Online inquiry processing method and device, electronic equipment and computer readable medium

Abstract

The invention discloses an online inquiry processing method and device, electronic equipment and a computer readable medium, and relates to the technical field of online medical treatment, and the method comprises the steps: responding to a triggering operation of a user for an online consulting room control, and obtaining historical symptom consultation data of the user in an online consulting room within a preset time; in response to the situation that the historical symptom consultation data is not empty, generating a guide copywriting according to the historical symptom consultation data, and pushing the guide copywriting to the user side; receiving reply data for the guide copywriting returned by the user side, and performing triage according to the historical symptom consultation data and the reply data to determine a specialized large model; and under the condition that the preliminary diagnosis process is executed, the specialized large model carries out inquiry interaction with the user side based on a preset inquiry question, obtains answer data returned by the user side, generates a diagnosis and treatment suggestion based on the obtained archive data, chief complaint data and the answer data, and pushes the diagnosis and treatment suggestion to the user side. And the flexibility of an online inquiry process and the accuracy of online inquiry processing are improved.

Description

Technical Field

[0001] This application relates to the field of online medical technology, and in particular to an online consultation processing method, device, electronic device and computer-readable medium. Background Technology

[0002] Currently, with the development of large-scale models, various question-and-answer and recommendation services can be provided based on them. In the medical field, large-scale models can provide users with services such as health education, drug information, and medication recommendations. However, when users currently use general-purpose large-scale models for health education and disease consultation, these models often follow fixed processes to answer questions, resulting in rigid processes and low accuracy in online consultations. Summary of the Invention

[0003] In view of this, embodiments of this application provide an online consultation processing method, device, electronic device, and computer-readable medium, which can solve the technical problem that when users use general large models for health education and disease consultation, the general large models often answer users' questions according to a fixed process, resulting in a rigid process and low accuracy of online consultation processing.

[0004] To achieve the above objectives, according to one aspect of the embodiments of this application, an online consultation processing method is provided, applied on the server side, the method comprising: In response to user actions triggered by online clinic controls, retrieve the user's historical symptom consultation data in the online clinic within a preset time period; If the historical symptom consultation data is not empty, generate guidance text based on the historical symptom consultation data and push the guidance text to the user's terminal; Receive user response data for the guidance text, and triage based on historical symptom consultation data and response data to determine the specialty model; During the initial diagnosis process, the specialized big data model interacts with the user based on preset consultation questions to obtain the user's response data to the preset consultation questions, acquire relevant file data and chief complaint data, and generate treatment suggestions based on the file data, chief complaint data and response data, and push the treatment suggestions to the user.

[0005] Optionally, after triage based on historical symptom consultation and response data to determine the specialty model, online consultation processing methods also include: When performing a follow-up visit, the specialized big data model obtains the user's memory data, record data, and chief complaint data. Based on memory data, archival data, and chief complaint data, treatment suggestions are generated and pushed to the user's device.

[0006] Optionally, based on historical symptom consultation data, guide text can be generated, including: Extract symptoms-related keywords from historical symptom consultation data, and generate guiding text for continued consultation based on the keywords.

[0007] Optionally, triage can be performed based on historical symptom consultation and response data to determine a major specialty model, including: The response data corresponds to a continued consultation, and the follow-up visit process is executed, with the target department determined based on historical symptom consultation data; If the response data remains empty within a preset time, the initial diagnosis process is executed, the chief complaint guidance text is pushed to the user terminal, the response data of the user terminal regarding the chief complaint guidance text is received, and the target department is determined based on the response data. The chief complaint guidance text includes the report upload guidance text. The response data corresponds to a new question, and the target department is determined based on the response data. Determine the major specialty model based on the target department.

[0008] Optionally, based on archival data, chief complaint data, and response data, treatment suggestions are generated, including: Generate diagnostic and treatment guidance keywords based on archival data, chief complaint data, and response data; The specialized big data model searches the department's knowledge base based on clues to the treatment approach, and generates treatment suggestions based on the search results.

[0009] Optionally, during the initial consultation process, when the specialist big data model interacts with the user based on preset consultation questions, the online consultation processing methods also include: The system updates the overall medical treatment progress and the specific progress percentage under the inquiry status in real time, and pushes the overall medical treatment progress and the specific progress percentage under the inquiry status to the user's terminal in real time.

[0010] Optionally, the overall medical progress and specific progress percentages under the inquiry status can be updated in real time, including: In response to the detection that a user has completed answering any medical question, update the overall medical progress and the specific progress percentage in the inquiry status.

[0011] Optionally, during the initial consultation process, when the specialist big data model interacts with the user based on preset consultation questions, the online consultation processing methods also include: Real-time updates of summary answers and status for each preset consultation question in the consultation question list; In response to the user's action of triggering the drop-down button, an expanded list of consultation questions is pushed to the user's device; The consultation question list is linked to the drop-down button, and the status includes pending answer and answered status.

[0012] Optionally, during the initial consultation process, when the specialist big data model interacts with the user based on preset consultation questions, the online consultation processing methods also include: In response to a request to exit the consultation, execute an exit query and obtain the user's selection data for the exit query options; If the selected option corresponds to an immediate exit, the online consultation will end. In response to the selected data, the system retains the progress of the online consultation and exits. The system retains the preset duration of the online consultation. If the user re-enters the online consultation room within the preset duration, the remaining online consultation process continues. If the user does not re-enter the online consultation room within the preset duration, the online consultation ends. The online consultation room corresponds to the online consultation room control triggered by the user.

[0013] According to another aspect of the embodiments of this application, an online consultation processing method is provided, applied to a user terminal, the method comprising: Receive and display the onboarding text pushed by the server to the user, obtain the user's response data to the onboarding text, and push the response data to the server. The system interacts with the specialized big data model determined by the triage on the server side based on preset consultation questions, obtains the user's answer data to the preset consultation questions, and returns the answer data to the server side. Receive and display treatment suggestions pushed from the server to the user.

[0014] Optionally, before engaging in follow-up questioning with the pre-set diagnostic model determined by the server-side triage, the online consultation processing method also includes: Receive and display the main complaint guidance text pushed by the server to the user, and push the user's response data to the main complaint guidance text to the server, including report data.

[0015] Optionally, during the online consultation process, when interacting with the server-side specialized big data model determined through triage based on preset consultation questions, the online consultation processing method also includes: Receive and pin the overall medical progress and the specific progress percentage under the inquiry status pushed by the server.

[0016] Optionally, during the online consultation process, when interacting with the server-side specialized big data model determined through triage based on preset consultation questions, the online consultation processing method also includes: Receive and display to the user an expanded list of consultation questions pushed from the server; The consultation question list displays summary answers and statuses for each preset consultation question, including pending answers and answered answers.

[0017] Optionally, user response data to preset consultation questions can be obtained, including: Obtain user's click-through data and / or manually entered data; Select the data option and / or manually enter the data to determine and obtain the user's answer data for the preset consultation questions.

[0018] In addition, this application also provides an online consultation processing device, which is set on the server side, and the device includes: The acquisition unit is configured to acquire the user's historical symptom consultation data in the online clinic within a preset time period in response to the user's trigger operation on the online clinic control. The guidance unit is configured to respond to historical symptom consultation data that is not empty, generate guidance text based on the historical symptom consultation data, and push the guidance text to the user's terminal; The triage unit is configured to receive response data from the user's terminal regarding the guidance text, and to perform triage based on historical symptom consultation data and response data to determine the specialty big model; The diagnosis and treatment unit is configured to, during the initial diagnosis process, have a specialized big data model engage in follow-up questioning and interaction with the user based on preset consultation questions, in order to obtain the user's response data to the preset consultation questions, acquire relevant file data and chief complaint data, and generate and push diagnosis and treatment suggestions to the user based on the file data, chief complaint data and response data.

[0019] Optionally, the treatment unit is further configured as follows: When performing a follow-up visit, the specialized big data model obtains the user's memory data, record data, and chief complaint data. Based on memory data, archival data, and chief complaint data, treatment suggestions are generated and pushed to the user's device.

[0020] Optionally, the guiding unit is further configured to: Extract symptoms-related keywords from historical symptom consultation data, and generate guiding text for continued consultation based on the keywords.

[0021] Optionally, the triage unit is further configured to: The response data corresponds to a continued consultation, and the follow-up visit process is executed, with the target department determined based on historical symptom consultation data; If the response data remains empty within a preset time, the initial diagnosis process is executed, the chief complaint guidance text is pushed to the user terminal, the response data of the user terminal regarding the chief complaint guidance text is received, and the target department is determined based on the response data. The chief complaint guidance text includes the report upload guidance text. The response data corresponds to a new question, and the target department is determined based on the response data. Determine the major specialty model based on the target department.

[0022] Optionally, the treatment unit is further configured as follows: Generate diagnostic and treatment guidance keywords based on archival data, chief complaint data, and response data; The specialized big data model searches the department's knowledge base based on clues to the treatment approach, and generates treatment suggestions based on the search results.

[0023] Optionally, the online consultation processing device also includes a progress update unit, configured to: The system updates the overall medical treatment progress and the specific progress percentage under the inquiry status in real time, and pushes the overall medical treatment progress and the specific progress percentage under the inquiry status to the user's terminal in real time.

[0024] Optionally, the progress update unit is further configured to: In response to the detection that a user has completed answering any medical question, update the overall medical progress and the specific progress percentage in the inquiry status.

[0025] Optionally, the online consultation processing device also includes a consultation question list updating unit, configured to: Real-time updates of summary answers and status for each preset consultation question in the consultation question list; In response to the user's action of triggering the drop-down button, an expanded list of consultation questions is pushed to the user's device; The consultation question list is linked to the drop-down button, and the status includes pending answer and answered status.

[0026] Optionally, the online consultation processing device also includes a consultation exit processing unit, configured to: In response to a request to exit the consultation, execute an exit query and obtain the user's selection data for the exit query options; If the selected option corresponds to an immediate exit, the online consultation will end. In response to the selected data, the system retains the progress of the online consultation and exits. The system retains the preset duration of the online consultation. If the user re-enters the online consultation room within the preset duration, the remaining online consultation process continues. If the user does not re-enter the online consultation room within the preset duration, the online consultation ends. The online consultation room corresponds to the online consultation room control triggered by the user.

[0027] In addition, this application also provides an online consultation processing device, installed on the user terminal, the device comprising: The guidance text display unit is configured to receive and display guidance text pushed from the server to the user, obtain user response data to the guidance text, and push the response data to the server. The interaction unit is configured to interact with the triage-determined specialty big data model on the server side based on preset consultation questions, obtain the user's answer data for the preset consultation questions, and return the answer data to the server side. The treatment suggestion display unit is configured to receive and display treatment suggestions pushed from the server to the user.

[0028] Optionally, the online consultation processing device also includes a chief complaint guidance text display unit, configured as follows: Receive and display the main complaint guidance text pushed by the server to the user, and push the user's response data to the main complaint guidance text to the server, including report data.

[0029] Optionally, the online consultation processing device also includes a progress display unit, configured to: Receive and pin the overall medical progress and the specific progress percentage under the inquiry status pushed by the server.

[0030] Optionally, the online consultation processing device also includes a consultation question list display unit, configured to: Receive and display to the user an expanded list of consultation questions pushed from the server; The consultation question list displays summary answers and statuses for each preset consultation question, including pending answers and answered answers.

[0031] Optionally, the interaction unit is further configured as follows: Obtain user's click-through data and / or manually entered data; Select the data option and / or manually enter the data to determine and obtain the user's answer data for the preset consultation questions.

[0032] In addition, this application also provides an online consultation processing electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, enable the one or more processors to implement the online consultation processing method described above.

[0033] In addition, this application also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the online consultation processing method described above.

[0034] To achieve the above objectives, according to another aspect of the embodiments of this application, a computer program product is provided.

[0035] A computer program product according to an embodiment of this application includes a computer program that, when executed by a processor, implements the online consultation processing method provided in the embodiment of this application.

[0036] One embodiment of the above invention has the following advantages or beneficial effects: This application obtains the user's historical symptom consultation data in the online clinic within a preset time period in response to the user's trigger operation on the online clinic control; in response to the historical symptom consultation data not being empty, it generates guidance text based on the historical symptom consultation data and pushes the guidance text to the user terminal; it receives the response data returned by the user terminal in response to the guidance text, and performs triage based on the historical symptom consultation data and response data to determine the specialty big model; in the case of executing the initial diagnosis process, the specialty big model interacts with the user terminal by asking follow-up questions based on preset consultation questions to obtain the answer data returned by the user terminal in response to the preset consultation questions, obtains the user's related file data and chief complaint data, and generates treatment suggestions based on the file data, chief complaint data, and answer data, and pushes the treatment suggestions to the user terminal. By introducing an immersive online consultation room that closely resembles the offline medical process, the psychological burden on patients seeking medical care online is reduced, the online user experience is improved, and professionalism and trust are enhanced. Through triage, a specialized model is determined, which then completes subsequent processes such as initial / follow-up visits, doctor consultations, and treatment suggestions. This allows users to consult different specialized models for different symptoms, providing targeted treatment suggestions and improving the flexibility and accuracy of the online consultation process.

[0037] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0038] The accompanying drawings are provided to better understand this application and do not constitute an undue limitation thereof. Wherein: Figure 1 This is a schematic diagram of the main flow of an online consultation processing method applied to the server side according to an embodiment of this application; Figure 2 This is a schematic diagram of the main flow of an online consultation processing method applied to a user terminal according to an embodiment of this application; Figure 3 This is a schematic diagram of the overall process of an online consultation processing method according to an embodiment of this application; Figure 4a This is a schematic diagram of the online consultation room entrance location according to an embodiment of the online consultation processing method of this application; Figure 4b This is a schematic diagram of the initial consultation page of an online consultation processing method according to an embodiment of this application; Figure 4c This is a schematic diagram of a follow-up consultation page for an online consultation processing method according to an embodiment of this application; Figure 4d This is a schematic diagram of the follow-up consultation direct input question page according to an embodiment of the online consultation processing method of this application; Figure 4e This is a schematic diagram showing the overall progress and the percentage change of specific progress under the inquiry state in an online consultation processing method according to an embodiment of this application. Figure 4f This is a schematic diagram of the exit query page of an online consultation processing method according to an embodiment of this application; Figure 4g This is a schematic diagram of the diagnosis suggestion result page of an online consultation processing method according to an embodiment of this application; Figure 4h This is a schematic diagram of a follow-up consultation page according to an embodiment of the online consultation processing method of this application; Figure 5 This is a schematic diagram of the main units of an online consultation processing device installed on a server according to an embodiment of this application; Figure 6 This is a schematic diagram of the main units of an online consultation processing device installed on a user terminal according to an embodiment of this application; Figure 7 This is an exemplary system architecture diagram to which embodiments of this application can be applied; Figure 8 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers in the embodiments of this application. Detailed Implementation

[0039] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These embodiments should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solutions of this application comply with relevant national laws and regulations. It should also be noted that certain software, components, models, and other existing industry solutions may be mentioned in the embodiments of this application. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solutions of this application, and do not imply that the applicant has already used or necessarily used such solutions. The collection, gathering, updating, analysis, processing, use, transmission, and storage of user personal information involved in the technical solutions of this application all comply with relevant laws and regulations, are used for legal and reasonable purposes, do not violate public order and good morals, are not shared, disclosed, or sold outside of these legal uses, and are subject to supervision and management by regulatory authorities. Necessary measures should be taken to prevent unauthorized access to user personal information, safeguard user personal information security, cybersecurity, and national security, and ensure that those authorized to access personal information comply with relevant laws and regulations. Once this user personal information is no longer needed, risks should be minimized by restricting or even prohibiting data collection and / or deleting the data.

[0040] When used, including in certain relevant applications, data is deidentified to protect user privacy, for example by removing specific identifiers, controlling the amount or specificity of stored data, controlling how data is stored, and / or other methods.

[0041] Figure 1 This is a schematic diagram of the main flow of an online consultation processing method applied to the server side according to an embodiment of this application, as shown below. Figure 1 As shown, the online consultation process mainly includes the following steps S101-S104.

[0042] Step S101: In response to the user's trigger operation on the online consultation room control, obtain the user's historical symptom consultation data in the online consultation room within a preset time period.

[0043] The online consultation room control, such as the "AI Consultation Room" control, triggers a server response when a user clicks the "AI Consultation Room" control on the app's page. This response retrieves the user's historical symptom consultation data from online consultations within a preset timeframe (e.g., 30 days). This historical symptom consultation data can be empty or not. Empty data indicates the user is visiting the online consultation room for the first time (initial consultation), while non-empty data indicates the user has visited multiple times (follow-up consultation).

[0044] Step S102: In response to the historical symptom consultation data not being empty, generate guidance text based on the historical symptom consultation data and push the guidance text to the user terminal.

[0045] Specifically, based on historical symptom consultation data, guiding text is generated, including: extracting symptom-related keywords from historical symptom consultation data, and generating guiding text for continued consultation based on the keywords.

[0046] For example, if the server obtains a user's historical symptom consultation data from the online clinic within a preset time period (e.g., within 30 days), it will prompt the user to revisit the clinic. The server will extract symptom-related keywords (e.g., sprained ankle) from the historical consultation data and generate a prompt for continued consultation based on these keywords (e.g., sprained ankle). This prompt (e.g., "We discussed sprained ankles last time, would you like to continue the consultation? Of course, you can also directly mention other questions") will be pushed to the user's mobile device.

[0047] In some embodiments, in response to empty historical symptom consultation data, initial diagnosis guidance is provided (e.g., guiding report upload, guiding the expression of chief complaint), and the initial diagnosis process is executed. During the initial diagnosis process, the specialized big data model determined by the server-side through triage interacts with the user based on preset consultation questions to obtain the user's response data to the preset consultation questions, acquire user-related file data and chief complaint data, and generate treatment suggestions based on the file data, chief complaint data, and response data, and push the treatment suggestions to the user.

[0048] Step S103: Receive the response data returned by the user terminal regarding the guidance text, and perform triage based on historical symptom consultation data and response data to determine the specialty big data model.

[0049] The server receives response data from the user regarding the prompt (e.g., "Last time we talked about ankle sprains, would you like to continue consulting? Of course, you can also directly ask other questions"). Based on historical symptom consultation data and response data, the server performs triage to determine the major specialty model.

[0050] Specifically, triage is performed based on historical symptom consultation data and response data to determine the specialty model. This includes: responding to response data (e.g., "Continue consulting about ankle sprains") corresponding to continued consultation, executing a follow-up consultation process, and determining the target department based on historical symptom consultation data. For example, extracting the department identifier (e.g., orthopedics) from historical symptom consultation data, and accurately determining the target department (e.g., orthopedics) based on the department identifier (e.g., orthopedics) of the historical triage; responding to a situation where the response data remains empty for a preset time (e.g., within 10 minutes) (i.e., the user has not responded to the prompt "We talked about ankle sprains last time, would you like to continue consulting? Of course, you can also directly say other questions"), executing an initial consultation process, and pushing a prompt to express the chief complaint (e.g., if convenient, you can...). The system sends the user's previous test results ("If convenient, you can send me your previous test results so I can better answer your questions") to the user's end. It then receives response data (e.g., uploaded reports / test results) from the user's end, based on the response data (e.g., uploaded reports / test results). The system determines the target department (e.g., orthopedics), where the main complaint guidance text includes report upload guidance. Responding to new questions based on reply data (e.g., "It rained yesterday, and I have a sore throat and a stuffy nose when I got home"), the system determines the target department (e.g., internal medicine). Finally, it determines a specialized macro-model (e.g., a macro-model for internal medicine) based on the target department (e.g., internal medicine). This allows users to specifically inquire about different specialized macro-models for different symptoms, providing targeted treatment suggestions, improving the flexibility and accuracy of online consultations.

[0051] Specifically, after triaging based on historical symptom consultation data and response data to determine the specialized big data model, the method further includes: in the case of executing a follow-up consultation process, the server-side, through the specialized big data model determined by triage, obtains user-related memory data, archival data, and chief complaint data. Furthermore, if necessary, the specialized big data model can also interact with the user through follow-up questioning to obtain the user's answer data to follow-up questions (i.e., preset consultation questions); based on the obtained memory data (e.g., a sprained ankle consultation on September 2nd) and archival data (e.g., basic information: gender)... Female, Age: 20, Height: To be added, Weight: To be added; Health History: Past Medical History: None, Allergies: Pollen Allergy, Surgical History: None, Family History: Hypertension, Diabetes, Heart Disease, etc.) and chief complaint data (e.g., "Continuing with the sprained ankle problem, why is my recovery so slow?"). The system can also combine the user's answers to follow-up questions (i.e., preset consultation questions) with data from the department's knowledge base to generate treatment suggestions that may include one or more of the following: self-medication, further offline examination, health management, and risk warnings. These suggestions are then pushed to the user for reference.

[0052] In step S104, during the initial diagnosis process, the specialized big data model interacts with the user based on preset consultation questions to obtain the user's answer data for the preset consultation questions, obtain the user's relevant file data and chief complaint data, and generate treatment suggestions based on the file data, chief complaint data and answer data, and push the treatment suggestions to the user.

[0053] During the initial consultation process, the specialized big data model determined by the server-side after triage interacts with the user based on preset consultation questions (e.g., whether there is fever or cough, sputum color; whether medication has been taken and its effectiveness; whether anyone around has a cold; whether there are any other issues). This process obtains the user's responses to the preset consultation questions (e.g., fever and cough; medication taken with little effect; no one around has a cold; no other issues). Based on this, the model acquires user-related profile data and chief complaint data. Age: 20, Height: To be added, Weight: To be added; Health History: Past Medical History: None, Allergies: Pollen Allergy, Surgical History: None, Family History: Hypertension, Diabetes, Heart Disease, etc.), chief complaint data (e.g., "My throat hurts and my nose is a little stuffy when I got home yesterday after the rain") and response data (e.g., I have fever and cough; I have taken xx medication, but the effect is not significant; no one around me has a cold; I have no xxxx questions). The system queries the department's knowledge base to generate treatment suggestions that can include one or more of the following: self-medication, further offline examination, health management, and risk warnings. These suggestions are then pushed to the user for reference.

[0054] Specifically, based on archival data, chief complaint data, and response data, treatment suggestions are generated, including: generating treatment approach prompts based on the archival data, chief complaint data, and response data; for example, determining the positions of the corresponding placeholders in the treatment approach prompt generation template for the archival data, chief complaint data, and response data, and filling the corresponding placeholder positions in the template to generate treatment approach prompts; the specialized big data model searches the departmental knowledge base based on the treatment approach prompts, generates treatment suggestions based on the search results, and inputs the generated treatment approach prompts into the specialized big data model determined by triage, so that the specialized big data model searches the departmental knowledge base based on the treatment approach prompts, and generates treatment suggestions that may include one or more of the following: self-medication, further offline examination, health management, and risk warnings. Guiding the specialized big data model to output treatment suggestions through prompts can make the output treatment suggestions more accurate.

[0055] Specifically, during the initial consultation process, when the specialized big data model interacts with the user based on preset consultation questions, the method also includes: real-time updating of the overall consultation progress (i.e., real-time updating). Figure 4e The overall stages in the process: triage > initial / follow-up visit > consulting a doctor > the stage reached in the treatment recommendations (e.g., reaching the "consulting a doctor" stage) and the specific progress percentage under the consultation status (e.g., Figure 4e The progress is 20%, 67%, and 100% (in the system). The updated overall medical progress and the specific progress percentage in the updated inquiry status are pushed to the user's terminal in real time.

[0056] Specifically, the overall medical treatment progress and the specific progress percentage in the inquiry state are updated in real time, including: in response to detecting that the user has completed answering any medical question (e.g., the second medical question: whether to take medication and how effective it is), the overall medical treatment progress is updated once (e.g., the overall medical treatment progress is updated to the "consult a doctor" stage) and the specific progress percentage in the inquiry state (e.g., the specific progress percentage in the inquiry state is updated to 67%).

[0057] Specifically, during the initial consultation process, when the specialized big data model interacts with the user based on preset consultation questions, the method also includes: real-time updating the summarized answer results (e.g., fever and cough, sputum color; whether medication has been taken and its effectiveness; whether people around have colds; whether there are any other problems) and status (e.g., fever and cough; medication taken with little effect; no one around has a cold; no other problems) for each preset consultation question in the consultation question list (e.g., fever and cough; medication taken with little effect; no one around has a cold; no other problems). Figure 4eThe top card in the image shows the expanded question status; a checkmark next to a question indicates it has been answered, and a dot indicates it is pending an answer. This responds to user actions on dropdown buttons (such as...). Figure 4e The trigger action (as shown by the drop-down button in the top card - question expanded state) pushes the expanded list of consultation questions (such as...) Figure 4e The top card in the drop-down menu (shown in the expanded question list) is sent to the user's device; the question list is associated with a drop-down button, and the status includes pending answer (marked with a dot in front of the question) and answered (marked with a checkmark in front of the question).

[0058] Specifically, during the initial consultation process, when the specialist big data model interacts with the user based on preset consultation questions, the method also includes: in response to an exit consultation request, executing an exit inquiry (e.g., such as...). Figure 4f As shown, you can choose to retain the current consultation progress and continue the communication if you re-enter within two hours. The options "Retain Progress and Exit" and "Exit Directly" are displayed. The system retrieves the user's choice of exit option (e.g., the user can choose "Exit Directly" or "Retain Progress and Exit"). Responding to the option selection data (e.g., the user chose "Exit Directly"), the system directly exits and ends the online consultation. Responding to the option selection data (e.g., the user chose "Retain Progress and Exit"), the system retains the online consultation for a preset duration. If the user re-enters the online consultation room within the preset duration, the remaining online consultation process continues. If the user does not re-enter the online consultation room within the preset duration, the online consultation ends. The online consultation room corresponds to the online consultation room control triggered by the user.

[0059] For example, if a user chooses to exit midway, there is a two-hour retention mechanism, allowing them to re-enter the unfinished consultation room next time to continue the consultation. Alternatively, they can exit directly without retention, and the next session will be a new one, thus enabling more flexible online consultations and improving the user experience.

[0060] This embodiment responds to user triggering operations on online consultation room controls, acquires the user's historical symptom consultation data in the online consultation room within a preset time; if the historical symptom consultation data is not empty, it generates guidance text based on the historical symptom consultation data and pushes the guidance text to the user's terminal; it receives the user's response data to the guidance text, and performs triage based on the historical symptom consultation data and response data to determine the specialty big data model; in the case of executing the initial diagnosis process, the specialty big data model interacts with the user's terminal based on preset consultation questions to obtain the user's response data to the preset consultation questions, acquires the user's relevant file data and chief complaint data, and generates treatment suggestions based on the file data, chief complaint data, and response data, and pushes the treatment suggestions to the user's terminal. By introducing an immersive online consultation room that closely resembles the offline medical process, the psychological burden on patients seeking medical care online is reduced, the online user experience is improved, and professionalism and trust are enhanced. Through triage, a specialized model is determined, which then completes subsequent processes such as initial / follow-up visits, doctor consultations, and treatment suggestions. This allows users to consult different specialized models for different symptoms, providing targeted treatment suggestions and improving the flexibility and accuracy of the online consultation process.

[0061] Figure 2 This is a schematic diagram of the main flow of an online consultation processing method applied to a user terminal according to an embodiment of this application, as shown below. Figure 2 As shown, the online consultation process mainly includes the following steps S201-S203.

[0062] Step S201: Receive and display the guidance text pushed by the server to the user, obtain the user's response data to the guidance text, and push the response data to the server.

[0063] The client receives and displays the prompts pushed by the server (e.g., "Last time we talked about sprained ankles, would you like to continue consulting?" or "Of course, you can also directly say other questions"), obtains the user's response data to the prompts (e.g., "Continue consulting about sprained ankles", response data remains empty, or "It rained yesterday and I got home with a sore throat and a stuffy nose"), and pushes the response data (e.g., "Continue consulting about sprained ankles", response data remains empty, or "It rained yesterday and I got home with a sore throat and a stuffy nose") to the server.

[0064] Step S202: The user interacts with the triage-determined specialty model on the server side based on preset consultation questions, obtains the user's answer data to the preset consultation questions, and returns the answer data to the server side.

[0065] The user-side and server-side specialized big data models, determined through triage, interact by asking follow-up questions based on preset consultation questions (e.g., whether there is fever or cough, sputum color; whether medication has been taken and its effectiveness; whether people around have colds; whether there are any other issues). The system obtains the user's responses to these questions (e.g., fever and cough; medication taken, but with little effect; no people around have colds; no other issues). The responses are then returned to the server (e.g., fever and cough; medication taken, but with little effect; no people around have colds; no other issues).

[0066] Specifically, before engaging in follow-up questioning with the server-side specialized big data model determined through triage based on preset consultation questions, the method further includes: the user receiving and displaying the main complaint guidance text pushed by the server (e.g., "If convenient, you can send me your previous examination results so I can better answer your questions"), and pushing the user's response data (e.g., uploaded reports / examination results) to the server in response to the main complaint guidance text (e.g., "If convenient, you can send me your previous examination results so I can better answer your questions"), wherein the response data includes report data. This allows for better answering of user questions during the initial consultation by incorporating the user's uploaded reports / examination results.

[0067] Specifically, during the interaction with the server-side specialized big data model determined through triage, based on preset consultation questions, the method also includes: receiving and pinning the overall consultation progress pushed by the server (such as...). Figure 4e As shown in the collapsed and expanded states of the pinned card in the system, the "Ask a Doctor" option under Triage > Initial / Follow-up Consultation > Consult a Doctor > Treatment Suggestions can be highlighted in the user's browser (for example, it can be bolded or have its color changed) and the specific progress percentage under the consultation status can be displayed (e.g., updating the specific progress percentage under the consultation status to 67%). This allows users to understand the online consultation progress in real time, improving user engagement and experience.

[0068] Specifically, during the interaction with the server-side specialized large-scale model determined through triage, based on preset consultation questions, the method also includes: receiving and displaying to the user an expanded list of consultation questions pushed by the server (such as...). Figure 4eThe top card in the "Expanded Questions" section displays a list of pre-set consultation questions, including: Do you have a fever or cough? What is the color of your sputum? Have you taken any medication, and how effective is it? Are there any people around you with colds? Are there any other questions? The list also shows summary answers (e.g., fever and cough; medication taken, but with little effect; no one around you with colds; no other questions) and statuses (e.g., fever and cough; medication taken, but with little effect; no one around you with colds; no other questions) for each pre-set question. Figure 4e The top card in the online consultation interface shows the expanded status of questions. A checkmark (√) in front of a question indicates that it has been answered, while a dot (·) indicates that it is pending an answer. The status includes pending (·) and answered (√). By displaying the summary answers and status of answers to questions during the online consultation process, users can understand the details and progress of their online consultation in real time, which helps to correct errors promptly and improves the accuracy of online consultation processing.

[0069] Specifically, the system acquires user response data to preset medical consultation questions, including: acquiring user option click data (for example, the user clicked one or more options such as fever, cough, phlegm, headache, and general weakness) and / or manual input data (for example, the user manually entered "It rained yesterday, and I had a sore throat and a stuffy nose when I got home"); based on the option click data (e.g., one or more options such as fever, cough, phlegm, headache, and general weakness) and / or manual input data (e.g., "It rained yesterday, and I had a sore throat and a stuffy nose when I got home"), the system determines and acquires user response data to preset medical consultation questions (e.g., one or more options such as fever, cough, phlegm, headache, and general weakness, and / or "It rained yesterday, and I had a sore throat and a stuffy nose when I got home"). By mapping corresponding data to user click operations and / or input operations as user response data to preset medical consultation questions, the system is both fast and comprehensive, helping to improve the accuracy of online consultation processing.

[0070] Step S203: Receive and display the treatment suggestions pushed by the server to the user.

[0071] By introducing an immersive online consultation room that closely resembles the offline medical process, the psychological burden on patients seeking medical care online is reduced, the online user experience is improved, and professionalism and trust are enhanced. Through triage, a specialized model is determined, which then completes subsequent processes such as initial / follow-up visits, doctor consultations, and treatment suggestions. This allows users to consult different specialized models for different symptoms, providing targeted treatment suggestions and improving the flexibility and accuracy of the online consultation process.

[0072] In the medical scenario described in this application, the online consultation room, for example, could be an AI consultation room, i.e., a consultation room where a large model provides online consultation services to users. Both general-purpose large models and specialized large models belong to the category of large models. The difference is that general-purpose large models often follow a fixed process to answer user questions, resulting in a rigid process and difficulty in obtaining targeted results; while specialized large models can provide targeted diagnosis and treatment suggestions based on different symptoms of users, improving the flexibility of the online consultation process and enhancing the accuracy of online consultation processing.

[0073] This application introduces an immersive AI clinic that closely resembles the offline consultation process, reducing the psychological burden of online medical treatment, improving the online user experience, and increasing professionalism and trust. A general-purpose model is used for triage, while specialized models handle subsequent processes such as initial / follow-up consultations, doctor inquiries, and treatment suggestions. This allows users to consult different specialized models (i.e., different departmental AI models) for different symptoms, just like seeing a doctor in a real hospital, enhancing user experience and trust, increasing the flexibility of the online consultation process, and improving the accuracy of online consultation processing.

[0074] Figure 3 This is a schematic diagram of the overall flow of an online consultation processing method according to one embodiment of this application. In a medical scenario, for example, a user clicks on the AI ​​consultation room (i.e., online consultation room) entrance (wherein, the interface can provide the AI ​​consultation room entrance in various ways, for example, directly displayed in the bottom service area of ​​the APP homepage, for example, such as...). Figure 4a Entry point 1 is shown; for example, using a general large model, after a dialogue with the user, an AI clinic card is recommended for the user to click and enter, as shown in the example. Figure 4a Entrance 2) shown indicates access to the online consultation room; Triage (assessment of initial / follow-up visits): Determine whether there have been any symptom consultations in the online clinic within a preset time period (e.g., within 30 days). For example, determine whether the user has consulted about symptoms through the AI ​​clinic within 30 days. If so, that is, within a preset time period (e.g., within 30 days), the user has consulted about symptoms through the AI ​​clinic (i.e., the user's historical symptom consultation data in the online clinic is not empty within the preset time period), then the keywords from the previous round (e.g., sprained ankle) will be extracted to provide a follow-up consultation prompt (e.g., such as...). Figure 4c As shown, we discussed ankle sprains last time. Would you like to continue the consultation? Of course, you can also directly state other questions. In response to the user clicking the "Continue" button (e.g....), Figure 4c As shown), it will automatically send "Continue to consult about sprained ankle issues" (e.g. Figure 4c As shown); based on the user's response (e.g., "Continue consulting about ankle sprains"), triage is performed to determine the relevant specialist model for the user's condition (e.g., ankle sprain), and a follow-up consultation process is executed. Of course, the user can also choose not to click the "Continue" button and directly enter a new question. For example, in response to the user not clicking the "Continue" button but directly entering a new question (e.g., ...), the execution entity... Figure 4d (As shown): "It rained yesterday, and I had a sore throat and a stuffy nose when I got home." Based on this user's response (e.g., a new question "It rained yesterday, and I had a sore throat and a stuffy nose when I got home"), triage is performed to determine the specialist model corresponding to the user's symptoms (e.g., sore throat, stuffy nose), and the initial diagnosis process is executed. When prompting for a follow-up consultation and guiding the user to a follow-up consultation, the latest symptom consultation intent dialogue content is summarized, and keywords are converged for guidance. The converged keywords must be less than or equal to 10 characters, for example, sprained ankle, cold, diarrhea, polycystic ovary syndrome, meniscus injury, etc., to generate guidance text. For example, the guidance text can be: Last time we talked about {xxx}, would you like to continue consulting? Of course, you can also directly say other questions. Here, {xxx} in the guidance text is the converged keyword mentioned above. In the guidance text, the style of the keywords can be set: keyword color, leading and trailing spaces, etc., to highlight the keywords and make them easy for users to see. The user clicks the "Continue" button (e.g., Figure 4c As shown in the image, the system will automatically send a message asking "Continue to consult on {xxx} issues". In exceptional circumstances, such as when a follow-up consultation prompts that no summary results have been received for an extended period, or when the user directly enters a new question, the initial consultation process can be executed, guiding the user to upload the report. If not, meaning the user has not consulted about symptoms through the AI ​​clinic within the preset time (e.g., within 30 days) (i.e., the user's historical symptom consultation data in the online clinic is empty within the preset time), or the user has not confirmed the follow-up consultation prompt (i.e., has not clicked the "Continue" button), then it will be treated as an initial consultation, guiding the user to express their chief complaint, such as... Figure 4b As shown, the text guiding the main complaint could be: "If it's convenient, you can send me your previous examination results so I can better answer your questions," followed by an "Upload" button. Users can click the "Upload" button to upload relevant reports / examination results. Furthermore, as... Figure 3As shown, during the process of guiding users to express their main complaints, it is also possible to determine whether the user's inquiry is a medical or health issue. If not, it means that it cannot be answered. If it is, it continues to determine whether it is a consultation / symptom consultation. If not, it asks follow-up questions and answers based on the user's questions and health knowledge (i.e., makes a basic judgment). If it is, it conducts triage, determines the major specialty model corresponding to the user's symptoms, and executes the initial diagnosis process.

[0075] Chief complaint expression & follow-up questioning and judgment: After triage, a specialized big data model corresponding to the user's symptoms will provide an answer based on medical information: it can make a basic diagnosis by combining memory data (if any, historical information / historical records), chief complaint data, departmental knowledge base and treatment ideas (prompt words), and can give a final diagnosis by asking follow-up questions (e.g., think about the following x questions).

[0076] Final diagnosis & service recommendation: A final diagnosis is given by asking follow-up questions (e.g., consider the following x questions). For example, the output of treatment suggestions can be summarized as one or more of the following: self-medication, further offline examination, health management, risk warning, etc. The output treatment suggestions can be recorded and archived.

[0077] In this application, during the initial consultation process, when the user enters the stage of expressing their chief complaint and asking follow-up questions, 4-6 questions will be asked to assess their current condition. Each time the user answers a question, the progress bar advances until it reaches 100%, at which point a summary assessment and recommendations are provided. Users can answer by clicking on options (e.g., clicking on one or more of the displayed options: fever, cough, phlegm, headache, general weakness, etc.) or by manually entering their answers (e.g., clicking the "Enter Manually" option). After each answer, explanations and analyses will be provided based on the latest information, and the list of questions to be answered will be updated accordingly. Users can clearly see the list of questions to be answered, information on answered questions, and the specific progress percentage. If necessary during the online consultation, users will be guided to upload historical examination and test reports (e.g., if you have an X-ray / your recent blood test report, please send it to me so I can make a comprehensive assessment) to obtain more information and assist in the judgment. If a user chooses to exit midway, there is a two-hour retention mechanism, allowing them to re-enter the unfinished consultation room for further consultation later. Alternatively, users can exit directly without retention, with the next session being a new session. For example, in response to a request to exit the consultation, the following action is performed: Figure 4fThe system displays an exit query (e.g., you can choose to retain the current consultation progress and re-enter within two hours to continue the communication, with options "Retain Progress and Exit" or "Exit Directly"). It retrieves the user's choice of exit option (e.g., the user can choose "Exit Directly" or "Retain Progress and Exit"). If the option selection corresponds to "Exit Directly," the online consultation ends. If the option selection corresponds to "Retain Progress and Exit," the online consultation is retained for a preset duration. If the user re-enters the online consultation room within the preset duration, the remaining online consultation process continues. If the user does not re-enter the online consultation room within the preset duration, the online consultation ends. Once all follow-up questions are completed and the progress reaches 100%, a complete judgment and conclusion will be output. For medical treatment, see the following... Figure 4g The doctor cards shown guide users to online consultations. Users can click the "More" button in the lower right corner of the doctor card to view more related doctors, and are reminded that they can continue to ask other questions, such as, "If you have any other new questions, you can start a new consultation."

[0078] For example, during the initial consultation process, a progress bar is displayed throughout the entire consultation process, including the overall progress and the specific progress percentage during the inquiry phase. Figure 4d As shown, after triage, the dialogue flow card is initially located below the new question (e.g., "My throat hurts and my nose is a little stuffy after the rain yesterday"), but this is temporary. It will quickly (1-2 seconds) be moved to the top, and the dialogue flow card (e.g., ...) will be moved to the top. Figure 4e As shown, this dialogue flow card can be in a collapsed or expanded state during the consultation process, and in a completed state at the end of the consultation. The card displays the overall stage (which can be updated according to progress), consultation status (initial / follow-up visit, follow-up question progress - percentage aligned (rounded to the nearest integer)), a question list (collapsed by default, which can summarize and display answers and status; for example, initial visit: consider the following x questions; follow-up visit: analyze previous medical records, and update the text according to progress), and image and department tags, prompting the user to consider the following x questions. For example,... Figure 4e As shown, users are prompted to consider the following four questions: Does the patient have a fever or cough? What is the color of their sputum? Whether medication was taken, and how effective it was; Are there any people around you with colds? Is there an issue with xxxx?

[0079] As users answer the above questions, the follow-up question progress is updated in real time (i.e., the specific progress percentage is updated, for example, ...). Figure 4eAs shown, the progress progresses from 20% to 67% to 100%, and the results of the responses are summarized and displayed (e.g., fever and cough are present; medication was taken but the effect was not significant; no one around has a cold; no xxxx questions are found) and status (where, for example...). Figure 4e As shown, a checkmark (√) in front of a question (i.e., a consultation question) indicates that it has been answered, while a dot (·) in front of a question (i.e., a consultation question) indicates that it is pending an answer.

[0080] Each time a user's symptoms are addressed, the specialized medical model can access historical records (analyzing relevant content such as "female, 20 years old, past medical history: headache; family history, etc.") and user profile information (reading profile data (scrolling display)). Combining this with hundreds of thousands of data points, it searches for a personalized answer, highlighting the unique individual differences. Specifically, during the initial consultation process, this specialized medical model generates treatment suggestions based on the user's answers to the consultation questions, as well as relevant profile data and chief complaint data, and pushes these suggestions to the user's device.

[0081] For example, the specialized model corresponding to the user's symptoms might output the following treatment suggestions for the new problem "My throat hurts and my nose is a little stuffy after getting home from yesterday's rain": This answer is based on [Little A's] profile: Basic information: Gender: Female, Age: 20, Height: To be added, Weight: To be added; Health history: Past medical history: None, Allergies: Pollen allergy, Surgical history: None, Family history: Hypertension, diabetes, heart disease…; Considering you are a 20-year-old young woman, and your father has hypertension, diabetes, and heart disease, the situation you described requires further observation… Possible cause: From a medical perspective, your sore throat and nasal congestion symptoms after being caught in the rain yesterday are very likely due to an upper respiratory tract infection. Getting chilled after being rained on can temporarily lower your immunity, making you more susceptible to infections from viruses, bacteria, and other pathogens. Further information is needed for an accurate diagnosis.

[0082] • Medical advice and treatment recommendations: For a sore throat, gargle with warm salt water: Dissolve half a teaspoon of salt in about 240 ml of warm water and gargle several times a day to reduce swelling and discomfort. Drink plenty of warm fluids: warm water, honey lemon water, light soup, or herbal tea. Honey is very effective in relieving coughs and sore throats. Suck on throat lozenges or hard candies; this promotes saliva production and keeps the throat moist. Over-the-counter medications: Pain relievers: such as xxx, can effectively relieve pain and reduce inflammation. Please follow the instructions for use and avoid repeated use. Topical sprays or lozenges: such as throat sprays or lozenges containing antiseptic and analgesic ingredients. For nasal congestion, use saline nasal spray / rinse: the safest and non-addictive method. You can purchase ready-made saline sprays or use a nasal irrigator with a special saline pack to rinse the nasal cavity, which can wash away secretions and allergens and reduce swelling. Steam inhalation: When safe to do so, use a hot water cup to steam or take a hot shower to breathe in moist air. Elevate your head: Using an extra pillow while sleeping helps reduce sinus congestion using gravity. Over-the-counter medications: Decongestant nasal sprays (e.g., xxx): These are highly effective, but should not be used continuously for more than 3-5 days, otherwise it may lead to drug-induced rhinitis (with a more severe rebound). Oral decongestants (e.g., xxx): These can constrict blood vessels to relieve nasal congestion, but may cause increased heart rate and blood pressure; patients with hypertension or heart disease should use them with caution. Antihistamines (e.g., xxx): If allergies are suspected, these medications are more effective for sneezing and runny nose, but have limited effectiveness for nasal congestion caused by the common cold.

[0083] • Lifestyle advice: Get plenty of rest and boost your immunity: This is the most fundamental way to fight the virus. Sleep more and reduce fatigue. Drink plenty of water: Staying hydrated helps dilute secretions. Maintain a balanced diet: Even if you have a poor appetite, try to eat easily digestible and nutritious foods. Wash your hands frequently and wear a mask: To prevent infecting others or cross-infection. Use medication with caution: Carefully read the instructions for use, especially for compound cold medicines, and avoid taking the same ingredients repeatedly to prevent overdose.

[0084] For example, when performing a follow-up consultation, the specialist big data model obtains the user's memory data, archival data, and chief complaint data. Based on the memory data (e.g., the last consultation was on September 2nd regarding a sprained ankle), archival data (e.g., basic information: gender: female, age: 20, height: to be added, weight: to be added; health history: past medical history: none, allergies: pollen allergy, surgical history: none, family history: hypertension, diabetes, heart disease, etc.), and chief complaint data (e.g., "Continue with the sprained ankle problem, why am I recovering so slowly"), treatment suggestions are generated and pushed to the user's device.

[0085] For example, the specialized big data model corresponding to the user's condition, in response to the follow-up question, "Continuing with the sprained ankle, why is my recovery so slow?", would reply, "I am still your previous AI orthopedic doctor. You last consulted on September 2nd, which is over a week ago. I'm sorry you feel the recovery is slow, but don't worry, I'll ask you a few questions from a professional perspective. It's possible that your ankle is improving." The treatment suggestions output based on the user's answers to follow-up questions could be as follows: This answer is based on [Little A's] profile: Basic information: Gender: Female, Age: 20, Height: To be added, Weight: To be added; Health history: Past medical history: None, Allergies: Pollen allergy, Surgical history: None, Family history: Hypertension, diabetes, heart disease…; Considering you are a 20-year-old young woman, and your father has hypertension, diabetes, and heart disease, the situation you described requires further observation… • More severe injuries: such as partial tearing or even complete rupture of ligaments, the recovery time is long and may take several weeks or even months.

[0086] • Incorrect treatment: If you do not rest and immobilize your ankle in time after a sprain and continue to move around frequently, it will affect the healing process; applying heat in the early stages may also aggravate local swelling and bleeding, which is not conducive to recovery.

[0087] • Complications: Complications such as traumatic arthritis and avulsion fractures can also lead to delayed recovery.

[0088] In some embodiments, such as Figure 4h As shown, if a user suddenly changes the questions they ask during a follow-up consultation, for example, by asking a new question like "I've been getting a lot of rashes lately, what's going on?", the current specialty model can then answer the question "I've been getting a lot of rashes lately, what's going on?": the question is no longer internal medicine, and the model will switch you to dermatology.

[0089] A dermatologist responded: It's springtime pollen season, and skin sensitivity is common. I have a few questions for you to help me provide better treatment advice. What color is this rash, and how big is it? Does it cover a large area of ​​the body?

[0090] Based on the users' answers to these follow-up questions, the diagnostic and treatment recommendations generated by the dermatology specialty model can be as follows: This answer is based on [Little A's] profile: Basic information: Gender: Female, Age: 20, Height: To be added, Weight: To be added; Health history: Past medical history: None, Allergies: Pollen allergy, Surgical history: None, Family history: Hypertension, diabetes, heart disease…; Considering you are a 20-year-old young woman, and your father has hypertension, diabetes, and heart disease, the situation you described requires further observation… Do not self-diagnose as pollen allergy; similar symptoms may be caused by other reasons. Please seek medical attention for a proper diagnosis.

[0091] If you are diagnosed with pollen allergy, pay attention to pollen concentration forecasts: check them daily during pollen season and reduce outdoor activities when concentrations are high.

[0092] Wear an effective pollen-proof mask and well-sealed windproof glasses.

[0093] Upon returning home, immediately wash your face, rinse your nasal cavity, gargle, and change your outer clothing.

[0094] • Indoor protection: During peak pollen season, close doors and windows and use a fresh air system or air purifier. Avoid drying clothes and bedding outdoors.

[0095] • Medication strategy: For seasonal allergies, a "stepwise treatment" and "anticipatory treatment" approach is recommended. This means starting to use nasal corticosteroids or other medications 1-2 weeks before pollen season to ensure sufficient drug concentration in the body when allergy peaks, resulting in better control.

[0096] The above answers are merely examples, and this application does not impose specific limitations on the answers for the college model.

[0097] This application introduces an immersive AI clinic that closely resembles the offline consultation process, reducing the psychological burden of online medical treatment, improving the online user experience, and increasing professionalism and trust. A general-purpose model is used for triage, while specialized models handle subsequent processes such as initial / follow-up consultations, doctor inquiries, and treatment suggestions. This allows users to consult different specialized models (i.e., different departmental AI models) for different symptoms, just like seeing a doctor in a real hospital, enhancing user experience and trust, increasing the flexibility of the online consultation process, and improving the accuracy of online consultation processing.

[0098] Figure 5 This is a schematic diagram of the main units of an online consultation processing device installed on a server side according to an embodiment of this application. Figure 5 As shown, the online consultation processing device 500 includes an acquisition unit 501, a guidance unit 502, a triage unit 503, and a treatment unit 504.

[0099] The acquisition unit 501 is configured to acquire historical symptom consultation data of the user in the online clinic within a preset time period in response to the user's trigger operation on the online clinic control.

[0100] The guidance unit 502 is configured to generate guidance text based on the historical symptom consultation data and push the guidance text to the user terminal in response to the historical symptom consultation data being non-empty.

[0101] Triage unit 503 is configured to receive response data to the guidance text returned by the user terminal, and perform triage based on historical symptom consultation data and response data to determine the specialty big data model.

[0102] The diagnosis and treatment unit 504 is configured to, during the initial diagnosis process, have a specialized big data model engage in follow-up questioning and interaction with the user based on preset consultation questions, in order to obtain the user's answer data for the preset consultation questions, acquire the user's relevant file data and chief complaint data, generate diagnosis and treatment suggestions based on the file data, chief complaint data and answer data, and push the diagnosis and treatment suggestions to the user.

[0103] In some embodiments, the treatment unit 504 is further configured to: in the case of performing a follow-up visit process, obtain memory data, archival data and chief complaint data related to the user from the specialist big data model; generate treatment suggestions based on the memory data, archival data and chief complaint data, and push the treatment suggestions to the user terminal.

[0104] In some embodiments, the guidance unit 502 is further configured to: extract symptom-related keywords from historical symptom consultation data, and generate guidance text for continued consultation based on the keywords.

[0105] In some embodiments, the triage unit 503 is further configured to: execute a follow-up consultation process in response to reply data corresponding to continued consultation, and determine the target department based on historical symptom consultation data; execute an initial consultation process in response to reply data remaining empty for a preset time, push the chief complaint guidance text to the user terminal, receive response data returned by the user terminal regarding the chief complaint guidance text, and determine the target department based on the response data, wherein the chief complaint guidance text includes report upload guidance text; determine the target department based on reply data corresponding to a new question in response to reply data; and determine a specialty big data model based on the target department.

[0106] In some embodiments, the diagnosis and treatment unit 504 is further configured to: generate diagnosis and treatment suggestion words based on the archive data, chief complaint data, and answer data; and have the specialty big data model search the departmental knowledge base based on the diagnosis and treatment suggestion words, and generate diagnosis and treatment suggestions based on the search results.

[0107] In some embodiments, the online consultation processing device also includes Figure 5 The progress update unit, not shown in the diagram, is configured to: update the overall medical treatment progress and the specific progress percentage under the inquiry status in real time, and push the overall medical treatment progress and the specific progress percentage under the inquiry status to the user terminal in real time.

[0108] In some embodiments, the progress update unit is further configured to update the overall medical progress and the specific progress percentage in the inquiry state once in response to detecting that the user has completed answering any medical question.

[0109] In some embodiments, the online consultation processing device also includes Figure 5 The consultation question list update unit (not shown) is configured to: update the summary answer results and status of each preset consultation question in the consultation question list in real time; and push the expanded consultation question list to the user terminal in response to the user's trigger operation of the drop-down button; wherein the consultation question list is associated with the drop-down button and the status includes pending answer and answered status.

[0110] In some embodiments, the online consultation processing device also includes Figure 5 The online consultation exit processing unit (not shown) is configured to: respond to an exit request, execute an exit query, and obtain the user's option selection data for the exit query; respond to the option selection data corresponding to direct exit, ending the current online consultation; respond to the option selection data corresponding to exit with progress saved, saving the current online consultation for a preset duration, and when the user re-enters the online consultation room within the preset duration, continue the remaining online consultation process; when the user does not re-enter the online consultation room within the preset duration, end the current online consultation. The online consultation room corresponds to the online consultation room control triggered by the user.

[0111] It should be noted that the online consultation processing method and the online consultation processing device in this application are related in terms of specific implementation content, so the repeated content will not be described again.

[0112] Figure 6 This is a schematic diagram of the main units of an online consultation processing device installed on a user terminal according to an embodiment of this application. Figure 6 As shown, the online consultation processing device 600 includes a guidance text display unit 601, an interaction unit 602, and a treatment suggestion display unit 603.

[0113] The guidance text display unit 601 is configured to receive and display guidance text pushed by the server to the user, obtain user response data to the guidance text, and push the response data to the server.

[0114] The interaction unit 602 is configured to interact with the triage-determined specialty model on the server side based on preset consultation questions, obtain the user's answer data for the preset consultation questions, and return the answer data to the server side.

[0115] The treatment suggestion display unit 603 is configured to receive and display treatment suggestions pushed from the server to the user.

[0116] In some embodiments, the online consultation processing device also includes Figure 6The main complaint guidance text display unit (not shown) is configured to: receive and display the main complaint guidance text pushed by the server to the user, and push user response data to the main complaint guidance text to the server, wherein the response data includes report data.

[0117] In some embodiments, the online consultation processing device also includes Figure 6 The progress display unit, not shown, is configured to receive and display the overall medical progress and the specific progress percentage in the inquiry state pushed by the server.

[0118] In some embodiments, the online consultation processing device also includes Figure 6 The consultation question list display unit (not shown) is configured to receive and display an expanded consultation question list pushed by the server to the user; wherein the consultation question list displays a summary answer result and status for each preset consultation question, and the status includes a pending answer status and an answered status.

[0119] In some embodiments, the interaction unit 602 is further configured to: acquire user option click data and / or manual input data; and determine and acquire user answer data for preset consultation questions based on the option click data and / or manual input data.

[0120] It should be noted that the online consultation processing method and the online consultation processing device in this application are related in terms of specific implementation content, so the repeated content will not be described again.

[0121] Figure 7 An exemplary system architecture 700 is shown that can be applied to the online consultation processing method or online consultation processing device according to the embodiments of this application.

[0122] like Figure 7 As shown, system architecture 700 may include terminal devices 701, 702, and 703, a network 704, and a server 705. Network 704 serves as the medium for providing communication links between terminal devices 701, 702, and 703 and server 705. Network 704 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0123] Users can use terminal devices 701, 702, and 703 to interact with server 705 via network 704 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 701, 702, and 703, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0124] Terminal devices 701, 702, and 703 can be various electronic devices with online consultation processing screens and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0125] Server 705 can be a server providing various services, such as a backend management server supporting user trigger operations on online consultation room controls using terminal devices 701, 702, and 703 (for example only). The backend management server can respond to user trigger operations on online consultation room controls by obtaining the user's historical symptom consultation data within a preset time period; if the historical symptom consultation data is not empty, it generates guidance text based on the historical symptom consultation data and pushes the guidance text to the user's terminal; it receives the user's response data to the guidance text, and triages patients based on the historical symptom consultation data and response data to determine the specialty model; in the case of executing the initial diagnosis process, the specialty model interacts with the user based on preset consultation questions to obtain the user's response data to the preset consultation questions, obtain user-related file data and chief complaint data, and generate treatment suggestions based on the file data, chief complaint data, and response data, and push the treatment suggestions to the user's terminal. By introducing an immersive online consultation room that closely resembles the offline medical process, the psychological burden on patients seeking medical care online is reduced, the online user experience is improved, and professionalism and trust are enhanced. Through triage, a specialized model is determined, which then completes subsequent processes such as initial / follow-up visits, doctor consultations, and treatment suggestions. This allows users to consult different specialized models for different symptoms, providing targeted treatment suggestions and improving the flexibility and accuracy of the online consultation process.

[0126] It should be noted that the online consultation processing method provided in this application embodiment is generally executed by server 705, and correspondingly, the online consultation processing device is generally set in server 705.

[0127] It should be understood that Figure 7 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0128] The following is for reference. Figure 8 It shows a schematic diagram of the structure of a computer system 800 suitable for implementing a terminal device according to the embodiments of this application. Figure 8 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0129] like Figure 8As shown, the computer system 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 802 or programs loaded from storage section 808 into random access memory (RAM) 803. The RAM 803 also stores various programs and data required for the operation of the computer system 800. The CPU 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0130] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 810 as needed so that computer programs read from it can be installed into storage section 808 as needed.

[0131] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit (CPU) 801, it performs the functions defined above in the system of this application.

[0132] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0133] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0134] The units described in the embodiments of this application can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may include an acquisition unit, a guidance unit, a triage unit, and a treatment unit. Alternatively, a processor may include a guidance text display unit, an interaction unit, and a treatment suggestion display unit. The names of these units do not necessarily limit the specific unit itself.

[0135] In another aspect, this application also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs that, when executed by the device, cause the device to respond to a user's trigger operation on the online consultation room control, acquire the user's historical symptom consultation data in the online consultation room within a preset time; responding to the historical symptom consultation data being non-empty, generate guidance text based on the historical symptom consultation data and push the guidance text to the user terminal; receive the user terminal's response data to the guidance text, and triage based on the historical symptom consultation data and response data to determine a specialized big data model; in the case of executing the initial diagnosis process, the specialized big data model interacts with the user terminal based on preset consultation questions to obtain the user terminal's answer data to the preset consultation questions, acquire user-related file data and chief complaint data, and generate treatment suggestions based on the file data, chief complaint data, and answer data, and push the treatment suggestions to the user terminal.

[0136] The computer program product of this application includes a computer program that, when executed by a processor, implements the online consultation processing method in the embodiments of this application.

[0137] According to the technical solution of this application embodiment, by introducing an immersive online consultation room that closely resembles the offline consultation process, the psychological burden of online medical treatment for users is reduced, the online user experience is improved, and professionalism and trust are increased. Through triage, a specialized model is determined, and the specialized model determined by the triage completes the subsequent processes such as initial / follow-up consultation, doctor consultation, and treatment suggestions. This allows users to consult different specialized models of different departments for different symptoms, so as to provide targeted treatment suggestions for users with different symptoms, improve the flexibility of the online consultation process, and enhance the accuracy of online consultation processing.

[0138] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An online consultation processing method, characterized in that, Applied to the server side, the method includes: In response to a user's triggering action on the online consultation room control, the system retrieves the user's historical symptom consultation data in the online consultation room within a preset time period. In response to the historical symptom consultation data being non-empty, a guiding message is generated based on the historical symptom consultation data and pushed to the user's terminal; Receive response data from the user terminal regarding the guidance text, and perform triage based on the historical symptom consultation data and the response data to determine the specialty big data model; During the initial diagnosis process, the specialized big data model engages in follow-up questioning with the user based on preset consultation questions to obtain the user's response data to the preset consultation questions, acquire the user's relevant medical records and chief complaint data, and generate treatment suggestions based on the medical records, chief complaint data, and response data, and push the treatment suggestions to the user.

2. The method according to claim 1, characterized in that, After determining the specialty model based on the historical symptom consultation data and the response data, the method further includes: During the follow-up visit process, the specialized big data model obtains memory data, record data, and chief complaint data related to the user. Based on the memory data, the archive data, and the chief complaint data, a treatment suggestion is generated and pushed to the user's terminal.

3. The method according to claim 1, characterized in that, The step of generating guiding text based on the historical symptom consultation data includes: Extract symptoms-related keywords from the historical symptom consultation data, and generate guiding text for continued consultation based on the keywords.

4. The method according to claim 1, characterized in that, The triage process based on the historical symptom consultation data and the response data to determine the specialty model includes: In response to the reply data corresponding to a continued consultation, a follow-up consultation process is executed, and the target department is determined based on the historical symptom consultation data; In response to the fact that the reply data remains empty for a preset time, the initial diagnosis process is executed, the chief complaint guidance text is pushed to the user terminal, the response data returned by the user terminal for the chief complaint guidance text is received, and the target department is determined based on the response data, wherein the chief complaint guidance text includes report upload guidance text; In response to the new question corresponding to the response data, the target department is determined based on the response data; Based on the target department, a specialized large model is determined.

5. The method according to claim 1, characterized in that, The process of generating treatment recommendations based on the file data, the chief complaint data, and the response data includes: Based on the file data, the chief complaint data, and the response data, generate diagnostic and treatment approach prompts; The specialized big data model searches the department's knowledge base based on the diagnostic and treatment approach prompts, and generates diagnostic and treatment suggestions based on the search results.

6. The method according to claim 1, characterized in that, In the process of performing the initial diagnosis procedure, during which the specialized big data model interacts with the user based on preset consultation questions, the method further includes: The system updates the overall medical treatment progress and the specific progress percentage under the inquiry status in real time, and pushes the overall medical treatment progress and the specific progress percentage under the inquiry status to the user's terminal in real time.

7. The method according to claim 6, characterized in that, The real-time updates of the overall medical progress and the specific progress percentage under the inquiry status include: In response to detecting that the user has completed answering any of the consultation questions, the overall consultation progress and the specific progress percentage under the consultation status are updated once.

8. The method according to claim 1, characterized in that, In the process of performing the initial diagnosis procedure, during which the specialized big data model interacts with the user based on preset consultation questions, the method further includes: Real-time updates of summary answers and status for each preset consultation question in the consultation question list; In response to the user's triggering action on the drop-down button, an expanded list of consultation questions is pushed to the user's device; The consultation question list is associated with the drop-down button, and the status includes pending answer and answered status.

9. The method according to claim 1, characterized in that, In the process of performing the initial diagnosis procedure, during which the specialized big data model interacts with the user based on preset consultation questions, the method further includes: In response to the request to exit the consultation, an exit inquiry is executed, and the user's selection data for the exit inquiry is obtained; If the selected option corresponds to exiting directly, the online consultation will end. In response to the selected data corresponding to the "Save Progress and Exit" option, the online consultation is retained for a preset duration. When the user re-enters the online consultation room within the preset duration, the remaining online consultation process continues. When the user does not re-enter the online consultation room within the preset duration, the online consultation ends. The online consultation room corresponds to the online consultation room control triggered by the user.

10. An online consultation processing method, characterized in that, When applied to a user terminal, the method includes: Receive and display the guidance text pushed by the server to the user, obtain the user's response data to the guidance text, and push the response data to the server. The system interacts with the specialized big data model determined by the triage on the server side based on preset consultation questions, obtains the user's answer data to the preset consultation questions, and returns the answer data to the server side. Receive and display treatment suggestions pushed from the server to the user.

11. The method according to claim 10, characterized in that, Before engaging in follow-up questioning with the pre-set diagnostic questions in the specialized large-scale model determined by the server-side triage, the method further includes: Receive and display the main complaint guidance text pushed by the server to the user, and push the user's response data to the main complaint guidance text to the server, wherein the response data includes report data.

12. The method according to claim 10, characterized in that, During the process of interacting with the specialized large model determined by triage on the server side based on preset consultation questions, the method further includes: Receive and pin the overall medical progress and the specific progress percentage under the inquiry status pushed by the server.

13. The method according to claim 10, characterized in that, During the process of interacting with the specialized large model determined by triage on the server side based on preset consultation questions, the method further includes: Receive and display to the user an expanded list of consultation questions pushed from the server; The consultation question list displays summary answers and statuses for each of the preset consultation questions, including pending answers and answered answers.

14. The method according to claim 10, characterized in that, The step of obtaining the user's answer data to the preset medical consultation question includes: Obtain the user's option click data and / or manual input data; Based on the selected data and / or the manually entered data, determine and obtain the user's answer data for the preset consultation question.

15. An online consultation processing device, characterized in that, The device, configured on the server side, includes: The acquisition unit is configured to acquire the user's historical symptom consultation data in the online clinic within a preset time period in response to the user's trigger operation on the online clinic control. The guidance unit is configured to generate guidance text based on the historical symptom consultation data in response to the historical symptom consultation data being non-empty, and push the guidance text to the user terminal. The triage unit is configured to receive response data from the user terminal in response to the guidance text, and to perform triage based on the historical symptom consultation data and the response data to determine the specialty model; The diagnosis and treatment unit is configured to, during the initial diagnosis process, have the specialized big data model engage in follow-up questioning and interaction with the user based on preset consultation questions, in order to obtain the user's response data to the preset consultation questions, acquire the user's file data and chief complaint data, generate diagnosis and treatment suggestions based on the file data, the chief complaint data and the response data, and push the diagnosis and treatment suggestions to the user.

16. An online consultation processing device, characterized in that, The device, located on the user end, includes: The guidance text display unit is configured to receive and display guidance text pushed by the server to the user, obtain the user's response data to the guidance text, and push the response data to the server. The interaction unit is configured to interact with the triage-determined specialty model on the server side based on preset consultation questions, obtain the user's answer data to the preset consultation questions, and return the answer data to the server side. The treatment suggestion display unit is configured to receive and display treatment suggestions pushed from the server to the user.

17. An electronic device for online consultation processing, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-14.

18. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-14.

19. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-14.

Images