AI-based multi-person synchronous inquiry method and system, medium and equipment

Abstract

The invention discloses an AI-based multi-person synchronous inquiry method and system, a medium and equipment. The AI-based multi-person synchronous inquiry method comprises the following steps: S1, acquiring symptom descriptions of a plurality of patients; s2, comparing the symptoms with standard medical terms; s3, corresponding patient symptom feature vectors; s4, dividing inquiry groups: analyzing the symptom feature vectors through a clustering algorithm, and dynamically dividing the patients with the similarity higher than a preset threshold value into the same inquiry group; and S5, video interrogation: when the number of the patients in the interrogation group reaches a preset upper limit or meets a doctor reception condition, triggering a video interrogation channel, so that a doctor can synchronously perform video interrogation on all the patients in the interrogation group. The system has the advantages that the patients with similar symptoms are grouped, and the doctors and the patients perform online synchronous inquiry on the patients in the same group in a one-to-many manner, so that the inquiry efficiency of the doctors can be improved, the working intensity of the doctors can be reduced, and the waiting time of the patients can be shortened.

Description

Technical Field

[0001] The present invention relates to the field of medical services, and particularly to a method, system, medium, and device for multi-person synchronous medical consultation based on AI. Background Art

[0002] Online medical consultation means that patients submit their symptoms online, and then doctors conduct one-on-one consultations with patients based on the reported symptoms. However, this method places a heavy workload on doctors. Moreover, since patients' descriptions may not be accurate, doctors need to analyze the patients' descriptions and then reconfirm the symptoms, which reduces the consultation efficiency.

[0003] In view of this, it is necessary to provide a method, system, medium, and device for multi-person synchronous medical consultation based on AI. Summary of the Invention

[0004] The method, system, medium, and device for multi-person synchronous medical consultation based on AI provided by the present invention effectively solve the problems of low efficiency in the one-on-one medical consultation mode of existing medical AI and heavy workload on doctors.

[0005] The technical solution adopted by the present invention is as follows:

[0006] The multi-person synchronous medical consultation method based on AI includes the following steps:

[0007] S1. Obtain symptom descriptions of multiple patients: The symptom descriptions include at least one of text, voice, and form.

[0008] S2. Compare symptoms with standard medical terms: Input the symptom description data into a natural language processing model, extract symptom entities, and map the symptom entities to a standard medical term library to generate standardized symptom features.

[0009] S3. Generate symptom feature vectors for corresponding patients: Based on the standardized symptom features, generate symptom feature vectors for each patient, and the symptom feature vectors include text semantic features and structured numerical features.

[0010] S4. Divide consultation groups: Analyze the symptom feature vectors through a clustering algorithm, and dynamically divide patients with a similarity higher than a preset threshold into the same consultation group.

[0011] S5. Video consultation: When the number of patients in the consultation group reaches a preset upper limit or meets the doctor's reception conditions, trigger the video consultation channel so that the doctor can synchronously conduct video consultations on all patients in the consultation group.

[0012] Furthermore, it also includes S6, display of symptom similarities and differences: The doctor's workbench displays the symptom differences among patients in the same consultation group.

[0013] Further: In S6, the doctor's workbench displays the causes of each patient and automatically generates solutions corresponding to the causes to assist the doctor in the consultation.

[0014] Further: In S6, the order of video consultations is automatically sorted according to the urgency.

[0015] Further: It also includes S7, automatic disease control monitoring: Based on the symptom feature vectors of each consultation group, statistically analyze the aggregated distribution of specific symptoms within a preset geographical area or time period. When the aggregation degree of the specific symptoms exceeds the epidemic warning threshold, generate a public health warning signal and send the warning signal and associated patient anonymized data to the public health management platform.

[0016] Further: In S2, the doctor's workbench displays the medical records of each patient in this hospital.

[0017] Further: The clustering algorithm in S4 is a density-based unsupervised clustering algorithm, such as DBSCAN clustering algorithm, DensityPeaks clustering algorithm, OPTICS clustering algorithm.

[0018] An AI-based multi-person synchronous consultation system includes

[0019] A data collection module for collecting patient symptoms;

[0020] An AI processing module for analyzing and clustering the patient symptoms;

[0021] A grouping module for grouping patients;

[0022] An interaction module for realizing video interaction when the doctor conducts video consultations with patients.

[0023] A computer-readable storage medium stores a computer program, and when the computer program is processed and executed, it implements the steps of the AI-based multi-person synchronous consultation method.

[0024] A computer device includes a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus: where

[0025] The memory is used to store the computer program;

[0026] The processor is used to execute the steps of the AI-based multi-person synchronous consultation method by running the program stored on the memory.

[0027] Advantages of the invention:

[0028] 1. Group patients with similar symptoms. Doctors conduct online synchronous consultations for patients in the same group in a one-to-many manner, which can improve the efficiency of doctors' consultations, reduce the work intensity of doctors, and shorten the waiting time of patients.

[0029] 2. It can automatically compare the symptoms described by patients with standard medical terms, enabling doctors to more intuitively understand the symptoms of patients, further improving the speed of doctors' consultations and reducing the work intensity of doctors.

[0030] 3. It can automatically analyze the causes of each patient and provide solutions to doctors, improving the consultation efficiency and reducing the work intensity of doctors.

[0031] 4. It can automatically monitor epidemics and effectively improve the prevention ability of epidemics. Description of the Drawings

[0032] Figure 1 It is a flowchart of the AI-based multi-person synchronous consultation method provided by the embodiment of the present application. Detailed Embodiments

[0033] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be given in conjunction with the drawings.

[0034] The first embodiment provided by the present application is an AI-based multi-person synchronous consultation method, including the following steps:

[0035] S1. Obtain symptom descriptions of multiple patients: The symptom descriptions include at least one of text, voice, and form; for example, sore throat, duration of one day; fever of 39°, duration of one day.

[0036] S2. Compare symptoms with standard medical terms: Input the symptom description data into a natural language processing model, extract symptom entities, and map the symptom entities to a standard medical term library to generate standardized symptom features; use medical field training models such as spaCy and BERT-Biomedical to extract keywords of symptoms, such as "sore throat" and "fever". Then import "sore throat" and "fever" into the standard medical terms for one-by-one comparison. The standard medical terms use the UMLS (Unified Medical Language System) or SNOMED CT term library.

[0037] S3. Generate symptom feature vectors corresponding to patients: Based on the standardized symptom features, generate symptom feature vectors for each patient. The symptom feature vectors include text semantic features and structured numerical features; use a word embedding model (such as BioWordVec or ClinicalBERT) to convert symptom text into high-dimensional vectors.

[0038] S4. Divide the consultation groups: Analyze the symptom feature vectors through a clustering algorithm, and dynamically divide patients with similarity higher than a preset threshold into the same consultation group;

[0039] S5. Video consultation: When the number of patients in the consultation group reaches the preset upper limit or meets the doctor's reception conditions, trigger the video consultation channel so that the doctor can synchronously conduct video consultations on all patients in the consultation group. The number of people in each group can be set, for example, 3 people. The video consultation can use the Tencent Meeting API.

[0040] In the above design, compared with the traditional one-on-one consultation mode, this application can achieve one-to-many synchronous consultations, reducing the doctor's workload, improving the consultation efficiency, and saving medical resources.

[0041] Specifically: It also includes S6, symptom similarities and differences display: The doctor's workbench displays the symptom differences of each patient in the consent consultation group. For example, both patient A and patient B have symptoms of "cough" and "sore throat", and both patient A and patient C have symptoms of "cough" and "fever".

[0042] In the above design, the display of symptom similarities and differences can improve the doctor's judgment speed.

[0043] Specifically: In the above S6, the doctor's workbench displays the causes of each patient and automatically generates solutions corresponding to the causes to assist the doctor in the consultation. For example, both patient A and patient B have symptoms of "cough" and "sore throat", and both patient A and patient C have symptoms of "cough" and "fever". Automatic solutions: Patient A is diagnosed with influenza, patient B is diagnosed with wind-cold, patient A takes oral medicine A, and patient B takes oral medicine B.

[0044] In the above design, it can automatically assist the doctor in obtaining the consultation results and consultation solutions, improving the consultation efficiency and reducing the doctor's work intensity.

[0045] Specifically: In the above S6, the order of video consultations is automatically sorted according to the urgency.

[0046] In the above design, it can effectively reduce the waiting time of patients with severe symptoms.

[0047] Specifically: It also includes S7, automatic disease control monitoring: Based on the symptom feature vectors of each consultation group, statistically analyze the aggregated distribution of specific symptoms in a preset geographical area or time period. When the aggregation degree of the specific symptoms exceeds the epidemic warning threshold, generate a public health warning signal, and send the warning signal and associated patient anonymized data to the public health management platform. For example, the number of people infected with norovirus in area A exceeds 20 within a week.

[0048] In the above design, it is possible to automatically determine possible infectious diseases in a timely manner and reduce the risk of the spread of infectious diseases.

[0049] Specifically: in S2, the doctor's workbench displays the medical records of each patient in the hospital.

[0050] In the above design, by tracing the medical records of patients, the doctor can understand the patient's medical history in a timely manner and obtain more information about the patient's illness.

[0051] Specifically: the clustering algorithm in S4 is a density-based unsupervised clustering algorithm, such as DBSCAN clustering algorithm, DensityPeaks clustering algorithm, OPTICS clustering algorithm.

[0052] The second embodiment provided by the present application is an AI-based multi-person synchronous consultation system, including

[0053] A data acquisition module for collecting patient symptoms;

[0054] An AI processing module for analyzing and clustering the patient symptoms;

[0055] A grouping module for grouping patients;

[0056] An interaction module for realizing video interaction when the doctor conducts a video consultation with the patient.

[0057] The third embodiment provided by the present application is a computer-readable storage medium storing a computer program, and when the computer program is processed and executed, the steps of the AI-based multi-person synchronous consultation method are implemented.

[0058] In addition, the computer-readable storage medium of this embodiment can adopt any combination of one or more readable storage media, where the readable storage medium includes an electrical, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above.

[0059] The fourth embodiment provided by the present application is a computer device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory communicate with each other through the communication bus: where

[0060] The memory is used to store a computer program;

[0061] The processor is configured to execute the steps of the AI-based multi-person synchronous consultation method by running the program stored in the memory. As an implementation manner of the present invention, the communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc.

[0062] As an implementation manner of the present invention, the communication interface is used for communication between the above terminal and other devices.

[0063] As an implementation manner of the present invention, the memory may include a Random Access Memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0064] As an implementation manner of the present invention, the above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may 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.

[0065] The fifth embodiment provided by this application is a multi-person synchronous consultation method based on AI, including the following steps: S1. Obtain symptom descriptions of multiple patients: The symptom descriptions include at least one of text, voice, and form; S2. Compare symptoms with standard medical terms: Input the symptom description data into a natural language processing model, extract symptom entities, and map the symptom entities to a standard medical term library to generate standardized symptom features; S3. Generate symptom feature vectors for corresponding patients: Based on the standardized symptom features, generate symptom feature vectors for each patient, and the symptom feature vectors include text semantic features and structured numerical features; S4. Divide consultation groups: Analyze the symptom feature vectors through a clustering algorithm, and dynamically divide patients with a similarity higher than a preset threshold into the same consultation group; S5. Video consultation: When the number of patients in the consultation group reaches a preset upper limit or meets the doctor's reception conditions, trigger a video consultation channel so that the doctor can synchronously conduct video consultations on all patients in the consultation group. It also includes S6, display of symptom similarities and differences: The doctor's workbench displays the symptom differences of each patient in the same consultation group. In the S6, the doctor's workbench displays the causes of each patient's illness and automatically generates solutions corresponding to the causes to assist the doctor in the consultation. In the S6, the order of video consultations is automatically sorted according to the urgency. It also includes S7, automatic disease control monitoring: Based on the symptom feature vectors of each consultation group, statistically analyze the aggregated distribution of specific symptoms in a preset geographical area or time period. When the aggregation degree of the specific symptoms exceeds the epidemic warning threshold, generate a public health warning signal, and send the warning signal and associated patient anonymized data to the public health management platform. In the S2, the doctor's workbench displays the medical records of each patient in this hospital. The clustering algorithm in the S4 is a density-based unsupervised clustering algorithm, such as DBSCAN clustering algorithm, DensityPeaks clustering algorithm, OPTICS clustering algorithm.

[0066] In the above design, it is possible to realize one-to-many consultation services and improve the consultation efficiency. It can automatically pre-diagnose patients and give corresponding treatment plans, reducing the doctor's work intensity and time. It can realize the monitoring of epidemic diseases and effectively improve the prevention ability of epidemic diseases.

[0067] For further detailed description, it should be understood that the above are only specific embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The AI-based multi-person synchronous consultation method is characterized by: The steps include: S1. Obtain symptom descriptions of multiple patients: the symptom descriptions include at least one form of text, voice, and form; S2. Comparison of symptoms with standard medical terms: inputting the symptom description data into a natural language processing model, extracting symptom entities, and mapping the symptom entities to a standard medical terminology library to generate standardized symptom features; S3, corresponding to the patient's symptom feature vector: based on the standardized symptom feature, generating a symptom feature vector for each patient, the symptom feature vector including text semantic features and structured numerical features; S4. Dividing consultation groups: Analyzing the symptom feature vectors by a clustering algorithm, and dynamically dividing patients whose similarity is higher than a preset threshold into the same consultation group; S5. Video consultation: When the number of patients in the consultation group reaches a preset upper limit or meets the doctor's consultation conditions, the video consultation channel is triggered, allowing the doctor to conduct video consultations on all patients in the consultation group simultaneously.

2. The AI-based multi-person synchronous medical consultation method according to claim 1, characterized in that: It also includes S6, display of symptom similarities and differences: the doctor's workbench displays the symptom differences among patients in the same consultation group.

3. The AI-based multi-person synchronous medical consultation method according to claim 2, characterized in that: In S6, the doctor's workstation displays the cause of each patient's illness and automatically generates a solution to the corresponding cause to assist the doctor in conducting a diagnosis.

4. The AI-based multi-person synchronous medical consultation method according to claim 3, characterized in that: In S6, the order of the video consultations is automatically sorted according to the urgency.

5. The AI-based multi-person synchronous medical consultation method according to claim 4, characterized in that: It also includes S7, automatic disease control monitoring: based on the symptom feature vectors of each consultation group, the cluster distribution of specific symptoms in a preset geographical area or time period is statistically analyzed. When the concentration of the specific symptoms exceeds the epidemic warning threshold, a public health warning signal is generated, and the warning signal and related patient anonymous data are sent to the public health management platform.

6. The AI-based multi-person synchronous medical consultation method according to claim 1, characterized in that: In S2, the doctor's workstation displays the medical records of each patient in the hospital.

7. The AI-based multi-person synchronous medical consultation method according to claim 1, characterized in that: The clustering algorithm in S4 is a density-based unsupervised clustering algorithm, such as the DBSCAN clustering algorithm, the DensityPeaks clustering algorithm, and the OPTICS clustering algorithm.

8. AI-based multi-person synchronous consultation system, characterized by: include, A data collection module, used to collect patient symptoms; AI processing module, used for patient symptom analysis and clustering calculation; A grouping module, used to group patients; The interactive module is used to realize video interaction when doctors conduct video consultations with patients.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is processed and executed, the steps of the AI-based multi-person synchronous medical consultation method according to any one of claims 1 to 7 are implemented.

10. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus: The memory is used to store computer programs; The processor is used to execute the steps of the AI-based multi-person synchronous medical consultation method according to any one of claims 1 to 7 by running the program stored in the memory.

Images