Artificial Intelligence-Based Referral Supervision Method, Device, Equipment and Storage Medium

Abstract

The present application relates to the fields of artificial intelligence and digital medical technology, and provides a referral supervision method based on artificial intelligence, including: parsing a received referral application; determining a supervision area according to the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital; identifying the vehicle information of a referral vehicle picture, and rendering a 3D virtual vehicle model on a 3D electronic map according to the vehicle information; obtaining the GPS coordinates of the referral vehicle, and determining whether to generate a first referral receiving instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital; when it is determined to generate a first referral receiving instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital, and a second referral receiving instruction confirmed by a supervisor according to the 3D virtual vehicle model rendered on the 3D electronic map is received, calling a disease level recognition model to recognize the disease level of the patient's electronic case. The present application can quickly provide medical services for patients with relatively serious conditions and improve the medical experience of patients seeking medical treatment.

Description

Technical Field

[0001] This application belongs to the technical field of artificial intelligence, and particularly relates to a referral supervision method, device, equipment, and storage medium based on artificial intelligence. Background Art

[0002] Patient referral and transfer is a behavior that often occurs during the medical treatment process, and it is also a link where medical disputes and medical accidents often occur. The supervision of referral and transfer has thus become an important task for medical supervision agencies.

[0003] The inventors found during the implementation of the present invention that existing supervision systems often can only count the stock data reported by hospitals, and there is a possibility of false reporting and omission in the hospital reports, resulting in poor accuracy of the supervision results statistically calculated by the supervision system. In addition, the existing supervision systems perform statistics in the form of regularly fetching data, and the statistical results are presented in text form, resulting in the inability to update the supervision results in real time, low supervision efficiency, and unfriendly supervision display methods. Summary of the Invention

[0004] In view of the above, the present invention provides a referral supervision method, device, equipment, and storage medium based on artificial intelligence, aiming to solve the technical problems of the inability to update the supervision results in real time and low supervision efficiency in the prior art.

[0005] To achieve the above object, the present invention provides a referral supervision method based on artificial intelligence, and the method includes:

[0006] Analyze the received referral application to obtain the transferring hospital, the receiving hospital, pictures of the referral vehicle, and the patient's electronic medical record;

[0007] Determine the supervision area according to the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital, and load and display the 3D electronic map corresponding to the supervision area on the display screen;

[0008] Identify the vehicle information in the pictures of the referral vehicle, and render a 3D virtual vehicle model on the 3D electronic map according to the vehicle information;

[0009] Obtain the GPS coordinates of the referral vehicle, and determine whether to generate a first referral receiving instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital;

[0010] When it is determined to generate a first referral receiving instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital, and a second referral receiving instruction confirmed by the supervisor according to the 3D virtual vehicle model rendered on the 3D electronic map is received, call the disease level recognition model to identify the disease level of the patient's electronic medical record;

[0011] Generate a referral form according to the disease level and send it to the terminal of the receiving hospital.

[0012] Preferably, before parsing the received referral application, the method further includes:

[0013] Receive a referral application;

[0014] Save the referral application to the WebSocket message queue;

[0015] Push WebSocket messages to the front end in real time through the WebSocket message queue.

[0016] Preferably, identifying the vehicle information of the referral vehicle picture and rendering a 3D virtual vehicle model on the 3D electronic map according to the vehicle information includes:

[0017] Identify the referral vehicle model, referral vehicle color, and referral vehicle license plate number in the referral vehicle picture;

[0018] Obtain the target 3D virtual vehicle model corresponding to the referral vehicle model;

[0019] Load the referral vehicle color and the referral vehicle license plate number onto the target 3D virtual vehicle model;

[0020] Generate a prompt box at a preset distance position from the target 3D virtual vehicle model, and enter referral information into the prompt box.

[0021] Preferably, determining whether to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital includes:

[0022] Calculate a first distance between the GPS coordinates of the referral vehicle and the GPS coordinates of the sending hospital;

[0023] Calculate a second distance between the GPS coordinates of the incoming vehicle and the GPS coordinates of the sending hospital;

[0024] Calculate the ratio of the first distance to the second distance and determine whether the ratio is greater than a preset ratio threshold;

[0025] When it is determined that the ratio is greater than the preset ratio threshold, determine to generate a first referral reception instruction;

[0026] When it is determined that the ratio is less than or equal to the preset ratio threshold, determine not to generate a first referral reception instruction.

[0027] Preferably, calling a disease level recognition model to recognize the disease level of the patient's electronic case includes:

[0028] Identify multiple entity types in the patient's electronic medical record and the entity names and entity attributes corresponding to each entity type;

[0029] Construct an entity attribute vector according to the type and the entity names and entity attributes corresponding to each entity type;

[0030] Input the entity attribute vector into the disease level recognition model for disease level recognition.

[0031] Preferably, before receiving the second referral acceptance instruction confirmed by the supervisor based on the 3D virtual vehicle model rendered on the 3D electronic map, the method further includes:

[0032] Control the 3D virtual vehicle model to move on the 3D electronic map according to the GPS coordinates of the referral vehicle;

[0033] Call the icon style to create a directed movement path from the first 3D virtual hospital model to the 3D virtual vehicle model and display the directed movement path;

[0034] Identify whether the directed movement path is the path between the first 3D virtual hospital model and the second 3D virtual hospital model;

[0035] When it is identified that the directed movement path is the path between the first 3D virtual hospital model and the second 3D virtual hospital model, pop up a referral text box;

[0036] Receive the second referral acceptance instruction input by the user through the referral text box.

[0037] Preferably, after generating the referral form according to the disease level and sending it to the terminal of the receiving hospital, the method further includes:

[0038] Receive the admission information fed back by the terminal of the receiving hospital according to the referral form;

[0039] Add the admission information to the historical admission information for real-time statistical analysis and generate a supervision report.

[0040] To achieve the above object, the present invention also provides an artificial intelligence-based referral supervision device, and the device includes:

[0041] A receiving module, configured to parse the received referral application to obtain the sending hospital, the receiving hospital, the picture of the referral vehicle, and the patient's electronic medical record;

[0042] A determination module, configured to determine a supervision area based on the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital, and load and display a 3D electronic map corresponding to the supervision area on a display screen;

[0043] A rendering module, configured to identify vehicle information of the referral vehicle picture, and render a 3D virtual vehicle model on the 3D electronic map according to the vehicle information;

[0044] A generation module, configured to obtain the GPS coordinates of the referral vehicle, and determine whether to generate a first referral receiving instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital;

[0045] A calling module, configured to, when it is determined to generate a first referral receiving instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital, and a second referral receiving instruction confirmed by a supervisor based on the 3D virtual vehicle model rendered on the 3D electronic map is received, call a disease level recognition model to recognize the disease level of the patient's electronic case;

[0046] A sending module, configured to generate a referral form according to the disease level and send it to the terminal of the receiving hospital.

[0047] To achieve the above object, the present invention further provides an electronic device, where the electronic device includes:

[0048] At least one processor; and,

[0049] A memory communicatively connected to the at least one processor; wherein,

[0050] The memory stores a program executable by the at least one processor, and the program is executed by the at least one processor so that the at least one processor can execute the referral supervision method based on artificial intelligence.

[0051] To achieve the above object, the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a referral supervision program based on artificial intelligence, and when the referral supervision program based on artificial intelligence is executed by a processor, the steps of the referral supervision method based on artificial intelligence are implemented.

[0052] The method provided by the present invention obtains the GPS coordinates of the referral vehicle by parsing the pictures of the transfer - out hospital, transfer - in hospital, and referral vehicle, and determines whether to generate a first referral reception instruction based on the GPS coordinates of the referral vehicle and the GPS coordinates of the transfer - in hospital. When it is determined to generate a first referral reception instruction based on the GPS coordinates of the referral vehicle and the GPS coordinates of the transfer - in hospital, the supervision area is determined based on the GPS coordinates of the transfer - out hospital and the GPS coordinates of the transfer - in hospital, and the 3D electronic map corresponding to the supervision area is loaded and displayed on the display screen; then the vehicle information of the referral vehicle picture is identified, and a 3D virtual vehicle model is rendered on the 3D electronic map according to the vehicle information, which can intuitively and vividly simulate the referral process of the referral vehicle and is convenient for the supervisor to intuitively determine whether to generate a second referral reception instruction; it can track the referral process in real - time and dynamically, avoiding false reporting and missed reporting. Moreover, when the referral vehicle arrives at the destination, a referral form can be generated in a timely manner, and the supervision efficiency is relatively high. Only when it is determined to generate a first referral reception instruction and a second referral reception instruction is received, a referral form is generated, which can effectively ensure the supervision result, and the accuracy rate of the supervision result is relatively high. Finally, the disease level recognition model is called to recognize the disease level of the patient's electronic case, and a referral form is generated according to the disease level and sent to the terminal of the transfer - in hospital, so that the medical staff in the transfer - in hospital can schedule and optimize the medical resources of the hospital in advance, quickly provide medical services for patients with more serious conditions, and improve the medical experience of the patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1 Schematic diagram of a preferred embodiment of the electronic device of the present invention;

[0055] Figure 2 For Figure 1 Module schematic diagram of a preferred embodiment of the referral supervision device based on artificial intelligence in

[0056] Figure 3 Flowchart of a preferred embodiment of the referral supervision method based on artificial intelligence of the present invention;

[0057] The realization, functional characteristics, and advantages of the object of the present invention will be further described with reference to the embodiments and the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0058] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0059] Referring to Figure 1 as shown, which is a schematic diagram of a preferred embodiment of the electronic device 1 of the present invention.

[0060] The electronic device 1 includes, but is not limited to: a memory 11, a processor 12, a display 13, and a network interface 14. The electronic device 1 is connected to a network through the network interface 14 to obtain original data. Among them, the network may be a wireless or wired network such as an enterprise internal network (Intranet), the Internet, Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network, Bluetooth, Wi-Fi call network, etc.

[0061] Among them, the memory 11 includes at least one type of readable storage medium. The readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as 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, magnetic disk, optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as the hard disk or memory of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped with the electronic device 1.

[0062] Of course, the memory 11 may also include both the internal storage unit of the electronic device 1 and its external storage device. In this embodiment, the memory 11 is generally used to store the operating system and various application software installed in the electronic device 1, such as the program code of the referral supervision program 10 based on artificial intelligence. In addition, the memory 11 can also be used to temporarily store various data that have been output or will be output.

[0063] In some embodiments, the processor 12 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 12 is generally used to control the overall operation of the electronic device 1, such as performing control and processing related to data interaction or communication. In this embodiment, the processor 12 is used to run the program code stored in the memory 11 or process data, such as running the program code of the referral supervision program 10 based on artificial intelligence.

[0064] The display 13 may be referred to as a display screen or a display unit. In some embodiments, the display 13 may be an LED display, a liquid crystal display, a touch liquid crystal display, and an organic light-emitting diode (OLED) toucher, etc. The display 13 is used to display the information processed in the electronic device 1 and to display a visual working interface, such as displaying the results of data statistics.

[0065] The network interface 14 may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), and the network interface 14 is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0066] Figure 1 Only the electronic device 1 with components 11-14 and the referral supervision program 10 based on artificial intelligence is shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively.

[0067] Optionally, the electronic device 1 may further include a target user interface. The target user interface may include a display, an input unit such as a keyboard, and optionally the target user interface may further include a standard wired interface and a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an organic light-emitting diode (OLED) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, and is used to display the information processed in the electronic device 1 and to display a visual target user interface.

[0068] The electronic device 1 may further include a radio frequency (RF) circuit, a sensor, an audio circuit, etc., which will not be elaborated here.

[0069] In the above embodiments, when the processor 12 executes the artificial intelligence-based referral supervision program 10 stored in the memory 11, the following steps may be implemented:

[0070] Parse the received referral application to obtain the transferring hospital, the receiving hospital, the picture of the referral vehicle, and the patient's electronic medical record;

[0071] Determine the supervision area according to the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital, and load and display the 3D electronic map corresponding to the supervision area on the display screen;

[0072] Identify the vehicle information of the picture of the referral vehicle, and render a 3D virtual vehicle model on the 3D electronic map according to the vehicle information;

[0073] Obtain the GPS coordinates of the referral vehicle, and determine whether to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital;

[0074] When it is determined to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital, and a second referral reception instruction confirmed by the supervisor according to the 3D virtual vehicle model rendered on the 3D electronic map is received, call the disease level recognition model to identify the disease level of the patient's electronic medical record;

[0075] Generate a referral form according to the disease level and send it to the terminal of the receiving hospital.

[0076] For a detailed introduction to the above steps, please refer to the following Figure 2 Regarding the functional module diagram of the artificial intelligence-based referral supervision device 100 embodiment and Figure 3 Regarding the flowchart description of the artificial intelligence-based referral supervision method embodiment.

[0077] Refer to Figure 2 As shown, it is the functional module diagram of the artificial intelligence-based referral supervision device 100 of the present invention.

[0078] The artificial intelligence-based referral supervision device 100 of the present invention can be installed in an electronic device. According to the functions achieved, the artificial intelligence-based referral supervision device 100 may include a receiving module 110, a determining module 120, a rendering module 130, a generating module 140, a calling module 150, and a sending module 160. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0079] In this embodiment, the functions of each module / unit are as follows:

[0080] A receiving module 110, configured to parse the received referral application to obtain the transferring hospital, the receiving hospital, pictures of the referral vehicle, and the electronic medical record of the patient.

[0081] In this embodiment, a medical consortium platform is installed in the computer device, and the medical consortium platform is used to supervise the referral information of each medical institution. The medical consortium platform can provide a smart large screen to visually display statistical data. A Hospital Information System (HIS) is installed in the terminals corresponding to each medical institution. Doctors in each medical institution can issue a referral application form through the HIS system, and the HIS system sends the referral application to the medical consortium platform through the HTTP-SERVER.

[0082] After receiving the referral application, the medical consortium platform parses the referral application to obtain a parsing result. The parsing result may include, but is not limited to: the transferring hospital, the receiving hospital, pictures of the referral vehicle, and the electronic medical record of the patient. Among them, the picture of the referral vehicle is a picture including the referral vehicle, and the electronic medical record of the patient refers to the original information of the patient recorded in an electronic manner during the treatment process by the receiving hospital.

[0083] In one embodiment, before parsing the received referral application, it further includes:

[0084] Receiving the referral application;

[0085] Saving the referral application to the WebSocket message queue;

[0086] Real-time pushing WebSocket messages to the front end through the WebSocket message queue.

[0087] In this embodiment, after receiving the referral application, the medical consortium platform first saves the referral application to the WebSocket message queue. Among them, WebSocket is a push service based on a long connection, and its function is to actively push messages to the end user without the end user initiating an interface request.

[0088] In this alternative embodiment, by means of the message push mechanism of the WebSocket message queue, the referral application can be quickly and real-time obtained and parsed.

[0089] A determination module 120, configured to determine a supervision area according to the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital, and load and display a 3D electronic map corresponding to the supervision area on a display screen.

[0090] In this embodiment, the computer device can determine a rectangular area with the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital as two symmetric points of the rectangle, and determine the rectangular area as the supervision area. The computer device only needs to load the 3D electronic map corresponding to the supervision area.

[0091] In this embodiment, by determining the supervision area and loading the 3D electronic map of the supervision area, rather than loading the entire 3D electronic map, the 3D electronic map can be loaded directionally and quickly, so as to quickly achieve the display effect of the 3D electronic map.

[0092] The rendering module 130 is used to identify the vehicle information of the referral vehicle picture and render a 3D virtual vehicle model on the 3D electronic map according to the vehicle information.

[0093] In this embodiment, the 3D model can be rendered on the display interface of the medical consortium platform by using the three-dimensional engine Cesium. The underlying layer of Cesium uses a Web graphics library to implement rendering. The Web graphics library creates Web interactive 3D animations through the HTML script itself and uses the underlying graphics hardware acceleration function to implement rendering. Cesium is an open-source framework based on JavaScript, which can be used to draw a 3D earth in a browser and draw maps on it (supporting tile services in multiple formats). This framework does not require any plugin support, but the browser must support WebGL. Cesium supports a variety of data visualization methods, can draw various geometric figures, import pictures, and even 3D models.

[0094] The corresponding relationship between the GPS range and the 3D virtual hospital model is pre-stored in the computer device. The corresponding first 3D virtual hospital model can be determined by matching the GPS range where the GPS coordinates of the transferring hospital are located, and the corresponding second 3D virtual hospital model can be determined by matching the GPS range where the GPS coordinates of the receiving hospital are located. The computer device determines a first positioning point on the 3D electronic map according to the GPS coordinates of the transferring hospital, and renders the first 3D virtual hospital model corresponding to the GPS coordinates of the transferring hospital with the first positioning point as the center; determines a second positioning point on the 3D electronic map according to the GPS coordinates of the receiving hospital, and renders the second 3D virtual hospital model corresponding to the GPS coordinates of the receiving hospital with the second positioning point as the center.

[0095] The medical consortium platform renders the first 3D virtual hospital model and the second 3D virtual hospital model on the 3D electronic map according to the GPS coordinates of the hospital, so as to more realistically simulate the referral scenario. The 3D display is more hierarchical, which is convenient for supervisors to intuitively understand the entire referral process.

[0096] In one embodiment, identifying the vehicle information of the referral vehicle picture and rendering a 3D virtual vehicle model on the 3D electronic map according to the vehicle information includes:

[0097] Identifying the referral vehicle model, referral vehicle color, and referral vehicle license plate number in the referral vehicle picture;

[0098] Obtaining a target 3D virtual vehicle model corresponding to the referral vehicle model;

[0099] Loading the referral vehicle color and the referral vehicle license plate number onto the target 3D virtual vehicle model;

[0100] Generating a prompt box at a preset distance position from the target 3D virtual vehicle model and typing referral information into the prompt box.

[0101] In this embodiment, in this optional embodiment, the referral vehicle model can be obtained by inputting the referral vehicle picture into a pre-trained vehicle model recognition model for recognition; the referral vehicle color can be obtained by inputting the referral vehicle picture into a pre-trained color recognition model for recognition; the referral vehicle license plate number can be obtained by using a license plate number recognition algorithm to recognize the referral vehicle picture.

[0102] Among them, the referral information may include, but is not limited to, the basic information of the patient (such as name, age, gender, etc.) and medical information (such as the admitting doctor, department of visit, diagnosis result).

[0103] Typing the referral information into the prompt box and synchronously moving with the 3D virtual vehicle model on the 3D electronic map.

[0104] A generation module 140, configured to obtain the GPS coordinates of the referral vehicle and determine whether to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital.

[0105] In this embodiment, the computer device may send a GPS coordinate acquisition request to the referral vehicle in real time or periodically, and determine the GPS coordinates of the referral vehicle through the GPS coordinates fed back by the referral vehicle. Alternatively, the referral vehicle may actively report the GPS coordinates to the computer device in real time or periodically, so that the computer device receives the GPS coordinates of the referral vehicle in real time or periodically.

[0106] In one embodiment, determining whether to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital includes:

[0107] Calculating a first distance between the GPS coordinates of the referral vehicle and the GPS coordinates of the sending hospital;

[0108] Calculate a second distance between the GPS coordinates of the transferred vehicle and the GPS coordinates of the transferring hospital;

[0109] Calculate a ratio of the first distance to the second distance and determine whether the ratio is greater than a preset ratio threshold;

[0110] When it is determined that the ratio is greater than the preset ratio threshold, determine to generate a first referral reception instruction;

[0111] When it is determined that the ratio is less than or equal to the preset ratio threshold, determine not to generate a first referral reception instruction.

[0112] In this optional embodiment, if the ratio of the first distance to the second distance is greater than the preset ratio threshold, it indicates that the referral vehicle is relatively close to the transferring hospital, and determine to generate a first referral instruction. If the ratio of the first distance to the second distance is not greater than the preset ratio threshold, it indicates that the referral vehicle is relatively far from the transferring hospital, and determine not to generate a first referral instruction.

[0113] Call module 150, which is used to, when it is determined to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the transferring hospital, and a second referral reception instruction confirmed by the supervisor based on the 3D virtual vehicle model rendered on the 3D electronic map is received, call a disease level recognition model to recognize the disease level of the patient's electronic case.

[0114] In this embodiment, the computer device will call the disease level recognition model to recognize the disease level of the patient's electronic case only when it is determined to generate a first referral reception instruction and a second referral reception instruction confirmed by the supervisor is received, which is convenient for generating different levels of referral forms according to the disease level later. The computer device will not call the disease level recognition model to recognize the disease level of the patient's electronic case when it is determined not to generate a first referral reception instruction and / or when a second referral reception instruction confirmed by the supervisor is not received.

[0115] When the computer device determines to generate a first referral reception instruction and a second referral reception instruction confirmed by the supervisor is received, it indicates that the referral vehicle in the real referral scenario is about to drive to the transferring hospital, generate a target referral reception instruction to generate a referral supervision event and store the referral supervision event, which is convenient for subsequent traceability and statistical analysis.

[0116] In one embodiment, the calling the disease level recognition model to recognize the disease level of the patient's electronic case includes:

[0117] Recognize multiple entity types in the patient's electronic case and the entity name and entity attribute corresponding to each entity type;

[0118] Construct an entity attribute vector according to the type and the entity name and entity attributes corresponding to each entity type.

[0119] Input the entity attribute vector into a disease level recognition model to recognize the disease level.

[0120] In this embodiment, the entity type refers to medical terms such as diseases, symptoms, diagnostic classifications, treatments, examinations, human tissues, examination items, etc. The entity name refers to the entity items included in each entity type, and the entity attribute refers to the degree of the entity item. For example, if the entity type is a disease, the entity item is cancer, and the entity attribute is stage 3 medium.

[0121] A medical knowledge graph constructed by professional medical entity taggers is pre-stored in the computer device. Multiple entity types in the patient's electronic case are identified through the medical knowledge graph, and the entity attributes of each entity item in the patient's electronic case are parsed according to the context semantic parsing algorithm.

[0122] The computer device can, according to the World Health Organization disease severity classification table, select 4 disease severities, corresponding to mild, moderate, severe, and high risk respectively, and establish an electronic case set based on this. The training set, test set, and validation set are divided in the ratio of 6:2:2 in sequence, and multiple entity types of the electronic cases in the training set, test set, and validation set and the entity name and entity attributes corresponding to each entity type are respectively identified through the medical knowledge graph, so as to construct a training entity attribute vector set, a test entity attribute vector set, and a validation entity attribute vector set respectively. Based on the training entity attribute vector set, the test entity attribute vector set, and the validation entity attribute vector set, a neural network model for analyzing disease levels is trained to obtain a disease level recognition model.

[0123] In one embodiment, before receiving the second referral reception instruction confirmed by the supervisor based on the 3D virtual vehicle model rendered on the 3D electronic map, it further includes:

[0124] Control the 3D virtual vehicle model to move on the 3D electronic map according to the GPS coordinates of the referral vehicle;

[0125] Call an icon style to create a directed movement path from the first 3D virtual hospital model to the 3D virtual vehicle model and display the directed movement path;

[0126] Identify whether the directed movement path is the path between the first 3D virtual hospital model and the second 3D virtual hospital model;

[0127] When it is recognized that the directed movement path is the path between the first 3D virtual hospital model and the second 3D virtual hospital model, a referral text box pops up;

[0128] Receive a second referral receiving instruction input by the user through the referral text box.

[0129] In this embodiment, the icon style can be BMAP.Symbol.

[0130] The computer device can call the roadbook function to control the 3D virtual vehicle model to move on the electronic map according to the GPS coordinates of the referral vehicle.

[0131] The computer device can determine whether the directed movement path is within the supervision area. When the directed movement path is within the supervision area, it is determined that the directed movement path is the path between the first 3D virtual hospital model and the second 3D virtual hospital model; when the directed movement path is not within the supervision area, it is determined that the directed movement path is not the path between the first 3D virtual hospital model and the second 3D virtual hospital model.

[0132] In an alternative embodiment, the computer device can also display a display color associated with the distance on the directed movement path. Different gradient color values can be displayed according to user or actual needs. Since it is a gradient, it is necessary to set the start display color and the end display color, and multiple display colors can be added in the middle. For example, when wanting to display a gradient color value that transitions from red to blue, the offset of the gradient starting point can be set to 0, and the corresponding color is red, and the offset of the gradient end point is set to 1, and the corresponding color is blue.

[0133] The sending module 160 is configured to generate a referral form according to the disease level and send it to the terminal of the transferred-in hospital.

[0134] In this embodiment, when the recognized disease level is higher, it indicates that the patient's condition is more serious and immediate medical treatment needs to be arranged, so a first-level referral form is generated for the patient; when the recognized disease level is lower, it indicates that the patient's condition is relatively mild and immediate medical treatment is not required, so a second-level referral form is generated for the patient.

[0135] By identifying the disease level to generate different levels of referral forms and sending them to the terminal of the transferred-in hospital, the medical staff in the transferred-in hospital can schedule the hospital's medical resources in advance, such as various medical equipment, allocate medical staff, etc., so as to optimize medical resources and quickly provide medical services for patients with more serious conditions, improving the medical experience of the patients.

[0136] In an optional embodiment, after generating a referral form according to the disease level and sending it to the terminal of the receiving hospital, the following steps are further included:

[0137] Receiving the admission information fed back by the terminal of the receiving hospital according to the referral form;

[0138] Adding the admission information to the historical admission information for real-time statistical analysis and generating a supervision report.

[0139] In this embodiment, the supervision report can be displayed in real time on the intelligent large screen of the medical consortium platform.

[0140] In this embodiment, by parsing the pictures of the transferring hospital, the receiving hospital, and the referral vehicle, the GPS coordinates of the referral vehicle are obtained, and whether to generate a first referral reception instruction is determined according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital. When it is determined to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital, the supervision area is determined according to the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital, and the 3D electronic map corresponding to the supervision area is loaded and displayed on the display screen; then the vehicle information of the referral vehicle picture is identified, and a 3D virtual vehicle model is rendered on the 3D electronic map according to the vehicle information, which can intuitively and vividly simulate the referral process of the referral vehicle and is convenient for the supervisor to intuitively determine whether to generate a second referral reception instruction; it can track the referral process in real time and dynamically, avoiding false reporting and missed reporting. Moreover, when the referral vehicle arrives at the destination, a referral form can be generated in a timely manner, and the supervision efficiency is relatively high. Only when it is determined to generate a first referral reception instruction and a second referral reception instruction is received, a referral form is generated, which can effectively ensure the supervision result and the accuracy rate of the supervision result is relatively high. Finally, the disease level recognition model is called to recognize the disease level of the patient's electronic case, and a referral form is generated according to the disease level and sent to the terminal of the receiving hospital, so that the medical staff of the receiving hospital can schedule and optimize the medical resources of the hospital in advance, quickly provide medical services for patients with more serious conditions, and improve the medical experience of the patients.

[0141] In addition, the present invention also provides an artificial intelligence-based referral supervision method. Refer to Figure 3 As shown, it is a schematic flowchart of the method of the embodiment of the artificial intelligence-based referral supervision method of the present invention. When the processor 12 of the electronic device 1 executes the artificial intelligence-based referral supervision program 10 stored in the memory 11, the artificial intelligence-based referral supervision method is implemented, including steps S101-S106. The following is a specific description of each step.

[0142] S101: Parse the received referral application to obtain the transferring hospital, the receiving hospital, pictures of the referral vehicle, and the patient's electronic medical record.

[0143] In this embodiment, a medical consortium platform is installed in the computer device, and the medical consortium platform is used to supervise the referral information of each medical institution. The medical consortium platform can provide a smart large screen to intuitively display statistical data. A Hospital Information System (HIS) is installed in the terminals corresponding to each medical institution. Doctors in each medical institution can issue a referral application form through the HIS system, and the HIS system sends the referral application to the medical consortium platform through the HTTP-SERVER.

[0144] After receiving the referral application, the medical consortium platform parses the referral application to obtain a parsing result. The parsing result may include, but is not limited to: the transferring hospital, the receiving hospital, pictures of the referral vehicle, and the patient's electronic medical record. Among them, the pictures of the referral vehicle are pictures including the referral vehicle, and the patient's electronic medical record refers to the original information of the patient recorded in an electronic manner during the treatment process by the receiving hospital.

[0145] In one embodiment, before parsing the received referral application, it further includes:

[0146] Receive the referral application;

[0147] Save the referral application to the WebSocket message queue;

[0148] Push WebSocket messages to the front end in real time through the WebSocket message queue.

[0149] In this embodiment, after receiving the referral application, the medical consortium platform first saves the referral application to the WebSocket message queue. Among them, WebSocket is a push service based on a long connection, and its function is to actively push messages to the end user without the end user initiating an interface request.

[0150] In this optional embodiment, by means of the message push mechanism of the WebSocket message queue, the referral application can be quickly and real-time obtained and parsed.

[0151] S102: Determine the supervision area according to the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital, and load and display the 3D electronic map corresponding to the supervision area on the display screen.

[0152] In this embodiment, the computer device can determine a rectangular area with the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital as two symmetric points of the rectangle, and determine the rectangular area as the supervision area. The computer device only needs to load the 3D electronic map corresponding to the supervision area.

[0153] In this embodiment, by determining the supervision area and loading the 3D electronic map of the supervision area, rather than loading the entire 3D electronic map, the 3D electronic map can be loaded directionally and quickly, so as to quickly achieve the display effect of the 3D electronic map.

[0154] S103: Identify the vehicle information of the referral vehicle picture, and render a 3D virtual vehicle model on the 3D electronic map according to the vehicle information.

[0155] In this embodiment, the three-dimensional engine Cesium can be used to render the 3D model on the display interface of the medical consortium platform. The underlying layer of Cesium uses a Web graphics library to implement rendering. The Web graphics library creates Web interactive three-dimensional animations through the HTML script itself and uses the underlying graphics hardware acceleration function to implement rendering. Cesium is an open-source framework based on JavaScript, which can be used to draw a 3D earth in the browser and draw maps on it (supporting tile services in multiple formats). This framework does not require any plugin support, but the browser must support WebGL. Cesium supports a variety of data visualization methods, can draw various geometric figures, import pictures, and even 3D models.

[0156] The corresponding relationship between the GPS range and the 3D virtual hospital model is pre-stored in the computer device. The corresponding first 3D virtual hospital model can be determined by matching the GPS range where the GPS coordinates of the transferring hospital are located, and the corresponding second 3D virtual hospital model can be determined by matching the GPS range where the GPS coordinates of the receiving hospital are located. The computer device determines a first positioning point on the 3D electronic map according to the GPS coordinates of the transferring hospital, and renders the first 3D virtual hospital model corresponding to the GPS coordinates of the transferring hospital with the first positioning point as the center; determines a second positioning point on the 3D electronic map according to the GPS coordinates of the receiving hospital, and renders the second 3D virtual hospital model corresponding to the GPS coordinates of the receiving hospital with the second positioning point as the center.

[0157] The medical consortium platform renders the first 3D virtual hospital model and the second 3D virtual hospital model on the 3D electronic map according to the GPS coordinates of the hospital, so as to more realistically simulate the referral scenario. The 3D display is more hierarchical, which is convenient for supervisors to intuitively understand the entire referral process.

[0158] In one embodiment, identifying the vehicle information of the referral vehicle picture and rendering a 3D virtual vehicle model on the 3D electronic map according to the vehicle information includes:

[0159] Identifying the referral vehicle model, referral vehicle color, and referral vehicle license plate number in the referral vehicle picture;

[0160] Obtaining a target 3D virtual vehicle model corresponding to the referral vehicle model;

[0161] Loading the referral vehicle color and the referral vehicle license plate number onto the target 3D virtual vehicle model;

[0162] Generating a prompt box at a preset distance position from the target 3D virtual vehicle model and typing referral information into the prompt box.

[0163] In this embodiment, in this optional embodiment, the referral vehicle model can be obtained by inputting the referral vehicle picture into a pre-trained vehicle model recognition model for recognition; the referral vehicle color can be obtained by inputting the referral vehicle picture into a pre-trained color recognition model for recognition; and the referral vehicle license plate number can be obtained by using a license plate number recognition algorithm to recognize the referral vehicle picture.

[0164] Wherein, the referral information may include, but is not limited to, the basic information of the patient (such as name, age, gender, etc.) and medical treatment information (such as the admitting doctor, department of treatment, diagnosis result).

[0165] Typing the referral information into the prompt box and synchronously moving with the 3D virtual vehicle model on the 3D electronic map.

[0166] S104: Obtaining the GPS coordinates of the referral vehicle and determining whether to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital.

[0167] In this embodiment, the computer device can send a GPS coordinate acquisition request to the referral vehicle in real time or periodically, and determine the GPS coordinates of the referral vehicle through the GPS coordinates fed back by the referral vehicle. Alternatively, the referral vehicle can actively report the GPS coordinates to the computer device in real time or periodically, so that the computer device can receive the GPS coordinates of the referral vehicle in real time or periodically.

[0168] In one embodiment, determining whether to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital includes:

[0169] Calculating a first distance between the GPS coordinates of the referral vehicle and the GPS coordinates of the sending hospital;

[0170] Calculate a second distance between the GPS coordinates of the transferred vehicle and the GPS coordinates of the transferring hospital;

[0171] Calculate a ratio of the first distance to the second distance and determine whether the ratio is greater than a preset ratio threshold;

[0172] When it is determined that the ratio is greater than the preset ratio threshold, determine to generate a first referral reception instruction;

[0173] When it is determined that the ratio is less than or equal to the preset ratio threshold, determine not to generate a first referral reception instruction.

[0174] In this alternative embodiment, if the ratio of the first distance to the second distance is greater than the preset ratio threshold, it indicates that the referral vehicle is relatively close to the transferring hospital, and determine to generate a first referral instruction. If the ratio of the first distance to the second distance is not greater than the preset ratio threshold, it indicates that the referral vehicle is relatively far from the transferring hospital, and determine not to generate a first referral instruction.

[0175] S105: When it is determined to generate a first referral reception instruction based on the GPS coordinates of the referral vehicle and the GPS coordinates of the transferring hospital, and a second referral reception instruction confirmed by the supervisor based on the 3D virtual vehicle model rendered on the 3D electronic map is received, call a disease level recognition model to recognize the disease level of the patient's electronic case.

[0176] In this embodiment, the computer device will call a disease level recognition model to recognize the disease level of the patient's electronic case only when it is determined to generate a first referral reception instruction and when a second referral reception instruction confirmed by the supervisor is received, which is convenient for generating different levels of referral forms according to the disease level later. The computer device will not call a disease level recognition model to recognize the disease level of the patient's electronic case when it is determined not to generate a first referral reception instruction and / or when a second referral reception instruction confirmed by the supervisor is not received.

[0177] When the computer device determines to generate a first referral reception instruction and a second referral reception instruction confirmed by the supervisor is received, it indicates that the referral vehicle in the real referral scenario is about to drive to the transferring hospital, generate a target referral reception instruction to generate a referral supervision event and store the referral supervision event, which is convenient for subsequent traceability and statistical analysis.

[0178] In one embodiment, the calling the disease level recognition model to recognize the disease level of the patient's electronic case includes:

[0179] Recognize multiple entity types in the patient's electronic case and the entity name and entity attribute corresponding to each entity type;

[0180] Construct an entity attribute vector according to the type and the entity name and entity attributes corresponding to each entity type.

[0181] Input the entity attribute vector into the disease level recognition model to recognize the disease level.

[0182] In this embodiment, the entity type refers to medical terms such as diseases, symptoms, diagnostic classifications, treatments, examinations, human tissues, examination items, etc. The entity name refers to the entity items included in each entity type, and the entity attribute refers to the degree of the entity items. For example, if the entity type is a disease, the entity item is cancer, and the entity attribute is stage 3 medium.

[0183] The computer device pre-stores a medical knowledge graph constructed by professional medical entity taggers, identifies multiple entity types in the patient's electronic case through the medical knowledge graph, and parses the entity attributes of each entity item in the patient's electronic case according to the context semantic parsing algorithm.

[0184] The computer device can, according to the World Health Organization disease severity classification table, select 4 disease severities, corresponding to mild, moderate, severe, and high risk respectively, and establish an electronic case set based on this. Divide the training set, test set, and validation set in the ratio of 6:2:2 in sequence, and respectively identify multiple entity types and the entity names and entity attributes corresponding to each entity type in the electronic cases in the training set, test set, and validation set through the medical knowledge graph, so as to construct a training entity attribute vector set, a test entity attribute vector set, and a validation entity attribute vector set respectively. Train a neural network model for analyzing disease levels based on the training entity attribute vector set, the test entity attribute vector set, and the validation entity attribute vector set to obtain a disease level recognition model.

[0185] In one embodiment, before receiving the second referral reception instruction confirmed by the supervisor according to the 3D virtual vehicle model rendered on the 3D electronic map, it further includes:

[0186] Control the 3D virtual vehicle model to move on the 3D electronic map according to the GPS coordinates of the referral vehicle.

[0187] Call the icon style to create a directed movement path from the first 3D virtual hospital model to the 3D virtual vehicle model and display the directed movement path.

[0188] Identify whether the directed movement path is the path between the first 3D virtual hospital model and the second 3D virtual hospital model.

[0189] When the identified directed movement path is the path between the first 3D virtual hospital model and the second 3D virtual hospital model, a referral text box pops up;

[0190] Receive a second referral receiving instruction input by the user through the referral text box.

[0191] In this embodiment, the icon style can be BMAP.Symbol.

[0192] The computer device can call the roadbook function to control the 3D virtual vehicle model to move on the electronic map according to the GPS coordinates of the referral vehicle.

[0193] The computer device can determine whether the directed movement path is within the supervision area. When the directed movement path is within the supervision area, it is determined that the directed movement path is the path between the first 3D virtual hospital model and the second 3D virtual hospital model; when the directed movement path is not within the supervision area, it is determined that the directed movement path is not the path between the first 3D virtual hospital model and the second 3D virtual hospital model.

[0194] In an alternative embodiment, the computer device can also display a display color associated with the distance on the directed movement path. Different gradient color values can be displayed according to user or actual needs. Since it is a gradient, the starting display color and the ending display color need to be set, and multiple display colors can be added in between. For example, when wanting to display a gradient color value that transitions from red to blue, the offset of the gradient starting point can be set to 0, and the corresponding color is red, and the offset of the gradient ending point is set to 1, and the corresponding color is blue.

[0195] S106: Generate a referral form according to the disease level and send it to the terminal of the receiving hospital.

[0196] In this embodiment, when the identified disease level is higher, it indicates that the patient's condition is more serious and immediate medical treatment needs to be arranged, so a first-level referral form is generated for the patient; when the identified disease level is lower, it indicates that the patient's condition is relatively mild and immediate medical treatment is not required, so a second-level referral form is generated for the patient.

[0197] By identifying the disease level to generate different levels of referral forms and sending them to the terminal of the receiving hospital, the medical staff in the receiving hospital can schedule the hospital's medical resources in advance, such as various medical equipment, allocate medical staff, etc., so as to optimize medical resources and quickly provide medical services for patients with more serious conditions, improving the medical experience of the patients.

[0198] In an optional embodiment, after generating the referral form according to the disease level and sending it to the terminal of the receiving hospital, the following steps are further included:

[0199] Receiving the admission information feedback by the terminal of the receiving hospital according to the referral form;

[0200] Adding the admission information to the historical admission information for real-time statistical analysis and generating a supervision report.

[0201] In this embodiment, the supervision report can be displayed on the intelligent large screen of the medical consortium platform in real time.

[0202] In this embodiment, by parsing the pictures of the transferring hospital, receiving hospital, and referral vehicle, the GPS coordinates of the referral vehicle are obtained, and whether to generate a first referral reception instruction is determined according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital. When it is determined to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital, the supervision area is determined according to the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital, and the 3D electronic map corresponding to the supervision area is loaded and displayed on the display screen; then the vehicle information of the referral vehicle picture is identified, and a 3D virtual vehicle model is rendered on the 3D electronic map according to the vehicle information, which can intuitively and vividly simulate the referral process of the referral vehicle and is convenient for the supervisor to intuitively determine whether to generate a second referral reception instruction; it can track the referral process in real time and dynamically, avoiding false reporting and missed reporting, and when the referral vehicle arrives at the destination, a referral form can be generated in time, with high supervision efficiency. Only when it is determined to generate a first referral reception instruction and a second referral reception instruction is received, a referral form is generated, which can effectively ensure the supervision result and the accuracy rate of the supervision result is relatively high. Finally, the disease level recognition model is called to recognize the disease level of the patient's electronic case, and a referral form is generated according to the disease level and sent to the terminal of the receiving hospital, so that the medical staff of the receiving hospital can schedule and optimize the medical resources of the hospital in advance and quickly provide medical services for patients with more serious conditions, improving the medical experience of the patients.

[0203] In addition, an embodiment of the present invention further provides a computer-readable storage medium, which may be any one or any combination of a hard disk, a multimedia card, an SD card, a flash card, an SMC, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, and the like. The computer-readable storage medium includes a storage data area and a storage program area. The storage data area stores data created according to the use of the blockchain node, and the storage program area stores a referral supervision program 10 based on artificial intelligence. When the referral supervision program 10 based on artificial intelligence is executed by a processor, the following operations are implemented:

[0204] Parse the received referral application to obtain the transferring hospital, the receiving hospital, the picture of the referral vehicle, and the patient's electronic medical record;

[0205] Determine a supervision area according to the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital, and load and display a 3D electronic map corresponding to the supervision area on a display screen;

[0206] Identify the vehicle information of the picture of the referral vehicle, and render a 3D virtual vehicle model on the 3D electronic map according to the vehicle information;

[0207] Obtain the GPS coordinates of the referral vehicle, and determine whether to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital;

[0208] When it is determined to generate a first referral reception instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital, and a second referral reception instruction confirmed by a supervisor according to the 3D virtual vehicle model rendered on the 3D electronic map is received, call a disease level recognition model to recognize the disease level of the patient's electronic medical record;

[0209] Generate a referral form according to the disease level and send it to the terminal of the receiving hospital.

[0210] In another embodiment, for the referral supervision method based on artificial intelligence provided by the present invention, to further ensure the privacy and security of all the data appearing above, all the above data may also be stored in a node of a blockchain. For example, two-dimensional codes, identification codes, etc., and these data can be stored in the blockchain node.

[0211] It should be noted that the blockchain referred to in the present invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithms. Blockchain, in essence, is a decentralized database, a series of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of the information (anti-counterfeiting) and generate the next block. The blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer, etc.

[0212] The specific implementation manner of the computer-readable storage medium of the present invention is substantially the same as that of the above-mentioned referral supervision method based on artificial intelligence, and will not be elaborated herein.

[0213] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments. And the term "comprising" or any other variant thereof in this article is intended to cover non-exclusive inclusion, so that a process, device, article or method comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or also includes elements inherent to such process, device, article or method. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of another identical element in the process, device, article or method comprising that element.

[0214] It should be noted that the above embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Among them, Artificial Intelligence (AI) is a 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.

[0215] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0216] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above and includes several instructions for causing an electronic device (which can be a mobile phone, computer, electronic device, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0217] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. An artificial intelligence-based referral supervision method, characterized in that, The method includes: Parsing the received referral application to obtain the transferring hospital, the receiving hospital, pictures of the referral vehicle, and the patient's electronic medical record; Determining a supervision area based on the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital, loading and displaying the 3D electronic map corresponding to the supervision area on a display screen, and rendering a first 3D virtual hospital model and a second 3D virtual hospital model on the 3D electronic map according to the GPS coordinates of the transferring hospital and the GPS coordinates of the receiving hospital; Identifying the vehicle information of the picture of the referral vehicle, and rendering a 3D virtual vehicle model on the 3D electronic map according to the vehicle information; Obtaining the GPS coordinates of the referral vehicle, and determining whether to generate a first referral receiving instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital; the 3D virtual vehicle model moves on the 3D electronic map according to the GPS coordinates of the referral vehicle; When it is determined to generate a first referral receiving instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital, and a second referral receiving instruction confirmed by the supervisor according to the 3D virtual vehicle model rendered on the 3D electronic map is received, calling a disease level recognition model to recognize the disease level of the patient's electronic medical record; Generating a referral form according to the disease level and sending it to the terminal of the receiving hospital; Among them, the identifying the vehicle information of the picture of the referral vehicle, and rendering a 3D virtual vehicle model on the 3D electronic map according to the vehicle information includes: Identifying the vehicle type, vehicle color, and license plate number of the referral vehicle in the picture of the referral vehicle; Obtaining a target 3D virtual vehicle model corresponding to the vehicle type of the referral vehicle; Loading the vehicle color and the license plate number of the referral vehicle onto the target 3D virtual vehicle model; Generating a prompt box at a preset distance position from the target 3D virtual vehicle model, and typing referral information into the prompt box, and the prompt box moves synchronously with the 3D virtual vehicle model on the 3D electronic map.

2. The artificial intelligence-based referral supervision method according to claim 1, characterized in that, Before parsing the received referral application, the method further includes: Receiving a referral application; Saving the referral application to a WebSocket message queue; Real-time pushing WebSocket messages to the front end through the WebSocket message queue.

3. The artificial intelligence-based referral supervision method according to claim 1, characterized in that, The determining whether to generate a first referral receiving instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital includes: Calculating a first distance between the GPS coordinates of the referral vehicle and the GPS coordinates of the transferring hospital; Calculating a second distance between the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital; Calculating the ratio of the first distance to the second distance and determining whether the ratio is greater than a preset ratio threshold; When it is determined that the ratio is greater than the preset ratio threshold, determining to generate a first referral receiving instruction; When it is determined that the ratio is less than or equal to the preset ratio threshold, determining not to generate a first referral receiving instruction.

4. The artificial intelligence-based referral supervision method according to claim 1, characterized in that, The step of calling the disease level recognition model to recognize the disease level of the patient's electronic medical record includes: Recognize multiple entity types in the patient's electronic medical record, as well as the entity names and entity attributes corresponding to each entity type; Construct an entity attribute vector based on the types, entity names, and entity attributes corresponding to each entity type; Input the entity attribute vector into the disease level recognition model for disease level recognition.

5. The artificial intelligence-based referral supervision method according to claim 4, characterized in that, Before receiving the second referral acceptance instruction confirmed by the supervisor based on the 3D virtual vehicle model rendered on the 3D electronic map, it further includes: Control the 3D virtual vehicle model to move on the 3D electronic map according to the GPS coordinates of the referral vehicle; Call the icon style to create a directed movement path from the first 3D virtual hospital model to the 3D virtual vehicle model and display the directed movement path; Identify whether the directed movement path is the path between the first 3D virtual hospital model and the second 3D virtual hospital model; When it is identified that the directed movement path is the path between the first 3D virtual hospital model and the second 3D virtual hospital model, pop up a referral text box; Receive the second referral acceptance instruction input by the user through the referral text box.

6. The referral supervision method based on artificial intelligence according to claim 1, characterized in that, After generating the referral form according to the disease level and sending it to the terminal of the receiving hospital, it further includes: Receive the admission information fed back by the terminal of the receiving hospital according to the referral form; Add the admission information to the historical admission information for real-time statistical analysis and generate a supervision report.

7. A referral supervision device based on artificial intelligence, characterized in that, The device includes: A receiving module, configured to parse the received referral application to obtain the sending hospital, receiving hospital, referral vehicle picture, and the patient's electronic medical record; A determining module, configured to determine the supervision area according to the GPS coordinates of the sending hospital and the GPS coordinates of the receiving hospital, load and display the 3D electronic map corresponding to the supervision area on the display screen, and render the first 3D virtual hospital model and the second 3D virtual hospital model on the 3D electronic map according to the GPS coordinates of the sending hospital and the GPS coordinates of the receiving hospital; A rendering module, configured to identify the vehicle information of the referral vehicle picture and render a 3D virtual vehicle model on the 3D electronic map according to the vehicle information; A generating module, configured to obtain the GPS coordinates of the referral vehicle, and determine whether to generate a first referral acceptance instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital; the 3D virtual vehicle model moves on the 3D electronic map according to the GPS coordinates of the referral vehicle; A calling module, configured to call the disease level recognition model to recognize the disease level of the patient's electronic medical record when it is determined to generate a first referral acceptance instruction according to the GPS coordinates of the referral vehicle and the GPS coordinates of the receiving hospital, and the second referral acceptance instruction confirmed by the supervisor based on the 3D virtual vehicle model rendered on the 3D electronic map is received; A sending module, configured to generate a referral form according to the disease level and send it to the terminal of the receiving hospital; Among them, the rendering module is specifically configured to: identify the vehicle model, vehicle color, and license plate number of the referral vehicle in the picture of the referral vehicle; obtain the target 3D virtual vehicle model corresponding to the vehicle model of the referral vehicle; load the vehicle color and license plate number of the referral vehicle onto the target 3D virtual vehicle model; generate a prompt box at a preset distance position from the target 3D virtual vehicle model, and enter referral information into the prompt box, and the prompt box moves synchronously with the 3D virtual vehicle model on the 3D electronic map.

8. An electronic device, characterized in that, The electronic device includes: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, the memory stores a program executable by the at least one processor, and the program is executed by the at least one processor so that the at least one processor can execute the artificial intelligence-based referral supervision method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an artificial intelligence-based referral supervision program, and when the artificial intelligence-based referral supervision program is executed by a processor, the steps of the artificial intelligence-based referral supervision method according to any one of claims 1 to 6 are implemented.

Images