Wounded personnel management system based on medical care AI robot and application method

Abstract

The invention discloses a wounded person management system based on a medical care AI robot and an application method, and relates to the technical field of artificial intelligence first aid, and the system comprises a triage emergency rescue module which is used for collecting and preprocessing vital sign data, calculating a comprehensive health score based on the preprocessed vital sign data, and carrying out the classification and emergency rescue; and the hospital guide psychological rehabilitation module is used for carrying out hospital guide and treatment according to the classification result, collecting facial expression images of the wounded after treatment and calculating the emotion intensity. According to the invention, a triage emergency rescue module is used for collecting and preprocessing vital sign data, calculating a comprehensive health score and carrying out classification and emergency rescue; the hospital guide psychological rehabilitation module is used for conducting hospital guide and treatment according to the classification result, collecting facial expression images of the wounded after treatment and calculating the emotion intensity; the efficiency and accuracy of emergency treatment are improved, delay and misjudgment in the process of wounded person treatment are reduced, and personalized and accurate suggestions for wounded person treatment are enhanced.

Description

Technical Field

[0001] The present invention relates to artificial intelligence first aid, and in particular to a casualty management system based on a medical care AI robot and an application method. Background Art

[0002] With the continuous advancement of medical technology and the development of artificial intelligence (AI) technology, intelligent medical care systems have gradually become a key tool for improving emergency efficiency, optimizing medical resource allocation and enhancing the feasibility of medical services. The application of AI technology, especially in the medical field, has made significant breakthroughs. Many AI-based systems are designed to assist in diagnosis, monitor patients' vital signs, and even make automated emergency decisions. Modern emergency systems have gradually introduced efficient and intelligent equipment, such as portable heart rate monitors, automatic inflatable cuffs, pulse oximeters, infrared thermometers, etc., which can provide more accurate emergency decision support by collecting the vital signs data of the injured in real time and combining artificial intelligence algorithms for rapid evaluation and processing. The introduction of these technologies not only greatly improves the efficiency of emergency treatment, but also can reduce the work pressure of medical staff to a certain extent, and provide new solutions for medical care work in public emergencies.

[0003] The existing medical care AI robot systems still have many shortcomings. Traditional systems mostly rely on the processing of single or local data, and fail to fully consider the correlation and interaction between various vital signs data, resulting in inaccurate comprehensive assessment of health status during emergency treatment. Faced with huge amounts of casualty data, the existing classification and treatment processes often cannot accurately identify the health status of the casualties, resulting in irrational allocation of emergency resources and failure to provide timely and effective treatment for critically ill patients. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a casualty management system and application method based on a medical care AI robot to solve the problem that traditional systems mostly rely on the processing of single or local data, fail to fully consider the correlation and interaction between various types of vital signs data, resulting in inaccurate comprehensive assessment of health status during first aid. Faced with huge amounts of casualty data, the existing classification and treatment processes often cannot accurately identify the health status of the casualties, resulting in unreasonable allocation of emergency resources and failure to provide timely and effective treatment for critically ill patients.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, the present invention provides a casualty management system based on a medical care AI robot, which includes a triage and emergency rescue module for collecting and preprocessing vital signs data, calculating a comprehensive health score based on the preprocessed vital signs data, and performing classification and emergency rescue; a guidance and psychological rehabilitation module for conducting guidance and treatment based on the classification results, collecting facial expression images of the casualties after treatment, and calculating the intensity of emotions; a visualization storage module for constructing a visualization interface to display the intensity of emotions, and storing the physical sign data collected and analyzed.

[0008] As a preferred solution of the wounded management system based on the medical care AI robot of the present invention, wherein: the collection of vital sign data and preprocessing refers to the medical care AI robot using infrared thermal imaging equipment to scan extremely harsh areas to collect infrared thermal imaging images, and using laser radar to collect point cloud data;

[0009] The collected infrared thermal imaging images and point cloud data are spatially aligned using a spatial alignment method;

[0010] Use image recognition algorithms to identify and mark the location of the injured in infrared thermal imaging images, and use the A* algorithm to plan the path for the marked injured location;

[0011] The medical care AI robot performs path planning and uses the Glasgow Coma Scale and first aid equipment to collect and pre-process the vital signs data of the injured;

[0012] The first aid equipment includes a heart rate monitor, a self-inflating cuff, a pulse oximeter, an infrared thermometer and a chest sensor;

[0013] The vital signs data include Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate;

[0014] The preprocessing includes using a Kalman filter algorithm to perform denoising and filtering, using a Z-score test to identify and delete outliers, using an interpolation method to fill in missing values, and standardizing vital sign data.

[0015] As a preferred solution of the wounded management system based on the medical care AI robot of the present invention, wherein: the calculation of the comprehensive health score based on the pre-processed vital signs data and the classification and emergency rescue refer to setting the number of principal components K using the cumulative variance contribution rate method;

[0016] Calculate the covariance matrix of the standardized vital sign data, perform eigenvalue decomposition on the covariance matrix, and obtain eigenvalues ​​and eigenvectors;

[0017] Sort the eigenvalues ​​from large to small, and select the first K eigenvalues ​​as the main eigenvalues;

[0018] The weight coefficients corresponding to Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate data were calculated using the eigenvector method;

[0019] According to the weight coefficient corresponding to the vital signs data, the comprehensive health score F of the injured is calculated using the weighted average method. The formula is:

[0020] ,

[0021] Among them, Z, A, B, C, D and E are Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate data respectively. , , , , and They are the weight coefficients corresponding to the Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate data;

[0022] Use percentile method to set classification threshold including upper limit , lower limit ;

[0023] Compare the comprehensive health score with the classification threshold. If the comprehensive health score is less than the lower limit, , then it is judged as an emergency wounded person who needs immediate treatment, a red chip mark is made, and emergency rescue is carried out on the wounded;

[0024] If the comprehensive health score is within the classification threshold, the patient is judged as a secondary emergency patient, a yellow chip is marked, and the wound is cleaned and bandaged;

[0025] If the comprehensive health score is greater than the upper limit , it is determined to be an observation wounded person, a yellow chip mark is given, and communication is carried out with the wounded person.

[0026] As a preferred solution of the wounded management system based on the medical care AI robot of the present invention, wherein: the guidance and treatment according to the classification results refers to using the WebSocket protocol to transmit the vital signs data and the classification results to the medical information system platform, and the medical information system platform receives the vital signs data and the classification results;

[0027] Collect and preprocess the historical vital sign data and classification results with labels, and establish a mapping table based on the ICD-10 coding standards in the medical database;

[0028] Use image recognition technology to label injury types in vital sign data;

[0029] According to the injury type and mapping table, the matching department is calculated using the atlas matching algorithm;

[0030] Convert the matching departments into department allocation instructions and transmit them to the medical information system platform to prepare the corresponding medical equipment and drugs for treatment;

[0031] The treatment includes the use of medical care AI robots to perform cardiopulmonary resuscitation, hemostasis, bandaging, fracture fixation, transportation, emergency disinfection of public areas, measurement of vital signs, wound cleaning and dressing changes, intramuscular injections, intravenous punctures, fluid replacement, and rehabilitation training for the wounded.

[0032] As a preferred solution of the wounded management system based on the medical care AI robot of the present invention, wherein: the collecting of facial expression images of the wounded after treatment and calculating the emotional intensity refers to the medical care AI robot using a high-definition camera to collect facial expression images of the wounded after treatment;

[0033] The facial expression images are converted into grayscale images using a single-channel method;

[0034] Use the pre-trained FER-2013 model to analyze the facial expressions of the grayscale images and obtain the probability value of the casualty's emotions;

[0035] According to the probability value of the casualty's emotions, the maximum probability method is used to calculate the emotional intensity of the casualty;

[0036] Use statistical analysis methods to set the judgment threshold, compare the emotion intensity with the judgment threshold, set the emotion intensity greater than or equal to the judgment threshold as normal, and continue to monitor the wounded; set the emotion intensity less than the judgment threshold as abnormal, and activate the psychological dialogue system to provide psychological counseling to the wounded.

[0037] As a preferred solution of the wounded management system based on the medical care AI robot described in the present invention, wherein: the construction of a visual interface to display the emotional intensity refers to using the front-end framework React.js to build a visual interface, and using a data visualization tool to display the wounded's comprehensive health score, classification results, department allocation instructions, and emotional intensity;

[0038] Users who have passed real-name verification are allowed to view the information.

[0039] As a preferred solution of the wounded management system based on the medical care AI robot described in the present invention, the storage, collection and analysis of the physical sign data refers to storing the collected vital sign data, facial expression images and emotion intensity generated by the analysis in a database, and setting security access measures. The database will back up the stored data in the cloud, and regularly perform integrity checks on the stored data and backup data. After the test is completed, an integrity test record is generated and stored synchronously in the database.

[0040] In a second aspect, the present invention provides an application method for wounded management based on a medical care AI robot, comprising:

[0041] Collect and preprocess vital sign data, calculate comprehensive health scores based on the preprocessed vital sign data, and perform classification and emergency rescue;

[0042] Provide guidance and treatment based on the classification results, collect facial expression images of the injured after treatment, and calculate the intensity of emotions;

[0043] Build a visual interface to display the intensity of emotions, and store the physical sign data collected and analyzed.

[0044] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the casualty management system based on the medical care AI robot as described in the first aspect of the present invention.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the casualty management system based on the medical care AI robot as described in the first aspect of the present invention.

[0046] The beneficial effects of the present invention are as follows: the present invention uses a triage emergency rescue module to collect and preprocess vital sign data, calculate a comprehensive health score based on the preprocessed vital sign data, and perform classification and emergency rescue; a guidance and psychological rehabilitation module to guide and treat according to the classification results, collect facial expression images of the injured after treatment, and calculate the intensity of emotions; a visualization storage module to construct a visualization interface to display the intensity of emotions, store, collect and analyze the generated physical sign data, improve the efficiency and accuracy of emergency treatment, reduce delays and misjudgments in the process of treating the injured, and enhance personalized and accurate suggestions for treating the injured. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0048] Figure 1 This is a flow chart of the casualty management system based on the medical care AI robot in Example 1.

[0049] Figure 2 This is a schematic diagram of the application method of wounded management based on the medical care AI robot in Example 1. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0051] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0052] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0053] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a wounded management system based on a medical care AI robot, comprising the following steps:

[0054] S1, triage and emergency rescue module, used to collect and preprocess vital signs data, calculate comprehensive health scores based on the preprocessed vital signs data, and perform classification and emergency rescue;

[0055] Specifically, collecting vital sign data and preprocessing it means that the medical care AI robot uses infrared thermal imaging equipment to scan extremely harsh areas to collect infrared thermal imaging images and uses lidar to collect point cloud data;

[0056] The collected infrared thermal imaging images and point cloud data are spatially aligned using a spatial alignment method;

[0057] Use image recognition algorithms to identify and mark the location of the injured in infrared thermal imaging images, and use the A* algorithm to plan the path for the marked injured location;

[0058] Medical care AI robots perform path planning and use first aid equipment to collect and pre-process the vital signs data of the injured;

[0059] Said emergency equipment includes a Glasgow Coma Scale, a heart rate monitor, an automatic inflating cuff, a pulse oximeter, an infrared thermometer and a chest sensor;

[0060] The vital signs data include heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate;

[0061] When the heart rate, blood pressure, blood oxygen saturation and respiratory rate are all 0, a black chip mark is performed;

[0062] The preprocessing includes using a Kalman filter algorithm to perform denoising and filtering, using a Z-score test to identify and delete outliers, using an interpolation method to fill in missing values, and standardizing vital sign data.

[0063] The first aid equipment is used to collect the patient's heart rate, blood pressure, blood oxygen saturation, body temperature, respiratory rate and other vital signs data in real time, and a series of preprocessing steps are used to improve the quality and accuracy of the data. The use of first aid equipment ensures the comprehensiveness and timeliness of data collection, ensures that the patient's comprehensive physiological information can be obtained during the treatment process, and provides reliable data support for subsequent health assessment and treatment decisions. By using the Kalman filter algorithm, the data noise caused by equipment errors or external environmental factors can be effectively removed, and the accuracy of vital signs data can be significantly improved, making the subsequent analysis results more reliable. Through Z-score detection, these abnormal data can be discovered and eliminated in time to prevent abnormal values ​​from interfering with subsequent health scores and classification judgments. By interpolating to fill missing values, incomplete analysis caused by missing data can be avoided, so that each vital sign data can participate in the health assessment, improving the accuracy and effectiveness of the analysis. Standardization processing allows the comparison of various data at the same scale, avoiding a certain data from having too much impact on the evaluation results, thereby improving the fairness and accuracy of the analysis model.

[0064] Furthermore, the comprehensive health score is calculated based on the preprocessed vital signs data and classified and the emergency rescue refers to setting the number of principal components K using the cumulative variance contribution rate method;

[0065] Calculate the covariance matrix of the standardized vital sign data, perform eigenvalue decomposition on the covariance matrix, and obtain eigenvalues ​​and eigenvectors;

[0066] Sort the eigenvalues ​​from large to small, and select the first K eigenvalues ​​as the main eigenvalues;

[0067] The weight coefficients corresponding to Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate data were calculated using the eigenvector method;

[0068] According to the weight coefficient corresponding to the vital signs data, the comprehensive health score F of the injured is calculated using the weighted average method. The formula is:

[0069] ,

[0070] Among them, Z, A, B, C, D and E are Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate data respectively. , , , , and They are the weight coefficients corresponding to the Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate data;

[0071] Use percentile method to set classification threshold including upper limit , lower limit ;

[0072] Compare the comprehensive health score with the classification threshold. If the comprehensive health score is less than the lower limit, , then it is judged as an emergency wounded person who needs immediate treatment, a red chip mark is made, and emergency rescue is carried out on the wounded;

[0073] If the comprehensive health score is within the classification threshold, the patient is judged as a secondary emergency patient, a yellow chip is marked, and the wound is cleaned and bandaged;

[0074] If the comprehensive health score is greater than the upper limit , it is determined to be an observation wounded person, a yellow chip mark is given, and communication is carried out with the wounded person.

[0075] The dimensionality reduction process not only improves the efficiency of subsequent calculations and reduces the complexity of calculations, but also reduces noise interference and enhances the robustness of the model. In the processing of vital signs data, reducing unnecessary dimensions helps to more accurately analyze the health status of the injured and avoid inefficient processing due to excessive data. Eigenvalue decomposition further helps to extract the most informative features and reduces the impact of unimportant variables on comprehensive health assessment. By setting weight coefficients, it can reflect the relative importance of different vital signs to the health status of the injured, thereby ensuring that the comprehensive health score is more scientific and fair. The calculation of the comprehensive health score is carried out by weighted average method. , taking into full consideration the weight and importance of each vital sign data. This score, as a key indicator for assessing the health status of the wounded, can help emergency personnel quickly determine the urgency of the wounded and make scientific treatment decisions based on the score. According to the comprehensive health score, the wounded are divided into emergency treatment, sub-emergency treatment and general observation levels, thereby providing emergency personnel with clear treatment priorities. By comparing the calculated comprehensive health score with the set classification threshold, the health status of the wounded can be automatically identified and classified according to the degree of urgency, thereby improving the timeliness and accuracy of emergency decision-making and ensuring the priority allocation of resources and efficient treatment of the wounded.

[0076] S2, the guidance and psychological rehabilitation module, is used to guide and treat patients according to the classification results, collect facial expression images of the injured after treatment, and calculate the emotional intensity;

[0077] Specifically, guiding and treating patients according to the classification results means using the WebSocket protocol to transmit the vital sign data and the classification results to the medical information system platform, and the medical information system platform receives the vital sign data and the classification results;

[0078] Collect and preprocess the labeled historical vital sign data and classification results, combine them with the ICD-10 coding standards in the medical database, and establish a mapping table to mark the relationship between the injury type and the department;

[0079] Use image recognition technology to label injury types in vital sign data;

[0080] According to the injury type and mapping table, the matching department is calculated using the atlas matching algorithm;

[0081] Convert the matching departments into department allocation instructions and transmit them to the medical information system platform to prepare the corresponding medical equipment and drugs for treatment;

[0082] The treatment includes the use of medical care AI robots to perform cardiopulmonary resuscitation, hemostasis, bandaging, fracture fixation, transportation, emergency disinfection of public areas, measurement of vital signs, wound cleaning and dressing changes, intramuscular injections, intravenous punctures, fluid replacement, and rehabilitation training for the wounded.

[0083] The low latency feature of WebSocket enables emergency personnel to obtain the latest vital signs data and classification results in real time, so as to make fast and accurate treatment decisions. By mapping vital signs data with injury types, the medical information system can accurately obtain the specific conditions of the injured, and provide a basis for subsequent diagnosis and treatment. Image recognition technology can not only automatically analyze injuries and reduce manual intervention, but also improve the accuracy and efficiency of diagnosis of the injured. The graph matching algorithm accurately assigns the injured to the department that best suits their condition, avoiding waste and mismatch of medical resources and improving the overall efficiency of the emergency system. The medical information system platform can receive timely department allocation instructions and mobilize corresponding medical equipment and drug resources accordingly, optimizing the management of medical resources and ensuring that all types of resources can be quickly and accurately deployed during the emergency process.

[0084] Furthermore, collecting facial expression images of the injured after treatment and calculating the emotion intensity means that the medical care AI robot uses a high-definition camera to collect facial expression images of the injured after treatment;

[0085] The facial expression images are converted into grayscale images using a single-channel method;

[0086] Use the pre-trained FER-2013 model to analyze the facial expressions of the grayscale images and obtain the probability value of the casualty's emotions;

[0087] According to the probability value of the casualty's emotions, the maximum probability method is used to calculate the emotional intensity of the casualty;

[0088] Use statistical analysis methods to set the judgment threshold, compare the emotion intensity with the judgment threshold, set the emotion intensity greater than or equal to the judgment threshold as normal, and continue to monitor the wounded; set the emotion intensity less than the judgment threshold as abnormal, and activate the psychological dialogue system to provide psychological counseling to the wounded.

[0089] Real-time collection of facial expression images of the injured by high-definition cameras can provide intuitive and real-time emotional state data. Converting color images into grayscale images can significantly reduce data dimensions and computational complexity while retaining key facial feature information. The introduction of the FER-2013 model can quickly and accurately identify the emotional state of the injured. Calculating the intensity of emotions simplifies the complexity of emotional analysis and enhances the interpretability of the analysis results. Setting the judgment threshold of emotional intensity through statistical analysis methods can dynamically adapt to changes in the emotional state of different injured persons, ensure the accuracy of classification, and respond quickly to abnormal emotions, thereby achieving early detection and early treatment of emotional problems, and effectively reducing the risk of psychological trauma or decreased cooperation with treatment caused by abnormal emotions in the injured.

[0090] S3, visualization storage module, used to build a visualization interface to display the intensity of emotions, store the physical sign data collected and analyzed;

[0091] Specifically, building a visual interface to display the emotional intensity means using the front-end framework React.js to build a visual interface, and using data visualization tools to display the comprehensive health score, classification results, department allocation instructions, and emotional intensity of the injured;

[0092] Users who have passed real-name verification are allowed to view the information.

[0093] The interface built with React.js can display the health data, emotional intensity, classification results and other information of the injured in real time, ensuring the smoothness and efficiency of the user interface. Through data visualization tools, complex health data can be presented in an intuitive way, and the emotional intensity of the injured can be displayed through charts or other visual methods, which can provide more dimensional information for the medical team. Real-name verification can prevent data leakage, protect the privacy of the injured, and ensure that medical data is only accessible to authorized personnel. By integrating real-time emotional data with the visual display of the injured's health data, medical staff can quickly obtain the overall condition of the injured, improve the transparency and readability of the data, and thus accelerate the speed of medical decision-making.

[0094] Furthermore, storing the physical sign data generated by collection and analysis means storing the collected vital sign data, facial expression images and emotion intensity generated by analysis in a database, and setting security access measures. The database will back up the stored data in the cloud, and regularly perform integrity checks on the stored data and backup data. After the test is completed, an integrity test record will be generated and stored synchronously in the database.

[0095] The collected vital signs data, facial expression images, and analyzed emotion intensity data are stored in the database, and security access measures are set to ensure that the data is not illegally accessed. The backup mechanism can protect the data from loss when the data is lost or the local device fails, providing higher reliability and data security. Integrity detection ensures that the data is not tampered with, lost or damaged during transmission, storage or backup. Traceability enables the source and change process of the data to be traced back when problems arise, ensuring the legality and compliance of the data, and providing strong support for medical quality management and legal supervision. Through the accumulation and analysis of historical data, the system can identify health trends, predict patient risks, and provide data support for personalized treatment, thereby improving patient treatment outcomes and the efficiency of medical resource utilization.

[0096] This embodiment also provides a wounded person management application method based on a medical care AI robot, including:

[0097] Collect and preprocess vital sign data, calculate comprehensive health scores based on the preprocessed vital sign data, and perform classification and emergency rescue;

[0098] Provide guidance and treatment based on the classification results, collect facial expression images of the injured after treatment, and calculate the intensity of emotions;

[0099] Build a visual interface to display the intensity of emotions, and store the physical sign data collected and analyzed.

[0100] This embodiment also provides a computer device, a wounded management system based on a medical care AI robot, comprising: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions, so as to implement the wounded management system based on a medical care AI robot as proposed in the above embodiment.

[0101] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0102] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the wounded management system based on the medical care AI robot as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

Claims

1. A casualty management system based on medical care AI robot, characterized by: include, The triage and emergency rescue module is used to collect and preprocess vital sign data, calculate the comprehensive health score based on the preprocessed vital sign data, and perform classification and emergency rescue; The guidance and psychological rehabilitation module is used to guide and treat patients according to the classification results, collect facial expression images of the injured after treatment, and calculate the intensity of emotions; The visualization storage module is used to build a visualization interface to display the intensity of emotions and to store the physical sign data collected and analyzed.

2. The wounded management system based on medical care AI robot as claimed in claim 1, characterized in that: The collection of vital sign data and preprocessing means that the medical care AI robot uses infrared thermal imaging equipment to scan extremely harsh areas to collect infrared thermal imaging images, and uses lidar to collect point cloud data; The collected infrared thermal imaging images and point cloud data are spatially aligned using a spatial alignment method; Use image recognition algorithms to identify and mark the location of the injured in infrared thermal imaging images, and use the A* algorithm to plan the path for the marked injured location; The medical care AI robot performs path planning and uses the Glasgow Coma Scale and first aid equipment to collect and pre-process the vital signs data of the injured; The first aid equipment includes a heart rate monitor, a self-inflating cuff, a pulse oximeter, an infrared thermometer and a chest sensor; The vital signs data include Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate; The preprocessing includes using a Kalman filter algorithm to perform denoising and filtering, using a Z-score test to identify and delete outliers, using an interpolation method to fill in missing values, and standardizing vital sign data.

3. The wounded management system based on medical care AI robot as claimed in claim 2, characterized in that: The calculation of comprehensive health scores based on pre-processed vital signs data and the classification and emergency rescue refer to setting the number of principal components K using the cumulative variance contribution rate method; Calculate the covariance matrix of the standardized vital sign data, perform eigenvalue decomposition on the covariance matrix, and obtain eigenvalues ​​and eigenvectors; Sort the eigenvalues ​​from large to small, and select the first K eigenvalues ​​as the main eigenvalues; The weight coefficients corresponding to Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate data were calculated using the eigenvector method; According to the weight coefficient corresponding to the vital signs data, the comprehensive health score F of the injured is calculated using the weighted average method. The formula is: ， Among them, Z, A, B, C, D and E are Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate data respectively. , , , , and They are the weight coefficients corresponding to the Glasgow Coma Scale, heart rate, blood pressure, blood oxygen saturation, body temperature and respiratory rate data; Use percentile method to set classification threshold including upper limit , lower limit ; Compare the comprehensive health score with the classification threshold. If the comprehensive health score is less than the lower limit, , then it is judged as an emergency wounded person who needs immediate treatment, a red chip mark is made, and emergency rescue is carried out on the wounded; If the comprehensive health score is within the classification threshold, the patient is judged as a secondary emergency patient, a yellow chip is marked, and the wound is cleaned and bandaged; If the comprehensive health score is greater than the upper limit , it is determined to be an observation wounded person, a yellow chip mark is given, and communication is carried out with the wounded person.

4. The wounded management system based on medical care AI robot as claimed in claim 3, characterized in that: The guiding and treating according to the classification results refers to transmitting the vital signs data and the classification results to the medical information system platform using the WebSocket protocol, and the medical information system platform receives the vital signs data and the classification results; Collect and preprocess the historical vital sign data and classification results with labels, and establish a mapping table based on the ICD-10 coding standards in the medical database; Use image recognition technology to label injury types in vital sign data; According to the injury type and mapping table, the matching department is calculated using the atlas matching algorithm; Convert the matching departments into department allocation instructions and transmit them to the medical information system platform to prepare the corresponding medical equipment and drugs for treatment; The treatment includes the use of medical care AI robots to perform cardiopulmonary resuscitation, hemostasis, bandaging, fracture fixation, transportation, emergency disinfection of public areas, measurement of vital signs, wound cleaning and dressing changes, intramuscular injections, intravenous punctures, fluid replacement, and rehabilitation training for the wounded.

5. The wounded management system based on medical care AI robot as claimed in claim 4, characterized in that: The collecting of facial expression images of the injured after treatment and calculating the emotion intensity refers to the medical care AI robot using a high-definition camera to collect facial expression images of the injured after treatment; The facial expression images are converted into grayscale images using a single-channel method; Use the pre-trained FER-2013 model to analyze the facial expressions of the grayscale images and obtain the probability value of the casualty's emotions; According to the probability value of the casualty's emotions, the maximum probability method is used to calculate the emotional intensity of the casualty; Use statistical analysis methods to set the judgment threshold, compare the emotion intensity with the judgment threshold, set the emotion intensity greater than or equal to the judgment threshold as normal, and continue to monitor the wounded; set the emotion intensity less than the judgment threshold as abnormal, and activate the psychological dialogue system to provide psychological counseling to the wounded.

6. The wounded management system based on medical care AI robot as claimed in claim 5, characterized in that: The construction of a visualization interface to display the emotional intensity refers to using the front-end framework React.js to construct a visualization interface, and using a data visualization tool to display the comprehensive health score, classification results, department allocation instructions, and emotional intensity of the injured; Users who have passed real-name verification are allowed to view the information.

7. The wounded management system based on medical care AI robot as claimed in claim 6, characterized in that: The storage, collection and analysis of the physical sign data refers to storing the collected vital sign data, facial expression images and emotion intensity generated by the analysis in a database, and setting security access measures. The database will back up the stored data in the cloud, and regularly perform integrity checks on the stored data and backup data. After the test is completed, an integrity test record will be generated and stored synchronously in the database.

8. A wounded person management application method based on a medical care AI robot, based on the wounded person management system based on a medical care AI robot according to any one of claims 1 to 7, characterized in that: include, Collect and preprocess vital sign data, calculate comprehensive health scores based on the preprocessed vital sign data, and perform classification and emergency rescue; Provide guidance and treatment based on the classification results, collect facial expression images of the injured after treatment, and calculate the intensity of emotions; Build a visual interface to display the intensity of emotions, and store the physical sign data collected and analyzed.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the wounded management system based on the medical care AI robot as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the wounded management system based on the medical care AI robot as described in any one of claims 1 to 7 are implemented.

Images