of the student's operation, such as "correct", "deviation" or "incorrect".

5. The midwifery practice teaching system based on scenario simulation according to claim 1 is characterized in that: The system includes an emergency situation simulation module, which randomly generates or simulates emergency delivery situations according to preset conditions. The module uses a Markov chain probability model to describe the state transition of emergency situations: P(X n+1 =j|X n =i)=p ij Among them, X n is the current state, X n +1 is the next state, p i j is the transition probability from state i to state j.

6. The midwifery practice teaching system based on scenario simulation according to claim 1 is characterized in that: The data collection and feedback module uses fuzzy logic algorithm to evaluate students' operation behavior. The fuzzy evaluation rules are as follows: Input variables: hand force F, operation speed V, posture angle θ; Output variable: operation score S; Example of rule set: IFF is "moderate" ANDV is "stable" ANDθ is "correct", THENS is "high score"; The fuzzy scoring function is defined as follows: S=w1·Linguistic(F)+w2·Linguistic(V)+w3·Linguistic(θ) Among them, w i is the weight, which indicates the relative importance of each indicator.

7. The midwifery practice teaching system based on scenario simulation according to claim 1 is characterized in that: The intelligent guidance module generates feedback suggestions based on multivariate analysis of operation data. The multivariate analysis formula is as follows: Y=β0+β1X1+β2X2+β3X3+…+β n X n Among them, Y is the final operation score, X i are the key indicators in the operation process, β i is the weight of the corresponding indicator. The system dynamically adjusts β according to the operation results. i To generate personalized guidance.

8. The midwifery practice teaching system based on scenario simulation according to claim 1 is characterized in that: The system includes a learning path optimization module that designs personalized learning plans based on a dynamic programming algorithm. The objective function of path optimization is as follows: Among them, T i The time required for each learning module, C i The difficulty level for each module.

9. The midwifery practice teaching system based on scenario simulation according to claim 1 is characterized in that: The system includes virtual reality and augmented reality modules to provide an immersive delivery process experience. The virtual reality and augmented reality modules use VR / AR modules. The VR / AR modules include: 3D visualization scene generation; real-time data sensors are used to track the head and hand movements of students.

10. Claim 10 The midwifery practice teaching system based on scenario simulation according to claim 1, characterized in that: The system supports remote collaborative teaching mode, allowing multiple users to simultaneously connect to the same virtual scene for group learning and collaborative discussion. The data synchronization of the remote collaboration module adopts the following time deviation adjustment formula: Where, ΔT i is the time deviation of the ith user, T i is the operation timestamp of the i-th user, and N is the total number of users.

Images