Consultation method and apparatus, and electronic device and computer-readable storage medium

Abstract

A consultation method and apparatus, and an electronic device and a computer-readable storage medium. The method comprises: acquiring target disease description information which is input by a user; and feeding back to the user a target diagnosis result about the target disease description information, wherein the determination of the target diagnosis result is related to the target disease description information and assistance diagnosis information, and the assistance diagnosis information comprises target profile information of a target consultation object that is indicated by the target disease description information. By means of the method, a high-quality consultation service can be provided for users.

Description

Inquiry method, device, electronic equipment and computer readable storage medium

[0001] The present application claims priority to the Chinese patent application No. 2024108497092, filed on June 27, 2024, and entitled "Inquiry method, device, electronic equipment and computer readable storage medium", which is incorporated by reference in its entirety.

TECHNICAL FIELD

[0002] The present application relates to the technical field of medicine, in particular to an inquiry method, device, electronic equipment and computer readable storage medium.

BACKGROUND

[0003] At present, the existing inquiry service is generally provided to patients by doctors in person or online. In the case of tight doctor resources, patients need to wait for a long time to get the inquiry result, resulting in low efficiency of obtaining the inquiry result.

SUMMARY

[0004] The technical problem solved by the present application is to provide an inquiry method, device, electronic equipment and computer readable storage medium, which can provide high-quality inquiry service to users.

[0005] To solve the above technical problem, one technical solution adopted by the present application is to provide an inquiry method, comprising: acquiring target disease description information input by a user; feeding back a target diagnosis result about the target disease description information to the user; wherein the determination of the target diagnosis result is related to the target disease description information and auxiliary diagnosis information, and the auxiliary diagnosis information includes target portrait information of a target inquiry object indicated by the target disease description information.

[0006] To solve the above technical problem, another technical solution adopted by the present application is to provide an inquiry device, comprising an acquisition module and a feedback module; the acquisition module is used to acquire target disease description information input by a user; the feedback module is used to feed back a target diagnosis result about the target disease description information to the user; wherein the target diagnosis result is determined in combination with the target disease description information and auxiliary diagnosis information, and the auxiliary diagnosis information includes target portrait information of a target inquiry object indicated by the target disease description information.

[0007] To solve the above technical problem, another technical solution adopted by the present application is to provide an electronic equipment, comprising a processor and a memory, the memory stores program instructions, and the processor is used to execute the program instructions to realize the above inquiry method.

[0008] To solve the above technical problems, another technical solution adopted by the present application is to provide a computer readable storage medium, the computer readable storage medium stores program instructions, the program instructions can be executed to implement the above-mentioned inquiry method.

[0009] The above technical solution, the target diagnosis result is determined in combination with the target disease description information input by the user and the target portrait information of the target inquiry object indicated by the target disease description information, that is, the target diagnosis result is determined according to more comprehensive information of the target inquiry object, so that the determined target diagnosis result is more accurate; therefore, the target diagnosis result about the target disease description information fed back to the user is accurate, and the user is provided with high-quality inquiry service. In addition, the target inquiry object indicated by the target disease description information is inquired through online interaction with the user, and the user is provided with convenient inquiry service. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0011] Fig. 1 is a flowchart of an embodiment of the inquiry method provided by the present application;

[0012] Fig. 2 is a schematic diagram of an embodiment of the interactive interface provided by the present application;

[0013] Fig. 3 is another embodiment of the interactive interface provided by the present application;

[0014] Fig. 4 is a flowchart of another embodiment of the inquiry method provided by the present application;

[0015] Fig. 5 is a flowchart of an embodiment of step S41 shown in Fig. 4;

[0016] Fig. 6 is a flowchart of an embodiment of step S43 shown in Fig. 4;

[0017] Fig. 7 is a structural schematic diagram of an embodiment of the inquiry device provided by the present application;

[0018] Fig. 8 is a structural schematic diagram of an embodiment of the electronic device provided by the present application;

[0019] Fig. 9 is a structural schematic diagram of an embodiment of the computer readable storage medium provided by the present application.

CONCRETE EMBODIMENT

[0020] The technical solutions of the embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0021] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, interfaces, techniques, etc. in order to provide a thorough understanding of the application.

[0022] The term "and / or", merely describes association relationship of associated objects, which means that there can be three relationships, for example, A and / or B, which can represent three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are an "or" relationship. In addition, "multiple" in this paper means two or more than two. In addition, the term "at least one" in this paper means any one of multiple or any combination of at least two of multiple, for example, including at least one of A, B and C, which can mean including any one or more elements selected from the set consisting of A, B and C.

[0023] Please refer to FIG. 1, which is a flowchart of an embodiment of the method for inquiring provided by the present application. It should be noted that the embodiment is not limited to the order of the flowchart shown in FIG. 1 if there is substantially the same result. As shown in FIG. 1, the embodiment includes:

[0024] Step S11: obtaining target disease description information input by a user.

[0025] In this embodiment, the target disease description information input by the user is obtained. Specifically, as shown in FIG. 2, which is a schematic diagram of an embodiment of the interactive interface provided by the present application, the interactive interface can be understood as an inquiry interface. The user inputs the target disease description information in the dialogue box of the exchange interface and confirms to complete the input of the target disease description information, so that the target disease description information input by the user can be obtained.

[0026] Wherein, the number of symptoms, the type of symptoms, and the disease type to which the symptoms belong involved in the target disease description information input by the user are not limited, and the user can input according to the actual situation. Since diverse training data is used in training, inquiry for more different patients can be provided, and inquiry errors such as rich inquiry and deviation from the core can be avoided. The inquiry will follow the inherent medical knowledge and proceed according to the diagnosis points.

[0027] For example, as shown in FIG. 2, the target disease description information input by the user is "I feel a little dizzy today". For another example, the target disease description information input by the user is "I have been sneezing recently". For another example, the target disease description information input by the user is "I have been coughing and short of breath recently". For another example, the target disease description information input by the user is "I have been feeling weak in limbs recently".

[0028] Step S12: feedback to the user the target diagnosis result about the target illness description information.

[0029] In this embodiment, the target diagnosis result about the target illness description information is fed back to the user, wherein the determination of the target diagnosis result is related to the target illness description information and the auxiliary diagnosis information, that is, the target diagnosis result is obtained in combination of the target illness description information and the auxiliary diagnosis information, and the auxiliary diagnosis information includes the target portrait information of the target interviewee indicated by the target illness description information. The combination of the target illness description information and the auxiliary diagnosis information provides more comprehensive information of the target interviewee, so as to provide more accurate diagnosis for the target interviewee; that is, the target diagnosis result determined in combination of the target illness description information input by the user and the target portrait information of the target interviewee indicated by the target illness description information is more accurate.

[0030] The target diagnosis result is determined in combination of the target illness description information input by the user and the target portrait information of the target interviewee indicated by the target illness description information, that is, the target diagnosis result is determined according to more comprehensive information of the target interviewee, so the target diagnosis result determined is more accurate; therefore, the target diagnosis result about the target illness description information fed back to the user is accurate, and high-quality interview service is provided to the user. In addition, the target interviewee indicated by the target illness description information is interviewed through online interaction with the user, and convenient interview service is provided to the user.

[0031] It should be noted that if the interviewee (such as the user himself / herself, the user's daughter, the user's mother, etc.) can be determined from the target illness description information input by the user, the interviewee is taken as the target interviewee; and if the interviewee cannot be determined from the target illness description information input by the user (such as the user inputting "feeling dizzy today", and the interviewee cannot be determined), considering the habit of expression, it should be said that the user himself / herself is the interviewee.

[0032] In an embodiment, the target illness description information input by the user is not comprehensive, and the target diagnosis result cannot be directly determined based on the target illness description information input by the user, at this time, the user will be fed back the to-be-supplemented information, the to-be-supplemented information is the illness description information missing in the determination of the target diagnosis result; the user inputted supplementary illness description information is acquired; the target diagnosis result determined based on the supplementary illness description information, the target illness description information and the target portrait information of the target interviewee is fed back to the user. That is, the user will be actively interviewed, and the target diagnosis result will be determined through multiple rounds of interaction with the user.

[0033] For example,

user input

disease summary

interview direction 1

interview direction 2

feedback

user supplementary input

disease summary

candidate diagnosis

interview direction 1

interview direction 2

feedback

user supplementary input

[0034] That is, the thought chain (disease summary, candidate diagnosis, next step of interview plan, interview question) is adopted when interacting with the user, mainly to make diagnosis first, and then make further inquiry.

[0035] For example, as shown in FIG. 2, the target disease description information input by the user is "I feel a little dizzy today"; as shown in FIG. 3, which is another embodiment of the interactive interface provided by the present application, since the user's description of the disease is not comprehensive, diagnosis cannot be performed, and therefore the user is fed back the to-be-supplemented information "Hello, could you please describe your dizziness in detail? For example, is it sudden or continuous, do you have a spinning sensation, are you accompanied by symptoms such as nausea and vomiting?"

[0036] In other embodiments, the target disease description information input by the user is comprehensive, and the target diagnosis result can be directly determined based on the target disease description information input by the user. In this case, the target diagnosis result is directly determined based on the target disease description information input by the user.

[0037] In a specific embodiment, when the to-be-supplemented information fed back to the user is "what medicine have you taken recently", that is, when the user is actively asked about what medicine has been taken recently, the user can directly input the medication information or upload a picture of the medicine box, and the medication information can be obtained by analyzing the picture of the medicine box.

[0038] In a specific embodiment, when the to-be-supplemented information fed back to the user is "what medical examination have you done recently", that is, when the user is actively asked about what medical examination has been done recently, the user can directly input the medical examination information or upload a picture of the medical examination report.

[0039] In an embodiment, the auxiliary diagnosis information further includes historical inquiry information of the target inquiry object, that is, the target diagnosis result is determined in combination with the historical inquiry information of the target inquiry object, the portrait information of the target inquiry object and the target disease description information input by the user. The combination of the target disease description information input by the user and the target portrait information of the target inquiry object provides more comprehensive information of the target inquiry object; the historical inquiry information of the target inquiry object records the medical experience, treatment response and disease change of the target inquiry object, and provides the dynamic change process of the disease of the target inquiry object. Therefore, in combination with the historical inquiry information of the target inquiry object, the target portrait information of the target inquiry object and the target disease description information input by the user, the target diagnosis result is more accurate, that is, the target diagnosis result fed back to the user about the target disease description information is more accurate, and high-quality inquiry service is provided to the user.

[0040] In an embodiment, the content covered by the target portrait information is not limited, and can be specifically set according to actual use needs. For example, the target portrait information includes population, gender, age, height, weight, disease history, operation history, medication history, etc.

[0041] In an embodiment, the target diagnosis result can include one of disease analysis, medical advice, precautions, disease type, etc., without limitation. In other embodiments, the target diagnosis result can include at least two of disease analysis, medical advice, precautions, disease type, etc., without limitation.

[0042] For example, taking the target diagnosis result including disease analysis, medical advice and precautions as an example, i.e., taking the target diagnosis result in the form of a syllogism as an example.

User input

Disease summary

Interview direction 1

Interview direction 2

Feedback

User supplementary input

Disease summary

Candidate diagnosis

Interview direction 1

Interview direction 2

Feedback

User supplementary input

[0043] Among them, the target diagnosis result is specifically:

[0044] Disease analysis: You recently have symptoms such as runny nose, mild sore throat, and mild fever, which are common manifestations of common cold.

[0045] Medical advice: 1. Examination suggestion: It is recommended that you go to the respiratory department of the hospital for further diagnosis and confirmation. Blood routine examination can be performed to check the white blood cell count, and virus nucleic acid detection and virus antigen detection can be performed.

[0046] 2. Treatment suggestion: Cause treatment: If combined with bacterial infection, antibiotics such as cephalosporins, amoxicillin, and roxithromycin may be needed. When combined with viral infection, antiviral drugs such as oseltamivir phosphate capsules can be used, but generally after common viral infection, self-limitation can be used. Symptomatic treatment: You can use compound amphenicol amide tablets and other drugs under the guidance of a doctor to relieve symptoms such as runny nose and nasal congestion. If the fever is more than 38.5℃, you can consider using ibuprofen or acetaminophen tablets.

[0047] Precautions: 1. Crowd: Please try to avoid going to crowded places to prevent infection of other pathogens.

[0048] 2. Sanitation and ventilation: Keep the environment clean and well ventilated to help reduce the spread of viruses.

[0049] 3. Adequate rest: More bed rest, adequate sleep is the key to recovery.

[0050] 4. Diet: Adequately supplement water and nutrients, avoid spicy and irritating foods to avoid irritating the throat.

[0051] The above target diagnosis result is for reference only and cannot replace the diagnosis of professional medical personnel. If the symptoms persist or worsen, please seek medical attention in a timely manner.

[0052] In an embodiment, before the target diagnosis result about the target disease description information is fed back to the user, a second identifier indicating that analysis is in progress is displayed on the interactive interface. It takes a certain analysis time from obtaining the target disease description information input by the user to feeding back the target diagnosis result about the target disease description information to the user; by displaying the second identifier indicating that analysis is in progress on the interactive interface, the user can be intuitively informed that the diagnosis of the target inquiry object is in progress.

[0053] In a specific embodiment, as shown in FIG. 2, the second identifier is the word "analysis in progress".

[0054] In an embodiment, after the user is fed back the target diagnosis result about the target disease description information, a third identifier that analysis is completed is displayed on the interactive interface. It should be noted that the user is fed back the final target diagnosis result, and it can be considered that the analysis is completed. The user is fed back the to-be-supplemented information, and it can also be temporarily considered that the analysis is completed.

[0055] In an embodiment, as shown in FIG. 2, a stop answering word is also displayed on the interactive interface. In response to the user triggering the stop answering word, the user triggers the suspension / termination of the diagnosis service, and the generation of the target diagnosis result based on the target disease description information and the target portrait information input by the user is stopped.

[0056] In a specific embodiment, as shown in FIG. 3, the third identifier is a word “analysis completed”.

[0057] In an embodiment, the user is fed back the target diagnosis result about the target disease description information, specifically: the user is fed back an initial diagnosis result about the target disease description information, wherein the initial diagnosis result is generated in combination with the target disease description information and the auxiliary diagnosis information; and the user is fed back the target diagnosis result, wherein the target diagnosis result is obtained by reviewing the initial diagnosis result. That is, the user is first fed back an initial diagnosis result, and then the user is fed back a target diagnosis result, that is, the initial diagnosis result and the target diagnosis result are fed back to the user in sequence. The target diagnosis result is obtained by reviewing the initial diagnosis result, and the target diagnosis result is more accurate. The user is fed back the accurate target diagnosis result, and high-quality diagnosis services are provided for the user. The initial diagnosis result is reviewed to obtain the target diagnosis result, which requires a certain amount of time. Therefore, the initial diagnosis result is fed back to the user, so that the review of the initial diagnosis result can be performed when the user views the initial diagnosis result, the user's subjective waiting time is reduced, and the user experience is improved.

[0058] In a specific embodiment, before the user is fed back the target diagnosis result, a first identifier that review is in progress is displayed on the interactive interface. The first identifier can be a word “reviewing”, “reviewing in progress”, and the like, which is not limited herein.

[0059] In other embodiments, the target diagnosis result is obtained by reviewing the initial diagnosis result, and the initial diagnosis result is generated in combination with the target disease description information and the target portrait information. That is, the user is not fed back the initial diagnosis result, which is an intermediate result of the analysis, but is directly fed back the target diagnosis result, which is a final analysis result.

[0060] In an embodiment, the reviewing manner includes at least one of the following: checking, modifying. That is, the initial diagnosis result is checked, modified, or the like, to review the initial diagnosis result and improve the accuracy of the initial diagnosis result. Of course, in other embodiments, other forms of review can also be used, which are not limited herein.

[0061] In an embodiment, the reviewing content includes at least one of the following: medical knowledge, logic. That is, the medical knowledge, logic, and the like in the initial diagnosis result are reviewed to improve the accuracy of the initial diagnosis result. Of course, in other embodiments, other contents can also be reviewed, which are not limited herein.

[0062] In an embodiment, the target disease description information input by the user and the subsequent steps are executed by using a large language model, and the large language model is trained by using training data. Since the training data is a wide range of disease conversations of different diseases and different departments, and the diagnosis result of the large language model can also include going to which department for treatment, the obtained general large language model is trained by using the above training data, and then the user can select a specialist agent of the corresponding department at the interaction level to further inquire after obtaining the department recommended by the current large language model. In addition, when the large language model obtains multiple candidate items for the same disease, and the multiple candidate items correspond to different specialties, the specialist agent can be involved to determine the target item selected from the candidate items, and the large language model can further ask questions.

[0063] In addition, the specialist agent can also provide an inquiry service to the user independently in addition to cooperating with the large language model to further ask questions to the inquiry object.

[0064] In an embodiment, the specialist agent can be directly obtained from other channels, or can be introduced in the role playing of the training stage, and then a separate large language model is obtained by training the training data.

[0065] In an embodiment, the target disease description information input by the user and the subsequent steps are executed by using a large language model, and the large language model is trained by using sample data, and the sample data includes sample conversation information, sample portrait information, and sample diagnosis result.

[0066] In an embodiment, the sample data construction step includes:

[0067] Step 1: Obtain sample portrait information corresponding to the first agent, wherein the sample portrait information is obtained by combining corresponding portrait attributes in a plurality of portrait slots.

[0068] In an embodiment, the sample portrait information is obtained by combining corresponding portrait attributes in a plurality of portrait slots by using a fourth agent.

[0069] In a specific embodiment, the image attributes required for combination are not limited, and can be combined randomly. For example, the sample image information is combined by the corresponding height in the A image slot, the corresponding weight in the B image slot, and the corresponding surgical history in the C image slot. For another example, the sample image information is combined by the corresponding weight in the B image slot, the corresponding medication history in the D image slot, and the corresponding age in the E image slot. For another example, the sample image information is combined by the corresponding medication history in the D image slot and the corresponding surgical history in the C image slot.

[0070] Step two: generating sample dialogue information of the sample consultation object by using the first intelligent agent and the second intelligent agent; wherein the sample dialogue information includes sample input information and sample reply information, the second intelligent agent generates the sample input information, and the sample input information at least includes sample condition description information, and the first intelligent agent generates the sample reply information. Specifically, the second intelligent agent generates the sample condition description information and sends it to the first intelligent agent; the first intelligent agent acquires the sample condition description information and generates reply information about the condition description information. Therefore, the interaction between the first intelligent agent and the second intelligent agent constitutes the sample dialogue information of the sample consultation object, or the interaction between the second intelligent agent playing the sample consultation object and the first intelligent agent playing the doctor constitutes the sample dialogue information of the sample consultation object.

[0071] In an embodiment, for the sample input information generated by the second intelligent agent, the first intelligent agent generates sample reply information of different reply modes, and the sample input information and the sample reply information of the plurality of different reply modes constitute the sample dialogue information of the sample consultation object. The sample input information and the sample reply information of the plurality of different reply modes are used to perform RLHF training on the large language model, so that the large language model after training can filter out the reply information in the preferred reply mode and feed back to the sample consultation object.

[0072] In an embodiment, the sample input information further includes sample supplementary condition description information. Specifically, the second intelligent agent generates the sample supplementary condition description information and sends it to the first intelligent agent; the first intelligent agent acquires the sample supplementary condition description information and generates reply information about the condition description information. In the case that the input sample condition description information cannot determine the sample diagnosis result, the first intelligent agent will feed back the sample condition description information to be supplemented to the second intelligent agent, so that the first intelligent agent and the second intelligent agent must have multiple rounds of interaction, and the first intelligent agent and the second intelligent agent must have multiple rounds of interaction, which constitutes the sample dialogue information of the sample consultation object, or the multiple rounds of interaction between the second intelligent agent playing the sample consultation object and the first intelligent agent playing the doctor constitutes the sample dialogue information of the sample consultation object.

[0073] In an embodiment, when the sample condition description information comprises at least one of a high-frequency single symptom and a high-frequency disease, the first intelligent agent invokes a high-frequency knowledge base matched with the sample condition description information when generating the sample reply information.

[0074] Step three: reviewing the sample dialogue information by the third intelligent agent to obtain a sample diagnosis result. In an embodiment, the sample dialogue information is reviewed by the third intelligent agent to obtain a sample diagnosis result, specifically: the third intelligent agent is used to invoke reference medical knowledge matched with the sample dialogue information, and the sample dialogue information is reviewed based on the reference medical knowledge and the sample dialogue information to obtain a sample diagnosis result. That is, the sample dialogue information is reviewed based on professional medical knowledge, which can accurately review the sample dialogue to generate an accurate sample diagnosis result.

[0075] In an embodiment, as shown in FIG. 4, FIG. 4 is a flowchart of another embodiment of the inquiry method provided by the present application. Before the target diagnosis result about the target condition description information is fed back to the user, the method further includes the following sub-steps:

[0076] Step S41: determining a target inquiry object indicated by the target condition description information.

[0077] In the embodiment, the target inquiry object indicated by the target condition description information is determined. That is, the object to be inquired is determined, and the object can be diagnosed more specifically subsequently.

[0078] In an embodiment, as shown in FIG. 5, FIG. 5 is a flowchart of an embodiment of step S41 in FIG. 4. The target inquiry object indicated by the target condition description information is determined, specifically including the following sub-steps:

[0079] Step S51: performing inquiry role recognition on the target condition description information to obtain a recognition result.

[0080] In the embodiment, the inquiry role recognition is performed on the target condition description information to obtain a recognition result, wherein the recognition result is used to represent whether the inquiry role exists in the target condition description information.

[0081] For example, when the target condition description information input by the user is “I feel a little dizzy today”, the inquiry role exists in the target condition description information. For example, when the target condition description information input by the user is “My sister has frequent headaches in recent period of time”, the inquiry role exists in the target condition description information. For example, when the target condition description information input by the user is “Yesterday, the fever reached 39℃”, the inquiry role does not exist in the target condition description information.

[0082] Step S52: in response to the absence of the interrogation role in the target illness description information, taking the user as the target interrogation object.

[0083] In this embodiment, in response to the absence of the interrogation role in the target illness description information, the interrogation role is taken as the target interrogation object. That is, when the interrogation role is absent in the target illness description information, the user himself / herself is taken as the target interrogation object.

[0084] For example, when the target illness description information input by the user is "high fever up to 39℃ yesterday", the interrogation role is absent in the target illness description information, and then the user himself / herself is taken as the target interrogation object.

[0085] Step S53: in response to the presence of the interrogation role in the target illness description information, taking the interrogation role as the target interrogation object.

[0086] In this embodiment, in response to the presence of the interrogation role in the target illness description information, the interrogation role is taken as the target interrogation object. That is, when the interrogation role is present in the target illness description information, the interrogation role is directly taken as the target interrogation object.

[0087] For example, when the target illness description information input by the user is "my sister has frequent headaches in recent period of time", the interrogation role "the sister of the user" is present in the target illness description information, and then the sister of the user is taken as the target interrogation object.

[0088] For another example, when the target illness description information input by the user is "I have frequent headaches in recent period of time", the interrogation role "the user himself / herself" is present in the target illness description information, and then the user himself / herself is taken as the target interrogation object.

[0089] Step S42: obtaining the target portrait information of the target interrogation object.

[0090] In this embodiment, the target portrait information of the target interrogation object is obtained.

[0091] Step S43: analyzing the target illness description information and the target portrait information to determine the initial diagnosis result.

[0092] In this embodiment, the target illness description information and the target portrait information are analyzed to determine the initial diagnosis result.

[0093] In an embodiment, as shown in FIG. 6, which is a flow diagram of an embodiment of step S43 shown in FIG. 4, the target illness description information and the target portrait information are analyzed to determine the initial diagnosis result, and specifically includes the following sub-steps:

[0094] Step S61: analyzing the target portrait information and the target illness description information to obtain at least one first estimated disease information.

[0095] In this embodiment, the target image information and the target disease description information are analyzed to obtain at least one first estimated disease information. That is, based on the target image information and the target disease description information, possible diseases are searched.

[0096] In an embodiment, a secondary diagnosis engine is called to analyze the target image and the target disease description information to obtain at least one first estimated disease information.

[0097] Step S62: In at least one first medical knowledge base, first medical knowledge associated with each first estimated disease information is searched.

[0098] In this embodiment, in at least one first medical knowledge base, first medical knowledge associated with each first estimated disease information is searched. Wherein, the specific medical knowledge base is not limited.

[0099] In an embodiment, a secondary diagnosis engine is called to search, in at least one first medical knowledge base, first medical knowledge associated with each first estimated disease information.

[0100] Step S63: An initial diagnosis result is generated by using the first medical knowledge.

[0101] In this embodiment, an initial diagnosis result is generated by using the first medical knowledge. That is, the initial diagnosis result is generated by referring to the searched professional medical knowledge.

[0102] In an embodiment, before the initial diagnosis result is generated by using the first medical knowledge, the user is also fed back to-be-supplemented information, wherein the to-be-supplemented information is the missing disease description information for determining the target diagnosis result; at least one second estimated disease information is obtained by analyzing the supplemented disease description information; and in at least one first medical knowledge base, second medical knowledge associated with the second estimated disease information is searched. That is, after the user feeds back the supplemented disease description information, the disease information is first estimated, and then the medical knowledge associated with the disease information is searched in at least one first medical knowledge base.

[0103] At this time, the initial diagnosis result is generated by using the first medical knowledge, specifically: the initial diagnosis result is generated by using the first medical knowledge and the second medical knowledge. That is, the medical knowledge searched about the target disease description information and the medical knowledge searched about the supplemented disease description information are both referred to, and the medical knowledge referred to is more and more complete, so that the initial diagnosis result is more accurate.

[0104] It should be noted that if the initial diagnosis result and the target diagnosis result need to be fed back to the user, after the initial diagnosis result is obtained by analyzing the target illness description information and the target portrait information, the initial diagnosis result needs to be fed back to the user, and then step S44 is executed. If the initial diagnosis result and the target diagnosis result do not need to be fed back to the user, after the initial diagnosis result is obtained by analyzing the target illness description information and the target portrait information, step S45 is directly executed.

[0105] Step S44: reviewing the initial diagnosis result to obtain a target diagnosis result.

[0106] In the embodiment, the initial diagnosis result is reviewed to obtain the target diagnosis result. The target diagnosis result is obtained by reviewing the initial diagnosis result, and the target diagnosis result has higher accuracy, and can feed back the diagnosis result with high accuracy to the user, and provide high-quality inquiry service for the user.

[0107] Please refer to FIG. 7, which is a structural schematic diagram of an embodiment of the inquiry device provided in the application. The inquiry device 70 comprises an acquisition module 71 and a feedback module 72; the acquisition module 71 is configured to acquire target illness description information input by a user; the feedback module 72 is configured to feed back a target diagnosis result about the target illness description information to the user; wherein the determination of the target diagnosis result is related to the target illness description information and auxiliary diagnosis information, and the auxiliary diagnosis information comprises target portrait information of a target inquiry object indicated by the target illness description information.

[0108] The feedback module 72 is configured to feed back the target diagnosis result about the target illness description information to the user, including: feeding back an initial diagnosis result about the target illness description information to the user; wherein the initial diagnosis result is generated in combination with the target illness description information and the auxiliary diagnosis information; feeding back the target diagnosis result to the user; wherein the target diagnosis result is obtained by reviewing the initial diagnosis result.

[0109] The inquiry device 70 further comprises a display module 73, and the display module 73 is configured to display a first identifier indicating that the review is in progress on an interactive interface before feeding back the target diagnosis result to the user.

[0110] The review mode comprises at least one of the following: checking and modifying; and / or the review content comprises at least one of the following: medical knowledge and logic.

[0111] The target diagnosis result is obtained by reviewing the initial diagnosis result, and the initial diagnosis result is generated in combination with the target illness description information and the target portrait information.

[0112] The target diagnosis result comprises at least one of the following: illness analysis, medical advice and matters needing attention.

[0113] The auxiliary diagnosis information further includes historical diagnosis information of the target interviewee.

[0114] The diagnosis module 74 is configured to determine the target interviewee indicated by the target disease description information, obtain target portrait information of the target interviewee, analyze the target disease description information and the target portrait information to determine an initial diagnosis result, and review the initial diagnosis result to obtain the target diagnosis result.

[0115] The diagnosis module 74 is configured to determine the target interviewee indicated by the target disease description information, including: performing interviewee role recognition on the target disease description information to obtain a recognition result, wherein the recognition result is used to represent whether the target disease description information contains an interviewee role; in response to the target disease description information not containing the interviewee role, taking the user as the target interviewee; and in response to the target disease description information containing the interviewee role, taking the interviewee role as the target interviewee.

[0116] The diagnosis module 74 is configured to analyze the target disease description information and the target portrait information to determine the initial diagnosis result, including: analyzing the target portrait information and the target disease description information to obtain at least one first estimated disease information; searching, in at least one first medical knowledge base, for first medical knowledge associated with each first estimated disease information; and generating the initial diagnosis result by using the first medical knowledge.

[0117] The diagnosis module 74 is configured to feed back to-be-supplemented information to the user before generating the initial diagnosis result by using the first medical knowledge, wherein the to-be-supplemented information is missing disease description information for determining the target diagnosis result, analyze the supplemented disease description information to obtain at least one second estimated disease information, search, in at least one first medical knowledge base, for second medical knowledge associated with each second estimated disease information, and generate the initial diagnosis result by using the first medical knowledge, including: generating the initial diagnosis result by using the first medical knowledge and the second medical knowledge.

[0118] The display module 73 is configured to display a second identifier indicating that the analysis is in progress on the interactive interface before feeding back the target diagnosis result about the target disease description information to the user, and / or display a third identifier indicating that the analysis is completed on the interactive interface after feeding back the target diagnosis result about the target disease description information to the user.

[0119] The target disease description information input by the user and the subsequent steps are performed by using a large language model, the large language model is trained by using sample data, and the sample data includes sample dialogue information, sample portrait information, and sample diagnosis results.

[0120] The constructing of the sample data comprises: obtaining sample portrait information corresponding to the first agent; the sample portrait information is obtained by combining corresponding portrait attributes in a plurality of portrait slots; generating sample dialogue information of a sample consultation object by using the first agent and the second agent; the sample dialogue information comprises sample input information and sample reply information, the first agent generates the sample input information, and the sample input information at least comprises sample condition description information, and the second agent generates the sample reply information; and reviewing the sample dialogue information by using the third agent to obtain a target diagnosis result.

[0121] When the sample condition description information comprises at least one of a high-frequency single symptom and a high-frequency disease, the second agent calls a high-frequency knowledge base matched with the sample condition description information when generating the sample reply information.

[0122] The reviewing of the sample dialogue information by using the third agent to obtain a sample diagnosis result comprises: calling, by using the third agent, reference medical knowledge matched with the sample dialogue information, reviewing the sample dialogue information based on the reference medical knowledge and the sample dialogue information, and obtaining the sample diagnosis result.

[0123] Referring to FIG. 8, FIG. 8 is a structural schematic diagram of an embodiment of an electronic device provided by the present application. The electronic device 80 comprises a memory 81 and a processor 82 coupled with each other, and the processor 82 is configured to execute program instructions stored in the memory 81 to implement the steps of any of the above-mentioned consultation method embodiments. In a specific implementation scenario, the electronic device 80 can include but is not limited to a microcomputer, a server, and in addition, the electronic device 80 can also include a notebook computer, a tablet computer and other mobile devices, which are not limited herein.

[0124] Specifically, the processor 82 is configured to control itself and the memory 81 to implement the steps of any of the above-mentioned embodiments of the method for querying a doctor. The processor 82 can also be referred to as a CPU (Central Processing Unit). The processor 82 can be an integrated circuit chip having a processing capability of signals. The processor 82 can also be a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like. In addition, the processor 82 can be implemented by an integrated circuit chip together.

[0125] Referring to FIG. 9, FIG. 9 is a structural schematic diagram of an embodiment of the computer readable storage medium provided in the present application. The computer readable storage medium 90 of the embodiment of the present application stores program instructions 91, which, when executed, implement the method provided by any of the embodiments of the method for querying a doctor and any non-conflicting combination. The program instructions 91 can form a program file and be stored in the computer readable storage medium 90 in the form of a software product, so that a computer device (which can be a personal computer, a server, or a network device, etc.) executes all or part of the steps of the method of each embodiment of the present application. The aforementioned computer readable storage medium 90 includes a U disk, a mobile hard disk, a ROM (Read-Only Memory), a RAM (Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes, or a terminal device such as a computer, a server, a mobile phone, a tablet computer, etc.

[0126] If the technical solutions of the present application involve personal information, the product applying the technical solutions of the present application has been explicitly informed of the personal information processing rules before processing the personal information, and has obtained the personal independent consent. If the technical solutions of the present application involve sensitive personal information, the product applying the technical solutions of the present application has obtained the personal independent consent before processing the sensitive personal information, and at the same time meets the requirement of "explicit consent". For example, at the personal information collection device such as camera, a clear and prominent mark is set to inform that it has entered the personal information collection range and will collect personal information. If the individual voluntarily enters the collection range, it is considered to agree to collect personal information. Or, on the device for processing personal information, the personal information processing rules are informed by using obvious marks / information, and the personal authorization is obtained by means of pop-up information or asking the individual to upload his / her personal information. The personal information processing rules can include personal information processor, personal information processing purpose, processing method and personal information type, etc.

[0127] The above is only an embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation using the content of the present application specification and drawings, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for taking medical history, characterized in that, The method includes: Obtain the target condition description information input by the user; Feedback is provided to the user regarding the target diagnosis result based on the target condition description information; wherein, the determination of the target diagnosis result is related to the target condition description information and auxiliary diagnostic information, and the auxiliary diagnostic information includes the target profile information of the target patient referred to in the target condition description information.

2. The method according to claim 1, characterized in that, The step of providing the user with the target diagnosis result regarding the description of the target condition includes: The system provides the user with an initial diagnostic result based on the target condition description information; wherein the initial diagnostic result is generated by combining the target condition description information and the auxiliary diagnostic information. The target diagnostic result is fed back to the user; wherein the target diagnostic result is obtained by reviewing the initial diagnostic result.

3. The method according to claim 2, characterized in that, Before providing the target diagnostic result to the user, the method further includes: The interactive interface displays a first indicator that the review is in progress.

4. The method according to claim 2, characterized in that, The target diagnostic result is obtained by reviewing the initial diagnostic result, which is generated by combining the target condition description information and the target profile information.

5. The method according to claim 2 or 4, characterized in that, The review method includes at least one of the following: inspection, modification; And / or, the content of the review includes at least one of the following: medical knowledge, logic.

6. The method according to claim 1, characterized in that, The target diagnostic results include at least one of the following: disease analysis, medical advice, and precautions.

7. The method according to claim 1, characterized in that, The auxiliary diagnostic information also includes the target patient's historical consultation information.

8. The method according to claim 1, characterized in that, Before providing the user with the target diagnosis result regarding the description of the target condition, the method further includes: Identify the target patient referred to by the target disease description information; Obtain the target profile information of the target patient. The target disease description information and the target profile information are analyzed to determine the initial diagnosis result; The initial diagnostic results are reviewed to obtain the target diagnostic results.

9. The method according to claim 8, characterized in that, The process of determining the target patient referred to by the target disease description information includes: The target disease description information is subjected to consultation role identification to obtain identification results; wherein, the identification results are used to characterize whether a consultation role exists in the target disease description information; If no consultation role is found in the target symptom description information, the user will be selected as the target consultation object. In response to the existence of a consultation role in the target condition description information, the consultation role is designated as the target consultation object.

10. The method according to claim 8, characterized in that, The analysis of the target disease description information and the target profile information to determine the initial diagnosis result includes: Analyze the target profile information and the target disease description information to obtain at least one first predicted disease information; In at least one first medical knowledge base, retrieve first medical knowledge associated with each of the first predicted disease information; The initial diagnostic result is generated using the first medical knowledge.

11. The method according to claim 10, characterized in that, Before generating the initial diagnostic result using the first medical knowledge, the method further includes: Provide feedback to the user regarding the missing information; wherein, the missing information is the description of the condition that indicates the target diagnostic result is missing. The supplementary description of the illness is analyzed to obtain at least one second predicted disease information; In at least one of the first medical knowledge bases, retrieve second medical knowledge associated with each of the second predicted disease information; The step of generating the initial diagnostic result using the first medical knowledge includes: The initial diagnostic result is generated using the first medical knowledge and the second medical knowledge.

12. The method according to claim 1, characterized in that, Before providing the user with the target diagnosis result regarding the description of the target condition, the method further includes: The second identifier being analyzed is displayed in the interactive interface; And / or, after providing the user with the target diagnosis result regarding the description of the target condition, the method further includes: The interactive interface displays a third indicator indicating that the analysis is complete.

13. The method according to claim 1, characterized in that, The acquisition of the target disease description information input by the user and subsequent steps are performed using a large language model, which is trained using sample data, including sample dialogue information, sample profile information and sample diagnosis results.

14. The method according to claim 13, characterized in that, The steps for constructing the sample data include: Obtain sample profile information corresponding to the first intelligent agent; wherein, the sample profile information is obtained by combining the profile attributes corresponding to multiple profile slots; Using the first and second intelligent agents, sample dialogue information of the sample consultation object is generated; wherein, the sample dialogue information includes sample input information and sample response information, the second intelligent agent generates the sample input information, and the sample input information includes at least sample disease description information, and the first intelligent agent generates the sample response information; A third intelligent agent is used to review the sample dialogue information to obtain the sample diagnosis result.

15. The method according to claim 14, characterized in that, When the sample condition description information includes at least one of high-frequency single symptom and high-frequency disease, the first intelligent agent calls a high-frequency knowledge base that matches the sample condition description information when generating the sample response information.

16. The method according to claim 14, characterized in that, The step of using a third-party intelligent agent to review the sample dialogue information and obtain the sample diagnosis result includes: Using the third intelligent agent, reference medical knowledge matching the sample dialogue information is invoked. Based on the reference medical knowledge and the sample dialogue information, the sample dialogue information is reviewed to obtain the sample diagnosis result.

17. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing program instructions, and the processor executing the program instructions to implement the consultation method as described in any one of claims 1-16.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program instructions that can be executed to implement the consultation method as described in any one of claims 1-16.

Images