WO2022267678A1

WO2022267678A1 - Video consultation method and apparatus, device and storage medium

Info

Publication number: WO2022267678A1
Application number: PCT/CN2022/088890
Authority: WO
Inventors: 朱章春
Original assignee: 康键信息技术（深圳）有限公司
Priority date: 2021-06-23
Filing date: 2022-04-25
Publication date: 2022-12-29
Also published as: CN113436723A

Abstract

A video consultation method and apparatus, a device and a storage medium. The method comprises: acquiring user consultation data according to a pre-configured intelligent sensing device (101); performing pre-diagnosis on the consultation data to obtain a pre-diagnosis result (102); when the pre-diagnosis result does not match a corresponding condition of the user, receiving a consultation request uploaded by a user side, and determining, according to the consultation request, a department allocated to the user (103); acquiring a medical knowledge graph corresponding to the department, and parsing the user consultation data according to the medical knowledge graph to obtain medical decision information (104); and diagnosing the user according to the medical decision information to generate a final diagnosis result (105). The convenience of online medical treatment is combined with the expertise of a conventional medical institution or hospital, condition predictions are performed for users by means of collecting a large amount of patient data, and the technical problem low diagnostic accuracy in current video consultation means is solved.

Description

Video consultation method, device, equipment and storage medium

This application claims the priority of the Chinese patent application with the application number 202110698592.9 and the title of the invention "video consultation method, device, equipment and storage medium" submitted to the China Patent Office on June 23, 2021, the entire contents of which are incorporated by reference in application.

technical field

The present application relates to the field of big data, and in particular to a video consultation method, device, equipment and storage medium.

Background technique

Online medical technology is an important emerging field of the national medical system. At present, major Internet giants have launched graphic consultation/video consultation. For some simple minor diseases, users can consult online through the mobile APP, and the doctor will give advice on prescribing medicine through the graphic information or video consultation given by the user, and complete the medical treatment directly online, avoiding long queues at the hospital. Greatly increase the rate of patients seeking medical treatment, and at the same time share the medical pressure of domestic medical institutions, empowering the national medical system.

However, due to the cumbersome questioning with pictures and texts, and it is difficult to take high-quality pictures of some parts, the inventor realized that it is difficult for users to accurately describe their own discomfort, which leads to misdiagnosis due to wrong judgments by doctors. However, video consultation is limited by issues such as device pixel quality and shooting angles. The quality of information that can be provided to doctors is low, making it difficult for doctors to accurately judge the patient's condition. Therefore, accurately predicting and diagnosing the user's condition has become a technical problem that those skilled in the art need to face.

Contents of the invention

This application is mainly to solve the technical problem of low diagnostic accuracy in the existing video consultation mode.

The first aspect of the present application provides a video consultation method, including: obtaining user consultation data based on a preset intelligent sensor device, wherein the consultation data includes the user's basic information and chief complaint content; Perform pre-diagnosis on the medical inquiry data to obtain the pre-diagnostic results; when the pre-diagnostic results do not match the corresponding symptoms of the user, receive the medical interrogation request uploaded by the user terminal, and determine the assignment to the user according to the interrogation request. department; obtain the medical knowledge map corresponding to the department, analyze the user's consultation data according to the medical knowledge map, and obtain medical decision information; diagnose the user according to the medical decision information, and generate the final diagnostic result.

The second aspect of the present application provides a video consultation device, including a memory and at least one processor, instructions are stored in the memory, and the memory and the at least one processor are interconnected through lines; the at least one processing The processor invokes the instructions in the memory, and the processor implements the following steps when executing the computer-readable instructions: acquiring user consultation data based on a preset intelligent sensing device, wherein the consultation data includes the Basic information and complaint content of the user; perform pre-diagnosis on the interrogation data to obtain the pre-diagnosis result; when the pre-diagnosis result does not match the user’s corresponding disease, receive the interrogation request uploaded by the user terminal, and The medical inquiry request determines the department assigned to the user; obtains the medical knowledge map corresponding to the department, analyzes the user's medical inquiry data according to the medical knowledge map, and obtains medical decision information; according to the medical The decision information diagnoses the user consultation data to generate a final diagnosis result.

The third aspect of the present application provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program runs on the computer, the computer executes the following steps: Sensing equipment acquires user consultation data, wherein the consultation data includes the user’s basic information and main complaint content; performs pre-diagnosis on the consultation data to obtain a pre-diagnosis result; when the pre-diagnosis result is consistent with the When the corresponding symptoms of the user do not match, receive the consultation request uploaded by the user terminal, and determine the department assigned to the user according to the consultation request; obtain the medical knowledge graph corresponding to the department, and use the medical knowledge graph to The user consultation data is analyzed to obtain medical decision information; the user consultation data is diagnosed according to the medical decision information to generate a final diagnosis result.

The fourth aspect of the present application provides a video medical consultation device, including: a first acquisition module, configured to obtain user consultation data based on a preset smart sensor device, wherein the consultation data includes basic information of the user and the content of the main complaint; an analysis module, used to pre-diagnose the interrogation data, and obtain a pre-diagnosis result; a determination module, used to receive the user-uploaded information when the pre-diagnosis result does not match the corresponding disease of the user A medical inquiry request, and determine the department assigned to the user according to the medical inquiry request; the parsing module is used to obtain the medical knowledge map corresponding to the department, and perform the user inquiry data according to the medical knowledge map Analyzing to obtain medical decision information; a diagnosis module configured to diagnose the user according to the medical decision information and generate a final diagnosis result.

In the technical solution provided by this application, the user’s consultation data is obtained based on the preset intelligent sensing device, and the consultation data is pre-diagnosed to obtain the pre-diagnosis result; when the pre-diagnosis result does not match the corresponding disease of the user, the receiving user Upload the consultation request, and determine the department assigned to the user according to the consultation request; obtain the medical knowledge graph corresponding to the department, analyze the user's consultation data according to the medical knowledge graph, and obtain medical decision information; Make a diagnosis and generate a final diagnosis result. Combining the convenience of online medical treatment with the professionalism of traditional medical institutions and hospitals, it predicts the condition of user groups through the collection of a large number of patient data, and solves the technical problem of low diagnosis accuracy in the existing video consultation methods.

Description of drawings

Fig. 1 is the schematic diagram of the first embodiment of the video consultation method of the present application;

Fig. 2 is the schematic diagram of the second embodiment of the video consultation method of the present application;

FIG. 3 is a schematic diagram of a third embodiment of the video consultation method of the present application;

FIG. 4 is a schematic diagram of a fourth embodiment of the video consultation method of the present application;

FIG. 5 is a schematic diagram of a fifth embodiment of the video consultation method of the present application;

Fig. 6 is a schematic diagram of the first embodiment of the video interrogation device of the present application;

FIG. 7 is a schematic diagram of a second embodiment of the video interrogation device of the present application;

Fig. 8 is a schematic diagram of an embodiment of a video consultation device of the present application.

detailed description

The embodiment of the present application provides a video medical consultation method, device, equipment and storage medium. In the technical solution of the present application, firstly, the user consultation data is obtained based on the preset intelligent sensing device, and the consultation data is pre-diagnosed to obtain Pre-diagnosis results; when the pre-diagnosis results do not match the corresponding symptoms of the user, receive the consultation request uploaded by the user terminal, and determine the department assigned to the user according to the consultation request; obtain the medical knowledge map corresponding to the department, according to the medical knowledge map Analyze the user consultation data to obtain medical decision-making information; diagnose the user according to the medical decision-making information, and generate the final diagnosis result. Combining the convenience of online medical treatment with the professionalism of traditional medical institutions and hospitals, it predicts the condition of user groups through the collection of a large number of patient data, and solves the technical problem of low diagnosis accuracy in the existing video consultation method.

The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and not necessarily Used to describe a specific sequence or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the term "comprising" or "having" and any variations thereof, are intended to cover a non-exclusive inclusion, for example, a process, method, system, product or device comprising a sequence of steps or elements is not necessarily limited to those explicitly listed instead, may include other steps or elements not explicitly listed or inherent to the process, method, product or apparatus.

For ease of understanding, the following describes the specific process of the embodiment of the application, please refer to Figure 1, the first embodiment of the video consultation method in the embodiment of the application includes:

101. Obtain user consultation data based on preset intelligent sensing devices;

In this embodiment, based on the preset intelligent sensing device, the user's medical inquiry data is obtained through the user terminal, wherein the medical inquiry data includes the user's basic information and chief complaint content.

The execution subject of the embodiment of the present application is the server end with the function of remote medical consultation. It should be noted that the user terminal can be a smart terminal such as a PC, mobile phone, tablet computer, smart watch, and smart bracelet used by a patient, and the user enters the consultation data through the user terminal, wherein the consultation data The information may include: the basic information of the patient and the content of the chief complaint. For example, the content of the main complaint may include: time of illness (time of onset, duration or duration of each attack), patient symptoms, patient identity information, patient's basic disease (for example: what kind of chronic disease the patient has suffered in addition to the current symptoms) )Wait.

102. Carry out pre-diagnosis on the interrogation data and obtain pre-diagnosis results;

In this embodiment, a pre-diagnosis is performed on the interrogation data to obtain a pre-diagnosis result. Wherein, the pre-diagnosis result is the analysis result corresponding to the consultation data.

Further, this embodiment also includes: receiving the main complaint content uploaded by the client, and extracting keywords from the main complaint content to obtain symptom keywords; querying the corresponding candidate disease information in the big data according to the symptom keywords ; When the matching degree between the candidate disease information and the main complaint content is greater than or equal to the preset matching degree, the candidate disease information is used as the target disease information; the target disease information is used as the analysis result.

It is easy to understand that the content of the chief complaint is language information for the patient to describe his symptoms, and the description method is more biased towards oral language. In order to make a preliminary diagnosis of the symptom information, it is necessary to extract keywords from the symptom information. For example: The symptom information described by the patient is: since Monday, he feels uncomfortable in the throat, sneezing, and dizzy. Then extract the keywords: "throat", "sneeze", "dizziness", and then analyze the symptom information, get the keyword "Monday" about the time of symptoms, and deduce the duration of the patient's symptoms according to today's time For N days, according to the above keywords and the number of days to query the candidate disease information in the big data.

103. When the pre-diagnosis result does not match the corresponding symptoms of the user, receive the consultation request uploaded by the user terminal, and determine the department assigned to the user according to the consultation request;

In this embodiment, when the pre-diagnosis result does not match the corresponding symptoms of the user, the consultation request uploaded by the user terminal is received, and the department assigned to the user is determined according to the consultation request. First, it is judged whether the pre-diagnosis result obtained by the user's analysis of the consultation data by the system, that is, whether the analysis result is approved or not. Combining with the user's basic health information, use big data analysis technology to calculate the possible cause of the user, and describe the user's possible symptoms in text form, for example, "Do you often feel shortness of breath and chest tightness?" If the user thinks that the described symptoms are satisfied ( Diagnosis results), you can give available medicines, purchase them online, and give rehabilitation advice; if the user does not agree with our symptom description, you can choose to start a video consultation with the doctor; combine the user's symptoms to match the doctor in the appropriate department. When the user does not agree with the analysis result, the consultation request uploaded by the user terminal is received, and the department assigned to the user is determined according to the consultation request.

In this embodiment, when the pre-diagnosis result does not match the corresponding symptoms of the user, the consultation request uploaded by the user terminal is received, and the department assigned to the user is determined according to the consultation request.

In this embodiment, the client is installed with an online consultation application, and when the user uploads a consultation request, some registration information of the user will be uploaded at the same time, including basic information such as user ID, gender, and department. When the user wants to consult a doctor online, he can click the consultation button in the application program to generate a consultation request, and send the consultation request to the server through the application program. The server receives the consultation request uploaded by the user terminal, invokes the first neural network model, and assigns a department to the user through the first neural network model. The server assigns the corresponding doctor to the user according to the department. The server establishes a communication connection between the user terminal and the doctor terminal.

The user terminal establishes a communication connection with the doctor terminal, so as to obtain the consultation request interface of the hospital visited from the user terminal, wherein the consultation request interface includes information of multiple departments of the hospital, and each department information corresponds to a department. Optionally, the user can use the "scan" function of a pre-installed application (APP) such as WeChat, Alipay or WeChat applet to scan and identify the QR code pasted in the hospital's leaflet or other media and communicate with the server. To establish a connection, or use a pre-developed supporting APP to establish a connection with the server, or to establish a connection with the server by visiting the relevant web page of the hospital. In this embodiment, the specific connection mode of the communication connection is not limited.

104. Obtain the medical knowledge map corresponding to the department, analyze the user consultation data according to the medical knowledge map, and obtain medical decision-making information;

In this embodiment, the medical knowledge map corresponding to the department is obtained, and the user inquiry data is analyzed according to the medical knowledge map to obtain medical decision information. Among them, the knowledge graph refers to a structured knowledge graph composed of entities and entity relationships. The medical knowledge graph is a knowledge graph in the medical field. Its entity dimensions include diseases, symptoms, symptom locations, inspection signs, and drugs. relationship", "does not include relationship" or "gold standard relationship" (such as all inflammations will bring fever is the gold standard), diseases and doctors can define "doctors are good at treating diseases", doctors and hospitals can define "belonging relationship", etc. . The medical knowledge maps corresponding to different departments are different. For example, the physical dimensions of the knowledge map of a medical room whose department is orthopedics include fractures, knees, and soreness.

It is understandable that the medical information data contained in the medical knowledge map is very large. Therefore, according to the department, the medical knowledge map corresponding to the department is obtained as the target medical knowledge map, which reduces the interference of the medical knowledge map corresponding to other departments and improves the follow-up. The speed of intelligent initial diagnosis.

In this embodiment, the medical decision-making information is the information of the entity dimension related to medical treatment in the knowledge structure graph constituting the medical knowledge map. Medical decision-making information is used as the basis for imaging screening decisions, that is, as the basis for preliminary diagnosis of diseases. The medical decision-making information may be, but not limited to, diseases, symptoms, symptom sites, inspection signs, or medicines.

Specifically, after obtaining the target medical knowledge graph, the keywords in the patient description information are extracted, and by mining the association between the keywords and the target medical knowledge graph, the association information between the keywords and the target medical knowledge graph is obtained, and through Analyze related information to determine medical decision-making information. Because the acquisition of medical decision-making information is obtained through association mining and analysis of patient description information on the target medical knowledge map, the accuracy of medical decision-making information is guaranteed and the accuracy of subsequent intelligent first-diagnosis is improved.

105. Diagnose the user according to the medical decision-making information, and generate a final diagnosis result.

In this embodiment, the user is diagnosed according to the medical decision information, and a final diagnosis result is generated. Wherein, the final diagnosis result is used to instruct the patient to perform the diagnosis result corresponding to the medical decision information.

In this embodiment, optionally, the diagnosis result may be a piece of text, or a schematic diagram, etc. For example, when the medical decision-making information is "uterine part", the diagnosis result is an imaging examination of the uterine part.

In this embodiment, based on the generated results of medical decision-making information, the intelligent preliminary diagnosis of patients is realized, the time of manual consultation is saved, and the efficiency of intelligent diagnosis is improved.

In this embodiment, firstly, a medical inquiry request sent by the terminal is acquired, and the medical inquiry request includes chief complaint information of departments and users. Then, the medical knowledge map corresponding to the department is obtained as the target medical knowledge map, which improves the speed of subsequent intelligent diagnosis.

In the embodiment of the present application, the pre-diagnosed data is obtained by obtaining the user’s medical inquiry data based on the preset intelligent sensing device, and the pre-diagnosed result is obtained; Inquiry request, and determine the department assigned to the user according to the inquiry request; obtain the medical knowledge map corresponding to the department, analyze the user's consultation data according to the medical knowledge map, and obtain medical decision information; diagnose the user according to the medical decision information , to generate the final diagnosis result. Combining the convenience of online medical treatment with the professionalism of traditional medical institutions and hospitals, it predicts the condition of user groups through the collection of a large number of patient data, and solves the technical problem of low diagnosis accuracy in the existing video consultation methods.

Please refer to Fig. 2, the second embodiment of the video consultation method in the embodiment of the present application includes:

201. Obtain user consultation data based on preset smart sensing devices;

202. Extract keywords from the medical inquiry data to obtain symptom keywords;

In this embodiment, keywords are extracted from the medical inquiry data to obtain symptom keywords. Wherein, the chief complaint information in the medical inquiry data is the language information for the patient to describe his symptoms, and the description method is more biased towards oral language. In order to perform a preliminary diagnosis on the symptom information, it is necessary to extract keywords from the symptom information . For example: The symptom information described by the patient is: since Monday, he feels uncomfortable in the throat, sneezing, and dizzy. The keywords extracted therein are: "throat", "sneezing", "dizziness".

203. Query the corresponding candidate disease information in the big data according to the symptom keywords;

In this embodiment, the corresponding candidate disease information is queried in the big data according to the symptom keywords. Among them, the symptom information is analyzed to obtain keywords about the time of symptoms, such as: feeling uncomfortable in the throat, sneezing, and dizzy since Monday. The keywords extracted therein are: "throat", "sneezing", "dizziness". Among them, according to the keyword "Monday", the duration of the patient's symptoms is deduced according to today's time as N, and the candidate disease information is queried in the big data according to the above keywords and the number of days.

It should be understood that if the symptom information given by the patient is not detailed enough, resulting in too much disease information to be selected, the disease information to be selected is sent to the user end, so that the user end can select the target disease by itself; or the disease information to be selected is sent to the user end. Symptom questioning enables the client to supplement symptom information to narrow down the range of diseases to be selected.

204. When the matching degree between the candidate disease information and the content of the main complaint is greater than the preset matching degree, use the candidate disease information as the target disease information;

In this embodiment, when the matching degree between the candidate disease information and the main complaint is greater than or equal to a preset matching degree, the candidate disease information is used as the target disease information. For example, when the matching degree is 80% to 100%, the user's main complaint information may include picture information, sound information and text information. For example, if the patient has skin allergies, the patient takes a photo of his skin and uploads the photo with a text message: if the skin develops a rash and itches, then query it in the big data according to the keywords in the picture information and text information. To initially confirm the patient's target disease information.

205. Taking target disease information as a pre-diagnosis result;

In this embodiment, the target disease information is used as the analysis result. Wherein, receiving the patient symptom information uploaded by the user terminal, performing keyword extraction on the patient symptom information to obtain the symptom keyword; querying the corresponding candidate disease information in the big data according to the symptom keyword; When the matching degree between the selected disease information and the patient symptom information is greater than or equal to the preset matching degree, the candidate disease information is taken as the target disease information; the target disease information is taken as the analysis result.

206. When the pre-diagnosis result does not match the user's corresponding illness, receive a medical inquiry request uploaded by the user terminal, and determine the department assigned to the user according to the medical inquiry request;

207. Obtain the medical knowledge map corresponding to the department, analyze the user consultation data according to the medical knowledge map, and obtain medical decision information;

208. Diagnose the user according to the medical decision information, and generate a final diagnosis result.

Steps 206-208 in this embodiment are similar to steps 103-105 in the first embodiment, and will not be repeated here.

In the embodiment of the present application, the pre-diagnosed data is obtained by obtaining the user’s medical inquiry data based on the preset intelligent sensing device, and the pre-diagnosed result is obtained; Inquiry request, and determine the department assigned to the user according to the inquiry request; obtain the medical knowledge map corresponding to the department, analyze the user's consultation data according to the medical knowledge map, and obtain medical decision information; diagnose the user according to the medical decision information , to generate the final diagnosis result. Combining the convenience of online medical treatment with the professionalism of traditional medical institutions and hospitals, it predicts the condition of user groups through the collection of a large number of patient data, and solves the technical problem of low diagnosis accuracy in the existing video consultation method.

Please refer to Figure 3, the third embodiment of the video consultation method in the embodiment of the present application includes:

301. Obtain user consultation data based on the preset intelligent sensing device;

302. Perform pre-diagnosis on the consultation data to obtain a pre-diagnosis result;

303. When the pre-diagnosis result matches the corresponding disease of the user, input the disease information into the preset disease matching model, and process the disease information through the disease matching model to obtain the disease information processing result;

In this embodiment, when the pre-diagnosis result matches the user's corresponding disease, the disease information is input into the preset disease matching model, and the disease information is matched through the disease matching model to obtain the disease information processing result. Among them, the disease matching model includes the mapping relationship between various disease characteristics and disease names. The mapping relationship can be, but not limited to, disease feature words extracted from information such as disease names, disease numbers, patient objects, and corresponding medications of various diseases. Composition, the corresponding disease can be uniquely determined through the mapping relationship. The feature matching between disease information and disease characteristics can be realized through the disease matching model, which can perform disease matching processing on the input disease information and output the disease information processing results. Specifically, the disease matching model may be a naive Bayesian probability model obtained based on the Bayesian algorithm, which can count the probability of each disease according to the input feature phrase. In addition, the disease matching model can also be based on a disease matching neural network obtained by an artificial neural network algorithm. By inputting the disease information into the disease matching model, the disease matching model performs matching processing on the disease information to obtain the disease information processing result.

304. Push the obtained disease information processing result to the default client;

In this embodiment, the result of disease information processing can be used as reference information for the doctor's diagnosis, or as the result of the patient's own diagnosis. Specifically, after obtaining the result of disease information processing, it is pushed to the doctor terminal for reference when the doctor diagnoses the patient; at the same time, the result of disease information processing can also be pushed to the patient terminal, so that the patient can have a preliminary understanding of their own disease, and follow-up Optionally go to the hospital for treatment.

In the above medical information push method, when receiving a service request message of the type of registered medical consultation service request, a dialogue consultation is performed through the corresponding consultation dialogue template, the disease information is obtained from the question and answer data in the dialogue consultation process, and finally the disease information The information is input into the disease matching model for processing, and the disease information processing result is obtained and the disease information processing result is pushed. Conduct dialogue and consultation directly through the consultation dialogue template, and then input the obtained disease information into the corresponding disease matching model for processing, and obtain the disease information processing results and push them.

305. Extracting pathological keywords in the disease information processing result;

In this embodiment, pathological keywords in the disease information processing result are extracted. After obtaining the patient's disease information, pathological keywords are extracted from it, such as disease site, disease name, ICD-10 disease code and symptom manifestation. For the sake of medical rigor, considering the medication of patients, in addition to the disease information, the patient's personal physical characteristics also need to be considered. For example, for patients whose allergens include penicillin, if the prescription is issued only based on the pathological keywords of the disease information, use Penicillin medicines may not work or cause serious side effects. Based on this, after pathology keywords are obtained, prescription keyword groups are further generated in combination with archive keywords. The prescription keyword group is obtained by combining pathology keywords and archive keywords according to preset combination conditions. For example, after prioritization can be performed according to preset prioritization conditions, the priority can reflect the degree of importance, and then combined according to the priority level, the prescription keyword group can be obtained.

306. Determine the corresponding prescription keywords according to the pathological keywords, and input the prescription keyword group into the corresponding drug matching model for feature matching;

In this embodiment, the corresponding prescription keywords are determined according to the pathological keywords, and the prescription keyword group is input into the corresponding drug matching model for feature matching. After obtaining the prescription keyword group, input it into the corresponding drug matching model for feature matching.

Among them, the drug matching model includes the mapping relationship of various drug features, which can be, but not limited to, drug features extracted from information such as drug names, drug numbers, use objects, usage, functions, dosages, and contraindications of various drugs. Word composition, the corresponding drug can be uniquely determined through the mapping relationship. The feature matching between the prescription keyword group and the drug feature can be realized through the drug matching model, which can perform drug matching according to the input prescription keyword group and output the matched drug. Specifically, the drug matching model can be a naive Bayesian probability model obtained based on the Bayesian algorithm, which can calculate the probability of each drug according to the input prescription keyword group, and output the drug with the highest probability.

307. Generate a prescription recommendation according to the drug list in the matching result, and push the prescription to the preset client;

In this embodiment, a prescription recommendation is generated according to the drug list in the matching result, and the prescription is pushed to a preset user terminal. In actual implementation, the drug matching models corresponding to the functional departments of each hospital may be different. At this time, you can first query the drug matching models corresponding to the functional departments of the hospital, and then input the prescription keyword group for feature matching to obtain the corresponding output results.

After obtaining the matching result of the drug matching model, a prescription recommendation is generated according to the drug list in the matching result, and the prescription recommendation is pushed. Among them, a prescription is a list of medicines issued by a doctor for a patient, a written document for a doctor to administer medicines to a patient, and a basis for pharmacists to dispense medicines. The prescription recommendation obtained in this embodiment can be used as a reference when a doctor writes a prescription. In particular, if the list of medicines in the prescription recommendation is appropriate, it can be directly used as a prescription.

308. When the pre-diagnosis result does not match the user's corresponding illness, receive a medical inquiry request uploaded by the user terminal, and determine the department assigned to the user according to the medical inquiry request;

309. Obtain the medical knowledge map corresponding to the department, analyze the user consultation data according to the medical knowledge map, and obtain medical decision information;

310. Diagnose the user according to the medical decision information, and generate a final diagnosis result.

Steps 301-303, 309-311 in this embodiment are similar to steps 101-103, 104-106 in the first embodiment, and will not be repeated here.

Please refer to Figure 4, the fourth embodiment of the video consultation method in the embodiment of the present application includes:

401. Obtain user consultation data based on the preset intelligent sensing device;

402. Perform pre-diagnosis on the consultation data to obtain a pre-diagnosis result;

403. When the pre-diagnosis result does not match the user's corresponding illness, receive a medical inquiry request uploaded by the user terminal, and determine the department assigned to the user according to the medical inquiry request;

404. Obtain the medical knowledge map corresponding to the department, analyze the user inquiry data according to the medical knowledge map, and obtain medical decision information;

405. Obtain the medical consultation data set corresponding to the previous medical consultation records, and preprocess the medical consultation data set;

In this embodiment, the medical inquiry data sets corresponding to previous medical inquiry records are obtained, and the medical inquiry data sets are preprocessed. Previous medical consultation records refer to all medical consultations that have been completed before the current time, and medical consultation information collection refers to the information collection composed of the consultation information of the consultation user and the reply information of the doctor user in a complete consultation. medical information.

406. Extract a second question-answer pair from the preprocessed medical inquiry data set, and perform feature extraction on the extracted second question-answer pair;

In this embodiment, in a complete consultation of the consultation user, the question is usually asked multiple times, and the doctor will reply each time the consultation user asks the question, and the question when the consultation user asks each time corresponds to the question. Physicians' replies form a question-answer pair. Extracting the question-answer pair means extracting the question-answer pair from the medical questioning information corresponding to a complete medical questioning.

Further, the server performs feature extraction on the extracted question-answer pairs. In one embodiment, the feature extraction may be to extract keywords from the questions in the question-answer pair. In another embodiment, the extracted features may be, for example, the number of single sentences, the number of adjectives, interrogative words, etc. in the question-answer pair.

407. Store the second question-answer pair and the features corresponding to the second question-answer pair in the consultation database;

In this embodiment, the second question-answer pair and the features corresponding to the second question-answer pair are correspondingly stored in a medical inquiry database. The server correspondingly stores the question-answer pairs and the features corresponding to the question-answer pairs in the consultation database, that is, stores the question-answer pairs and the features corresponding to the question-answer pairs as different columns in the same row of a table in the database.

In one embodiment, when the consultation user communicates with the doctor through instant messages, the message carries the respective user identifications of both communication parties, including the consultation user identification and the doctor user identification. Specifically, the consultation terminal The information sent carries the user ID of the consultation, and the information sent by the doctor terminal carries the user ID of the doctor. Therefore, when the server obtains the medical inquiry information corresponding to the previous consultation, it can simultaneously obtain the user identification corresponding to the medical consultation information, and then The user identification corresponding to the question-answer pair is stored in a one-to-one correspondence with the question-answer pair and the features corresponding to the question-answer pair in the medical inquiry database.

408. Indexing the consultation database according to the characteristics;

In this embodiment, the query database is indexed according to the features. The server builds an index according to the column data where the features in the query database are located, and each node in the index corresponds to a row of data in the query database, at least including question-answer pairs and features corresponding to question-answer pairs. In one embodiment, the server can also create an index according to user identification and characteristics

409. Diagnose the user according to the medical decision information, and generate a final diagnosis result.

Steps 401-404, 409 in this embodiment are similar to steps 101-104, 105 in the first embodiment, and will not be repeated here.

Please refer to Figure 5, the fifth embodiment of the video consultation method in the embodiment of the present application includes:

501. Obtain user consultation data based on the preset intelligent sensing device;

502. Perform pre-diagnosis on the consultation data to obtain a pre-diagnosis result;

503. When the pre-diagnosis result does not match the user's corresponding illness, receive a medical inquiry request uploaded by the user terminal, and determine the department assigned to the user according to the medical inquiry request;

504. Obtain the medical knowledge map corresponding to the department, analyze the user consultation data according to the medical knowledge map, and obtain medical decision information;

505. Receive real-time medical inquiry data, perform preprocessing on the medical inquiry data, and obtain the first question-answer pair in the medical inquiry data;

In this embodiment, real-time medical inquiry data is received, and the medical inquiry data is preprocessed to obtain the first question-answer pair in the medical inquiry data. Among them, the real-time consultation refers to each consultation completed before the current time, and the collection of consultation information refers to the information collection composed of the consultation information of the consultation user and the reply information of the doctor user in a complete consultation. Inquiry information.

In this embodiment, the preprocessing includes sentence clause, anaphora resolution, context processing and so on. Among them, sentence segmentation refers to dividing a piece of information into individual sentences; anaphora resolution refers to calculating the reference content of pronouns in a sentence, which can be calculated through syntactic analysis and edit distance; context processing refers to completing the context . For example: D: Are you dizzy? U: Yes, expand "yes" to "I'm dizzy". Make the meaning expressed in the second sentence more comprehensive; use syntactic analysis and sentence pattern judgment for context processing.

In a complete consultation, the user usually asks questions multiple times, and the doctor will answer each time the user asks a question. The question and the doctor's answer corresponding to the question are formed A question and answer is right. Extracting the question-answer pair means extracting the question-answer pair from the medical questioning information corresponding to a complete medical questioning.

506. Perform feature extraction on the first question-answer pair to obtain a second feature corresponding to the first question-answer pair;

In this embodiment, feature extraction is performed on the first question-answer pair to obtain a second feature corresponding to the first question-answer pair. Wherein, the feature extraction in this embodiment refers to character feature extraction. Many machine learning problems involve natural language processing (NLP), which necessarily deals with textual information. The literals must be converted into quantifiable feature vectors. Let's introduce the most commonly used text representation method: the Bag-of-words model.

Thesaurus model is the most common method of text modeling. For a document (document), ignore its word order and grammar, syntax, it is only regarded as a set of words, or a combination of words, the appearance of each word in the document is independent and does not depend on other words Whether it appears, or when the author of this article chooses a word at any position is not affected by the previous sentence and is independently selected. Thesaurus model can be seen as an extension of one-hot encoding, which sets a feature value for each word. The basis of the thesaurus model is that articles with similar words have similar meanings. Thesaurus models can achieve efficient document classification and retrieval with limited encoding information.

The server performs feature extraction on the extracted question-answer pairs. In one embodiment, the feature extraction may be to extract keywords from the questions in the question-answer pair. In another embodiment, the extracted features may be, for example, the number of single sentences, the number of adjectives, interrogative words, etc. in the question-answer pair.

507. Selecting historical medical inquiry records matching the first question-answer pair and the second characteristic from the preset medical inquiry database;

In this embodiment, historical medical questioning records matching the first question-answer pair and the second characteristic are screened out from a preset medical questioning database.

In this embodiment, the server correspondingly stores the question-answer pairs and the features corresponding to the question-answer pairs obtained from the historical question-and-answer records into the question-and-answer database, that is, stores the question-answer pairs and the features corresponding to the question-answer pairs as different values in the same row of the table in the database. column. When a new patient comes to see a doctor, the features and question-answer pairs extracted from the new patient's medical inquiry data (chief complaint information) can be matched with the question-answer pairs and features corresponding to the question-answer pairs in the preset question-and-answer database to match patients with similar symptoms. user. Obtain the highest-scoring consultation records from the historical consultation records, and give possible etiology and treatment reference opinions.

508. Obtain the diagnosis results and treatment opinions corresponding to the historical consultation records, and push the diagnosis results and treatment opinions to the user end corresponding to the real-time consultation request;

In this embodiment, the diagnosis results and treatment opinions corresponding to the historical consultation records are obtained, and the diagnosis results and treatment opinions are pushed to the user terminal of the user corresponding to the real-time consultation request. For example, when a new patient comes to see a doctor, the features and question-answer pairs extracted from the new patient's medical inquiry data (main complaint information) can be matched with the question-answer pairs and the features corresponding to the question-answer pairs in the preset medical inquiry database. The matching is similar to symptomatic users. Obtain the highest-scoring consultation records from the historical consultation records, and give possible etiology and treatment reference opinions. Reduce the time for users to see a doctor, improve the patient's experience in seeing a doctor, and improve the accuracy of diagnosis. At the same time, based on the large amount of patient data collected, it can analyze the possible diseases of various groups of people through big data analysis, and give prevention advice in advance.

509. Diagnose the user according to the medical decision information, and generate a final diagnosis result.

Steps 501-504, 509 in this embodiment are similar to steps 101-104, 105 in the first embodiment, and will not be repeated here.

In this embodiment of the application, the pre-diagnosed data is obtained by obtaining the user’s medical inquiry data based on the preset intelligent sensor device, and the pre-diagnosed result is obtained; According to the consultation request, determine the department assigned to the user according to the consultation request; obtain the medical knowledge map corresponding to the department, analyze the user's consultation data according to the medical knowledge map, and obtain medical decision information; Diagnose to generate the final diagnosis result. Combining the convenience of online medical treatment with the professionalism of traditional medical institutions and hospitals, it predicts the condition of user groups through the collection of a large number of patient data, and solves the technical problem of low diagnosis accuracy in the existing video consultation method.

The video consultation method in the embodiment of the application is described above, and the video consultation device in the embodiment of the application is described below. Please refer to FIG. 6. The first embodiment of the video consultation device in the embodiment of the application includes:

The first acquisition module 601 is configured to acquire user consultation data based on a preset smart sensor device, wherein the consultation data includes the user's basic information and chief complaint content;

An analysis module 602, configured to pre-diagnose the interrogation data and obtain a pre-diagnosis result;

A determining module 603, configured to receive a medical inquiry request uploaded by the user terminal when the pre-diagnosis result does not match the corresponding symptom of the user, and determine the department assigned to the user according to the medical inquiry request;

An analysis module 604, configured to obtain a medical knowledge map corresponding to the department, analyze the user's consultation data according to the medical knowledge map, and obtain medical decision information;

Diagnosis module 605, configured to diagnose the user according to the medical decision information, and generate a final diagnosis result.

Please refer to Fig. 7, the second embodiment of the video consultation device in the embodiment of the present application, the video consultation device specifically includes:

An acquisition module 601, configured to acquire user medical inquiry data based on a preset smart sensor device, wherein the medical inquiry data includes the user's basic information and chief complaint content;

In this embodiment, the analysis module 602 includes:

An extracting unit 6021, configured to extract keywords from the medical inquiry data to obtain symptom keywords;

A query unit 6022, configured to query corresponding candidate disease information in the big data according to the symptom keywords;

A marking unit 6023, configured to mark the candidate disease information as target disease information when the matching degree between the candidate disease information and the main complaint content is greater than a preset matching degree; use the target disease information as Pre-diagnosis results.

In this embodiment, the video interrogation device also includes:

Disease matching module 606, configured to input the disease information into a preset disease matching model when the pre-diagnosis result matches the corresponding disease of the user, and perform matching processing on the disease information through the disease matching model , get the disease information processing result;

The first push module 607 is configured to push the obtained disease information processing result to a preset client.

In this embodiment, the video interrogation device also includes:

The first extraction module 608 is used to extract pathological keywords in the disease information processing result;

A feature matching module 609, configured to determine corresponding prescription keywords according to the pathological keywords, and input the prescription keyword group into the corresponding drug matching model for feature matching;

The second push module 610 is configured to push a prescription recommendation generated according to the drug list in the matching result, and push the prescription to a preset user terminal.

In this embodiment, the video interrogation device also includes:

A preprocessing module 611, configured to receive real-time medical inquiry data, perform preprocessing on the medical inquiry data, and obtain the first question-answer pair in the medical inquiry data;

The second extraction module 612 is configured to perform feature extraction on the first question-answer pair to obtain a second feature corresponding to the first question-answer pair;

A screening module 613, configured to filter out historical medical inquiry records matching the first question-answer pair and the second feature from a preset medical inquiry database;

The third push module 614 is configured to obtain the diagnosis result and treatment opinion corresponding to the historical medical inquiry record, and push the diagnosis result and treatment opinion to the client end of the user corresponding to the real-time medical inquiry request.

In this embodiment, the video interrogation device also includes:

The second acquisition module 615 is configured to acquire the medical inquiry data sets corresponding to previous medical inquiry records, and preprocess the medical inquiry data sets;

The third extraction module 616 is configured to extract a second question-answer pair from the preprocessed medical inquiry data set, and perform feature extraction on the extracted second question-answer pair;

The storage module 617 is configured to store the second question-answer pair and the features corresponding to the second question-answer pair in a medical inquiry database; and index the medical inquiry database according to the features.

The above Figures 6 and 7 describe in detail the video consultation device in the embodiment of the present application from the perspective of modular functional entities, and the following describes the video consultation device in the embodiment of the present application in detail from the perspective of hardware processing.

FIG. 8 is a schematic structural diagram of a video consultation device provided by an embodiment of the present application. The video consultation device 800 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units) , CPU) 810 (eg, one or more processors) and memory 820, and one or more storage media 830 (eg, one or more mass storage devices) for storing application programs 833 or data 832 . Wherein, the memory 820 and the storage medium 830 may be temporary storage or persistent storage. The program stored in the storage medium 830 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the video consultation device 800 . Furthermore, the processor 810 can be configured to communicate with the storage medium 830, and execute a series of instruction operations in the storage medium 830 on the video consultation device 800, so as to implement the steps of the video consultation method provided by the above method embodiments.

The video consultation device 800 can also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input and output interfaces 860, and/or, one or more operating systems 831, such as Windows Server , Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art can understand that the structure of the video consultation equipment shown in Figure 8 does not constitute a limitation to the video consultation equipment provided in this application, and may include more or less components than those shown in the illustration, or combine certain components, or different component arrangements.

The present application also provides a computer-readable storage medium. The computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium may also be a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium, and when the instructions are run on the computer, the computer is made to execute the steps of the above-mentioned video consultation method.

The blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain (Blockchain), essentially a decentralized database, is a series of data blocks associated with each other using cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify its Validity of information (anti-counterfeiting) and generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

Those skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still understand the foregoing The technical solutions recorded in each embodiment are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the application.

Claims

A video consultation method, wherein the video consultation method comprises:

Acquiring user medical inquiry data based on preset intelligent sensing devices, wherein the medical inquiry data includes the user's basic information and chief complaint content;

Performing a pre-diagnosis on the interrogation data to obtain a pre-diagnosis result;

When the pre-diagnosis result does not match the user's corresponding illness, receive a medical inquiry request uploaded by the user terminal, and determine the department assigned to the user according to the medical inquiry request;

Obtain a medical knowledge map corresponding to the department, analyze the user's consultation data according to the medical knowledge map, and obtain medical decision information;

Diagnose the user consultation data according to the medical decision information to generate a final diagnosis result.
The video consultation method according to claim 1, wherein said performing pre-diagnosis on said consultation data, and obtaining a pre-diagnosis result comprises:

Carrying out keyword extraction from the medical inquiry data to obtain symptom keywords;

Query corresponding candidate disease information in the big data according to the symptom keywords;

When the degree of matching between the disease information to be selected and the content of the chief complaint is greater than a preset matching degree, marking the disease information to be selected as target disease information;

The target disease information is used as the pre-diagnosis result.
The video consultation method according to claim 1, wherein, after performing pre-diagnosis on said consultation data and obtaining a pre-diagnosis result, further comprising:

When the pre-diagnosis result matches the user's corresponding disease, input the disease information into a preset disease matching model, and perform matching processing on the disease information through the disease matching model to obtain a disease information processing result;

Push the obtained disease information processing result to the preset client.
The video consultation method according to claim 3, wherein, after the obtained disease information processing result is pushed to a preset client terminal, further comprising:

Extracting pathological keywords in the disease information processing result;

Determine the corresponding prescription keywords according to the pathological keywords, and input the prescription keyword group into the corresponding drug matching model for feature matching;

A prescription recommendation is generated according to the drug list in the matching result, and the prescription is pushed to a preset user terminal.
The video consultation method according to claim 1, wherein, after acquiring the medical knowledge map corresponding to the department, analyzing the user consultation data according to the medical knowledge map, and obtaining medical decision information, Also includes:

receiving real-time medical inquiry data, performing preprocessing on the medical inquiry data, and obtaining the first question-answer pair in the medical inquiry data;

performing feature extraction on the first question-answer pair to obtain second features corresponding to the first question-answer pair;

Selecting historical medical inquiry records matching the first question-answer pair and the second feature from a preset medical inquiry database;

Acquiring the diagnosis results and treatment opinions corresponding to the historical medical inquiry records, and pushing the diagnosis results and treatment opinions to the user terminal of the user corresponding to the real-time medical inquiry request.
The video consultation method according to claim 5, wherein, before receiving the real-time consultation data, preprocessing the consultation data, and obtaining the first question-answer pair in the consultation data, further comprising:

Obtaining a medical inquiry data set corresponding to previous medical inquiry records, and preprocessing the medical inquiry data set;

Extracting a second question-answer pair from the preprocessed interrogation data set, and performing feature extraction on the extracted second question-answer pair;

storing the second question-answer pair and the features corresponding to the second question-answer pair in an inquiry database;

An index is established for the medical inquiry database according to the characteristics.
A video consultation device, wherein the video consultation device includes: a memory and at least one processor, instructions are stored in the memory, and the memory and the at least one processor are interconnected through a line;

The at least one processor invokes the instructions in the memory, so that the video consultation device performs the following steps of the video consultation method:

Acquiring user medical inquiry data based on preset intelligent sensing devices, wherein the medical inquiry data includes the user's basic information and chief complaint content;

Performing a pre-diagnosis on the interrogation data to obtain a pre-diagnosis result;

When the pre-diagnosis result does not match the user's corresponding illness, receive a medical inquiry request uploaded by the user terminal, and determine the department assigned to the user according to the medical inquiry request;

Obtain a medical knowledge map corresponding to the department, analyze the user's consultation data according to the medical knowledge map, and obtain medical decision information;

Diagnose the user consultation data according to the medical decision information to generate a final diagnosis result.
The video medical consultation device according to claim 7, wherein, when the video medical consultation program is executed by the processor to implement the step of pre-diagnosing the medical consultation data and obtaining a pre-diagnosis result, the following steps are also performed: step:

Carrying out keyword extraction from the medical inquiry data to obtain symptom keywords;

Query corresponding candidate disease information in the big data according to the symptom keyword;

When the degree of matching between the disease information to be selected and the content of the chief complaint is greater than a preset matching degree, marking the disease information to be selected as target disease information;

The target disease information is used as the pre-diagnosis result.
The video medical consultation device according to claim 7, wherein the video medical consultation program is executed by the processor so that after the step of pre-diagnosing the medical consultation data and obtaining the pre-diagnosis result, further executing The following steps:

When the pre-diagnosis result matches the user's corresponding disease, input the disease information into a preset disease matching model, and perform matching processing on the disease information through the disease matching model to obtain a disease information processing result;

Push the obtained disease information processing result to the preset client.
The video consultation device according to claim 9, wherein, the video consultation program is executed by the processor so that after the step of pushing the obtained disease information processing result to the preset user terminal, further execution The following steps:

Extracting pathological keywords in the disease information processing result;

Determine the corresponding prescription keywords according to the pathological keywords, and input the prescription keyword group into the corresponding drug matching model for feature matching;

A prescription recommendation is generated according to the drug list in the matching result, and the prescription is pushed to a preset user terminal.
The video consultation device according to claim 7, wherein the video consultation program is executed by the processor to realize the acquisition of the medical knowledge map corresponding to the department, and the After analyzing the user consultation data and obtaining medical decision-making information, the following steps are also performed:

receiving real-time medical inquiry data, performing preprocessing on the medical inquiry data, and obtaining the first question-answer pair in the medical inquiry data;

performing feature extraction on the first question-answer pair to obtain second features corresponding to the first question-answer pair;

Selecting historical medical inquiry records matching the first question-answer pair and the second feature from a preset medical inquiry database;

Acquiring the diagnosis results and treatment opinions corresponding to the historical medical inquiry records, and pushing the diagnosis results and treatment opinions to the user terminal of the user corresponding to the real-time medical inquiry request.
The video medical consultation device according to claim 11, wherein, the video medical consultation program is executed by the processor to realize receiving real-time medical consultation data, preprocessing the medical consultation data, and obtaining the consultation Before the step of the first question-answer pair in the diagnostic data, the following steps are also performed:

Obtaining a medical inquiry data set corresponding to previous medical inquiry records, and preprocessing the medical inquiry data set;

Extracting a second question-answer pair from the preprocessed interrogation data set, and performing feature extraction on the extracted second question-answer pair;

storing the second question-answer pair and the features corresponding to the second question-answer pair in an inquiry database;

An index is established for the medical inquiry database according to the characteristics. .
A computer-readable storage medium, the computer-readable storage medium is stored with a computer program, wherein, when the computer program is executed by a processor, the steps of the following video consultation method are realized:

Acquiring user medical inquiry data based on preset intelligent sensing devices, wherein the medical inquiry data includes the user's basic information and chief complaint content;

Performing a pre-diagnosis on the interrogation data to obtain a pre-diagnosis result;

When the pre-diagnosis result does not match the user's corresponding illness, receive a medical inquiry request uploaded by the user terminal, and determine the department assigned to the user according to the medical inquiry request;

Obtain a medical knowledge map corresponding to the department, analyze the user's consultation data according to the medical knowledge map, and obtain medical decision information;

Diagnose the user consultation data according to the medical decision information to generate a final diagnosis result.
The computer-readable storage medium according to claim 13, wherein, when the computer program is executed by the processor to pre-diagnose the interrogation data and obtain a pre-diagnosis result, the following steps are also performed:

Carrying out keyword extraction from the medical inquiry data to obtain symptom keywords;

Query corresponding candidate disease information in the big data according to the symptom keyword;

When the degree of matching between the disease information to be selected and the content of the chief complaint is greater than a preset matching degree, marking the disease information to be selected as target disease information;

The target disease information is used as the pre-diagnosis result.
The computer-readable storage medium according to claim 13, wherein, after the computer program is executed by the processor, after the step of pre-diagnosing the medical inquiry data and obtaining a pre-diagnosis result, the following steps are further performed:

When the pre-diagnosis result matches the user's corresponding disease, input the disease information into a preset disease matching model, and perform matching processing on the disease information through the disease matching model to obtain a disease information processing result;

Push the obtained disease information processing result to the preset client.
The computer-readable storage medium according to claim 15, wherein, after the computer program is executed by the processor, after the step of pushing the obtained disease information processing result to a preset client terminal, the following steps are further performed:

Extracting pathological keywords in the disease information processing result;

Determine the corresponding prescription keywords according to the pathological keywords, and input the prescription keyword group into the corresponding drug matching model for feature matching;

A prescription recommendation is generated according to the drug list in the matching result, and the prescription is pushed to a preset user terminal.
The computer-readable storage medium according to claim 13, wherein the computer program is executed by the processor in the acquisition of the medical knowledge map corresponding to the department, and the user inquiry data is analyzed according to the medical knowledge map After analyzing and obtaining medical decision-making information, the following steps are also performed:

receiving real-time medical inquiry data, performing preprocessing on the medical inquiry data, and obtaining the first question-answer pair in the medical inquiry data;

performing feature extraction on the first question-answer pair to obtain second features corresponding to the first question-answer pair;

Selecting historical medical inquiry records matching the first question-answer pair and the second feature from a preset medical inquiry database;

Acquiring the diagnosis results and treatment opinions corresponding to the historical medical inquiry records, and pushing the diagnosis results and treatment opinions to the user terminal of the user corresponding to the real-time medical inquiry request.
The computer-readable storage medium according to claim 17, wherein the computer program is executed by the processor in receiving real-time medical inquiry data, preprocessing the medical inquiry data, and obtaining the Before the step of the first question and answer, the following steps are also performed:

Obtaining a medical inquiry data set corresponding to previous medical inquiry records, and preprocessing the medical inquiry data set;

Extracting a second question-answer pair from the preprocessed interrogation data set, and performing feature extraction on the extracted second question-answer pair;

storing the second question-answer pair and the features corresponding to the second question-answer pair in an inquiry database;

An index is established for the medical inquiry database according to the characteristics.
A video interrogation device, wherein the video interrogation device includes:

The first acquisition module is configured to acquire user medical inquiry data based on a preset intelligent sensor device, wherein the medical inquiry data includes the user's basic information and chief complaint content;

An analysis module, configured to pre-diagnose the interrogation data, and obtain a pre-diagnosis result; a determination module, configured to receive an interrogation request uploaded by the user terminal when the pre-diagnosis result does not match the user's corresponding illness, and determine the department assigned to the user according to the consultation request;

An analysis module, configured to obtain a medical knowledge map corresponding to the department, and analyze the user inquiry data according to the medical knowledge map to obtain medical decision information;

A diagnosis module, configured to diagnose the user according to the medical decision information, and generate a final diagnosis result.
The video consultation device according to claim 19, wherein the video consultation device further comprises:

a disease matching module, configured to input the disease information into a preset disease matching model when the pre-diagnosis result matches the corresponding disease of the user, and perform matching processing on the disease information through the disease matching model, Obtain the result of disease information processing;

The first push module is configured to push the obtained disease information processing result to a preset client.