A rapid medical treatment method, device, computer equipment and storage medium

Abstract

The present application discloses a method, device, computer equipment and storage medium for rapid medical treatment, which belongs to the field of artificial intelligence technology. The operation steps of the accident handling process are obtained, the first operation step is displayed on the terminal of the reporter, the trigger operation of the reporter is responded to, the accident photo is obtained, the accident photo is imported into the human injury detection model, and the injury detection result is obtained, the second operation step and the injury detection result are displayed on the terminal of the medical staff, the trigger operation of the medical staff is responded to, the first aid operation steps for the injured are generated, and the first aid operation steps for the injured are displayed on the terminal of the reporter. In addition, the present application also involves blockchain technology, and accident photos can be stored in the blockchain. Under the guidance of the operation steps of the accident handling process, the present application prompts medical staff to communicate with the reporter in real time and complete the operation steps of the medical operation process, thereby quickly completing the complete medical operation process and improving the speed of medical treatment for the injured.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to a rapid medical treatment method, device, computer equipment and storage medium. Background Art

[0002] With the rapid development of social economy, the number of motor vehicles is increasing day by day, and the traffic accidents caused by them are also increasing. The current process of handling traffic accidents is cumbersome, lengthy, time-consuming and labor-intensive. For example, when a road traffic accident occurs, if someone is injured in a road traffic accident, the parties involved or witnesses need to complete the process of reporting to the police, seeking medical treatment and claim settlement, and they need to communicate, confirm and handle with the traffic police, hospitals and insurance companies respectively. Only after completing the accident rules, claim settlement and preliminary assessment of the injury can they formally seek medical treatment. The entire process is relatively cumbersome, which can easily delay treatment and cause conflicts and disputes. Summary of the invention

[0003] The purpose of the embodiments of the present application is to propose a rapid medical treatment method, device, computer equipment and storage medium to solve the technical problems that the existing traffic accident medical treatment process is cumbersome and lengthy, time-consuming and labor-intensive, and easily leads to delays in treatment.

[0004] In order to solve the above technical problems, the present application embodiment provides a rapid medical treatment method, which adopts the following technical solutions:

[0005] A quick way to get medical attention includes:

[0006] Receiving an accident handling instruction, and acquiring operation steps of an accident handling process according to the accident handling instruction, wherein the operation steps of the accident handling process include a first operation step and a second operation step;

[0007] Generating a first operation guide interface on a terminal of the first user, and displaying the first operation steps on the first operation guide interface, wherein the first operation steps at least include taking a photo of the accident;

[0008] In response to a triggering operation of the first user on the first operation guidance interface, acquiring accident photos;

[0009] Importing the accident photo into a pre-trained human injury detection model to obtain an injury detection result of the injured person;

[0010] Generate a second operation guide interface on the second user's terminal, and display the second operation steps and the injury detection result on the second operation guide interface;

[0011] In response to a triggering operation of the second user on the second operation guide interface, generating first aid operation steps for the wounded;

[0012] The first operation guide interface displays the first emergency operation steps for the injured.

[0013] Furthermore, the step of acquiring the accident photo in response to the triggering operation of the first user on the first operation guidance interface specifically includes:

[0014] In response to the first user's triggering operation on the screenshot control, generating a viewfinder on the first operation guide interface;

[0015] The accident photo is obtained by intercepting the picture content in the viewfinder.

[0016] Furthermore, the accident photo includes a first accident photo and a second accident photo, and after the step of obtaining the accident photo by intercepting the picture content in the viewfinder, the method further includes:

[0017] receiving the first accident photo, and performing content recognition on the first accident photo to obtain the limb condition in the first accident photo;

[0018] Analyze the limb condition in the first accident photo to obtain first injury data of the injured person, wherein the first injury data is body surface injury data;

[0019] Determine a detection action video based on the first injury data, and display the detection action video on the first operation guidance interface;

[0020] The image of the injured person completing the detection action video is obtained through the viewfinder to obtain the injury detection video;

[0021] Key frames are extracted from the injury detection video to obtain the second accident photo.

[0022] Furthermore, the step of importing the accident photo into a pre-trained human injury detection model to obtain the injury detection result of the injured person specifically includes:

[0023] Importing the second accident photo into a pre-trained human disability detection model to obtain second injury data of the injured person, wherein the second injury data is joint injury data;

[0024] Based on the first injury data and the second injury data, an injury detection result of the injured person is generated.

[0025] Furthermore, the step of importing the second accident photo into a pre-trained human disability detection model to obtain the second injury data of the injured person specifically includes:

[0026] Performing joint point detection on the second accident photo to obtain body joint points of the injured person;

[0027] Marking the joints of the injured person's body to obtain information of the joints;

[0028] The human body injury detection model is used to predict the joint injury of the injured person based on the human body joint point information to obtain second injury data of the injured person.

[0029] Furthermore, after the step of displaying the first aid operation steps for the wounded on the first operation guide interface, the method further includes:

[0030] Obtaining accident responsibility determination operation steps, and displaying the accident responsibility determination operation steps on the first operation guidance interface;

[0031] In response to the first user's triggering operation on the first operation guidance interface for determining the responsibility for the accident, performing content recognition on the accident photo, determining the accident vehicle in the accident photo, and obtaining driving information of the accident vehicle;

[0032] Retrieving surveillance video within a preset time period before and after the accident, and identifying the driving trajectory of the accident vehicle based on the surveillance video;

[0033] A pre-constructed traffic control regulations knowledge graph is obtained, and the accident liability of the accident vehicle is determined based on the driving trajectory of the accident vehicle, the driving information of the accident vehicle and the traffic control regulations knowledge graph.

[0034] Furthermore, after the step of obtaining the pre-constructed traffic control regulations knowledge graph and determining the accident responsibility of the accident vehicle based on the driving trajectory of the accident vehicle, the driving information of the accident vehicle and the traffic control regulations knowledge graph, it also includes:

[0035] Obtaining accident claim settlement operation steps, and displaying the accident claim settlement operation steps on the first operation guidance interface;

[0036] In response to the triggering operation of the first user on the first operation guidance interface for accident claim settlement, calling a pre-trained vehicle damage recognition model to recognize the accident photo to obtain the degree of vehicle damage;

[0037] A compensation plan is generated based on the injury detection results, the degree of vehicle damage and the accident liability.

[0038] In order to solve the above technical problems, the present application also provides a rapid medical treatment device, which adopts the following technical solution:

[0039] A rapid medical treatment device, comprising:

[0040] An operation step acquisition module, used to receive an accident handling instruction, and acquire the operation steps of the accident handling process according to the accident handling instruction, wherein the operation steps of the accident handling process include a first operation step and a second operation step;

[0041] A first guidance module, configured to generate a first operation guidance interface on a terminal of a first user, and display the first operation steps on the first operation guidance interface, wherein the first operation steps at least include taking a photo of the accident;

[0042] A first trigger operation module, configured to obtain accident photos in response to a trigger operation of the first user on the first operation guide interface;

[0043] An injury detection module is used to import the accident photo into a pre-trained human injury detection model to obtain an injury detection result of the injured person;

[0044] A second guidance module, configured to generate a second operation guidance interface on a terminal of a second user, and display the second operation steps and the injury detection result on the second operation guidance interface;

[0045] A second trigger operation module, configured to generate first aid operation steps for the wounded in response to a trigger operation of the second user on the second operation guide interface;

[0046] The first aid operation guidance module is used to display the first aid operation steps for the injured on the first operation guidance interface. In order to solve the above technical problems, the embodiment of the present application also provides a computer device, which adopts the following technical solution:

[0047] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the rapid medical treatment method as described in any one of the above items are implemented.

[0048] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0049] A computer-readable storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by a processor, implement the steps of any one of the above-described rapid medical treatment methods.

[0050] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0051] The present application discloses a method, device, computer equipment and storage medium for rapid medical treatment, and belongs to the field of artificial intelligence technology. The present application generates a first operation guide interface on the terminal of the reporter by acquiring the first operation step and the second operation step of the accident handling process, and displays the first operation step on the first operation guide interface, instructs the reporter to complete the shooting of accident photos through the first step, acquires accident photos by responding to the trigger operation of the reporter on the first operation guide interface, imports the accident photos into a pre-trained human injury detection model, obtains the injury detection results of the injured, finds a suitable hospital for medical treatment and determines the corresponding medical staff according to the injury detection results, generates a second operation guide interface on the terminal of the medical staff, and displays the second operation step and the injury detection results on the second operation guide interface, responds to the trigger operation of the medical staff on the second operation guide interface, generates the first aid operation steps for the injured, and displays the first aid operation steps for the injured on the first operation guide interface to guide the reporter to complete the first aid. This application guides the reporter to obtain accident photos and conduct injury tests on the injured in the accident photos to find a suitable hospital and determine the corresponding medical staff. Under the guidance of the accident handling process steps, medical staff are encouraged to communicate with the reporter in real time to complete the medical treatment process steps, thereby quickly completing the entire medical treatment process and improving the speed of medical treatment for the injured. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 An exemplary system architecture diagram is shown in which the present application can be applied;

[0054] Figure 2 A flowchart showing an embodiment of a rapid medical treatment method according to the present application;

[0055] Figure 3 A schematic structural diagram of an embodiment of a rapid medical treatment device according to the present application is shown;

[0056] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0058] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0060] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0061] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0062] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers and desktop computers, etc.

[0063] Server 105 can be a server that provides various services, such as a background server that provides support for pages displayed on terminal devices 101, 102, and 103. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0064] It should be noted that the rapid medical treatment method provided in the embodiment of the present application is generally executed by a server, and accordingly, the rapid medical treatment device is generally set in the server.

[0065] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0066] Continue to refer Figure 2 , showing a flow chart of an embodiment of the rapid medical treatment method according to the present application. The embodiment of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0067] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning. The rapid medical treatment method includes the following steps:

[0068] S201, receiving an accident handling instruction, and acquiring operation steps of an accident handling process according to the accident handling instruction, wherein the operation steps of the accident handling process include a first operation step and a second operation step.

[0069] Specifically, after receiving the accident handling instructions uploaded by the reporter, the server obtains the operating steps of the accident handling process according to the accident handling instructions, wherein the operating steps of the accident handling process are pre-stored in the cloud storage, and the operations of the reporter and medical staff are standardized through the operating steps of the accident handling process. The operating steps of the accident handling process include a first operating step and a second operating step. The first operating step is used to instruct the reporter to complete the corresponding reporting operation, such as instructing to confirm the safety of the surrounding environment, instructing to turn on the hazard warning flash, instructing to place a tripod, instructing to take pictures of the accident scene, etc. The second operating step is used to instruct medical staff to give corresponding first aid operation steps for the injured according to the situation at the accident scene, such as instructing how to stop bleeding, how to prevent secondary injuries, etc., to prevent the injured from getting worse.

[0070] S202: Generate a first operation guidance interface on a terminal of the first user, and display the first operation steps on the first operation guidance interface, wherein the first operation steps at least include taking photos of the accident.

[0071] Specifically, in a specific embodiment of the present application, the first user is the reporter, who can be an injured person or a witness to the accident. After the reporter initiates the accident handling instruction, the server generates a first operation guidance interface on the reporter's terminal, and displays the first operation steps on the first operation guidance interface, wherein the first operation steps at least include the specific operation steps of confirming the safety of the surrounding environment, turning on the hazard warning flash, placing a tripod, and taking photos of the accident.

[0072] S203: Acquire accident photos in response to a triggering operation of the first user on the first operation guidance interface.

[0073] Specifically, the first operation guidance interface includes a plurality of controls, each of which is configured to correspond to an operation function, for example, a screenshot control on the first operation guidance interface, the screenshot control is configured to generate a viewfinder and capture the screen content in the viewfinder. In response to the reporter's triggering operation of the screenshot control on the first operation guidance interface, the server generates a viewfinder on the first operation guidance interface and obtains shooting guidance information, such as shooting voice guidance information, to guide the reporter to obtain accident photos.

[0074] S204, importing the accident photo into a pre-trained human injury detection model to obtain an injury detection result of the injured person.

[0075] Specifically, the human injury detection model can be trained based on a machine learning model, and the training data is various human injury images with annotated joint information. The server imports the accident photos into the pre-trained human injury detection model to obtain the injury detection results of the injured.

[0076] In a specific embodiment of the present application, after obtaining the injury detection result of the injured person, the server selects a matching emergency hospital from the connected emergency medical list based on the injury detection result, the distance from the emergency hospital, and the availability of each emergency hospital, and determines the corresponding medical staff. After determining the hospital to be treated, the server sends an emergency notice to the hospital, which contains the personal information and injury situation of the injured person (including accident information, identity information of the injured person, injured part, approximate time of arrival at the hospital, injury pictures, etc.). The server will send the emergency notice to the injured person and related personnel, and synchronize the corresponding information with the hospital emergency system through the interface, and notify the relevant on-duty personnel of the hospital to prepare for treatment through text messages.

[0077] S205: Generate a second operation guidance interface on the second user's terminal, and display the second operation steps and the injury detection result on the second operation guidance interface.

[0078] Among them, for the injured in the accident, only by taking corresponding rescue methods for different injured parts and different injury conditions can the situation of the injured be alleviated. If the first aid method taken is wrong, it will not only fail to alleviate the situation of the injured, but also very likely cause the situation of the injured to worsen. Therefore, this application can effectively alleviate the situation of the injured by sending the injury detection results to the corresponding medical staff, allowing the medical staff to give professional first aid operation steps for the injured according to the injury detection results, and instructing the reporter to complete the rescue according to the first aid operation steps for the injured given by the medical staff.

[0079] Specifically, in a specific embodiment of the present application, the second user is a medical staff. After determining the target hospital for medical treatment, the server automatically contacts the medical staff of the corresponding department associated with the injury, and generates a second operation guide interface on the terminal of the medical staff, through which the second operation steps and the injury detection results are displayed on the second operation guide interface. The second operation steps are used to instruct the medical staff to enter the first aid operation steps for the injured on the second operation guide interface. After checking the injury detection results, the medical staff enters the first aid operation steps for the injured on the second operation guide interface according to the injury detection results.

[0080] In a specific embodiment of the present application, after it is discovered that emergency rescue is needed on site, a multi-party video connection is initiated through the server. After receiving the connection request, the emergency rescue personnel access the video connection to remotely view the on-site situation, deploy corresponding medical personnel and first aid supplies to prepare for treatment, and remotely guide the on-site personnel to carry out rescue work and wait for the rescue personnel to arrive.

[0081] S206: In response to the triggering operation of the second user on the second operation guidance interface, generate first aid operation steps for the wounded.

[0082] Specifically, the server responds to the triggering operation of the medical staff on the second operation guide interface, obtains the first aid operation steps for the injured uploaded by the medical staff, and sends the first aid operation steps for the injured to the reporter's terminal.

[0083] S207, displaying the first aid operation steps for the injured on the first operation guide interface.

[0084] Specifically, after receiving the first aid operation steps for the injured, the reporter's terminal displays the first aid operation steps for the injured on the first operation guidance interface for the reporter to view, and instructs the reporter to perform real-time rescue of the injured according to the first aid operation steps for the injured, prevent secondary injuries, and prevent the injured's condition from worsening.

[0085] In the above embodiment, the present application guides the reporter to obtain accident photos and conducts injury detection on the injured in the accident photos to find a suitable hospital for medical treatment and determine the corresponding medical staff. Under the guidance of the accident handling process operation steps, the medical staff is prompted to communicate with the reporter in real time to complete the operation steps of the medical treatment process, thereby quickly completing the complete medical treatment process and improving the speed of medical treatment for the injured.

[0086] Furthermore, the step of acquiring the accident photo in response to the triggering operation of the first user on the first operation guidance interface specifically includes:

[0087] In response to the first user's triggering operation on the screenshot control, generating a viewfinder on the first operation guide interface;

[0088] The accident photo is obtained by intercepting the picture content in the viewfinder.

[0089] Specifically, the server responds to the reporter's triggering operation on the screenshot control, generates a viewfinder on the first operation guidance interface, and obtains shooting guidance information, such as shooting voice guidance information "Please keep the rear camera aimed at the injured person", etc., and detects the picture content in the viewfinder. When the picture content in the viewfinder meets the requirements, the picture content in the viewfinder is captured to obtain the accident photo.

[0090] Furthermore, the accident photo includes a first accident photo and a second accident photo, and after the step of obtaining the accident photo by intercepting the picture content in the viewfinder, the method further includes:

[0091] receiving the first accident photo, and performing content recognition on the first accident photo to obtain the limb condition in the first accident photo;

[0092] Analyze the limb condition in the first accident photo to obtain first injury data of the injured person, wherein the first injury data is body surface injury data;

[0093] Determine a detection action video based on the first injury data, and display the detection action video on the first operation guidance interface;

[0094] The image of the injured person completing the detection action video is obtained through the viewfinder to obtain the injury detection video;

[0095] Key frames are extracted from the injury detection video to obtain the second accident photo.

[0096] The accident photos include the first accident photo and the second accident photo. The first accident photo is used to determine the surface injury data of the injured person, and the second accident photo is used to determine the joint injury data of the injured person. After the reporter triggers the screenshot control for the first time, the first accident photo is obtained. After the reporter triggers the screenshot control for the second time, the injury detection video is obtained. The second accident photo is obtained by extracting the key frames in the injury detection video.

[0097] Specifically, the server responds to the first trigger operation of the screenshot control by the reporter, generates a viewfinder on the first operation guide interface, and obtains the first accident photo by capturing the screen content in the viewfinder. Then, the first accident photo is subjected to content recognition to obtain the background area and the human body area in the first accident photo, and the limb condition is obtained by identifying the human body area. The limb condition in the first accident photo is analyzed to obtain the first injury data of the injured person, wherein the first injury data is the surface injury data.

[0098] The server determines the detection action video based on the first injury data. If the first injury data shows that the injured person has an arm injury, the detection action video corresponding to the arm injury is obtained, and the detection action video is displayed on the first operation guide interface. The second trigger operation of the screenshot control by the reporter is obtained, and the picture when the injured person completes the detection action video is obtained through the viewfinder to obtain the injury detection video. The key frames of the injury detection video are extracted to obtain a second accident photo, which is used to determine the joint injury data of the injured person.

[0099] Furthermore, the step of importing the accident photo into a pre-trained human injury detection model to obtain the injury detection result of the injured person specifically includes:

[0100] Importing the second accident photo into a pre-trained human disability detection model to obtain second injury data of the injured person, wherein the second injury data is joint injury data;

[0101] Based on the first injury data and the second injury data, an injury detection result of the injured person is generated.

[0102] Specifically, the second accident photo is imported into a pre-trained human disability detection model to obtain second injury data of the injured person, wherein the second injury data is joint injury data, and the injury detection result of the injured person is generated based on the body surface injury data and the joint injury data.

[0103] Furthermore, the step of importing the second accident photo into a pre-trained human disability detection model to obtain the second injury data of the injured person specifically includes:

[0104] Performing joint point detection on the second accident photo to obtain body joint points of the injured person;

[0105] Marking the joints of the injured person's body to obtain information of the joints;

[0106] The human body injury detection model is used to predict the joint injury of the injured person based on the human body joint point information to obtain second injury data of the injured person.

[0107] Among them, the server first detects the joints of the second accident photo based on the multi-stage key point affinity field network (PartAffinityFields, PAF) to obtain the human joint information. PAF can achieve real-time human joint detection and generate human joint images. PAF adopts a bottom-up method. The network framework is divided into two paths. One path uses the CNN network to predict the joints according to the human body contour map and the preset confidence parameters; the other path uses the CNN network to obtain the PAF value of each joint. The PAF value is the affinity value of the joint. PAF can be regarded as a 2D vector that records the position and direction of the line connecting two adjacent joints. Among them, both CNN networks are multi-stage network structures, each stage has an output value, and each stage represents a dimension. The two CNN networks perform joint prediction and connection of human joints to obtain human joint images.

[0108] In a specific embodiment of the present application, a human injury detection model can be constructed based on a transformer network architecture. Transformer is a model based on an encoder-decoder structure. Both the encoder and decoder are composed of an attention module and a pre-term neural network. It is the first model built with pure attention. It not only has a faster calculation speed, but also achieves better results in translation tasks.

[0109] Specifically, the server imports the second accident photo into the multi-stage key point affinity field network, performs human joint point detection on the key frame image based on the preset multi-stage key point affinity field network, identifies the human joint points on the second accident photo, and marks the human joint points in the second accident photo to obtain human joint point information, wherein the human joint point information includes human joint point coordinates and human joint activity angles. Finally, the server imports the human joint point information into the pre-trained human injury detection model, and generates the second injury data of the user to be detected by feature encoding / decoding and feature mapping the human joint point information.

[0110] In this embodiment, the present application obtains a first accident photo by capturing the image content in the viewfinder, analyzes the limb condition in the first accident photo, obtains the surface injury data of the injured person, determines a detection action video based on the first injury data, and displays the detection action video on the first operation guidance interface, obtains the image of the injured person completing the detection action video through the viewfinder, obtains an injury detection video, extracts key frames from the injury detection video, obtains a second accident photo, performs joint point detection on the second accident photo based on a multi-stage key point affinity field network PAF, identifies the joint point information of the injured person through an injury detection model, obtains joint injury data, generates injury detection results for the injured person based on the surface injury data and the joint injury data, and can quickly find a matching hospital and determine the corresponding medical staff based on the injury detection results.

[0111] Furthermore, after the step of displaying the first aid operation steps for the wounded on the first operation guide interface, the method further includes:

[0112] Obtaining accident responsibility determination operation steps, and displaying the accident responsibility determination operation steps on the first operation guidance interface;

[0113] In response to the first user's triggering operation on the first operation guidance interface for determining the responsibility for the accident, performing content recognition on the accident photo, determining the accident vehicle in the accident photo, and obtaining driving information of the accident vehicle;

[0114] Retrieving surveillance video within a preset time period before and after the accident, and identifying the driving trajectory of the accident vehicle based on the surveillance video;

[0115] A pre-constructed traffic control regulations knowledge graph is obtained, and the accident liability of the accident vehicle is determined based on the driving trajectory of the accident vehicle, the driving information of the accident vehicle and the traffic control regulations knowledge graph.

[0116] Furthermore, after the step of obtaining the pre-constructed traffic control regulations knowledge graph and determining the accident responsibility of the accident vehicle based on the driving trajectory of the accident vehicle, the driving information of the accident vehicle and the traffic control regulations knowledge graph, it also includes:

[0117] Obtaining accident claim settlement operation steps, and displaying the accident claim settlement operation steps on the first operation guidance interface;

[0118] In response to the triggering operation of the first user on the first operation guidance interface for accident claim settlement, calling a pre-trained vehicle damage recognition model to recognize the accident photo to obtain the degree of vehicle damage;

[0119] A compensation plan is generated based on the injury detection results, the degree of vehicle damage and the accident liability.

[0120] Among them, knowledge graph, as a semantic network, has extremely strong expressive power and modeling flexibility. First, knowledge graph is a semantic representation that can model entities, concepts, attributes and the relationships between them in the real world; second, knowledge graph is the data exchange standard of its derivative technology, which is itself a "protocol" for data modeling. Related technologies cover various aspects such as knowledge extraction, knowledge integration, knowledge management and knowledge application.

[0121] Specifically, the server obtains the accident responsibility determination operation steps and displays the accident responsibility determination operation steps on the first operation guidance interface, responds to the reporter's trigger operation for accident responsibility determination on the first operation guidance interface, performs content recognition on the accident photo, determines the accident vehicle in the accident photo, and obtains the driving information of the accident vehicle, calls up the surveillance video within a preset time period before and after the accident, and identifies the driving trajectory of the accident vehicle based on the surveillance video, obtains a pre-constructed traffic control regulations knowledge graph, and determines the accident responsibility of the accident vehicle based on the driving trajectory of the accident vehicle, the driving information of the accident vehicle and the traffic control regulations knowledge graph, and generates an accident responsibility determination letter.

[0122] In another embodiment of the present application, after a traffic accident occurs, the reporter calls the police. After the traffic police answers the call, they inquire about the case. The server guides the reporter to establish a video connection with the traffic police at the accident handling post. The traffic police conducts remote investigation and evidence collection through video to determine the responsibility for the accident and generate an accident responsibility determination letter.

[0123] Specifically, after generating the accident responsibility document, the server can also guide the car owner to automatically complete the vehicle damage claim. The server obtains the accident claim operation steps and displays the accident claim operation steps on the first operation guidance interface. In response to the first user's trigger operation for the accident claim on the first operation guidance interface, the server calls a pre-trained vehicle damage recognition model to identify the accident photo, obtains the degree of vehicle damage, and generates a compensation plan based on the injury detection results, the degree of vehicle damage and the accident responsibility.

[0124] It should be noted that the vehicle damage identification model is also trained based on the machine learning model. The training data used is a series of pre-collected vehicle damage photos, and the vehicle damage features are pre-marked on the vehicle damage photos. The corresponding compensation plan is matched according to the vehicle damage features, and the vehicle damage photos and the compensation plan corresponding to the vehicle damage photos are imported into the machine learning model to obtain the vehicle damage identification model.

[0125] In another embodiment of the present application, the server and the insurance company system achieve data intercommunication. When the injured person is admitted to the hospital for registration, he can connect to the server to inquire about the insurance policy status of the vehicle involved in the accident and confirm whether to file a case for compensation. If the compensation conditions are met, the pre-payment process can be initiated. The medical expenses of the injured person are reimbursed directly by the insurance company, and the injured person or the driver involved in the accident does not need to advance the medical expenses. After the treatment is completed, the treatment expenses are automatically settled through the server and the insurance company system.

[0126] In this embodiment, the present application discloses a method for rapid medical treatment, which belongs to the field of artificial intelligence technology. The present application obtains the first operation step and the second operation step of the accident handling process, generates a first operation guide interface on the terminal of the reporter, and displays the first operation step on the first operation guide interface, instructs the reporter to complete the shooting of the accident photo through the first step, obtains the accident photo by responding to the trigger operation of the reporter on the first operation guide interface, imports the accident photo into a pre-trained human injury detection model, obtains the injury detection result of the injured, finds a suitable hospital for medical treatment and determines the corresponding medical staff according to the injury detection result, generates a second operation guide interface on the terminal of the medical staff, and displays the second operation step and the injury detection result on the second operation guide interface, responds to the trigger operation of the medical staff on the second operation guide interface, generates the first aid operation steps for the injured, and displays the first aid operation steps for the injured on the first operation guide interface to guide the reporter to complete the first aid. This application guides the reporter to obtain accident photos and conduct injury tests on the injured in the accident photos to find a suitable hospital and determine the corresponding medical staff. Under the guidance of the accident handling process steps, medical staff are encouraged to communicate with the reporter in real time to complete the medical treatment process steps, thereby quickly completing the entire medical treatment process and improving the speed of medical treatment for the injured.

[0127] In this embodiment, the electronic device (eg, Figure 1 The server shown in the figure) can quickly receive medical treatment through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0128] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned accident photos, the above-mentioned accident photos can also be stored in a blockchain node.

[0129] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0130] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0131] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0132] Further references Figure 3 , as a response to the above Figure 2The present application provides an embodiment of a rapid medical treatment device, which is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0133] like Figure 3 As shown, the rapid medical treatment device described in this embodiment includes:

[0134] The operation step acquisition module 301 is used to receive an accident handling instruction and acquire the operation steps of the accident handling process according to the accident handling instruction, wherein the operation steps of the accident handling process include a first operation step and a second operation step;

[0135] A first guidance module 302 is used to generate a first operation guidance interface on a terminal of a first user, and display the first operation steps on the first operation guidance interface, wherein the first operation steps at least include taking a photo of the accident;

[0136] A first trigger operation module 303, configured to obtain accident photos in response to a trigger operation of the first user on the first operation guide interface;

[0137] The injury detection module 304 is used to import the accident photo into a pre-trained human injury detection model to obtain the injury detection result of the injured person;

[0138] A second guidance module 305, configured to generate a second operation guidance interface on a second user's terminal, and display the second operation steps and the injury detection result on the second operation guidance interface;

[0139] A second trigger operation module 306, configured to generate first aid operation steps for the wounded in response to the trigger operation of the second user on the second operation guide interface;

[0140] The first aid operation guidance module 307 is used to display the first aid operation steps for the injured on the first operation guidance interface.

[0141] Furthermore, the first trigger operation module 303 specifically includes:

[0142] A framing frame generating unit, configured to generate a framing frame on the first operation guiding interface in response to a triggering operation of the first user on the screenshot control;

[0143] The picture capturing unit is used to obtain the accident photo by capturing the picture content in the viewfinder.

[0144] Furthermore, the accident photo includes a first accident photo and a second accident photo, and the first trigger operation module 303 further includes:

[0145] a first accident photo acquisition unit, configured to receive the first accident photo, and perform content recognition on the first accident photo to obtain the limb condition in the first accident photo;

[0146] a body surface injury prediction unit, configured to analyze the limb condition in the first accident photo to obtain first injury data of the injured person, wherein the first injury data is body surface injury data;

[0147] a detection action display unit, configured to determine a detection action video based on the first injury data, and display the detection action video on the first operation guide interface;

[0148] The injured person's action shooting unit is used to obtain the picture of the injured person completing the detection action video through the viewfinder to obtain the injury detection video;

[0149] The second accident photo acquisition unit is used to extract key frames from the injury detection video to obtain the second accident photo.

[0150] Furthermore, the injury detection module 304 specifically includes:

[0151] a joint injury prediction unit, used for importing the second accident photo into a pre-trained human disability detection model to obtain second injury data of the injured person, wherein the second injury data is joint injury data;

[0152] An injury detection unit is used to generate an injury detection result of the injured person based on the first injury data and the second injury data.

[0153] Furthermore, the joint injury prediction unit specifically includes:

[0154] A joint point detection subunit, used for performing joint point detection on the second accident photo to obtain the body joint points of the injured person;

[0155] A joint point marking subunit is used to mark the joint points of the injured person's body to obtain the joint point information of the injured person;

[0156] The joint injury prediction subunit is used to use the human body injury detection model to predict the joint injury of the injured person based on the human body joint point information to obtain the second injury data of the injured person.

[0157] Furthermore, the rapid medical treatment device also includes:

[0158] A responsibility determination operation module, used to obtain accident responsibility determination operation steps and display the accident responsibility determination operation steps on the first operation guide interface;

[0159] a rule guidance module, configured to respond to the triggering operation of the first user on the first operation guidance interface for determining the responsibility for the accident, perform content recognition on the accident photo, determine the accident vehicle in the accident photo, and obtain driving information of the accident vehicle;

[0160] A trajectory recognition module is used to call the surveillance video within a preset time period before and after the accident, and identify the driving trajectory of the accident vehicle based on the surveillance video;

[0161] The accident rule module is used to obtain a pre-constructed traffic control regulations knowledge graph, and determine the accident responsibility of the accident vehicle based on the driving trajectory of the accident vehicle, the driving information of the accident vehicle and the traffic control regulations knowledge graph.

[0162] Furthermore, the device for obtaining rapid medical treatment also includes:

[0163] A claim settlement operation module, used to obtain accident claim settlement operation steps and display the accident claim settlement operation steps on the first operation guide interface;

[0164] a claim guidance module, configured to respond to the triggering operation of the first user on the first operation guidance interface for accident claim, call a pre-trained vehicle damage recognition model to recognize the accident photo, and obtain the degree of vehicle damage;

[0165] The accident claim settlement module is used to generate a compensation plan based on the injury detection results, the degree of vehicle damage and the accident liability.

[0166] In this embodiment, the present application discloses a rapid medical treatment device, which belongs to the field of artificial intelligence technology. The present application generates a first operation guide interface on the terminal of the reporter by acquiring the first operation step and the second operation step of the accident handling process, and displays the first operation step on the first operation guide interface, instructs the reporter to complete the shooting of the accident photo through the first step, obtains the accident photo by responding to the trigger operation of the reporter on the first operation guide interface, imports the accident photo into a pre-trained human injury detection model, obtains the injury detection result of the injured, finds a suitable hospital for medical treatment and determines the corresponding medical staff according to the injury detection result, generates a second operation guide interface on the terminal of the medical staff, and displays the second operation step and the injury detection result on the second operation guide interface, responds to the trigger operation of the medical staff on the second operation guide interface, generates the first aid operation steps for the injured, and displays the first aid operation steps for the injured on the first operation guide interface to guide the reporter to complete the first aid. This application guides the reporter to obtain accident photos and conduct injury tests on the injured in the accident photos to find a suitable hospital and determine the corresponding medical staff. Under the guidance of the accident handling process steps, medical staff are encouraged to communicate with the reporter in real time to complete the medical treatment process steps, thereby quickly completing the entire medical treatment process and improving the speed of medical treatment for the injured.

[0167] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0168] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0169] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0170] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of a rapid medical treatment method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0171] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the rapid medical treatment method.

[0172] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0173] The present application discloses a computer device, belonging to the field of artificial intelligence technology. The present application generates a first operation guide interface on the terminal of the reporter by acquiring the first operation step and the second operation step of the accident handling process, and displays the first operation step on the first operation guide interface, instructs the reporter to complete the shooting of the accident photo through the first step, acquires the accident photo by responding to the trigger operation of the reporter on the first operation guide interface, imports the accident photo into a pre-trained human injury detection model, obtains the injury detection result of the injured, finds a suitable hospital for medical treatment and determines the corresponding medical staff according to the injury detection result, generates a second operation guide interface on the terminal of the medical staff, and displays the second operation step and the injury detection result on the second operation guide interface, responds to the trigger operation of the medical staff on the second operation guide interface, generates the first aid operation steps for the injured, and displays the first aid operation steps for the injured on the first operation guide interface, so as to guide the reporter to complete the first aid. This application guides the reporter to obtain accident photos and conduct injury tests on the injured in the accident photos to find a suitable hospital and determine the corresponding medical staff. Under the guidance of the accident handling process steps, medical staff are encouraged to communicate with the reporter in real time to complete the medical treatment process steps, thereby quickly completing the entire medical treatment process and improving the speed of medical treatment for the injured.

[0174] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the rapid medical treatment method as described above.

[0175] The present application discloses a storage medium, belonging to the field of artificial intelligence technology. The present application generates a first operation guide interface on the terminal of the reporter by acquiring the first operation step and the second operation step of the accident handling process, and displays the first operation step on the first operation guide interface, instructs the reporter to complete the shooting of the accident photo through the first step, acquires the accident photo by responding to the trigger operation of the reporter on the first operation guide interface, imports the accident photo into a pre-trained human injury detection model, obtains the injury detection result of the injured, finds a suitable hospital for medical treatment and determines the corresponding medical staff according to the injury detection result, generates a second operation guide interface on the terminal of the medical staff, and displays the second operation step and the injury detection result on the second operation guide interface, responds to the trigger operation of the medical staff on the second operation guide interface, generates the first aid operation steps for the injured, and displays the first aid operation steps for the injured on the first operation guide interface, so as to guide the reporter to complete the first aid. This application guides the reporter to obtain accident photos and conduct injury tests on the injured in the accident photos to find a suitable hospital and determine the corresponding medical staff. Under the guidance of the accident handling process steps, medical staff are encouraged to communicate with the reporter in real time to complete the medical treatment process steps, thereby quickly completing the entire medical treatment process and improving the speed of medical treatment for the injured.

[0176] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0177] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0178] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A rapid medical treatment method, characterized in that: include: Receiving an accident handling instruction, and acquiring operation steps of an accident handling process according to the accident handling instruction, wherein the operation steps of the accident handling process include a first operation step and a second operation step; Generating a first operation guide interface on a terminal of the first user, and displaying the first operation steps on the first operation guide interface, wherein the first operation steps at least include taking a photo of the accident; In response to a triggering operation of the first user on the first operation guidance interface, acquiring accident photos; Importing the accident photo into a pre-trained human injury detection model to obtain an injury detection result of the injured person; Generate a second operation guide interface on the second user's terminal, and display the second operation steps and the injury detection result on the second operation guide interface; In response to a triggering operation of the second user on the second operation guide interface, generating first aid operation steps for the wounded; Displaying the first aid operation steps for the injured on the first operation guide interface; The accident photo includes a first accident photo and a second accident photo. After the step of obtaining the accident photo by intercepting the picture content in the viewfinder, the method further includes: receiving the first accident photo, and performing content recognition on the first accident photo to obtain the limb condition in the first accident photo; Analyze the limb condition in the first accident photo to obtain first injury data of the injured person, wherein the first injury data is body surface injury data; Determine a detection action video based on the first injury data, and display the detection action video on the first operation guidance interface; The image of the injured person completing the detection action video is obtained through the viewfinder to obtain the injury detection video; Extracting key frames from the injury detection video to obtain the second accident photo; The step of importing the accident photo into a pre-trained human injury detection model to obtain the injury detection result of the injured person specifically includes: Importing the second accident photo into a pre-trained human disability detection model to obtain second injury data of the injured person, wherein the second injury data is joint injury data; Based on the first injury data and the second injury data, an injury detection result of the injured person is generated.

2. The rapid medical treatment method according to claim 1, characterized in that: The step of acquiring the accident photo in response to the triggering operation of the first user on the first operation guidance interface specifically includes: In response to the first user's triggering operation on the screenshot control, generating a viewfinder on the first operation guide interface; The accident photo is obtained by intercepting the picture content in the viewfinder.

3. The rapid medical treatment method according to claim 1, characterized in that: The step of importing the second accident photo into a pre-trained human disability detection model to obtain the second injury data of the injured person specifically includes: Performing joint point detection on the second accident photo to obtain body joint points of the injured person; Marking the joints of the injured person's body to obtain information of the joints; The human body injury detection model is used to predict the joint injury of the injured person based on the human body joint point information to obtain second injury data of the injured person.

4. The rapid medical treatment method according to any one of claims 1 to 3, characterized in that: After the step of displaying the first aid operation steps for the wounded on the first operation guide interface, the method further includes: Obtaining accident responsibility determination operation steps, and displaying the accident responsibility determination operation steps on the first operation guidance interface; In response to the first user's triggering operation on the first operation guidance interface for determining the responsibility for the accident, performing content recognition on the accident photo, determining the accident vehicle in the accident photo, and obtaining driving information of the accident vehicle; Retrieving surveillance video within a preset time period before and after the accident, and identifying the driving trajectory of the accident vehicle based on the surveillance video; A pre-constructed traffic control regulations knowledge graph is obtained, and the accident liability of the accident vehicle is determined based on the driving trajectory of the accident vehicle, the driving information of the accident vehicle and the traffic control regulations knowledge graph.

5. The rapid medical treatment method according to claim 4, characterized in that: After the step of obtaining the pre-constructed traffic control regulations knowledge graph and determining the accident responsibility of the accident vehicle based on the driving trajectory of the accident vehicle, the driving information of the accident vehicle and the traffic control regulations knowledge graph, the method further includes: Obtaining accident claim settlement operation steps, and displaying the accident claim settlement operation steps on the first operation guidance interface; In response to the triggering operation of the first user on the first operation guidance interface for accident claim settlement, calling a pre-trained vehicle damage recognition model to recognize the accident photo to obtain the degree of vehicle damage; A compensation plan is generated based on the injury detection results, the degree of vehicle damage and the accident liability.

6. A rapid medical treatment device, characterized in that: include: An operation step acquisition module, used to receive an accident handling instruction, and acquire the operation steps of the accident handling process according to the accident handling instruction, wherein the operation steps of the accident handling process include a first operation step and a second operation step; A first guidance module, configured to generate a first operation guidance interface on a terminal of a first user, and display the first operation steps on the first operation guidance interface, wherein the first operation steps at least include taking a photo of the accident; A first trigger operation module, configured to obtain accident photos in response to a trigger operation of the first user on the first operation guide interface; An injury detection module is used to import the accident photo into a pre-trained human injury detection model to obtain an injury detection result of the injured person; A second guidance module, configured to generate a second operation guidance interface on a terminal of a second user, and display the second operation steps and the injury detection result on the second operation guidance interface; A second trigger operation module, configured to generate first aid operation steps for the wounded in response to a trigger operation of the second user on the second operation guide interface; A first aid operation guidance module, used to display the first aid operation steps for the injured on the first operation guidance interface; The accident photo includes a first accident photo and a second accident photo, and the first trigger operation module further includes: a first accident photo acquisition unit, configured to receive the first accident photo, and perform content recognition on the first accident photo to obtain the limb condition in the first accident photo; a body surface injury prediction unit, configured to analyze the limb condition in the first accident photo to obtain first injury data of the injured person, wherein the first injury data is body surface injury data; a detection action display unit, configured to determine a detection action video based on the first injury data, and display the detection action video on the first operation guide interface; The injured person's action shooting unit is used to obtain the picture of the injured person completing the detection action video through the viewfinder to obtain the injury detection video; A second accident photo acquisition unit is used to extract key frames from the injury detection video to obtain the second accident photo; The injury detection module specifically includes: a joint injury prediction unit, used for importing the second accident photo into a pre-trained human disability detection model to obtain second injury data of the injured person, wherein the second injury data is joint injury data; An injury detection unit is used to generate an injury detection result of the injured person based on the first injury data and the second injury data.

7. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the rapid medical treatment method as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the rapid medical treatment method according to any one of claims 1 to 5.

Images