Intelligent training system and method for nursing operation in operating room

Abstract

The invention provides an operating room nursing operation intelligent training system and method, and the method comprises the steps: collecting a nursing operation track of a target user in a high-fidelity operation situation simulation environment matched with a target operation type in real time, generating a deviation map of the nursing operation track and a standard operation, and recognizing a space-time operation abnormality feature in the deviation map; determining a pressure load index of the target user when the emergency event occurs according to the combined characteristics of the various physiological signals of the target user on frequency change in combination with heart rate variability, and when the pressure load index exceeds a preset psychological pressure threshold value, guiding the target user to relieve psychological pressure and recording a physiological stress state track of the target user; and carrying out emergency response training on the target user based on the spatio-temporal operation abnormal features and the physiological stress state trajectory pushing special training strategy. By adopting the scheme of the invention, an adaptive intraoperative nursing emergency response capability training system can be constructed to perform dynamic intervention training on the intraoperative emergency response capability of nursing personnel.

Description

Technical Field

[0001] This application relates to the field of intelligent training technology, and more specifically, to an intelligent training system and method for operating room nursing operations. Background Technology

[0002] In modern clinical surgical environments, nurses not only need to possess proficient nursing skills, but also the psychological stability and emergency response capabilities to quickly deal with unexpected situations during surgery. With the development of digital technology and intelligent training platforms, more and more medical institutions are trying to improve nurses' operational stability and adaptability in surgical environments through simulation training systems.

[0003] However, most existing simulation training methods only focus on standardized training of nursing operation procedures, lacking real-time assessment and control of nurses' psychological stress responses in intraoperative emergency situations. They cannot develop personalized emergency training plans based on the operational deficiencies and psychological load of target users, and generally ignore the impact of nurses' psychological state on nursing decisions and response behaviors, resulting in a gap between training effects and real clinical performance. Therefore, how to construct an adaptive intraoperative nursing emergency response capability training system to dynamically intervene and train nurses' intraoperative emergency response capabilities has become a challenge for the industry. Summary of the Invention

[0004] This application provides an intelligent training system and method for operating room nursing operations, which can construct an adaptive intraoperative nursing emergency response capability training system to dynamically intervene and train nursing staff's intraoperative emergency response capabilities.

[0005] Firstly, this application provides a method for training intraoperative emergency response in operating room nursing procedures, which trains the intraoperative emergency response capabilities of target users during operating room nursing procedure training. The method includes: A high-fidelity surgical scenario simulation environment matching the target surgical type is generated by using a dynamic scene generation engine combined with a surgical emergency knowledge graph in the medical system. The system collects the nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment in real time. Based on the spatiotemporal dependence characteristics of the standard operation in the high-fidelity surgical scenario simulation environment, it generates a deviation map between the nursing operation trajectory and the standard operation. Then, it identifies the spatiotemporal operation abnormal characteristics of the target user when performing nursing operations in the high-fidelity surgical scenario simulation environment in the deviation map. Based on the combined characteristics of the frequency changes of various physiological signals of the target user in the high-fidelity surgical scenario simulation environment, combined with the target user's heart rate variability, the stress load index of the target user's psychological state when an emergency occurs is determined. When the stress load index exceeds the preset psychological stress threshold, the target user is guided to relieve psychological stress through the breathing regulation engine and the target user's physiological stress dynamic trajectory is recorded. Based on the spatiotemporal operational anomaly characteristics and the physiological stress dynamic trajectory, the intraoperative stress response efficacy index of the target user in emergency response to operating room nursing operations is determined. Then, based on the intraoperative stress response efficacy index, a special training strategy matching the target user's current ability is pushed to conduct emergency response training for the target user.

[0006] In some embodiments, generating a deviation map between the nursing operation trajectory and the standard operation based on the spatiotemporal dependence characteristics of the standard operation in the high-fidelity surgical scenario simulation environment specifically includes: Obtain the standard operation sequence corresponding to the high-fidelity surgical scenario simulation environment; By jointly encoding the occurrence time and spatial location of action nodes in the nursing standard operation sequence, the spatiotemporal dependency features of the standard operation in the high-fidelity surgical scenario simulation environment are obtained; The spatiotemporal trajectory characteristics of the target user's nursing operation are determined based on the occurrence time and spatial location of the action nodes in the nursing operation trajectory. By comparing the deviations of the spatiotemporal dependency features and the spatiotemporal trajectory features, an error vector field between the target user's nursing operation and the standard operation is obtained. The deviation map between the nursing operation trajectory and the standard operation sequence is determined based on the error vector field.

[0007] In some embodiments, identifying spatiotemporal operational anomalies of a target user performing nursing procedures in a high-fidelity surgical simulation environment within the deviation map specifically includes: The standard error distribution of the target user performing nursing operations in a high-fidelity surgical simulation environment is determined based on the deviation map. Extract the dynamic error characteristics of the target user during the nursing operation process from the standard error distribution; Based on the dynamic error characteristics, anomalies are identified in the nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment, and all abnormal spatiotemporal points with operational defects are obtained. Based on all anomalous spatiotemporal points, determine the anomalous spatiotemporal operational characteristics of the target user when performing nursing operations in a high-fidelity surgical scenario simulation environment.

[0008] In some embodiments, determining the stress load index of the target user's psychological state during an emergency event based on the joint characteristics of frequency changes of various physiological signals in the high-fidelity surgical scenario simulation environment, combined with the target user's heart rate variability, specifically includes: When an emergency event is triggered, various physiological signals of the target user are collected; Joint feature extraction is performed on all physiological signals to obtain joint features of frequency changes in various physiological signals; Determine the heart rate variability of the target user at the time the emergency event is triggered; By fusing the joint features with the heart rate variability, a stress load index of the target user's psychological state during an emergency is obtained.

[0009] In some embodiments, the breathing regulation engine, based on mindfulness-based stress reduction therapy, combines text prompts, visual animations, and voice prompts to guide the target user to focus on the present breathing rhythm to achieve self-regulation.

[0010] In some embodiments, determining the intraoperative stress response efficacy index of the target user in terms of emergency response to operating room nursing procedures based on the spatiotemporal operational anomaly characteristics and the physiological stress dynamic trajectory specifically includes: The spatiotemporal operational anomaly features and the physiological stress dynamic trajectory are fused to generate a joint state vector of the target user in operating room nursing operations. Based on the joint state vector, the target user's ability fit is scored to obtain the target user's intraoperative stress response efficacy index in terms of emergency response to operating room nursing operations.

[0011] In some embodiments, the specialized training strategy includes multiple specialized training modules that match the current state of the target user, and the corresponding specialized training modules are activated to conduct emergency response training for the target user.

[0012] Secondly, this application provides an intelligent training system for operating room nursing operations, which includes an emergency response training unit, the emergency response training unit comprising: The data acquisition module is used to generate a high-fidelity surgical scenario simulation environment that matches the target surgical type by combining a dynamic scene generation engine with a surgical emergency knowledge graph in the medical system. The processing module is used to collect the nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment in real time, generate the deviation map between the nursing operation trajectory and the standard operation based on the spatiotemporal dependence characteristics of the standard operation in the high-fidelity surgical scenario simulation environment, and then identify the spatiotemporal operation abnormal characteristics of the target user when performing nursing operations in the high-fidelity surgical scenario simulation environment in the deviation map. The processing module is used to determine the stress load index of the target user's psychological state when an emergency occurs based on the combined characteristics of the frequency changes of various physiological signals in the high-fidelity surgical scenario simulation environment and the target user's heart rate variability. When the stress load index exceeds the preset psychological stress threshold, the module guides the target user to relieve psychological stress through the breathing regulation engine and records the target user's physiological stress dynamic trajectory. The execution module is used to determine the intraoperative stress response efficacy index of the target user in terms of emergency response to operating room nursing operations based on the spatiotemporal operation anomaly characteristics and the physiological stress dynamic trajectory, and then push a special training strategy that matches the target user's current ability to conduct emergency response training for the target user based on the intraoperative stress response efficacy index.

[0013] Thirdly, this application provides a computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described intraoperative emergency response training method for operating room nursing operations.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intraoperative emergency response training method for operating room nursing operations.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The intelligent training system and method for operating room nursing operations provided in this application first utilizes a dynamic scene generation engine combined with a surgical emergency knowledge graph in the medical system to generate a high-fidelity surgical scenario simulation environment that matches the target surgical type; it then collects the nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment in real time, generates a deviation map between the nursing operation trajectory and the standard operation based on the spatiotemporal dependence characteristics of the standard operation in the high-fidelity surgical scenario simulation environment, and identifies the spatiotemporal operation abnormalities of the target user when performing nursing operations in the high-fidelity surgical scenario simulation environment in the deviation map; based on the target user's performance in the high-fidelity surgical scenario simulation environment... The combined characteristics of frequency changes in various physiological signals in the environment, combined with the target user's heart rate variability, determine the stress load index of the target user's psychological state during an emergency. When the stress load index exceeds a preset psychological stress threshold, the target user is guided to relieve psychological stress through a breathing regulation engine, and the target user's physiological stress dynamic trajectory is recorded. Based on the spatiotemporal operational anomaly characteristics and the physiological stress dynamic trajectory, the intraoperative stress response efficacy index of the target user in emergency response to operating room nursing operations is determined. Then, based on the intraoperative stress response efficacy index, a specialized training strategy matching the target user's current capabilities is pushed to conduct emergency response training for the target user.

[0016] Therefore, this application utilizes the intraoperative stress response efficacy index to push specialized training strategies that match the target user's current capabilities for emergency response training. First, identifying spatiotemporal operational anomalies provides structured information reflecting problems in the target user's actual nursing operations within a high-fidelity surgical simulation environment. This identification allows for precise location of spatial positional deviations and temporal rhythm errors in nursing operations and reveals the target user's deviations in nursing operation steps, providing data support for subsequent training plan development and effectiveness evaluation. This improves the target user's operational skills, reduces the error rate in actual work, and ensures patient safety. Second, determining the physiological stress dynamic trajectory yields a curve reflecting the trend of ECG signal changes during nursing operation training. This determination reflects the target user's immediate psychological and physiological response dynamics under emergency high-pressure conditions and the target user's physiological response to mindfulness-guided breathing. Adaptability, thereby enhancing the adaptability and real-time nature of the dynamic training plan to the target user's state, enables the training system to not only identify operational deviations but also provide real-time intervention capabilities based on psychological states, thus strengthening the system's "human-machine co-adaptation" performance. Finally, determining the intraoperative stress response efficacy index provides an indicator to measure the target user's comprehensive operational performance and psychological resilience in the face of emergencies during operating room nursing operation training. The determination of the intraoperative stress response efficacy index allows for precise matching of training content with the target user's current capabilities, enabling adaptive adjustments to address specific deficiencies in operational skills and psychological resilience. This promotes repeated consolidation of skill points and effective training of stress patterns in specific emergency scenarios, thereby comprehensively improving the target user's overall emergency response capabilities in real surgical environments. In summary, based on the above scheme, an adaptive intraoperative nursing emergency response capability training system can be constructed to dynamically intervene and train nursing staff's intraoperative emergency response capabilities. Attached Figure Description

[0017] Figure 1 This is an exemplary flowchart of an intraoperative emergency response training method for operating room nursing procedures according to some embodiments of this application; Figure 2 This is an exemplary flowchart illustrating the determination of a deviation map according to some embodiments of this application; Figure 3 This is a schematic diagram illustrating an application scenario of an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an emergency response training unit according to some embodiments of this application; Figure 5 This is an internal structural diagram of a computer device for implementing an intraoperative emergency response training method for operating room nursing operations, according to some embodiments of this application. Detailed Implementation

[0018] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] refer to Figure 1 The figure is an exemplary flowchart of an intraoperative emergency response training method for operating room nursing operations according to some embodiments of this application. The intraoperative emergency response training method 100 for operating room nursing operations mainly includes the following steps: In step 101, a high-fidelity surgical scenario simulation environment matching the target surgical type is generated by using a dynamic scene generation engine combined with a surgical emergency knowledge graph in the medical system.

[0020] It should be noted that in this application, the high-fidelity surgical scenario simulation environment is a virtual environment driven by high-fidelity simulation technology and medical emergency knowledge graph. This high-fidelity surgical scenario simulation environment can be used to reproduce nursing operations under a predetermined surgical type, thereby safely and efficiently improving the target user's ability to cope with actual surgical emergency situations, and effectively reducing training risks, improving operational proficiency and team collaboration efficiency.

[0021] In specific implementation, the generation of a high-fidelity surgical scenario simulation environment matching the target surgical type using a dynamic scene generation engine combined with a surgical emergency knowledge graph in the medical system can be achieved in the following way: First, clinical guidelines and emergency procedures for clinical surgery can be obtained from existing clinical practice guidelines of the Emergency Surgery Society. Based on these clinical guidelines and emergency procedures, a surgical emergency knowledge graph can be constructed in a graph database management system (such as the Neo4j graph database). After the target user selects the target surgical type (e.g., "cesarean section") on the interface, the user can extract the subgraph matching the target surgical type scenario from the surgical emergency knowledge graph by executing a query statement. Then, the subgraph of the knowledge graph can be input into the dynamic scene generation engine (…). (e.g., Unreal Engine), by importing standardized operating room equipment and high-precision 3D anatomical models, a virtual nursing training environment with lighting, physical interaction, and multi-view rendering can be quickly built and output, which is completely matched with the target surgical type. The surgical emergency knowledge graph is a network structure graph that represents the dependencies between surgical types, emergency events, and nursing operations. Nodes represent surgical types, emergency events, and nursing operations, and edges represent semantic relationships such as "trigger-treatment" and "dependency-prerequisite". This surgical emergency knowledge graph provides queryable emergency process subgraphs as parameterized inputs to achieve dynamic assembly and intelligent triggering of nursing scenarios for different surgical types, thereby significantly improving the relevance and practicality of the training scenarios.

[0022] It should be noted that a dynamic scene generation engine is a system capable of constructing and rendering a 3D virtual environment in real time based on input structured data (such as knowledge graphs, text descriptions, or target user behavior). It achieves highly customizable and interactive virtual scene generation by automatically loading and combining scene elements, animations, and interactive logic. Furthermore, the dynamic scene generation engine's blueprint visualization scripts and powerful physical simulation capabilities enable developers to quickly implement complex scene interactions and logic controls, improving development efficiency and scene realism. In this application, the dynamic scene generation engine is responsible for constructing a high-fidelity, interactive virtual training environment in real time based on surgical types and emergency knowledge graphs, effectively shortening scene setup time, improving training consistency, and ensuring scene accuracy for different surgical types.

[0023] In step 102, the nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment is collected in real time. Based on the spatiotemporal dependence characteristics of the standard operation in the high-fidelity surgical scenario simulation environment, a deviation map between the nursing operation trajectory and the standard operation is generated. Then, the spatiotemporal operation abnormal characteristics of the target user when performing nursing operations in the high-fidelity surgical scenario simulation environment are identified in the deviation map.

[0024] It should be noted that in this application, the real-time acquisition of the nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment can be achieved in the following way: In the high-fidelity surgical scenario simulation environment, firstly, the three-dimensional coordinates of the key joints of the target user's hand can be obtained at preset acquisition time intervals (e.g., one minute) using a depth camera, and the acceleration and angular velocity of the target user's hand can be acquired at preset acquisition time intervals (e.g., one minute) using an inertial measurement unit worn on the target user's wrist; then, existing trajectory fusion algorithms (such as extended Kalman filtering or complementary filtering algorithms) can be used to fuse the data. The three-dimensional coordinates of key joints of the target user's skeleton, along with the acceleration and angular velocity of the hand, are used to generate a nursing operation trajectory for the target user in a high-fidelity surgical simulation environment. This nursing operation trajectory refers to the spatiotemporal data of the hand movement path and operation steps recorded by the target user during nursing operations in the high-fidelity surgical simulation environment. In this solution, the nursing operation trajectory can be used to comprehensively assess the target user's operational skills and behavioral norms. By comparing the nursing operation trajectory with standard operating procedures, deviations and deficiencies in the target user's operation can be identified in a timely manner, thereby enabling the development of personalized training plans to improve nursing quality and patient safety.

[0025] In some embodiments, reference Figure 2The figure is an exemplary flowchart illustrating the determination of a deviation map according to some embodiments of this application. In this application, generating the deviation map between the nursing operation trajectory and the standard operation based on the spatiotemporal dependence characteristics of the standard operation in the high-fidelity surgical scenario simulation environment can be achieved using the following steps: In step 1021, the standard operation sequence corresponding to the high-fidelity surgical scenario simulation environment is obtained; In step 1022, the occurrence time and spatial location of the action nodes in the nursing standard operation sequence are jointly encoded to obtain the spatiotemporal dependency features of the standard operation in the high-fidelity surgical scenario simulation environment; In step 1023, the spatiotemporal trajectory characteristics of the target user's nursing operation are determined based on the occurrence time and spatial location of the action nodes in the nursing operation trajectory; In step 1024, the spatiotemporal dependency features and the spatiotemporal trajectory features are compared to obtain the error vector field between the target user's nursing operation and the standard operation. In step 1025, the deviation map between the nursing operation trajectory and the standard operation sequence is determined based on the error vector field.

[0026] It should be noted that in this application, the standard operating sequence is a predefined template that precisely describes the ideal nursing operation process in chronological order and spatial location. It includes the three-dimensional coordinates and time nodes of each action node in the nursing operation process. This standard operating sequence provides a unified evaluation benchmark for training, enabling the system to accurately identify and correct the operation deviations of the target user, thereby significantly improving the training effect and safety. In specific implementation, the standard operating sequence corresponding to the high-fidelity surgical scenario simulation environment can be obtained in the following way: the standard operating sequence matching the target surgical type corresponding to the high-fidelity surgical scenario simulation environment can be obtained in the surgical emergency knowledge graph through a query statement (such as a relational execution query statement).

[0027] In specific implementation, the occurrence time and spatial location of the action nodes in the nursing standard operation sequence are jointly encoded to obtain the spatiotemporal dependency features of the standard operation in the high-fidelity surgical scenario simulation environment. This can be achieved in the following way: the three-dimensional coordinates and time nodes of each action node in the nursing standard operation sequence can be input into an existing spatiotemporal encoder (such as a dual-stream spatiotemporal encoder) for encoding, and the high-dimensional spatiotemporal embedding vector obtained by encoding can be used as the spatiotemporal dependency features of the standard operation in the high-fidelity surgical scenario simulation environment. The spatiotemporal dependency features are high-dimensional embedding vectors that represent the intrinsic spatial and temporal correlation between each action node in the nursing standard operation sequence. These spatiotemporal dependency features can provide a precise reference for trajectory alignment and deviation map generation, greatly improving the sensitivity and positioning accuracy of deviation detection.

[0028] It should be noted that in the spatiotemporal encoder, the spatial branch uses a graph convolutional network based on skeleton topology to capture the structural dependencies between action nodes and aggregates the features of adjacent nodes layer by layer according to a predefined or self-learned adjacency matrix. The temporal branch extracts long-range temporal correlations across frames through a multi-head self-attention mechanism and retains temporal order information through position encoding. The two outputs are then concatenated and linearly mapped to obtain a high-dimensional spatiotemporal embedding vector that displays spatial and temporal features.

[0029] In specific implementation, determining the spatiotemporal trajectory features of the target user's nursing operation based on the occurrence time and spatial location of the action nodes in the nursing operation trajectory can be achieved in the following way: the three-dimensional coordinates and time nodes of each action node in the nursing operation trajectory can be input into an existing spatiotemporal encoder (such as a dual-stream spatiotemporal encoder) for encoding, and the high-dimensional spatiotemporal embedding vector obtained by encoding can be used as the spatiotemporal trajectory features of the target user's nursing operation; wherein, the spatiotemporal trajectory features are high-dimensional embedding vectors that represent the intrinsic spatial and temporal correlation between each action node in the target user's nursing operation trajectory. This spatiotemporal dependency feature can achieve accurate alignment and deviation quantification of the target user's actions and the standard template, thereby quickly identifying and reporting operational defects.

[0030] In specific implementation, the error vector field between the target user's nursing operation and the standard operation can be obtained by comparing the deviations of the spatiotemporal dependency features and the spatiotemporal trajectory features. This can be achieved in the following way: the spatiotemporal dependency features and the spatiotemporal trajectory features can be spatially offset using existing matching algorithms (such as dynamic time warping algorithms) to obtain the error vector field between the target user's nursing operation and the standard operation. The dynamic time warping algorithm can calculate the optimal alignment path based on the minimum cumulative distance and calculate the three-dimensional spatial offset vector, time error vector, and velocity error vector point by point along the optimal matching path. Then, the three-dimensional spatial offset vector, time error vector, and velocity error vector are merged into an error vector field to quantify the degree of deviation at each spatiotemporal node. The error vector field is a field composed of vectors that measure the three-dimensional spatial offset, time delay, and velocity difference between the target user's nursing trajectory and the standard operation sequence at each spatiotemporal node. This error vector field can be used to accurately quantify and visualize small deviations in nursing operations, thereby achieving precise defect localization and targeted training.

[0031] In specific implementation, the deviation map between the nursing operation trajectory and the standard operation sequence can be determined based on the error vector field in the following way: First, the composite error vector of each time node in the error vector field can be summarized into a two-dimensional matrix with the target user time axis and the standard time axis as coordinates by weighted accumulation method to form a deviation matrix. Then, the deviation matrix can be visualized and rendered using existing visualization rendering functions (such as the imshow function in the Matplotlib visualization library) to output a heat map image and highlight typical error areas on the heat map image. Finally, the marked heat map image is used as the deviation map between the nursing operation trajectory and the standard operation sequence.

[0032] It should be noted that in this application, the deviation map is a visualized deviation matrix that displays the errors between the target user's operation and the standard operation in multiple dimensions such as spatial location, time progress and speed. This deviation map can clearly quantify and locate the high-incidence areas of deviation between the target user's nursing operation and the standard procedure, thereby laying the foundation for real-time identification of operational defects and providing accurate corrective feedback.

[0033] In some embodiments, identifying spatiotemporal operational anomalies of a target user performing nursing procedures in a high-fidelity surgical simulation environment within the deviation map can be achieved through the following steps: The standard error distribution of the target user performing nursing operations in a high-fidelity surgical simulation environment is determined based on the deviation map. Extract the dynamic error characteristics of the target user during the nursing operation process from the standard error distribution; Based on the dynamic error characteristics, anomalies are identified in the nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment, and all abnormal spatiotemporal points with operational defects are obtained. Based on all anomalous spatiotemporal points, determine the anomalous spatiotemporal operational characteristics of the target user when performing nursing operations in a high-fidelity surgical scenario simulation environment.

[0034] In specific implementation, determining the standard error distribution of the target user performing nursing operations in a high-fidelity surgical simulation environment based on the deviation map can be achieved in the following way: First, existing data smoothing methods (such as Gaussian smoothing) can be used to smooth the deviation map to weaken high-frequency noise and enhance spatial consistency. Then, the smoothed matrix values ​​are transformed into a distribution with a mean of zero and a variance of one to unify the error scale and accelerate the convergence of subsequent calculations. Next, the standard error value of each spatial location in the deviation map is calculated, and the standard error values ​​of all spatial locations are rearranged into a standard error distribution matrix of the same size as the deviation map. The standard error distribution matrix is ​​used as the standard error distribution when the target user performs nursing operations in a high-fidelity surgical simulation environment. The standard error distribution is a graph showing the accuracy of the target user's operation in different nursing operations. The standard error distribution intuitively reflects the concentration of local errors and the global distribution characteristics of the entire nursing operation process, providing a reliable benchmark input for subsequent dynamic error feature extraction and defect identification. At the same time, the standard error distribution can be used to quickly identify the key operations and key moments with the most significant error fluctuations, thereby accurately focusing on dynamic error feature extraction and defect identification, improving detection efficiency and reliability.

[0035] In specific implementation, extracting the dynamic error features of the target user during nursing operations from the standard error distribution can be achieved in the following way: First, the standard error distribution map is divided into multiple two-dimensional frame sequences in chronological order. Then, an existing neural network (such as a two-dimensional convolutional neural network) can be used to identify defects in the target user's nursing operations based on all the two-dimensional frame sequences to obtain the dynamic error features of the target user during the nursing operations. The neural network can automatically learn the spatial error pattern in each two-dimensional frame sequence. Convolutional and pooling layers can extract local error feature maps and flatten the output feature vectors. Subsequently, these feature vectors are input into a long short-term memory network in chronological order to capture the dynamic dependency of errors evolving with the operation process. The hidden states of the long short-term memory network can effectively model long-range temporal dependencies, making the feature vector sequence reflect the time-varying error features in the operation and outputting the dynamic error feature embedding generated at each time step. Then, all the dynamic error feature embeddings are concatenated through a fully connected layer to obtain the dynamic error features. The dynamic error features refer to high-dimensional vectors describing the evolution trend of the target user's operational errors with the nursing operation process. These dynamic error features can be used to identify and quantify operational defects, thereby significantly improving the targeting and effectiveness of training feedback.

[0036] In specific implementation, the abnormal identification of the target user's nursing operation trajectory in the high-fidelity surgical simulation environment based on the dynamic error characteristics can be achieved in the following way: First, the dynamic error characteristics are input into a sparse covariance matrix to purify the feature correlation. Then, an existing unsupervised anomaly detection algorithm (such as the isolated forest algorithm) can be used to identify the abnormal score of each spatiotemporal node in the target user's nursing operation trajectory in the high-fidelity surgical simulation environment based on the purified dynamic error characteristics. Finally, all spatiotemporal nodes with scores exceeding the threshold are filtered out according to a set threshold (such as 0.7), and these spatiotemporal nodes with scores exceeding the threshold are regarded as abnormal spatiotemporal points with operational defects, thus obtaining all abnormal spatiotemporal points with operational defects. Here, the abnormal spatiotemporal point is a coordinate point that displays the time and space coordinates of the abnormal operation event in the target user's nursing operation. The abnormal spatiotemporal point can accurately locate the specific error of the target user in the nursing operation process. In this solution, identifying these abnormal spatiotemporal points can be used to accurately capture the time and location of the operation defect, thereby realizing accurate evaluation and personalized training feedback of the nursing operation.

[0037] It should be noted that, in this application, the spatiotemporal operational anomaly features are structured information reflecting problems existing in the actual nursing operations of the target user in a high-fidelity surgical simulation environment. In this solution, these spatiotemporal operational anomaly features can be used to accurately locate spatial position deviations and temporal rhythm errors in nursing operations, and provide data support for subsequent training plan development and effect evaluation, thereby improving the target user's operational skills, reducing the error rate in actual work, and ensuring patient safety. Specifically, the spatiotemporal operational anomaly features of the target user in a high-fidelity surgical simulation environment can be determined based on all abnormal spatiotemporal points in the following way: Existing classification models (such as support vector machines or decision trees) can be used to perform cluster analysis on all abnormal spatiotemporal points through density-based spatial clustering algorithms, and the clustered abnormal spatiotemporal points can be mapped to predefined operational defect types (such as "omission of disinfection steps" or "incorrect instrument placement") to generate a structured defect feature set containing defect type, occurrence time, spatial location, and severity. This structured defect feature set is then used as the spatiotemporal operational anomaly features of the target user in a high-fidelity surgical simulation environment.

[0038] In step 103, the stress load index of the target user's psychological state during an emergency is determined based on the combined characteristics of the frequency changes of various physiological signals in the high-fidelity surgical scenario simulation environment and the target user's heart rate variability. When the stress load index exceeds the preset psychological stress threshold, the target user is guided to relieve psychological stress through the breathing regulation engine and the target user's physiological stress dynamic trajectory is recorded.

[0039] In some embodiments, determining the stress load index of the target user's psychological state during an emergency event based on the joint characteristics of frequency changes of various physiological signals in the high-fidelity surgical scenario simulation environment, combined with the target user's heart rate variability, can be achieved through the following steps: When an emergency event is triggered, various physiological signals of the target user are collected; Joint feature extraction is performed on all physiological signals to obtain joint features of frequency changes in various physiological signals; Determine the heart rate variability of the target user at the time the emergency event is triggered; By fusing the joint features with the heart rate variability, a stress load index of the target user's psychological state during an emergency is obtained.

[0040] In specific implementation, when an emergency event is triggered, the collection of various physiological signals of the target user can be achieved in the following way: when an emergency event is triggered in a high-fidelity surgical scenario simulation environment, wearable devices (such as ECG monitoring chest straps and respiratory sensors) collect the target user's ECG and respiratory signals at preset collection time intervals (such as one minute), and use the collected ECG and respiratory signals as the target user's physiological signals; wherein, the physiological signals refer to the electrophysiological activity signals generated by the human body under the regulation of the autonomic nervous system, such as ECG or respiratory signals. These physiological signals can objectively reflect the target user's physiological and psychological state. In this scheme, the collection and analysis of physiological signals can accurately assess the target user's psychological stress level in an emergency event, providing a scientific basis for personalized stress intervention and nursing training.

[0041] In specific implementation, joint feature extraction of all physiological signals to obtain joint features of various physiological signals in terms of frequency changes can be achieved in the following way: First, the electrocardiogram (ECG) signal can be segmented using a sliding window technique (e.g., a 60-second window with 30-second overlap), and the segmented ECG signal can be analyzed in the frequency domain using existing feature extraction methods (e.g., Fast Fourier Transform) to obtain the frequency domain features of the ECG signal; then, the respiratory signal can be segmented using a sliding window technique (e.g., a 60-second window with 30-second overlap), and the segmented respiratory signal can be analyzed in the frequency domain using existing feature extraction methods (e.g., Fast Fourier Transform) to obtain the frequency domain features of the respiratory signal; finally, the multidimensional features composed of the frequency domain features of the ECG signal and the respiratory signal are used as the joint features of various physiological signals in terms of frequency changes. The joint features are multidimensional features reflecting the frequency changes of the target user's autonomic nervous system activity signals. These joint features can objectively assess the target user's psychological stress level under emergency events, providing a scientific basis for real-time monitoring and intervention.

[0042] In practice, determining the heart rate variability of the target user at the time of an emergency event can be achieved as follows: First, acquire the target user's electrocardiogram (ECG) signal at the time of the emergency event. Extract the R-wave peak value from the ECG signal and calculate the time interval between adjacent R waves (i.e., the RR interval). Then, use a histogram method to perform statistical analysis on all RR intervals and draw an RR interval histogram. Next, extract the mode amplitude, modal value, and maximum-minimum difference from the RR interval histogram. Substitute the mode amplitude, modal value, and maximum-minimum difference into the existing stress index calculation formula (e.g., the stress index equals the product of the mode amplitude and the percentage, divided by...). The psychological stress index of the target user is calculated as twice the product of the modal value and the maximum-minimum difference, and this stress index is used as the target user's heart rate variability when an emergency event is triggered. The heart rate variability is a physiological indicator that quantifies the level of sympathetic activation of the human autonomic nervous system. The higher the heart rate variability, the stronger the sympathetic nerve activity and the higher the stress state of the human body. In this scheme, heart rate variability serves as a key physiological indicator for assessing the psychological stress load of the target user in an emergency event. It can reflect the target user's stress state and self-regulation ability in real time, thereby providing a scientific basis for stress intervention and personalized training.

[0043] It should be noted that, in this application, the stress load index is a comprehensive indicator that quantifies the psychological stress level experienced by the target user during an emergency. This stress load index can be used to monitor the stress status of the target user in real time, guide timely intervention and personalized training, and improve the effectiveness of emergency response. Specifically, the stress load index of the target user's psychological state during an emergency can be obtained by feature fusion of the joint features and the heart rate variability as follows: an existing feature fusion model (such as a regression model based on a lightweight gradient booster) can be loaded, the joint features and the heart rate variability can be used as inputs to the feature fusion model, the feature fusion model can be executed to perform feature-level weighted fusion operation, and the latest fused feature value in the output of the feature fusion model can be used as the stress load index of the target user's psychological state.

[0044] It should be noted that in this application, the feature fusion model can capture more comprehensive stress signal patterns by integrating multimodal physiological features. Then, the multimodal physiological features and heart rate variability index are weighted and fitted to learn the relative importance of different features. Finally, the fused feature values ​​with values ​​ranging from 0 to 1 are obtained. The stress load index calculated by the feature fusion model can significantly improve the prediction accuracy and stability of the stress load index. In the case of multi-sensor noise and signal loss, the feature fusion model can automatically compensate for information loss through the remaining features, maintain stable stress assessment capability, realize personalized stress assessment, and provide good interpretability, thereby supporting rapid and scientific intervention decision-making.

[0045] It should be noted that, in this application, the psychological stress threshold refers to the critical point at which the perceived stress intensity of a target user exceeds their coping ability or tolerance range when facing a stressor. In this solution, by setting a psychological stress threshold, the stress response of the target user when an emergency event is triggered can be identified more accurately. Then, based on the target user's stress threshold, customized intervention measures can be provided. When the target user's stress reaches the critical point, timely intervention can be provided to enhance the pertinence and effectiveness of the intervention, improve the target user's coping ability, and thus avoid over-intervention or under-intervention.

[0046] In specific implementation, when the stress load index exceeds a preset psychological stress threshold, the breathing regulation engine can guide the target user to relieve psychological stress in the following way: when the stress load index exceeds the preset psychological stress threshold (e.g., 0.8), the system publishes a "stress overload" event through a message queue, notifying the breathing regulation engine to start. A text prompt, animation, or voice prompt pops up on the client (e.g., mobile phone or VR headset) to guide the target user to perform mindfulness breathing exercises. In this solution, the breathing regulation engine can be set to a slow breathing rhythm of 6 breaths per minute (e.g., 4 seconds of inhalation and 6 seconds of exhalation), and the target user's breathing can be guided synchronously through visual waveforms and voice prompts. In other embodiments, the breathing rhythm of the breathing regulation engine can also be set to other frequencies, which are not specifically limited here.

[0047] It should be noted that in this application, the breathing regulation engine is a digital intervention system module based on mindfulness-based stress reduction therapy. This breathing regulation engine can guide the target user to focus on the current breathing rhythm to achieve self-regulation based on mindfulness-based stress reduction therapy, combined with text prompts, visual animations, and voice prompts. This reduces psychological stress, stabilizes emotions, and improves the balance of the autonomic nervous system. The introduction of the breathing regulation engine can be used to promptly initiate personalized breathing training when the target user's stress load index exceeds a preset psychological stress threshold. At the same time, by collecting and analyzing the target user's physiological signals in real time, it can achieve dynamic monitoring and intervention of stress status, thereby improving the pertinence and effectiveness of training and providing data support for subsequent training plan optimization.

[0048] In specific implementation, the recording of the target user's physiological stress dynamic trajectory can be achieved in the following way: During the process of guiding the target user to perform mindfulness breathing exercises, the target user's electrocardiogram (ECG) signal during mindfulness breathing training can be collected at preset collection intervals (e.g., one second) using a wearable device (e.g., an ECG monitoring chest strap) as the training ECG signal. The curve synthesized by combining the ECG signal collected when the emergency event is triggered with the training ECG signal is used as the target user's physiological stress dynamic trajectory. The physiological stress dynamic trajectory is a trajectory curve that reflects the trend of ECG signal changes during the target user's nursing operation training. In this solution, the physiological stress dynamic trajectory can be used to quantify the target user's physiological response to emergency events and mindfulness breathing guidance, thereby providing personalized training feedback and optimizing subsequent emergency response training plans.

[0049] In step 104, the intraoperative stress response efficacy index of the target user in terms of emergency response to operating room nursing operations is determined based on the spatiotemporal operation anomaly characteristics and the physiological stress dynamic trajectory. Then, based on the intraoperative stress response efficacy index, a special training strategy matching the target user's current ability is pushed to conduct emergency response training for the target user.

[0050] In some embodiments, determining the intraoperative stress response efficacy index of a target user in terms of emergency response to operating room nursing procedures based on the spatiotemporal operational anomaly characteristics and the physiological stress dynamic trajectory can be achieved through the following steps: The spatiotemporal operational anomaly features and the physiological stress dynamic trajectory are fused to generate a joint state vector of the target user in operating room nursing operations. Based on the joint state vector, the target user's ability fit is scored to obtain the target user's intraoperative stress response efficacy index in terms of emergency response to operating room nursing operations.

[0051] In specific implementation, the feature fusion of the spatiotemporal operational anomaly features and the physiological stress dynamic trajectory to generate a joint state vector of the target user in operating room nursing operations can be achieved in the following way: First, the physiological stress dynamic trajectory can be segmented using a sliding window technique (e.g., a 60-second window with 30-second overlap), and existing feature extraction methods (such as Fast Fourier Transform) can be used to perform frequency domain feature analysis on the segmented physiological stress dynamic trajectory to obtain a stress feature vector of the target user's psychological stress changes during nursing operation training; then, the operational feature vector and the stress feature vector can be concatenated with a multidimensional tensor to form a comprehensive joint state vector; wherein, the joint state vector is a multidimensional feature representation that comprehensively describes the target user's skill level and psychological state, and this joint state vector can be used as input for subsequent competency fit scoring, thereby providing data support for the development of personalized and dynamically adjusted operating room nursing emergency response training plans.

[0052] It should be noted that, in this application, the intraoperative stress response efficacy index is an indicator that measures the target user's comprehensive operational performance and psychological resilience in the face of emergencies during operating room nursing operation training. This intraoperative stress response efficacy index can be used to achieve a precise match between training content and the target user's current capabilities, thereby improving the pertinence and effectiveness of emergency response training.

[0053] In specific implementation, the target user's ability fit score is calculated based on the joint state vector to obtain the intraoperative stress response efficacy index of the target user in emergency response to operating room nursing operations. This can be achieved in the following way: a pre-trained ability fit scoring model (such as a lightweight gradient booster model) can be loaded, the joint state vector is input into the ability fit scoring model for ability fit scoring, and the ability score that best matches the target user's current state is output as the target user's intraoperative stress response efficacy index in emergency response to operating room nursing operations. The ability fit scoring model can be trained based on a large number of labeled scoring samples. The input is the target user's action deviation data (such as spatiotemporal operation abnormalities) and physiological stress characteristics (such as physiological stress dynamic trajectories) under a specified nursing task. The output is the target user's intraoperative stress response efficacy index, which is used to quantify the target user's comprehensive coping ability level under intraoperative emergencies.

[0054] It should be noted that in this application, the specialized training strategy is an intelligent training scheme that dynamically adjusts the specialized training modules and their corresponding training difficulty based on the target user's current skill deviation and psychological state. This specialized training strategy includes multiple specialized training modules that match the target user's current state, and the corresponding specialized training modules can be activated to conduct emergency response training for the target user.

[0055] In specific implementation, the emergency response training for the target user, based on the intraoperative stress response efficacy index and matching the target user's current capabilities, can be achieved in the following way: First, a training content decision model (such as a content decision model based on deep reinforcement learning) can be loaded, and the intraoperative stress response efficacy index can be used as the input of the training content decision model. The training content decision model is then executed, and multiple specialized training modules (e.g., fine motor skills training module, instrument placement training module, psychological adjustment training module, and operational sequence reinforcement training module) that best match the target user's current state and their corresponding difficulty levels are output as a set of modules that match the target user's current capabilities. A specialized training strategy is then developed. All specialized training modules and their corresponding difficulty levels within this strategy are output to a mobile app or VR / AR all-in-one device via an API interface. Target users can launch the corresponding specialized training module with a single click. Simultaneously, during the training process, the specialized training module can collect the target user's operational trajectory and physiological signals in real time as input to continuously update the target user profile. The updated target user profile, along with the dynamic training plan, is then input into the competency fit scoring model to train the model. This provides data support for outputting the intraoperative stress response efficacy index for the next round, achieving a closed-loop optimization of training-evaluation-recommendation.

[0056] It should be noted that in this application, the training content decision model adopts a proximal strategy optimization algorithm, taking the intraoperative stress response efficacy index as the input state and outputting the optimal selection of specialized training modules and their corresponding difficulty levels. The action space of this training content decision model covers a variety of specialized training modules (e.g., fine motor skills training, instrument placement training, psychological adjustment training modules, and operation sequence reinforcement training modules) and their different difficulty levels. By designing a reward function, the change in the target user's intraoperative stress response efficacy index after each round of training can be used as the model's reward signal to guide the training content decision model to learn the optimal training content selection strategy. Thus, the system generates personalized specialized training strategies based on the output of the training content decision model, determining the specialized training modules and their difficulty levels that the target user needs to perform in terms of emergency response to operating room nursing operations.

[0057] Additionally, it should be noted that in this application, the specialized training module is a training unit designed for specific emergency response skills or scenarios. This specialized training module provides personalized and contextualized training content by simulating real or virtual emergency situations to improve the target user's operational capabilities and response efficiency in specific emergency situations. In this solution, the specialized training module is matched and pushed according to the target user's nursing operation deviations and psychological state, which can ensure that the training content is consistent with the target user's current skill level and needs, thereby achieving efficient and targeted emergency response training.

[0058] Another aspect of this application, reference to Figure 3 This figure is a schematic diagram of an application scenario of an embodiment of this application. It illustrates the application structure of the intelligent training system for operating room nursing operations and the relationships between its functional modules, including three main parts: the engine device, the emergency response unit, and the specialized training module cluster. The engine device, as the core driving module of the system, includes a dynamic scene generation engine and a breathing regulation engine. The dynamic scene generation engine dynamically generates a high-fidelity surgical scenario simulation environment matching the target surgical type by combining surgical type, risk nodes, and emergency knowledge graphs, providing a realistic operating environment for the training of the emergency response unit. The breathing regulation engine triggers mindful breathing guidance to assist the user in restoring their psychological state when the emergency response unit detects abnormal psychological stress in the user. The emergency response unit monitors the training status of the target user and processes training data, generating control commands to activate the breathing regulation engine and specialized training modules to regulate the target user's psychological state and conduct emergency response training. Specialized training modules are training units designed for specific emergency response skills or scenarios, including but not limited to: fine motor skills training modules, equipment placement training modules, psychological adjustment training modules, and operational sequence reinforcement training modules; the emergency response unit identifies specialized training modules that match the target user's current capabilities and activates the corresponding specialized training modules through control commands for training.

[0059] Furthermore, in another aspect of this application, in some embodiments, this application provides an intelligent training system for operating room nursing operations, the system including an emergency response training unit, referenced... Figure 4 The figure is a schematic diagram of the structure of an emergency response training unit according to some embodiments of this application. The emergency response training unit 400 includes: a data acquisition module 401, a processing module 402, and an execution module 403, which are described below: The acquisition module 401 in this application is mainly used to generate a high-fidelity surgical scenario simulation environment that matches the target surgical type by combining a dynamic scene generation engine with a surgical emergency knowledge graph in the medical system. Processing module 402, in this application, is mainly used to collect the nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment in real time, generate a deviation map between the nursing operation trajectory and the standard operation based on the spatiotemporal dependence characteristics of the standard operation in the high-fidelity surgical scenario simulation environment, and then identify the spatiotemporal operation abnormal characteristics of the target user when performing nursing operations in the high-fidelity surgical scenario simulation environment in the deviation map. It should be noted that the processing module 402 in this application is also used to determine the stress load index of the target user's psychological state when an emergency occurs based on the joint characteristics of the frequency changes of various physiological signals of the target user in the high-fidelity surgical scenario simulation environment and the target user's heart rate variability. When the stress load index exceeds the preset psychological stress threshold, the target user is guided to relieve psychological stress through the breathing regulation engine and the target user's physiological stress dynamic trajectory is recorded. The execution module 403 in this application is mainly used to determine the intraoperative stress response efficacy index of the target user in emergency response to operating room nursing operations based on the spatiotemporal operation abnormality characteristics and the physiological stress dynamic trajectory, and then push a special training strategy that matches the target user's current ability to conduct emergency response training for the target user according to the intraoperative stress response efficacy index.

[0060] Each module in the aforementioned intelligent training system for operating room nursing operations can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0061] In another embodiment, this application provides a computer device, which may be a server, and its internal structure diagram may be as follows. Figure 5 As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data on intraoperative emergency response training methods for operating room nursing procedures. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements an intraoperative emergency response training method for operating room nursing procedures.

[0062] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0063] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps in the above-described embodiment of the intraoperative emergency response training method for operating room nursing operations.

[0064] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described embodiment of the intraoperative emergency response training method for operating room nursing operations.

[0065] In one embodiment, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in the above-described embodiment of the intraoperative emergency response training method for operating room nursing operations.

[0066] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0067] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0068] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. An intraoperative emergency response training method for an operating room nursing operation, which trains an intraoperative emergency response ability of a target user in an operating room nursing operation training, characterized by, The method comprises the following steps: A dynamic scene generation engine is used to generate a high-fidelity surgical scenario simulation environment matched with the target surgical type in combination with the surgical emergency knowledge graph in the medical system; Real-time collection of a nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment, generation of a deviation graph of the nursing operation trajectory and the standard operation according to the spatiotemporal dependence characteristics of the standard operation in the high-fidelity surgical scenario simulation environment, and identification of spatiotemporal operation abnormal characteristics of the target user when performing the nursing operation in the high-fidelity surgical scenario simulation environment in the deviation graph; Determination of a stress load index of the psychological state of the target user when an emergency occurs according to the joint characteristics of various physiological signals of the target user in the high-fidelity surgical scenario simulation environment in the frequency variation in combination with the heart rate variability of the target user, and guidance of the target user to relieve psychological stress through a breathing regulation engine when the stress load index exceeds a preset psychological stress threshold and recording of a physiological stress dynamic trajectory of the target user; Determination of an intraoperative stress response efficiency index of the target user in the emergency response of the nursing operation in the operating room based on the spatiotemporal operation abnormal characteristics and the physiological stress dynamic trajectory, and pushing of a special training strategy matched with the current ability of the target user to the target user for emergency response training according to the intraoperative stress response efficiency index.

2. The method of claim 1, wherein, The generation of the deviation graph of the nursing operation trajectory and the standard operation according to the spatiotemporal dependence characteristics of the standard operation in the high-fidelity surgical scenario simulation environment specifically comprises: Obtaining a standard operation sequence corresponding to the high-fidelity surgical scenario simulation environment; Jointly encoding the occurrence time and spatial position of the action nodes in the nursing standard operation sequence to obtain the spatiotemporal dependence characteristics of the standard operation in the high-fidelity surgical scenario simulation environment; Determining the spatiotemporal trajectory characteristics of the nursing operation of the target user according to the occurrence time and spatial position of the action nodes in the nursing operation trajectory; Comparing the spatiotemporal dependence characteristics and the spatiotemporal trajectory characteristics to obtain an error vector field between the nursing operation of the target user and the standard operation; Determining the deviation graph of the nursing operation trajectory and the standard operation sequence according to the error vector field.

3. The method of claim 1, wherein, The identification of the spatiotemporal operation abnormal characteristics of the target user when performing the nursing operation in the high-fidelity surgical scenario simulation environment in the deviation graph specifically comprises: Determining a standard error distribution of the target user when performing the nursing operation in the high-fidelity surgical scenario simulation environment according to the deviation graph; Extracting dynamic error characteristics of the target user in the nursing operation process in the standard error distribution; Abnormal identification of the nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment according to the dynamic error characteristics to obtain all abnormal spatiotemporal points with operation defects; Determination of the spatiotemporal operation abnormal characteristics of the target user when performing the nursing operation in the high-fidelity surgical scenario simulation environment based on all the abnormal spatiotemporal points.

4. The method of claim 1, wherein, The determination of the stress load index of the psychological state of the target user when an emergency occurs according to the joint characteristics of various physiological signals of the target user in the high-fidelity surgical scenario simulation environment in the frequency variation in combination with the heart rate variability of the target user specifically comprises: collect various physiological signals of a target user when an emergency event is triggered; joint feature extraction is performed on all physiological signals to obtain joint features of various physiological signals in frequency variation; determining heart rate variability of the target user when the emergency event is triggered; characteristic fusion is performed on the joint features and the heart rate variability to obtain a stress load index of the target user in a psychological state when the emergency event occurs.

5. The method of claim 1, wherein, The breathing regulation engine guides the target user to focus on the current breathing rhythm based on mindfulness-based stress reduction therapy combined with text prompts, visual animations and voice prompts to achieve self-regulation.

6. The method of claim 1, wherein, Based on the spatio-temporal operation abnormality features and the physiological stress dynamic trajectory, a surgical stress response efficiency index of the target user in emergency response of the operating room nursing operation is determined, which specifically includes: Feature fusion is performed on the spatio-temporal operation abnormality features and the physiological stress dynamic trajectory to generate a joint state vector of the target user in the operating room nursing operation; According to the joint state vector, an ability adaptation score of the target user is obtained to obtain the surgical stress response efficiency index of the target user in emergency response of the operating room nursing operation.

7. The method of claim 1, wherein, The special training strategy contains a plurality of special training modules matched with the current state of the target user, and the corresponding special training module is started to train the target user in emergency response.

8. An operating room nursing operation intelligent training system, the system comprising an emergency response training unit, characterized in that, The emergency response training unit includes: The acquisition module is used to generate a high-fidelity surgical scenario simulation environment matched with the target surgical type by using a dynamic scene generation engine combined with a surgical emergency knowledge graph in a medical system; The processing module is used to collect a nursing operation trajectory of the target user in the high-fidelity surgical scenario simulation environment in real time, generate a deviation graph of the nursing operation trajectory and standard operation according to the spatio-temporal dependence features of the standard operation in the high-fidelity surgical scenario simulation environment, and further identify spatio-temporal operation abnormality features of the target user in the high-fidelity surgical scenario simulation environment in the deviation graph. The processing module is used to determine a stress load index of a psychological state of the target user when an emergency event occurs according to the joint features of various physiological signals of the target user in frequency variation combined with the heart rate variability of the target user, and guide the target user to relieve psychological stress through the breathing regulation engine when the stress load index exceeds a preset psychological stress threshold and record the physiological stress dynamic trajectory of the target user. The execution module is used to determine a surgical stress response efficiency index of the target user in emergency response of the operating room nursing operation based on the spatio-temporal operation abnormality features and the physiological stress dynamic trajectory, and further push a special training strategy matched with the current ability of the target user to the target user for emergency response training according to the surgical stress response efficiency index. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the surgical emergency response training method of the operating room nursing operation in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to realize the steps of the surgical emergency response training method of the operating room nursing operation in any one of claims 1 to 7.

Images