A method and system for intelligent reminders of nursing interruption events

Abstract

The application relates to a nursing interruption event intelligent reminding method and system and a storage medium. First, a nursing interruption event is accurately recognized and judged, then the social relationship between external personnel and medical staff involved in the nursing interruption event is recognized and judged, the emotion of the external personnel is timely monitored, dangerous behaviors that the external personnel may implement are predicted, the medical staff are reminded, the state of confusion and helplessness when the nursing interruption event occurs is filled, personnel injury that may be caused is avoided, and the influence on patients in the nursing process in the nursing interruption event is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of emergency handling, in particular to a nursing interruption event intelligent reminding method and system. BACKGROUND

[0002] During the process of nursing, treatment, inquiry and surgery, medical staffs may be interrupted, delayed, suspended or terminated due to the interference, dispute or sudden event of external personnel, such as talking, quarreling, protesting and shouting with medical staffs. At this time, both medical staffs and patients may be in a state of confusion and be difficult to accurately judge and correctly respond to the possible danger during the nursing interruption. Moreover, the current emergency event handling lacks effective judgment on nursing interruption events and the correlation of external personnel and social relations, personnel emotions and behaviors, so it is difficult to remind and handle emergencies in the first time. SUMMARY

[0003] The present application aims to provide a nursing interruption event intelligent reminding method and system to solve the technical problems described in the background.

[0004] A nursing interruption event intelligent reminding method, comprising the following steps:

[0005] S100, evaluating a nursing interruption event in a medical environment;

[0006] S110, collecting and preprocessing nursing interruption event related data, including video, image and medical device monitoring data in the nursing process;

[0007] S120, automatically learning features related to the nursing interruption event from the preprocessed data using a convolutional neural network, including interruption, delay, suspension and termination of the nursing, treatment, inquiry and surgery process;

[0008] S130, constructing a neural network model suitable for identifying the nursing interruption event, including multiple convolutional layers, pooling layers and fully connected layers; dividing the data into a training set, a validation set and a test set, and training the neural network model for identifying the nursing interruption event using the training set;

[0009] S140, adjusting the model parameters using the validation set, verifying the trained neural network model suitable for identifying the nursing interruption event, and evaluating the model performance on the test set;

[0010] S150, applying the neural network model suitable for identifying the nursing interruption event to identify the occurrence of the nursing interruption event, and jumping to step 200;

[0011] S200, obtaining identity information of external persons within a certain distance from the medical staff involved in the nursing interruption event, identifying the identity of the external persons; and identifying the relationship between the external persons and the medical staff involved in the nursing interruption event based on the identity of the external persons;

[0012] S300, identifying facial expressions of external personnel and monitoring negative emotions of external personnel;

[0013] S400, identifying the hand and leg movements of the external personnel, predicting that the external personnel's hands and legs will touch the medical personnel, or detecting the external personnel's actions of throwing objects at the medical personnel involved in the nursing interruption event;

[0014] S500: Based on the monitoring results of steps 300 and 400, if any monitoring result reaches a threshold, a reminder is issued to the medical staff involved in the nursing interruption event, and an emergency solution is provided.

[0015] Furthermore, step S200 further includes:

[0016] S210: Obtaining facial print information of an external person through a monitoring device in the medical environment; or obtaining identity-related information of the external person through an identity verification device in the medical environment; and identifying the identity of the external person based on the facial print information or identity-related information of the external person;

[0017] S220: Based on the medical staff information and external personnel identity information involved in the nursing interruption event, obtain the relationship between the external personnel and the medical staff involved in the nursing interruption event, including: the parties or relatives of the medical staff involved in L-level medical accidents within N years; the number of medical disputes involving the external personnel within N years reaches M times;

[0018] S230: Assign an external personnel relationship value A to the interruption event based on the relationship between the external personnel and the medical staff involved in the nursing interruption event. The external personnel relationship value A to the interruption event is a grade rating value. The rating grade is set by the management expert team.

[0019] Furthermore, step S300 further includes:

[0020] S310: Collect a dataset of facial images with different expressions, including multiple expression labels, including: "anger", "hate", "anger", "disgust", "fear", "sadness", "surprise", "happy", and "neutral".

[0021] S320: Locate the face in the image, pre-process the input image, adjust the image size, and obtain the face position detection result;

[0022] S330: Build an expression classification model, input the extracted features into the fully connected layer for classification, and use a labeled facial expression image dataset for training;

[0023] S340: Use the YOLO framework to train the model and adjust training parameters, including learning rate, batch size, and training rounds, to optimize model performance.

[0024] S350: Applying an external person's facial expression recognition model to obtain a recognition result.

[0025] Furthermore, step S400 further includes:

[0026] S410: Define the space of the hand and leg states, including the position, velocity, and acceleration parameters of the hand and leg;

[0027] S420: Randomly sample and generate a series of possible hand and leg states, representing possible positions and motion states of the hands and legs at different time points;

[0028] S430: For each randomly generated state, simulate the movement of the hands and legs;

[0029] S440: For each simulated trajectory, evaluate its likelihood and plausibility using prior knowledge;

[0030] S450: estimating the probability of state transition by statistically analyzing the frequency of each state in the simulation trajectory;

[0031] S460: Aggregate all simulated trajectories to estimate the overall probability distribution of hand and leg movements;

[0032] S470: Based on the aggregated probability distribution, predict the next movement of the hands and legs, thereby predicting that the hands and legs of the external person will touch the medical staff, or monitoring the external person's action of throwing objects at the medical staff involved in the nursing interruption incident.

[0033] Furthermore, step S500 further includes:

[0034] It is detected that the external personnel relationship value A of the interruption event is lower than the threshold, or the negative emotions of the external personnel are detected, or it is predicted that the external personnel's hands or legs will touch the medical staff, or it is detected that the external personnel has the action of throwing objects at the medical staff involved in the nursing interruption event; a reminder message is sent to the medical staff terminal, and a voice alarm sounds on the medical staff terminal to remind the medical staff to evacuate the patient. The medical staff terminal displays the evacuation route; and a reminder message is sent to the security personnel to guide the security personnel to check the on-site situation.

[0035] Furthermore, the medical environment is any one of a hospital, a clinic, a research institute, a pharmacy, and a physical therapy center.

[0036] Furthermore, nursing interruption events include: interrupting or delaying current medical work; and external behaviors that distract doctors and nurses.

[0037] A nursing interruption event intelligent reminder system is used to implement the nursing interruption event intelligent reminder method described above.

[0038] Furthermore, the intelligent reminder system for nursing interruption events also includes:

[0039] Medical staff terminal, used to receive control information sent by the nursing interruption event reminder system server; issue warnings to medical staff; and display emergency solutions;

[0040] Cameras, used to record and transmit videos of medical staff performing their nursing work, to assist in determining the distance between outsiders and the medical staff involved in the nursing interruption incident;

[0041] Authentication device, used to verify the identity-related information of external personnel;

[0042] The server is used to run the intelligent reminder method for nursing interruption events; obtain, process and store nursing work videos of medical staff; obtain, process and store identity-related information; and send control information to medical staff terminals.

[0043] A storage medium for intelligent reminder of nursing interruption events, on which a computer program (instructions) is stored, wherein the computer program (instructions) is used to implement the above-mentioned intelligent reminder method for nursing interruption events.

[0044] Compared with the existing technology, the advantages and positive effects of the present invention are: first, accurately identifying and judging the nursing interruption event, then identifying and judging the social relationship between the external personnel and the medical staff involved in the nursing interruption event, and then timely monitoring the emotions of the external personnel, predicting the dangerous behaviors that the external personnel may perform, and reminding the medical staff, filling the confusion and helplessness when the nursing interruption event occurs, avoiding possible personal injuries, and reducing the impact of the nursing interruption event on patients in the nursing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 This is a schematic diagram of the architecture of an intelligent reminder system for nursing interruption events.

[0047] Figure 2 The present invention is a flowchart of an intelligent reminder method for nursing interruption events.

[0048] Figure 3 The present invention is a flowchart of a nursing interruption event identification process for a nursing interruption event intelligent reminder method.

[0049] Figure 4 A flowchart for identifying external personnel's social relationships in an intelligent reminder method for nursing interruption events.

[0050] Figure 5 This is a schematic diagram of the external personnel emotion recognition process for an intelligent reminder method for nursing interruption events.

[0051] Figure 6 This is a flow chart of monitoring and predicting dangerous actions of external personnel in an intelligent reminder method for nursing interruption events.

[0052] Figure 7 A path distance diagram of an intelligent reminder method for nursing interruption events. DETAILED DESCRIPTION

[0053] The following describes the embodiments of the present invention in conjunction with the accompanying drawings. The terms used in the embodiments of the present invention are only used to explain the specific embodiments of the present invention, and are not intended to limit the present invention.

[0054] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0055] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, and this is merely a way of distinguishing the objects of the same attributes when describing them in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0056] The following describes the embodiments of the present invention in conjunction with the accompanying drawings. The terms used in the embodiments of the present invention are only used to explain the specific embodiments of the present invention, and are not intended to limit the present invention.

[0057] As the instruction manual Figures 1-7 As shown:

[0058] A method for intelligently reminding nursing interruption events, comprising the following steps:

[0059] S100. Assess interruptions of care in healthcare settings:

[0060] Specifically, medical environments include: hospitals, clinics, research institutes, pharmacies, physical therapy clinics, etc.

[0061] S110: Collect and pre-process data related to nursing interruption events, including videos, images, and medical equipment monitoring data during the nursing process.

[0062] Specifically, the preprocessing of data related to nursing interruption events includes: cropping and scaling videos and images; cleaning medical equipment monitoring data; normalization, etc., so that it can be input into the convolutional neural network model.

[0063] S120: Use Convolutional Neural Networks (CNN) to automatically learn features related to nursing interruption events from preprocessed data, including interruptions, delays, suspensions, and terminations of nursing, treatment, consultations, and surgical procedures.

[0064] Specifically, nursing interruptions include: interruptions or delays to current medical work; external behaviors that distract doctors and nurses; and other emergencies. For example, an outsider may chat, argue, protest, or shout at medical staff, interrupting their ongoing nursing, treatment, consultation, surgery, or other medical work.

[0065] S130: Construct a neural network model suitable for identifying nursing interruption events, including: multiple convolutional layers, pooling layers, and fully connected layers; divide the data into a training set, a validation set, and a test set, and use the training set to train the neural network model for identifying nursing interruption events.

[0066] Specifically, during the training process of a neural network model suitable for identifying nursing interruption events, a labeled dataset is used and the network parameters are continuously adjusted through the back-propagation algorithm to minimize the prediction error.

[0067] S140: Use the validation set to adjust model parameters, validate the trained neural network model suitable for identifying nursing interruptions, and evaluate model performance on the test set. This assesses the accuracy and generalization ability of the model in identifying nursing interruptions and prevents overfitting.

[0068] S150: Apply a neural network model suitable for identifying nursing interruption events, identify the occurrence of a nursing interruption event, and jump to step 200.

[0069] S200. Obtain identity-related information of external persons within a certain distance from the medical staff involved in the nursing interruption event, and identify the identity of the external persons; and identify the relationship between the external persons and the medical staff involved in the nursing interruption event based on the identity of the external persons.

[0070] Specifically, the certain distance range is a path distance of 5, 10, 20 meters, etc. The path distance is the length of the route from one location to another, not the straight-line distance between two points in a three-dimensional space, such as Figure 7 As shown in the figure, the path distance from point A to point B is the sum of the plane distance from point A to the stairs, the inclined distance of going up the stairs, and the plane distance from the stairs to point B, rather than the spatial straight-line distance from point A to point B.

[0071] S300: Identify facial expressions of external personnel and monitor negative emotions of external personnel. Negative emotions include: "anger," "hatred," "anger," "disgust," "fear," "sadness," and "surprise."

[0072] S400: Identify the hand and leg movements of the external personnel, predict that the external personnel's hands and legs will touch the medical staff, or monitor the external personnel's actions of throwing objects at the medical staff involved in the nursing interruption incident.

[0073] S500, step 150 identifies the result as "a nursing interruption event has occurred"; based on the identity of the external personnel and the relationship between the medical staff involved in the nursing interruption event, according to the monitoring results of steps 300 and 400, if any monitoring result reaches the threshold, a reminder will be issued to the medical staff involved in the nursing interruption event, and an emergency solution will be provided.

[0074] In this embodiment, the intelligent reminder method for nursing interruption events involved in this application first accurately identifies and determines the nursing interruption events, then identifies and determines the social relationship between the external personnel and the medical staff involved in the nursing interruption events, and then timely monitors the emotions of the external personnel, predicts the dangerous behaviors that may be performed by the external personnel, and reminds the medical staff, filling the confusion and helplessness when the nursing interruption events occur, avoiding possible personal injuries, and reducing the impact of the nursing interruption events on patients in the nursing process.

[0075] Specifically, step S200 further includes:

[0076] S210: Obtain facial print information of an external person through a monitoring device in the medical environment; or obtain identity-related information of the external person through an identity authentication device in the medical environment; and identify the identity of the external person based on the facial print information or identity-related information of the external person.

[0077] Specifically, identity-related information includes: ID card information, hospitalization card information, outpatient card information, consultation QR code information, bed number information, etc.

[0078] S220: Based on the medical staff information involved in the nursing interruption incident and the identity information of the external personnel, the relationship between the external personnel and the medical staff involved in the nursing interruption incident is obtained, including: the parties or relatives of the medical staff involved in the L-level medical accident within N years; the number of medical disputes involved by the external personnel within N years reaches M times.

[0079] S230: According to the relationship between the external personnel and the medical staff involved in the nursing interruption incident, the interruption incident external personnel relationship value A is assigned. The interruption incident external personnel relationship value A is a grade rating value. The rating grade is set by the management expert team. For example: if the medical staff is involved in a party or relative of a third-level medical accident within 0.5 years, the interruption incident external personnel relationship value A=-3; if the external personnel is involved in 6 medical disputes within 2 years, the interruption incident external personnel relationship value A=-2.

[0080] In this embodiment, the intelligent reminder method for nursing interruption events involved in this application can accurately and finely identify and divide the social relationship between external personnel and medical staff involved in the nursing interruption event.

[0081] Specifically, step S300 further includes:

[0082] S310: Collect a dataset of facial images with different expressions, including multiple expression labels, such as "anger", "hate", "anger", "disgust", "fear", "sadness", "surprise", "happy", "grateful", "neutral", etc.

[0083] S320: Locate the face in the image, pre-process the input image, adjust the image size, and obtain the face position detection result.

[0084] S330: Build an expression classification model, input the extracted features into the fully connected layer for classification, and use a labeled facial expression image dataset for training.

[0085] S340: Use the YOLO framework for model training and adjust training parameters, including learning rate, batch size, and training rounds, to optimize model performance.

[0086] S350: Applying an external person's facial expression recognition model to obtain a recognition result.

[0087] In this embodiment, the intelligent reminder method for nursing interruption events involved in this application can quickly and accurately identify the facial expressions of external personnel after a nursing interruption event occurs, thereby improving the robustness of the method and optimizing the training strategy.

[0088] Specifically, step S400 further includes:

[0089] S410: define the space of hand and leg states, including the position, velocity, acceleration, etc. of the hands and legs.

[0090] S420: randomly sample a series of possible hand and leg states, representing the possible positions and motion states of the hands and legs at different time points.

[0091] S430: for each randomly generated state, simulate the motion of the hands and legs.

[0092] S440: for each simulated trajectory, use prior knowledge to evaluate its likelihood and reasonableness.

[0093] S450: estimate the probability of state transition by counting the frequency of each state appearing in the simulated trajectories.

[0094] S460: aggregate all simulated trajectories to estimate the overall probability distribution of hand and leg motion.

[0095] S470: according to the aggregated probability distribution, predict the next step of the hands and legs, and thus predict that the hands and legs of the external personnel will touch the medical staff, or monitor the external personnel's action of throwing objects at the medical staff involved in the care interruption event.

[0096] In this embodiment, the care interruption event intelligent reminding method related to the present application, after the occurrence of the care interruption event, the social relationship of the external personnel is identified, and the identification and judgment of the hand and leg actions of the external personnel can be processed in parallel, which enhances the reliability and accuracy of suspected dangerous action identification.

[0097] Specifically, step S500 further includes:

[0098] When the interruption event external personnel relationship value A is lower than the threshold value, or when the external personnel negative emotion is monitored, or when it is predicted that the hands and legs of the external personnel will touch the medical staff, or when it is monitored that the external personnel has the action of throwing objects at the medical staff involved in the care interruption event, the medical staff terminal sends a reminder information, the medical staff terminal sounds a voice alarm, reminds the medical staff to evacuate the patient, and the medical staff terminal displays the evacuation route; and sends a reminder information to the security personnel, and guides the security personnel to go to the scene to check the situation.

[0099] A care interruption event intelligent reminding system for implementing the care interruption event intelligent reminding method described above, comprising:

[0100] A medical staff terminal for receiving control information sent by the care interruption event reminding system server; sending an alarm to the medical staff; and displaying a sudden situation solution.

[0101] Specifically, medical staff terminals include: mobile phones, notebooks, tablets, wearable devices, smart glasses, smart bracelets, smart watches, etc.

[0102] The camera is used to record and transmit the nursing work video of medical staff to assist in determining the distance between outsiders and medical staff involved in the nursing interruption incident.

[0103] Authentication device, used to verify the identity-related information of external personnel.

[0104] Specifically, identity authentication devices include: facial information collection devices, NFC recognition devices, RFID recognition devices, code scanning devices, etc.

[0105] The server is used to run the intelligent reminder method for nursing interruption events; obtain, process and store nursing work videos of medical staff; obtain, process and store identity-related information; and send control information to medical staff terminals.

[0106] Specifically, the server can be a local server, a cloud server, etc.

[0107] A storage medium for intelligent reminder of nursing interruption events, on which a computer program (instructions) is stored, wherein the computer program (instructions) is used to implement the above-mentioned intelligent reminder method for nursing interruption events.

[0108] It should be noted that the explanations and definitions of the same steps or terms are also applicable to different embodiments. For the sake of brevity, repeated descriptions are appropriately omitted herein.

[0109] Those skilled in the art will appreciate that the functions described in conjunction with the various illustrative logic blocks, modules, and algorithm steps disclosed herein can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions described in the various illustrative logic blocks, modules, and steps can be stored or transmitted as one or more instructions or codes on a computer-readable medium and executed by a hardware-based processing unit. Computer-readable media can include computer-readable storage media, which corresponds to tangible media, such as data storage media, or communication media including any media that facilitates the transfer of computer programs from one place to another (e.g., according to a communication protocol). In this manner, computer-readable media can generally correspond to (1) non-transitory tangible computer-readable storage media, or (2) communication media, such as signals or carrier waves. Data storage media can be any available media that can be accessed by one or more computers or one or more processors to retrieve instructions, codes, and / or data structures for implementing the techniques described in this application. A computer program product can include computer-readable media.

[0110] By way of example, and not limitation, such computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer. Furthermore, any connection is properly referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of medium. However, it should be understood that computer-readable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but are actually directed to non-transitory tangible storage media. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), and Blu-ray disc, where disks typically reproduce data magnetically, while discs reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0111] The corresponding functions may be performed by one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuits. Therefore, the term "processor" as used herein may refer to any of the aforementioned structures or any other structure suitable for implementing the techniques described herein. In addition, in some aspects, the functions described by the various illustrative logic blocks, modules, and steps described herein may be provided within dedicated hardware and / or software modules configured for encoding and decoding, or incorporated into a combined codec. Moreover, the techniques may be fully implemented in one or more circuits or logic elements. In one example, the various illustrative logic blocks, units, and modules in video encoder 20 and video decoder 30 may be understood as corresponding circuit devices or logic elements.

[0112] The techniques of this application can be implemented in a variety of devices or apparatuses, including wireless handsets, integrated circuits (ICs), or a set of ICs (e.g., a chipset). Various components, modules, or units are described herein to emphasize functional aspects of devices for performing the disclosed techniques, but they do not necessarily require implementation by different hardware units. In fact, as described above, the various units may be combined in a codec hardware unit in conjunction with appropriate software and / or firmware, or provided by interoperating hardware units (including one or more processors as described above).

[0113] The above description is merely an exemplary embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for intelligently reminding nursing interruption events, characterized in that the steps include: S100. Assess interruptions of care in healthcare settings: S110: Collect and pre-process data related to nursing interruption events, including videos, images, and medical equipment monitoring data during the nursing process; S120: Using a convolutional neural network to automatically learn features related to nursing interruption events from pre-processed data, including interruptions, delays, suspensions, and terminations of nursing, treatment, consultation, and surgical procedures; S130: Constructing a neural network model suitable for identifying nursing interruption events, including: multiple convolutional layers, pooling layers, and fully connected layers; dividing the data into a training set, a validation set, and a test set, and using the training set to train the neural network model for identifying nursing interruption events; S140: Using the validation set to adjust model parameters, verify the trained neural network model suitable for identifying nursing interruption events, and evaluate the model performance on the test set; S150: applying a neural network model suitable for identifying nursing interruption events, identifying the occurrence of a nursing interruption event, and jumping to step 200; S200, obtaining identity information of external persons within a certain distance from the medical staff involved in the nursing interruption event, identifying the identity of the external persons; and identifying the relationship between the external persons and the medical staff involved in the nursing interruption event based on the identity of the external persons; S300, identifying facial expressions of external personnel and monitoring negative emotions of external personnel; S400, identifying the hand and leg movements of the external personnel, predicting that the external personnel's hands and legs will touch the medical personnel, or detecting the external personnel's actions of throwing objects at the medical personnel involved in the nursing interruption event; S500: Based on the monitoring results of steps 300 and 400, if any monitoring result reaches a threshold, a reminder is issued to the medical staff involved in the nursing interruption event, and an emergency solution is provided.

2. The intelligent reminder method for nursing interruption events according to claim 1 is characterized in that: Step S200 also includes: S210: Obtaining facial print information of an external person through a monitoring device in the medical environment; or obtaining identity-related information of the external person through an identity verification device in the medical environment; and identifying the identity of the external person based on the facial print information or identity-related information of the external person; S220: Based on the medical staff information and external personnel identity information involved in the nursing interruption event, obtain the relationship between the external personnel and the medical staff involved in the nursing interruption event, including: the parties or relatives of the medical staff involved in L-level medical accidents within N years; the number of medical disputes involving the external personnel within N years reaches M times; S230: Assign an external personnel relationship value A to the interruption event based on the relationship between the external personnel and the medical staff involved in the nursing interruption event. The external personnel relationship value A to the interruption event is a grade rating value. The rating grade is set by the management expert team.

3. The intelligent reminder method for nursing interruption events according to claim 2 is characterized in that: Step S300 also includes: S310: Collect a dataset of facial images with different expressions, including multiple expression labels, including: "anger", "hate", "angry", "disgusted", "fear", "sad", "surprised", "happy", and "neutral"; S320: Locate the face in the image, pre-process the input image, adjust the image size, and obtain the face position detection result; S330: Build an expression classification model, input the extracted features into the fully connected layer for classification, and use a labeled facial expression image dataset for training; S340: Use the YOLO framework to train the model and adjust training parameters, including learning rate, batch size, and training rounds, to optimize model performance. S350: Applying an external person's facial expression recognition model to obtain a recognition result.

4. The intelligent reminder method for nursing interruption events according to claim 3 is characterized in that: Step S400 also includes: S410: Define the space of the hand and leg states, including the position, velocity, and acceleration parameters of the hand and leg; S420: Randomly sample and generate a series of possible hand and leg states, representing possible positions and motion states of the hands and legs at different time points; S430: For each randomly generated state, simulate the movement of the hands and legs; S440: For each simulated trajectory, evaluate its likelihood and plausibility using prior knowledge; S450: estimating the probability of state transition by statistically analyzing the frequency of each state in the simulation trajectory; S460: Aggregate all simulated trajectories to estimate the overall probability distribution of hand and leg movements; S470: Based on the aggregated probability distribution, predict the next movement of the hands and legs, thereby predicting that the hands and legs of the external person will touch the medical staff, or monitoring the external person's action of throwing objects at the medical staff involved in the nursing interruption incident.

5. The intelligent reminder method for nursing interruption events according to claim 4 is characterized in that: Step S500 further includes: It is detected that the external personnel relationship value A of the interruption event is lower than the threshold, or the negative emotions of the external personnel are detected, or it is predicted that the external personnel's hands or legs will touch the medical staff, or it is detected that the external personnel has the action of throwing objects at the medical staff involved in the nursing interruption event; a reminder message is sent to the medical staff terminal, and a voice alarm sounds on the medical staff terminal to remind the medical staff to evacuate the patient. The medical staff terminal displays the evacuation route; and a reminder message is sent to the security personnel to guide the security personnel to check the on-site situation.

6. The intelligent reminder method for nursing interruption events according to any one of claims 1 to 5, characterized in that: The medical environment is any one of a hospital, clinic, research institute, pharmacy, and physical therapy center.

7. The intelligent reminder method for nursing interruption events according to any one of claims 1 to 5, characterized in that: Nursing interruption events include: interrupting or delaying current medical work; external behaviors that distract doctors and nurses.

8. A nursing interruption event intelligent reminder system, used to implement the nursing interruption event intelligent reminder method according to any one of claims 1 to 7.

9. The intelligent reminder system for nursing interruption events according to claim 8, characterized in that: Also includes: Medical staff terminal, used to receive control information sent by the nursing interruption event reminder system server; Alert medical staff; Show solutions to emergencies; Cameras, used to record and transmit videos of medical staff performing their nursing work, to assist in determining the distance between outsiders and the medical staff involved in the nursing interruption incident; Authentication device, used to verify the identity-related information of external personnel; A server, configured to run an intelligent reminder method for nursing interruption events; Acquire, process, and store videos of medical staff performing nursing work; acquire, process, and store identity-related information; Control information sent to medical staff terminals.

10. A storage medium for intelligent reminder of nursing interruption events, on which a computer program is stored, wherein the computer program is used to implement the intelligent reminder method for nursing interruption events according to any one of claims 1 to 6.

Images