AI-based medical guidance system

Abstract

The invention relates to the field of medical treatment guide equipment, in particular to an AI-based medical treatment guide system, which constructs a medical treatment reference process based on medical treatment demand information input by a user, so that all nodes required by the user for medical treatment are arranged in sequence, and in addition, the place where each process node needs to arrive is not required to be matched with the position where each process node needs to arrive. The method comprises the following steps of: storing a plurality of flow nodes and reference images of a surrounding environment in a system, and performing full-flow guidance according to the plurality of flow nodes during guidance. And the required arriving place and the surrounding environment are sent to the user for reference, so that the user can refer to the system in the whole course of seeing a doctor. The method and the device can provide whole-process medical treatment guidance for the user, can effectively reduce the time of hospital stagnation of the user, and improve the medical treatment efficiency and the medical treatment experience of the user.

Description

Technical Field

[0001] The present invention relates to the field of medical guidance equipment, and in particular to an AI-based medical guidance system. Background Art

[0002] Medical guidance refers to providing patients with necessary guidance and support in the process of seeking medical services to ensure that they can smoothly and efficiently obtain the medical resources and services they need. Especially for first-time patients, reasonable guidance can help patients quickly find the right department and doctor, reduce unnecessary waiting time, and improve the efficiency of the entire medical process.

[0003] Most of the existing internal guidance methods in hospitals use guide signs to indicate the locations and floors of different departments. However, for first-time patients, it is impossible to provide full-process medical guidance based on the real-time location of the first-time patients. First-time patients often need a lot of time to sort out the medical process and find the locations of various environments in the medical process. The process is very cumbersome. Summary of the invention

[0004] In view of this, an object of the present invention is to provide an AI-based medical guidance system to solve the problems in the background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] An AI-based medical guidance system of the present invention includes:

[0007] An acquisition module is used to acquire the user's medical demand information, wherein the medical demand information includes the type of medical treatment and the hospital information;

[0008] A process construction module, used to construct a medical reference process based on the medical demand information, wherein the medical reference process includes multiple process nodes, reference locations of the process nodes, and multiple environmental reference images of the reference locations;

[0009] The positioning module is used to obtain the user's real-time positioning information when the user seeks medical treatment;

[0010] A guidance module is used to perform medical guidance based on the medical reference process and the real-time positioning information.

[0011] In one embodiment of the present application, a medical reference process is constructed based on the medical demand information, including:

[0012] Selecting a target process template from a pre-built template library based on the medical treatment type, wherein the medical treatment type includes initial visit, follow-up visit, emergency visit, specialist clinic and physical examination;

[0013] Acquire the location information of each department or division in the visiting hospital information, and extract the location information of multiple process nodes in the target process template from the location information of each department or division;

[0014] A plurality of environmental reference images corresponding to the positioning information are obtained, and a medical reference process is constructed based on a plurality of process nodes, the positioning information of the plurality of process nodes, and the plurality of environmental reference images corresponding to the positioning information of the plurality of process nodes.

[0015] In one embodiment of the present application, performing medical guidance based on the medical reference process and the real-time positioning information includes:

[0016] S1, when the status of the current process node is unfinished, calling a navigation tool based on the reference location of the current process node and the current location information of the user, generating a guidance path, and providing medical guidance based on the guidance path;

[0017] S2, when the user reaches the end point of the guidance path and receives a completion command from the user, the current process node is completed, the next process node is used as the current process node, and the process returns to step S1 until all process nodes are completed;

[0018] S3, when the user reaches the end point of the guidance path and receives unfinished positioning feedback from the user, obtain the real-time environment image of the current positioning collected by the user, and provide medical guidance based on the real-time environment image and the multiple environment reference images; until a completion command is received from the user, complete the current process node, use the next process node as the current process node, and return to step S1 until all process nodes are completed.

[0019] In one embodiment of the present application, the multiple environmental reference images are evenly distributed around a circle with the reference location as the center, wherein medical guidance is performed based on the real-time environmental image and the multiple environmental reference images, including:

[0020] Matching the real-time environment image with the multiple environment reference images based on a pre-built similarity comparison model to obtain a target reference image that matches the real-time environment image;

[0021] The user is guided to seek medical treatment based on the relative position relationship between the target reference image and the guidance target point of the current process node.

[0022] In one embodiment of the present application, matching the real-time environment image with the multiple environment reference images based on a pre-built similarity comparison model to obtain a target reference image matching the real-time environment image includes:

[0023] Preprocessing the real-time environment image and the multiple environment reference images respectively to obtain a preprocessed real-time image and a preprocessed reference image, wherein the preprocessing includes grayscale conversion and high-pass filtering;

[0024] Cutting the preprocessed real-time image to obtain a plurality of vertical strip images;

[0025] Combining each strip image with each preprocessed reference image to obtain input data;

[0026] Inputting the input data into a pre-built similarity comparison model to obtain a similarity score for each set of input data;

[0027] The input data with similarity scores greater than a preset threshold are regarded as similar data;

[0028] The environment reference image containing similarity data is used as the target reference image.

[0029] In one embodiment of the present application, the method for constructing the similarity comparison model includes:

[0030] Obtain multiple sets of data sets containing paired images, where each set of paired images contains a complete image and a strip image obtained after being cropped;

[0031] Preprocessing and labeling multiple groups of paired images in the data set to obtain a training data set, wherein the preprocessing includes grayscale conversion and high-pass filtering, and the labeling information is a similarity score;

[0032] The artificial neural network is trained based on the training data set to obtain a similarity comparison model.

[0033] In one embodiment of the present application, guiding the user to seek medical treatment based on the relative position relationship between the target reference image and the guidance target point of the current process node includes:

[0034] Determine an angle between the target reference image and a reference reference image, wherein the reference reference image is an image directly facing the guidance target point among the multiple environment reference images;

[0035] The user is guided to seek medical treatment based on the angle.

[0036] In an embodiment of the present application, obtaining a real-time environment image of the current location collected by a user includes:

[0037] Comparing the user's real-time location with an endpoint range, wherein the endpoint range is a circular range formed by taking the endpoint of the guidance path as the origin and a preset radius;

[0038] When the real-time location of the user does not fall within the destination range, outputting movement prompt information based on the user's moving path direction and real-time location to prompt the user to move within the destination range, and returning to compare the user's real-time location with the destination range;

[0039] When the real-time location of the user falls within the end point range, a camera call request is sent, and when the call permission is obtained, a real-time environment image of the current location is acquired.

[0040] In one embodiment of the present application, it also includes:

[0041] The triage module is used to perform triage and obtain the target department based on the symptom complaint and identity information received from the user, based on the symptom complaint, identity information and the externally accessed triage model.

[0042] In one embodiment of the present application, the multiple environment reference images for reference positioning are collected in advance and stored in a server.

[0043] The beneficial effects of the present invention are: an AI-based medical guidance system of the present invention, the present application constructs a medical reference process based on the medical demand information input by the user, so that all the nodes required for the user's medical treatment are arranged in order. In addition, the location required to be reached by each process node and the reference image of the surrounding environment are stored in the system. When guiding, the whole process guidance is carried out according to multiple process nodes. The required location and the surrounding environment are sent to the user for reference, and the user can refer to this system throughout the medical treatment. The present application can provide users with full-process medical guidance, which can effectively reduce the user's hospital stay time and improve the user's medical efficiency and medical experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0045] Figure 1 is a structural diagram of an AI-based medical guidance system shown in an embodiment of the present application;

[0046] Figure 2 This is an application scenario diagram in an embodiment of the present application;

[0047] Figure 3 Construct a flow chart for the reference process in this application;

[0048] Figure 4 This is a flowchart of collecting real-time environment images in one embodiment of the present application. DETAILED DESCRIPTION

[0049] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0050] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show the layers related to the present invention rather than being drawn according to the number, shape and size of the layers in actual implementation. In actual implementation, the type, quantity and proportion of each layer may be changed arbitrarily, and the layer layout may also be more complicated.

[0051] In the following description, numerous details are discussed to provide a more thorough explanation of embodiments of the present invention; however, it is apparent to one skilled in the art that embodiments of the present invention may be practiced without these specific details.

[0052] Figure 1 is a structural diagram of an AI-based medical guidance system shown in an embodiment of the present application, such as Figure 1 As shown: An AI-based medical guidance system of this embodiment includes:

[0053] The acquisition module 110 is used to acquire the user's medical demand information, wherein the medical demand information includes the type of medical treatment and the hospital information;

[0054] Figure 2 This is an application scenario diagram in an embodiment of the present application, such as Figure 2 As shown, this application mainly relies on the user's handheld smart terminal 210 and server 220 to perform guidance. The user's medical demand information is input through the smart terminal 210. The medical demand information mainly records which hospital and department the user needs to go to for treatment, and what the type of treatment is. The type of treatment determines the subsequent treatment process, and the hospital information determines the specific location of each process node.

[0055] A process construction module 120 is used to construct a medical reference process based on the medical demand information, wherein the medical reference process includes multiple process nodes, reference locations of the process nodes, and multiple environmental reference images of the reference locations;

[0056] In this embodiment, different types of medical consultations correspond to different processes, such as: initial consultation, follow-up consultation, emergency consultation, specialist clinic and physical examination.

[0057] Taking the initial visit as an example, the process of the initial visit and the follow-up visit includes registration-waiting-treatment. The process of the emergency visit is emergency department-registration evaluation-treatment, etc. In this application, different process templates are constructed for different types of visits, and then the corresponding information is filled in the template to perform location guidance. Figure 3 Construct a flow chart for the reference process in this application, such as Figure 3 As shown, the process of constructing a medical reference process based on the medical demand information includes:

[0058] S310, selecting a target process template from a pre-built template library based on the medical treatment type, wherein the medical treatment type includes initial visit, follow-up visit, emergency visit, specialist clinic and physical examination;

[0059] Among them, the process templates corresponding to initial visit, follow-up visit, emergency visit, and specialist outpatient clinic are as described above.

[0060] For the physical examination process, since physical examinations are divided into many categories and different physical examination packages include different types of physical examinations, there is no order relationship between process nodes for the physical examination process template, and you only need to build a physical examination node set.

[0061] S320, obtaining the location information of each department or division in the visiting hospital information, and extracting the location information of multiple process nodes in the target process template from the location information of each department or division;

[0062] The positioning information is acquired in advance, and the relevant personnel perform positioning collection at the corresponding position. At the same time, the environmental reference image of the positioning is collected. The environmental reference image can help users determine their own position. If the user still cannot find the target after reaching the positioning point, the position can be further determined by referring to the environmental image. Multiple environmental reference images are evenly distributed around the reference positioning as the center of the circle, so as to collect environmental images in a surrounding manner.

[0063] S330, obtaining multiple environmental reference images corresponding to the positioning information, and constructing a medical reference process based on multiple process nodes, the positioning information of the multiple process nodes, and the multiple environmental reference images corresponding to the positioning information of the multiple process nodes.

[0064] Finally, multiple process nodes are associated with corresponding positioning information and environmental reference images and stored in the server, thus completing the construction of the process template.

[0065] The positioning module 130 is used to obtain the real-time positioning information of the user when the user seeks medical treatment;

[0066] If the user enters a start command when seeking medical treatment, the guidance process can be automatically executed. At this time, the user's smart terminal location permission is requested, and after obtaining authorization, the user's real-time location can be obtained.

[0067] The guidance module 140 is used to perform medical guidance based on the medical reference process and the real-time positioning information.

[0068] Specifically, the specific process of performing medical guidance based on the medical reference process and the real-time positioning information includes:

[0069] S1, when the status of the current process node is unfinished, calling a navigation tool based on the reference location of the current process node and the current location information of the user, generating a guidance path, and providing medical guidance based on the guidance path;

[0070] In this application, if there is a sequence relationship between the processes, each process node is navigated in turn according to the sequence relationship. If it is a physical examination type, there is no sequence relationship, and the user specifies each process node for navigation.

[0071] S2, when the user reaches the end point of the guidance path and receives a completion command from the user, the current process node is completed, the next process node is used as the current process node, and the process returns to step S1 until all process nodes are completed;

[0072] After the user reaches the navigation end point, if the user can directly find the corresponding department / division, the user can click the completion command to complete the guidance of the current process node, and then proceed to the guidance process of the next process node.

[0073] S3, when the user reaches the end point of the guidance path and receives unfinished positioning feedback from the user, obtain the real-time environment image of the current positioning collected by the user, and provide medical guidance based on the real-time environment image and the multiple environment reference images; until a completion command is received from the user, complete the current process node, use the next process node as the current process node, and return to step S1 until all process nodes are completed.

[0074] If the user still cannot find the corresponding department / section when reaching the navigation end point, the environmental reference image is used for further guidance. In this application, the environmental reference image is taken in advance, so the AI ​​model of this application compares the real-time environmental image of the current location with the environmental reference image to determine the user's current position and orientation for further guidance.

[0075] Figure 4 This is a flow chart of collecting real-time environment images in one embodiment of the present application, such as Figure 4 As shown, the following process is used to obtain the real-time environment image of the current location collected by the user, including:

[0076] S410, comparing the real-time location of the user with an endpoint range, wherein the endpoint range is a circular range formed by taking the endpoint of the guidance path as the origin and a preset radius;

[0077] In order to ensure that the real-time environmental image collected can match the pre-collected environmental reference image, it is first necessary to ensure that the shooting positions are close. Therefore, this application first constructs a range based on the end point of the guidance path, and then acquires the image when the real-time positioning falls into the end point range.

[0078] S420, when the real-time location of the user does not fall within the destination range, outputting movement prompt information based on the moving path direction of the user and the real-time location to prompt the user to move within the destination range, and returning to comparing the real-time location of the user with the destination range;

[0079] When the user is not within the range, the smart terminal prompts the user to walk into the range before taking photos.

[0080] S430, when the real-time location of the user falls within the end point range, sending a camera call request, and when the call permission is obtained, obtaining a real-time environment image of the current location.

[0081] If it reaches this range, it will collect real-time environment images by requesting authorization for subsequent comparison.

[0082] The specific process of guiding medical treatment based on the real-time environmental images and multiple environmental reference images collected in the previous article includes:

[0083] S510, matching the real-time environment image with the multiple environment reference images based on a pre-built similarity comparison model to obtain a target reference image that matches the real-time environment image;

[0084] This application uses an AI model to perform similarity matching on images. The matching process includes:

[0085] (1) preprocessing the real-time environment image and the multiple environment reference images respectively to obtain a preprocessed real-time image and a preprocessed reference image, wherein the preprocessing includes grayscale conversion and high-pass filtering;

[0086] Grayscale conversion removes color information, thereby reducing the dimensionality of the image. High-pass filtering is used to filter out low-frequency information in the image, thereby retaining high-frequency information such as contours.

[0087] (2) cropping the preprocessed real-time image to obtain a plurality of vertical strip images;

[0088] Since it is impossible to ensure that the user's shooting angle is completely consistent with the shooting angle of the environmental reference image, the pre-processed real-time image is cropped to obtain a vertical strip image, which is used to compare the environmental reference image to improve the comparison success rate.

[0089] (3) combining each strip image with each preprocessed reference image to obtain input data;

[0090] (4) inputting the input data into a pre-built similarity comparison model to obtain a similarity score for each set of input data;

[0091] This application uses an AI comparison model to compare the similarity of each group of images to obtain a similarity score. The training method of the similarity comparison model is:

[0092] Obtain multiple sets of data sets containing paired images, where each set of paired images contains a complete image and a strip image obtained after being cropped;

[0093] Preprocessing and labeling multiple groups of paired images in the data set to obtain a training data set, wherein the preprocessing includes grayscale conversion and high-pass filtering, and the labeling information is a similarity score;

[0094] The artificial neural network is trained based on the training data set to obtain a similarity comparison model.

[0095] During the training process, paired images are also used as training data, and the gradient descent method is combined to train the Siamese Network to obtain a similarity comparison model.

[0096] (5) taking the input data whose similarity score is greater than a preset threshold as similar data;

[0097] (6) The environment reference image containing similarity data is used as the target reference image.

[0098] S520, guiding the user to seek medical treatment based on the relative position relationship between the target reference image and the guidance target point of the current process node, specifically including:

[0099] Determine an angle between the target reference image and a reference reference image, wherein the reference reference image is an image directly facing the guidance target point among the multiple environment reference images;

[0100] The user is guided to seek medical treatment based on the angle.

[0101] For example, after determining the target reference image, it is determined that the angle between the target reference image and the baseline reference image is 30°. Combined with the user's motion trajectory, a guiding sentence "the destination is 30° to your right" can be output. At the same time, the baseline reference image is output, and a prompt mark is marked in the baseline reference image for further guidance.

[0102] The triage module is used to perform triage and obtain the target department based on the symptom complaint and identity information received from the user, based on the symptom complaint, identity information and the externally accessed triage model.

[0103] In addition, in order to facilitate the medical treatment of users who have just received a diagnosis, this application also has a built-in triage model, which can be used for triage using the triage model, the user's symptoms and user information. The triage model used in this application is an existing model and will not be repeated here.

[0104] The present invention is an AI-based medical guidance system. The present application constructs a medical reference process based on the medical demand information input by the user, so that all the nodes required for the user's medical treatment are arranged in order. In addition, the location required to be reached by each process node and the reference image of the surrounding environment are stored in the system. When guiding, the whole process guidance is carried out according to multiple process nodes. The required location and the surrounding environment are sent to the user for reference, and the user can refer to this system throughout the medical treatment. The present application can provide users with full-process medical guidance, which can effectively reduce the user's hospital stay time and improve the user's medical efficiency and medical experience.

[0105] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, any one of the methods in this embodiment is implemented, wherein the method is the execution logic of this system.

[0106] This embodiment also provides an electronic terminal, including: a processor and a memory;

[0107] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any one of the methods in this embodiment.

[0108] The computer-readable storage medium in this embodiment can be understood by ordinary technicians in this field: all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0109] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run computer programs so that the electronic terminal executes each step of the above method.

[0110] In this embodiment, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0111] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0112] In the above-mentioned embodiments, although the present invention has been described in conjunction with the specific embodiments of the present invention, many replacements, modifications and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. The embodiments of the present invention are intended to cover all such replacements, modifications and variations falling within the broad scope of the appended claims.

[0113] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. An AI-based medical guidance system, characterized in that: include: An acquisition module is used to acquire the user's medical demand information, wherein the medical demand information includes the type of medical treatment and the hospital information; A process construction module, used to construct a medical reference process based on the medical demand information, wherein the medical reference process includes multiple process nodes, reference locations of the process nodes, and multiple environmental reference images of the reference locations; The positioning module is used to obtain the user's real-time positioning information when the user seeks medical treatment; A guidance module is used to perform medical guidance based on the medical reference process and the real-time positioning information.

2. The AI-based medical guidance system according to claim 1, characterized in that: A medical reference process is constructed based on the medical demand information, including: Selecting a target process template from a pre-built template library based on the medical treatment type, wherein the medical treatment type includes initial visit, follow-up visit, emergency visit, specialist clinic and physical examination; Acquire the location information of each department or division in the visiting hospital information, and extract the location information of multiple process nodes in the target process template from the location information of each department or division; A plurality of environmental reference images corresponding to the positioning information are obtained, and a medical reference process is constructed based on a plurality of process nodes, the positioning information of the plurality of process nodes, and the plurality of environmental reference images corresponding to the positioning information of the plurality of process nodes.

3. The AI-based medical guidance system according to claim 2, characterized in that: Executing medical guidance based on the medical reference process and the real-time positioning information includes: S1, when the status of the current process node is unfinished, calling a navigation tool based on the reference location of the current process node and the current location information of the user, generating a guidance path, and providing medical guidance based on the guidance path; S2, when the user reaches the end point of the guidance path and receives a completion command from the user, the current process node is completed, the next process node is used as the current process node, and the process returns to step S1 until all process nodes are completed; S3, when the user reaches the end point of the guidance path and receives unfinished positioning feedback from the user, obtain the real-time environment image of the current positioning collected by the user, and provide medical guidance based on the real-time environment image and the multiple environment reference images; until a completion command is received from the user, complete the current process node, use the next process node as the current process node, and return to step S1 until all process nodes are completed.

4. The AI-based medical guidance system according to claim 3, characterized in that: The multiple environmental reference images are evenly distributed in a circle with the reference location as the center, wherein medical guidance is performed based on the real-time environmental image and the multiple environmental reference images, including: Matching the real-time environment image with the multiple environment reference images based on a pre-built similarity comparison model to obtain a target reference image that matches the real-time environment image; The user is guided to seek medical treatment based on the relative position relationship between the target reference image and the guidance target point of the current process node.

5. The AI-based medical guidance system according to claim 4, characterized in that: Matching the real-time environment image with the multiple environment reference images based on a pre-built similarity comparison model to obtain a target reference image matching the real-time environment image includes: Preprocessing the real-time environment image and the multiple environment reference images respectively to obtain a preprocessed real-time image and a preprocessed reference image, wherein the preprocessing includes grayscale conversion and high-pass filtering; Cutting the preprocessed real-time image to obtain a plurality of vertical strip images; Combining each strip image with each preprocessed reference image to obtain input data; Inputting the input data into a pre-built similarity comparison model to obtain a similarity score for each set of input data; The input data with similarity scores greater than a preset threshold are regarded as similar data; The environment reference image containing similarity data is used as the target reference image.

6. The AI-based medical guidance system according to claim 4, characterized in that: The method for constructing the similarity comparison model includes: Obtain multiple sets of data sets containing paired images, where each set of paired images contains a complete image and a strip image obtained after being cropped; Preprocessing and labeling multiple groups of paired images in the data set to obtain a training data set, wherein the preprocessing includes grayscale conversion and high-pass filtering, and the labeling information is a similarity score; The artificial neural network is trained based on the training data set to obtain a similarity comparison model.

7. The AI-based medical guidance system according to claim 4, characterized in that: Guiding the user to seek medical treatment based on the relative position relationship between the target reference image and the guidance target point of the current process node, including: Determine an angle between the target reference image and a reference reference image, wherein the reference reference image is an image directly facing the guidance target point among the multiple environment reference images; The user is guided to seek medical treatment based on the angle.

8. The AI-based medical guidance system according to claim 3, characterized in that: Get the real-time environment image of the current location collected by the user, including: Comparing the user's real-time location with an endpoint range, wherein the endpoint range is a circular range formed by taking the endpoint of the guidance path as the origin and a preset radius; When the real-time location of the user does not fall within the destination range, outputting movement prompt information based on the user's moving path direction and real-time location to prompt the user to move within the destination range, and returning to compare the user's real-time location with the destination range; When the real-time location of the user falls within the end point range, a camera call request is sent, and when the call permission is obtained, a real-time environment image of the current location is acquired.

9. The AI-based medical guidance system according to claim 1, characterized in that: Also includes: The triage module is used to perform triage and obtain the target department based on the symptom complaint and identity information received from the user, based on the symptom complaint, identity information and the externally accessed triage model.

10. The AI-based medical guidance system according to claim 1, characterized in that: The multiple environment reference images for reference positioning are collected in advance and stored in the server.

Images