CN112837772A - Pre-inquiry case history generation method and device - Google Patents

Pre-inquiry case history generation method and device Download PDF

Info

Publication number
CN112837772A
CN112837772A CN202110120160.XA CN202110120160A CN112837772A CN 112837772 A CN112837772 A CN 112837772A CN 202110120160 A CN202110120160 A CN 202110120160A CN 112837772 A CN112837772 A CN 112837772A
Authority
CN
China
Prior art keywords
user
inquiry
inquired
medical record
question
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110120160.XA
Other languages
Chinese (zh)
Inventor
韦成勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Iflytek Medical Information Technology Co ltd
Original Assignee
Anhui Iflytek Medical Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anhui Iflytek Medical Information Technology Co ltd filed Critical Anhui Iflytek Medical Information Technology Co ltd
Priority to CN202110120160.XA priority Critical patent/CN112837772A/en
Publication of CN112837772A publication Critical patent/CN112837772A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295—Named entity recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Primary Health Care (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Epidemiology (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The application discloses a method and a device for generating a medical record for pre-inquiry, wherein the method comprises the following steps: after input data which are input by a user to be asked and carry disease condition information self-written by the user to be asked are obtained, a disease description text of the user to be asked is generated according to the input data; generating basic information of the disease condition of the user to be diagnosed and a first inquiry question corresponding to the user to be diagnosed according to the disease condition description text, so that after the first inquiry question is displayed to the user to be diagnosed, a first inquiry answer input by the user to be diagnosed aiming at the first inquiry question is obtained; and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question and the first inquiry answer, so that the pre-inquiry medical record can accurately describe the physical condition of the user to be inquired, and a doctor does not need to manually inquire for a long time (even does not need to manually inquire) after obtaining the pre-inquiry medical record, thereby improving the inquiry efficiency of the doctor.

Description

Pre-inquiry case history generation method and device
Technical Field
The application relates to the technical field of computers, in particular to a method and a device for generating a medical record for pre-inquiry.
Background
Currently, the commonly used medical procedures are: firstly, a doctor makes an inquiry for a long time to a medical seeker to obtain an inquiry result of the medical seeker; then, the doctor makes a disease diagnosis according to the inquiry result and other reference information (such as medical knowledge, clinical experience, examination results related to some examinations, and the like) to obtain the disease diagnosis result and treatment means of the medical staff.
However, since the medical procedure needs to be performed for a long time, the contradiction between medical supply and demand increases with the increase of medical needs, so how to improve the medical efficiency becomes an urgent technical problem to be solved.
Disclosure of Invention
The embodiment of the application mainly aims to provide a method and a device for generating a medical record for pre-inquiry, which can improve the inquiry efficiency, so that the medical efficiency can be improved.
The embodiment of the application provides a method for generating a medical record for pre-inquiry, which comprises the following steps:
generating a disease description text of a user to be asked according to input data of the user to be asked; wherein, the input data carries the self-stated disease information of the user to be asked;
generating the disease basic information of the user to be inquired and a first inquiry question corresponding to the user to be inquired according to the disease description text of the user to be inquired; the first inquiry question is used for inquiring condition supplementary information corresponding to the basic information of the disease condition from the user to be inquired;
after the first inquiry question is displayed to the user to be inquired, acquiring a first inquiry answer input by the user to be inquired aiming at the first inquiry question;
and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question and the first inquiry answer.
In a possible implementation manner, the generating a disease description text of the user to be asked according to the input data of the user to be asked includes:
if the input data of the user to be asked for diagnosis comprises the voice to be recognized, performing voice recognition on the voice to be recognized to obtain a voice recognition result; determining a disease description text of the user to be asked according to the voice recognition result;
if the input data of the user to be asked for diagnosis comprises an image to be identified, carrying out image identification on the image to be identified to obtain an image identification result; determining a disease description text of the user to be asked according to the image recognition result;
if the input data of the user to be asked comprise a text to be processed, determining a disease description text of the user to be asked according to the text to be processed;
if the input data of the user to be asked for a consultation comprises a video to be identified, carrying out image identification on each frame of video picture in the video to be identified to obtain a video identification result; and determining the disease description text of the user to be asked according to the video identification result.
In a possible implementation, the generation process of the basic information of the disease condition of the user to be asked for diagnosis includes:
carrying out entity labeling on the disease description text of the user to be asked for diagnosis to obtain a labeled text; determining the basic information of the disease symptoms of the user to be asked according to the labeling text;
alternatively, the first and second electrodes may be,
the generation process of the disease basic information of the user to be asked for diagnosis comprises the following steps:
semantic understanding is carried out on the disease condition description text of the user to be inquired to obtain a semantic understanding result corresponding to the disease condition description text; and determining the basic information of the disease symptoms of the user to be asked according to the semantic understanding result corresponding to the disease symptom description text.
In a possible implementation manner, the generating process of the first inquiry question corresponding to the user to be inquired includes:
determining the symptoms to be inquired of the user to be inquired according to the symptom description text of the user to be inquired;
determining a first inquiry question corresponding to the user to be inquired according to the symptom to be inquired of the user to be inquired and a pre-constructed question knowledge base; wherein the question knowledge base comprises a corresponding relationship between the symptoms to be interrogated and the first interrogation question.
In one possible embodiment, the method further comprises:
generating an inquiry mode of the first inquiry question according to the disease description text of the user to be inquired;
generating inquiry display content of the first inquiry question according to the inquiry mode of the first inquiry question; wherein the interrogation display content of the first interrogation question comprises the first interrogation question;
the displaying the first inquiry question to the user to be inquired comprises:
and displaying the inquiry display content of the first inquiry question to the user to be inquired.
In one possible embodiment, the method further comprises:
acquiring a medical record template corresponding to the user to be asked;
generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question and the first inquiry answer, wherein the pre-inquiry medical record comprises:
and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question, the first inquiry answer and a medical record template corresponding to the user to be inquired.
In a possible implementation manner, the acquiring a medical record template corresponding to the user to be asked for consultation includes:
determining the symptoms to be inquired of the user to be inquired according to the symptom description text of the user to be inquired;
obtaining a medical record template corresponding to the user to be inquired according to the symptom to be inquired of the user to be inquired and a pre-constructed template knowledge base; the template knowledge base comprises a corresponding relation between the symptoms to be asked and the medical record templates corresponding to the users to be asked.
In a possible implementation manner, the generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question, the first inquiry answer, and a medical record template corresponding to the user to be inquired includes:
generating an initial medical record corresponding to the user to be asked according to the disease basic information, the first inquiry question, the first inquiry answer and a medical record template corresponding to the user to be asked;
generating a second inquiry question corresponding to the user to be inquired according to the initial medical record corresponding to the user to be inquired; the second inquiry question is used for inquiring whether the user to be inquired has the symptoms to be supplemented corresponding to the initial medical record;
after the second inquiry question is displayed to the user to be inquired, acquiring a second inquiry answer input by the user to be inquired aiming at the second inquiry question;
updating the initial medical record corresponding to the user to be asked by using the second inquiry question and the second inquiry answer, and returning to execute the step of generating the second inquiry question corresponding to the user to be asked according to the initial medical record corresponding to the user to be asked until a preset stop condition is reached, and determining the pre-inquiry medical record corresponding to the user to be asked according to the initial medical record corresponding to the user to be asked.
In a possible implementation manner, the generating a second inquiry question corresponding to the user to be inquired according to the initial medical record corresponding to the user to be inquired includes:
obtaining a similar medical record corresponding to the initial medical record according to the initial medical record corresponding to the user to be inquired and a pre-constructed medical record knowledge base; the similarity between the similar medical record and the initial medical record corresponding to the user to be asked for diagnosis meets a preset similarity condition; the medical record knowledge base comprises the similar medical records;
determining a candidate disease diagnosis result corresponding to the initial medical record according to the actual disease diagnosis result of the similar medical record;
determining the symptom to be supplemented corresponding to the initial medical record according to the actual symptom corresponding to the candidate disease diagnosis result;
and determining a second inquiry question corresponding to the user to be inquired according to the symptom to be supplemented corresponding to the initial medical record.
An embodiment of the present application further provides a device for generating a medical record for pre-inquiry, where the device includes:
the text generation unit is used for generating a disease description text of the user to be asked according to the input data of the user to be asked; wherein, the input data carries the self-stated disease information of the user to be asked;
the problem generation unit is used for generating the disease basic information of the user to be asked and the first inquiry problem corresponding to the user to be asked according to the disease description text of the user to be asked; the first inquiry question is used for inquiring condition supplementary information corresponding to the basic information of the disease condition from the user to be inquired;
the answer obtaining unit is used for obtaining a first inquiry answer input by the user to be inquired aiming at the first inquiry question after the first inquiry question is displayed to the user to be inquired;
and a medical record generating unit, configured to generate a pre-inquiry medical record corresponding to the user to be subjected to inquiry according to the disease basic information, the first inquiry question, and the first inquiry answer.
Based on the technical scheme, the method has the following beneficial effects:
according to the method for generating the medical record for pre-inquiry, after input data which are input by a user to be inquired and carry disease condition information of the user to be inquired are obtained, a disease description text of the user to be inquired is generated according to the input data; generating the disease condition basic information of the user to be queried and a first query question corresponding to the user to be queried according to the disease condition description text, so as to obtain a first query answer input by the user to be queried for the first query question after the first query question is displayed to the user to be queried; and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question and the first inquiry answer.
Wherein, because the first inquiry question is used for inquiring the patient condition supplementary information related to the disease condition basic information of the user to be inquired about, the first inquiry answer input by the user to be inquired about aiming at the first inquiry question and the first inquiry question can accurately describe the patient condition supplementary information related to the disease condition basic information of the user to be inquired about, so that the disease condition basic information, the first inquiry question and the first inquiry answer can comprehensively describe the body condition of the user to be inquired about, and further the pre-inquiry medical record generated based on the disease condition basic information, the first inquiry question and the first inquiry answer can accurately describe the body condition of the user to be inquired about, thus the doctor does not need to manually diagnose the user to be inquired for a long time after obtaining the pre-inquiry medical record (even does not need to manually inquire the user to be inquired about), therefore, the inquiry efficiency of doctors can be improved, and the medical efficiency can be improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic view of an application scenario of a method for generating a medical record for pre-inquiry applied to a terminal device according to an embodiment of the present application;
fig. 2 is a schematic view of an application scenario of a method for generating a medical record for pre-inquiry applied to a server according to an embodiment of the present application;
fig. 3 is a flowchart of a method for generating a medical record for pre-inquiry according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a pre-inquiry medical record generation apparatus according to an embodiment of the present application.
Detailed Description
In order to solve the technical problem in the background art, an embodiment of the present application provides a method for generating a medical record for pre-inquiry, which may specifically include: generating a disease description text of the user to be inquired according to the input data of the user to be inquired; generating the disease basic information of the user to be inquired and a first inquiry question corresponding to the user to be inquired according to the disease description text of the user to be inquired; after the first inquiry question is displayed to the user to be inquired, acquiring a first inquiry answer input by the user to be inquired aiming at the first inquiry question; and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question and the first inquiry answer. Wherein, the input data carries the self-written illness state information of the user to be asked for diagnosis; the first inquiry question is used for inquiring the disease description information related to the disease basic information from the user to be inquired.
It can be seen that, since the first inquiry question is used to inquire the user to be inquired about the disease condition supplementary information related to the disease condition basic information of the user to be inquired, the first inquiry answer input by the user to be inquired for the first inquiry question and the first inquiry question can accurately describe the disease condition supplementary information related to the disease condition basic information of the user to be inquired, so that the disease condition basic information, the first inquiry question and the first inquiry answer can comprehensively describe the body condition of the user to be inquired, and the pre-inquiry medical record generated based on the disease condition basic information, the first inquiry question and the first inquiry answer can accurately describe the body condition of the user to be inquired, so that the user to be inquired does not need to be manually diagnosed for a long time after the doctor obtains the pre-inquiry medical record (even does not need to manually ask the user to be inquired), therefore, the inquiry efficiency of doctors can be improved, and the medical efficiency can be improved.
In addition, the embodiment of the present application does not limit the execution subject of the pre-inquiry medical record generation method, and for example, the pre-inquiry medical record generation method provided in the embodiment of the present application may be applied to a data processing device such as a terminal device or a server. The terminal device may be a smart phone, a computer, a Personal Digital Assistant (PDA), a tablet computer, or the like. The server may be a stand-alone server, a cluster server, or a cloud server.
In order to facilitate understanding of the technical solutions provided in the embodiments of the present application, an application scenario of the method for generating a medical record for pre-inquiry provided in the embodiments of the present application is exemplarily described below with reference to fig. 1 and fig. 2, respectively. Fig. 1 is a schematic view of an application scenario of a method for generating a medical record for pre-inquiry applied to a terminal device according to an embodiment of the present application; fig. 2 is a schematic view of an application scenario of the method for generating a medical record for pre-inquiry applied to a server according to the embodiment of the present application.
In the application scenario shown in fig. 1, when the user 101 to be queried triggers a pre-query medical record generation request on the terminal device 102, the terminal device 102 receives the pre-query medical record generation request, and performs a pre-query to the user 101 to be queried by executing the pre-query medical record generation method provided in the embodiment of the present application, so as to obtain a pre-query medical record corresponding to the user 101 to be queried. For example, the generation process of the pre-inquiry medical record corresponding to the user 101 to be inquired may specifically be: the terminal device 102 generates a disease description text of the user 101 to be asked according to the input data of the user 101 to be asked; then, generating the disease condition basic information of the user 101 to be queried and a first query question corresponding to the user 101 to be queried according to the disease condition description text of the user 101 to be queried, and after the first query question is displayed to the user 101 to be queried, acquiring a first query answer input by the user 101 to be queried for the first query question; finally, according to the basic information of the disease, the first inquiry question and the first inquiry answer, a pre-inquiry medical record corresponding to the user 101 to be inquired is generated, so that the subsequent terminal device 102 displays the pre-inquiry medical record, and a doctor can know the physical condition of the user 201 to be inquired according to the pre-inquiry medical record. The pre-inquiry refers to an automatic inquiry process performed on a user to be inquired before a doctor performs treatment on the user to be inquired.
In the application scenario shown in fig. 2, when the user 201 to be queried triggers a pre-query medical record generation request on the terminal device 202, the terminal device 202 receives the pre-query medical record generation request, and forwards the pre-query medical record generation request to the server 203, so that the server 203 performs pre-query on the user 201 to be queried by executing the pre-query medical record generation method provided by the embodiment of the present application, and obtains a pre-query medical record corresponding to the user 201 to be queried. For example, the generation process of the pre-inquiry medical record corresponding to the user 201 to be inquired may specifically be: the server 203 firstly generates a disease description text of the user 201 to be asked according to the input data of the user 201 to be asked; then, generating the disease condition basic information of the user 201 to be queried and a first query question corresponding to the user 201 to be queried according to the disease condition description text of the user 201 to be queried, and after the first query question is displayed to the user 201 to be queried, acquiring a first query answer input by the user 201 to be queried for the first query question; finally, according to the basic information of the disease, the first inquiry question and the first inquiry answer, a pre-inquiry medical record corresponding to the user 201 to be inquired is generated, so that the server 203 can send the pre-inquiry medical record to the terminal device 202 for display, and a doctor can know the physical condition of the user 201 to be inquired according to the pre-inquiry medical record.
It should be noted that the method for generating a medical record for pre-inquiry provided in the embodiment of the present application can be applied to not only the application scenarios shown in fig. 1 or fig. 2, but also other application scenarios that require generation of a medical record for pre-inquiry, and the embodiment of the present application is not particularly limited to this.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Method embodiment
Referring to fig. 3, the figure is a flowchart of a method for generating a medical record for pre-inquiry according to an embodiment of the present application.
The method for generating the medical record for pre-inquiry provided by the embodiment of the application comprises the following steps of S301-S305:
s301: and generating a disease description text of the user to be inquired according to the input data of the user to be inquired.
Wherein, the user to be asked refers to the medical staff who needs to perform automatic pre-inquiry.
The input data of the user to be asked refers to the disease condition information which is input to the medical record generation equipment for pre-inquiry by the user to be asked in a self-describing manner and is used for describing the physical condition of the user to be asked, so that the input data carries the self-described disease condition information of the user to be asked. The pre-inquiry medical record generation equipment is used for executing any implementation mode of the pre-inquiry medical record generation method provided by the embodiment of the application.
In addition, the input data of the user to be asked is not limited in the embodiment of the application, for example, for a pre-inquiry case history generation device supporting input modes such as voice input, image input, text input, and video input, the input data of the user to be asked may include at least one of a voice to be recognized, an image to be recognized, a text to be processed, and a video to be recognized. The voice to be recognized refers to voice information input by a user to be asked through a voice input mode on the medical record generation equipment for pre-inquiry. The image to be identified refers to image information input by a user to be asked through an image input mode on the medical record generation equipment for pre-inquiry. The text to be processed refers to text information input by the user to be asked through a text entry mode on the medical record generation equipment for pre-inquiry. The video to be identified refers to video information input by a user to be asked through a video input mode on the medical record generation equipment for pre-inquiry.
The disease description text of the user to be asked expresses the self-described disease information of the user to be asked in a text mode; moreover, the present embodiment does not limit the disease description text of the user to be asked, for example, the disease description text of the user to be asked may include at least one of symptom description information, disease description information, and symptom attribute information. Wherein the symptom description information is used for representing symptoms (such as dizziness and the like) appearing on the user to be asked. The disease description information is used to indicate a disease (e.g., hypertension, etc.) that the user to be diagnosed has. The symptom attribute information is used for representing attributes (such as onset time, inducement, frequency characteristics, relieving factors and the like) corresponding to symptoms appearing by the user to be asked for diagnosis.
In addition, the embodiment of the present application does not limit the generation process of the disease description text of the user to be asked for diagnosis (that is, the implementation manner of S301), for example, in one possible implementation manner, S301 may specifically include S3011 to S3014:
s3011: if the input data of the user to be inquired comprises the voice to be recognized, performing voice recognition on the voice to be recognized to obtain a voice recognition result; and determining a disease description text of the user to be asked according to the voice recognition result.
The voice recognition result is used for representing voice information carried by the voice to be recognized, so that the voice recognition result can represent disease condition information input by the user to be asked in a voice input mode in a text mode.
It should be noted that the embodiment of the present application is not limited to the speech recognition process in S3011, and may be implemented by any existing speech recognition method or any speech recognition method that appears in the future.
S3012: if the input data of the user to be inquired comprises the image to be identified, carrying out image identification on the image to be identified to obtain an image identification result; and determining a disease description text of the user to be asked according to the image recognition result.
The image recognition result is used for representing image information carried by the image to be recognized, so that the image recognition result can represent disease condition information input by the user to be asked in an image input mode in a text mode.
It should be noted that the image recognition process in S3012 is not limited in the embodiments of the present application, and any image recognition method that is currently available or will come in the future may be used for implementation.
S3013: and if the input data of the user to be asked comprises the text to be processed, determining the disease description text of the user to be asked according to the text to be processed.
S3014: if the input data of the user to be asked for a consultation comprises the video to be identified, carrying out image identification on each frame of video picture in the video to be identified to obtain a video identification result; and determining a disease description text of the user to be asked according to the video identification result.
The video to be identified comprises at least one frame of video picture. In addition, the video identification result is used for representing image information carried by the video to be identified, so that the video identification result represents the disease condition information input by the user to be asked in a video input mode in a text mode.
Based on the relevant content of S3011 to S3014, if the input data of the user to be asked for diagnosis includes the voice to be recognized, the image to be recognized, the text to be processed, and the video to be recognized, the voice to be recognized may be subjected to voice recognition to obtain a voice recognition result, so that the voice recognition result may accurately represent the illness state information input by the voice input method; carrying out image recognition on the image to be recognized to obtain an image recognition result, so that the image recognition result can accurately represent the disease condition information input in an image input mode; and carrying out image recognition on each frame of video picture in the video to be recognized to obtain a video recognition result, so that the video recognition result can accurately represent the disease condition information input in a video input mode. At this time, since the voice recognition result, the image recognition result, the video recognition result, and the text to be processed all belong to text-type data, the disease description text of the user to be asked can be determined according to the set of the voice recognition result, the image recognition result, the video recognition result, and the text to be processed (for example, the set of the voice recognition result, the image recognition result, the video recognition result, and the text to be processed is directly determined as the disease description text of the user to be asked).
Therefore, the medical record generation equipment for pre-inquiry supports four input modes, namely voice input, text input, image input and video input, so that when the user to be inquired performs pre-inquiry, the user to be inquired can independently select at least one input mode from the four input modes to input the self-stated disease information according to personal requirements in the medical record generation equipment for pre-inquiry, and subsequently can determine the disease description text of the user to be inquired according to the input data of the user to be inquired, so that the disease description text can accurately show the disease information of the user to be inquired, and the input flexibility and the accuracy of user data can be effectively improved.
Based on the relevant content in S301, for a user to be asked, who has medical needs, in order to reduce the time for a doctor to perform manual inquiry, the user to be asked may input the self-cited disease information in the medical record generation device for pre-inquiry, as the input data of the user to be asked; and then, performing text-type data conversion (for example, voice recognition or image recognition) on the input data of the user to be asked to obtain a disease description text of the user to be asked, so that the disease description text can accurately represent the disease information of the user to be asked.
S302: and generating the disease condition basic information of the user to be inquired and a first inquiry question corresponding to the user to be inquired according to the disease condition description text of the user to be inquired.
The basic information of the symptoms of the user to be diagnosed refers to the relevant information (for example, symptoms, symptom attributes, diseases, etc.) of the symptoms recorded in the description text of the symptoms of the user to be diagnosed. It should be noted that the present embodiment does not limit the way of representing the basic information of the disease condition of the user to be queried, for example, the basic information of the disease condition of the user to be queried may be represented in a structured way (for example, a binary way).
In addition, the generation process of the basic information of the disease state of the user to be asked for diagnosis is not limited in the embodiments of the present application, and for convenience of understanding, the following description is made with reference to two possible embodiments.
In a first possible implementation, the generation process of the basic information of the disease condition of the user to be diagnosed may specifically include steps 11 to 12:
step 11: and carrying out semantic understanding on the disease description text of the user to be diagnosed to obtain a semantic understanding result corresponding to the disease description text.
And the semantic understanding result corresponding to the disease description text is used for representing semantic information recorded in the disease description text of the user to be asked.
In addition, the embodiment of the present application is not limited to the implementation of semantic understanding in step 11, and may be implemented by any existing or future semantic understanding method. For example, step 11 may be implemented using a pre-built semantic understanding model.
It should be noted that, in the embodiment of the present application, the construction process of the semantic understanding model is not limited, and any existing or future construction method of the semantic understanding model may be used for implementation. In addition, since the medical practitioner usually uses the spoken word to make the statement of illness, in order to improve the semantic understanding accuracy, a large amount of spoken statement of illness text and the corresponding actual semantic understanding result can be used in advance to train the semantic understanding model, so that the trained semantic understanding model can accurately identify the semantic information recorded in the spoken statement of illness text (e.g., the illness description text).
Step 12: and determining the basic information of the disease symptoms of the user to be inquired according to the semantic understanding result corresponding to the disease symptom description text.
In the embodiment of the application, after the semantic understanding result corresponding to the disease description text is obtained, the disease basic information of the user to be asked for diagnosis can be determined according to the semantic understanding result corresponding to the disease description text; and the determination process may specifically be: if the semantic understanding result corresponding to the disease state description text is represented in a binary group (intention, slot), the semantic understanding result corresponding to the disease state description text can be directly determined as the disease state basic information of the user to be asked, so that the disease state basic information can represent the disease state related information recorded in the disease state description text of the user to be asked in a structured manner.
As can be seen from the related contents of the above steps 11 to 12, in some cases, the disease condition basic information of the user to be queried can be extracted from the disease condition description text of the user to be queried by means of a semantic understanding method, so that the disease condition basic information can accurately represent the disease condition related information recorded in the disease condition description text of the user to be queried.
In a second possible implementation, the generation process of the basic information of the disease condition of the user to be diagnosed may specifically include steps 21 to 22:
step 21: and carrying out entity labeling on the disease description text of the user to be inquired to obtain a labeling text.
The label text is a disease description text carrying entity label information, so that the label text can be used for recording part-of-speech labels of various objects to be processed in the disease description text of the user to be asked. The object to be processed may be a word and/or a word.
In addition, the embodiment of the application does not limit entity labeling, and any existing or future method capable of performing entity labeling on the disease description text can be adopted for implementation. For example, step 21 may be implemented using a pre-constructed entity annotation model.
It should be noted that, the embodiment of the present application does not limit the process of constructing the entity annotation model, and may be implemented by using any existing or future method of constructing the entity annotation model. In addition, because medical practitioners usually use spoken words to make disease statement, in order to improve the accuracy of entity tagging, a large amount of spoken disease statement texts and corresponding actual entity tagging results can be utilized in advance to train the entity tagging model, so that the trained entity tagging model can accurately perform part-of-speech tagging on characters and/or words in the spoken disease statement texts (such as disease description texts).
Step 22: and determining the basic information of the disease symptoms of the user to be asked according to the labeling text.
In the embodiment of the application, after the annotation text is obtained, the basic information of the disease condition of the user to be asked for diagnosis can be determined according to the annotation text; and the process may specifically be: according to the form of the binary group (the object to be processed, the entity labeling result of the object to be processed), extracting each binary group from the labeling text, determining the set of all the extracted binary groups as the disease basic information of the user to be asked, so that the disease basic information can represent the disease related information recorded in the disease description text of the user to be asked in a structured manner.
As can be seen from the related contents of the above steps 21 to 22, in some cases, the disease basic information of the user to be queried can be extracted from the disease description text of the user to be queried by means of an entity tagging method, so that the disease basic information can accurately represent the disease related information recorded in the disease description text of the user to be queried.
In fact, since the user to be asked for a diagnosis usually does not have professional medical knowledge, it is almost impossible for the user to be asked for a diagnosis to provide complete disease information to the pre-inquiry medical record generating device in a self-describing manner, so that the basic information of the disease is incomplete, and therefore, in order to improve the accuracy of the pre-inquiry, the pre-inquiry medical record generating device can guide the user to be asked for a diagnosis to provide the disease complementary information corresponding to the basic information of the disease in an inquiring and answering manner, so that the basic information of the disease and the complementary information of the disease corresponding to the basic information of the disease can relatively and completely represent the disease information of the user to be asked for a diagnosis.
Based on this, after the disease description text of the user to be queried is obtained, the pre-inquiry medical record generation device may generate the first inquiry question corresponding to the user to be queried according to the disease description text of the user to be queried, so that the first inquiry question is used to inquire the user to be queried about the disease condition supplementary information corresponding to the disease condition basic information.
In addition, the embodiment of the present application does not limit the generation process of the first inquiry question, for example, in a possible implementation manner, the generation process of the first inquiry question corresponding to the user to be inquired may specifically include steps 31 to 32:
step 31: and determining the symptoms to be inquired of the user to be inquired according to the symptom description text of the user to be inquired.
The symptoms to be asked of the user to be asked refer to the symptoms recorded in the disease description text of the user to be asked, that is, the symptoms (for example, dizziness) input by the user to be asked to the pre-inquiry medical record generation device. In addition, the number of symptoms to be investigated is not limited in the examples of the present application.
In addition, the embodiment of step 31 is not limited in the examples of the present application, and for the convenience of understanding, the following description is made in conjunction with two possible embodiments.
In a first possible implementation, step 31 may specifically include: and carrying out symptom identification on the symptom description text of the user to be inquired to obtain the symptom to be inquired of the user to be inquired.
The present embodiment is not limited to the symptom identification method, and may be implemented using a symptom identification model that is constructed in advance, for example. The embodiment of the present application does not limit the method for constructing the symptom identification model, and may be implemented by any method that can construct a symptom identification model, which is currently available or will appear in the future.
In some cases, after the disease description text of the user to be asked is acquired, the disease description text can be directly input into a pre-constructed symptom identification model, so that the symptom identification model can perform symptom identification on the disease description text, and the symptom to be asked of the user to be asked is obtained and output.
In a second possible implementation, step 31 may specifically include steps 311 to 312:
step 311: and generating the disease basic information of the user to be inquired according to the disease description text of the user to be inquired.
It should be noted that, the relevant content in step 311 refers to the above "generation process of basic information of disease condition of user to be queried".
Step 312: and respectively determining at least one symptom in the disease basic information of the user to be inquired as the symptom to be inquired of the user to be inquired.
In the embodiment of the application, after the basic information of the symptoms of the user to be diagnosed is obtained, each symptom in the basic information of the symptoms can be respectively determined as the symptom to be diagnosed of the user to be diagnosed, so that a first interrogation problem corresponding to each symptom to be diagnosed can be generated based on each symptom to be diagnosed in the following.
Based on the related contents of steps 311 to 312, in some cases, after the disease description text of the user to be queried is obtained, the disease basic information of the user to be queried may be extracted from the disease description text of the user to be queried, so that the disease basic information can accurately represent the diseased information of the user to be queried; and then, determining each symptom recorded in the disease basic information of the user to be queried as the symptom to be queried of the user to be queried respectively, so that the inquiry problem is generated for each symptom to be queried by the pre-inquiry medical record generating equipment for pre-inquiry.
Step 32: and determining a first inquiry question corresponding to the user to be inquired according to the symptom to be inquired of the user to be inquired and a pre-constructed question knowledge base. Wherein the question knowledge base comprises a corresponding relation between the symptoms to be interrogated and the first interrogation question.
The question knowledge base can be used for recording attribute inquiry questions corresponding to all symptoms. In addition, the present application does not limit the expression of the question knowledge base, and for example, in one possible implementation, the question knowledge base may include a correspondence between an h-th symptom and an attribute of the h-th symptom, and a correspondence between an attribute of the h-th symptom and an attribute inquiry question corresponding to the attribute of the h-th symptom.
The attribute inquiry question corresponding to the attribute of the h-th symptom is used for inquiring the attribute of the h-th symptom from medical personnel (for example, a user to be inquired). Wherein the attribute of the h symptom refers to the performance characteristics of the patient with the h symptom. In addition, the present application does not limit the attribute of the h-th symptom, and for example, if the h-th symptom is "dizziness", the attribute of the h-th symptom may include the onset time, the cause, the frequency characteristics, and the alleviation factors, etc. H is a positive integer, H is less than or equal to H, and H is the total number of symptoms.
In fact, since the medical practitioner usually does not have professional medical knowledge, so that the medical practitioner cannot answer the attribute inquiry question generated by the pre-inquiry medical record generating device in a standard answer manner, in order to improve the feedback accuracy of the medical practitioner, the embodiment of the present application further provides another possible implementation manner of the question knowledge base.
The inquiry method corresponding to the attribute of the h-th symptom is used for describing display contents (for example, candidate answers corresponding to the attribute inquiry question and the like) adopted when inquiring the attribute inquiry question corresponding to the attribute of the h-th symptom from the medical staff and a response method (for example, single selection, multiple selection, dial code, self organization language description and the like) adopted when the medical staff answers the attribute inquiry question corresponding to the attribute of the h-th symptom. For example, the attribute "time to onset" corresponds to a query pattern of "dial-XXX days"; the inquiry modes corresponding to the attribute of the inducement are multi-selection, after fatigue, after trauma and after catching a cold; the query mode corresponding to the attribute of the frequency characteristic is single selection-continuity and paroxysmal; the inquiry mode corresponding to the attribute of the relief factor is 'multi-selection-after taking medicine and after rest'.
In fact, some symptoms may be related to the patient's medical history, so to further improve the completeness of the medical information, the present application provides another possible implementation of the question knowledge base, in which the question knowledge base may further include the corresponding relationship between the h-th symptom and the question asked by the medical history if the relationship between the h-th symptom and the medical history to be asked exceeds the preset relationship threshold. Wherein, the medical history inquiry question is used for inquiring whether the medical personnel has the medical history to be inquired. The preset association threshold may be preset.
It should be noted that, the embodiment of the present application does not limit the manner of obtaining the association between the h-th symptom and the medical history to be interrogated, for example, if the question knowledge base is constructed by using the following first history medical record, the association between the h-th symptom and the medical history to be interrogated may be according to the co-occurrence probability of the medical history to be interrogated and the h-th symptom in the first history medical record.
As can be seen, for the h-th symptom in the question knowledge base, if the correlation between the h-th symptom and the medical history to be interrogated exceeds the preset correlation threshold, it indicates that the h-th symptom and the medical history to be interrogated are more likely to appear on the patient at the same time, so the question knowledge base may include the corresponding relationship between the h-th symptom and the attribute of the h-th symptom, the corresponding relationship between the attribute of the h-th symptom and the attribute interrogation question corresponding to the attribute of the h-th symptom, the corresponding relationship between the attribute of the h-th symptom and the interrogation mode corresponding to the attribute of the h-th symptom, and the corresponding relationship between the h-th symptom and the medical history interrogation question. However, if the correlation between the h-th symptom and the medical history to be interrogated does not exceed the preset correlation threshold, it indicates that the probability that the h-th symptom and the medical history to be interrogated appear on the patient at the same time is relatively low (even no probability), so in order to improve the pre-interrogation efficiency, the question knowledge base may include a correspondence between the attributes of the h-th symptom and the h-th symptom, a correspondence between the attributes of the h-th symptom and the attribute interrogation question corresponding to the attributes of the h-th symptom, and a correspondence between the attributes of the h-th symptom and the interrogation manner corresponding to the attributes of the h-th symptom.
In addition, the embodiment of the present application does not limit the construction manner of the problem knowledge base, for example, the problem knowledge base may be constructed according to the first historical medical record, and the construction process may specifically be: firstly, the corresponding relation between the h-th symptom and the attribute of the h-th symptom, the corresponding relation between the attribute of the h-th symptom and the attribute inquiry question corresponding to the attribute of the h-th symptom, and the corresponding relation between the attribute of the h-th symptom and the inquiry mode corresponding to the attribute of the h-th symptom are mined from a large number of first history medical records by adopting any existing or future big data mining method (even the corresponding relation between the h-th symptom and the medical history inquiry question is mined).
It should be noted that, since the attribute of the h-th symptom may include at least one attribute, in order to improve the accuracy of the attribute of the h-th symptom, the at least one attribute may be sorted according to the frequency of occurrence, so that the attribute of the h-th symptom may include the at least one attribute sorted according to the frequency of occurrence. The frequency of occurrence of an attribute refers to the number of times that the attribute and the h-th symptom co-occur in the first historical medical record.
In addition, the embodiment of the present application is not limited to the implementation of step 32, for example, step 32 may specifically include: at least one attribute corresponding to the symptoms to be interrogated of the user to be interrogated is inquired in a problem knowledge base which is constructed in advance and is used as the attribute to be interrogated of the user to be interrogated; and then inquiring attribute inquiry questions corresponding to each attribute to be inquired in a pre-constructed question knowledge base, wherein the attribute inquiry questions are all used as first inquiry questions corresponding to the user to be inquired.
In fact, the input data of the user to be diagnosed usually carries some attributes of the symptom to be diagnosed, so in order to improve the efficiency of the diagnosis, the embodiment of the present application further provides another possible implementation manner of step 32, which may specifically include steps 321 to 322:
step 321: and determining at least one candidate inquiry question of the user to be inquired according to the symptoms to be inquired of the user to be inquired and a question knowledge base established in advance. Wherein the question knowledge base comprises a correspondence between the symptoms to be interrogated and at least one candidate interrogation question.
As a first example, step 321 may specifically include steps 3211-3212:
step 3211: and inquiring at least one attribute corresponding to the symptoms to be interrogated of the user to be interrogated in a pre-constructed question knowledge base as the attribute to be interrogated of the user to be interrogated.
Step 3212: and inquiring attribute inquiry questions corresponding to each attribute to be inquired in a pre-constructed question knowledge base, wherein the attribute inquiry questions are all used as candidate inquiry questions of the user to be inquired.
As a second example, if the question knowledge base may further include the corresponding relationship between the symptoms to be interrogated and the questions interrogated with the medical history, step 321 may further include, in addition to the above steps 3211 to 3212, step 3213:
step 3213: and inquiring the medical history inquiry questions corresponding to the symptoms to be inquired in a question knowledge base constructed in advance to serve as candidate inquiry questions of the user to be inquired.
Based on the related content in step 321, after the symptom to be diagnosed of the user to be diagnosed is obtained, the question knowledge base may query the attribute questions and/or medical history questions corresponding to the symptom to be diagnosed, and determine all of the attribute questions and/or medical history questions as candidate questions for the user to be diagnosed.
Step 322: and deleting the answered inquiry questions corresponding to the user to be inquired from at least one candidate inquiry question of the user to be inquired to obtain first inquiry questions corresponding to the user to be inquired.
The answered inquiry questions corresponding to the users to be inquired are determined according to the disease description texts of the users to be inquired. That is, the answered inquiry questions corresponding to the user to be inquired refer to the attribute inquiry questions that have been answered by the user to be inquired in the input data of the user to be inquired.
In addition, the embodiment of the present application does not limit the process of acquiring the questions asked and answered corresponding to the user to be asked, for example, in a possible implementation manner, the process of acquiring the questions asked and answered corresponding to the user to be asked and answered may include: extracting at least one attribute of symptoms to be interrogated from a disease description text of a user to be interrogated, and determining the attribute as the interrogated attribute of the user to be interrogated; and inquiring attribute inquiry questions corresponding to each inquired attribute in a pre-constructed question knowledge base, wherein the attribute inquiry questions are used as answered inquiry questions corresponding to the user to be inquired.
Based on the related content from step 321 to step 322, after the symptom to be queried of the user to be queried is obtained, all attribute query questions corresponding to the symptom to be queried may be first queried from a pre-constructed question knowledge base, and all the attribute query questions are determined to be candidate query questions of the user to be queried; and deleting the answered inquiry questions corresponding to the user to be inquired from all the candidate inquiry questions to obtain at least one candidate inquiry question which is not yet answered by the user to be inquired, and respectively determining each candidate inquiry question which is not yet answered by the user to be inquired as a first inquiry question corresponding to the user to be inquired, so that the first inquiry questions displayed by the pre-inquiry medical record generating equipment can be used for inquiring the user to be inquired about the disease description information which is not mentioned by the user to be inquired.
S303: and displaying the first inquiry question to the user to be inquired.
The display mode of the first inquiry question is not limited in the embodiments of the present application, and any display mode (for example, a display mode such as voice, text, or video) existing or appearing in the future may be used for displaying.
In addition, an embodiment of the present application further provides an implementation manner of S303, which may specifically include S3031 to S3033:
s3031: and generating an inquiry mode of the first inquiry question according to the symptom description text of the user to be inquired.
The inquiry mode of the first inquiry question comprises display content corresponding to the first inquiry question and a reply mode adopted by the medical seeker when answering the first inquiry question. In addition, the display content corresponding to the first inquiry question is not limited in the embodiments of the present application, for example, the display content corresponding to the first inquiry question may include the first inquiry question (e.g., "what is the cause.
In addition, the embodiment of the present application is not limited to the implementation of S3031, for example, in one possible implementation, S3031 may specifically include S30311 to S30312:
s30311: and determining the symptoms to be inquired of the user to be inquired according to the symptom description text of the user to be inquired.
Please refer to the relevant content of step 31 above for the relevant content of S30311.
S30312: according to the symptoms to be interrogated of the user to be interrogated and a pre-constructed question knowledge base, determining a first interrogation question corresponding to the user to be interrogated and an interrogation mode of the first interrogation question.
The embodiment of the present application is not limited to the implementation of S30312, for example, S30312 may specifically include: at least one attribute corresponding to the symptoms to be interrogated of the user to be interrogated is inquired in a problem knowledge base which is constructed in advance and is used as the attribute to be interrogated of the user to be interrogated; and querying an attribute inquiry question and an inquiry mode corresponding to the q-th attribute to be inquired in a pre-constructed question knowledge base, and determining the attribute inquiry question and the inquiry mode as the q-th first inquiry question and the q-th first inquiry question. Wherein Q is a positive integer, Q is not more than Q, and Q refers to the number of attributes to be interrogated.
It can be seen that, since each attribute in the question knowledge base may correspond to one attribute inquiry question, and each attribute may also correspond to one inquiry manner, so that the inquiry manner corresponding to one attribute is the inquiry manner of the attribute inquiry question corresponding to the attribute, after Q attributes to be inquired corresponding to symptoms to be inquired are obtained by inquiring from the question knowledge base, the attribute inquiry question corresponding to the qth attribute to be inquired is inquired in the question knowledge base as the qth first inquiry question, and the inquiry manner corresponding to the qth attribute to be inquired is inquired in the question knowledge base as the inquiry manner of the qth first inquiry question. Wherein Q is a positive integer, Q is not more than Q, and Q refers to the number of attributes to be interrogated.
In addition, when the question knowledge base may further include a corresponding relationship between the symptoms to be interrogated and the questions asked with the medical history, and a corresponding relationship between the questions asked with the medical history and the inquiry manners of the questions asked with the medical history, S30312 may further include: inquiring a medical history inquiry question corresponding to a symptom to be inquired from a pre-constructed question knowledge base to serve as a first inquiry question corresponding to a user to be inquired, and inquiring an inquiry mode corresponding to the medical history inquiry question from the question knowledge base to serve as an inquiry mode corresponding to the first inquiry question.
Based on the relevant contents of the foregoing S30311 to S30312, after the disease description text of the user to be asked is obtained, the symptom to be asked may be extracted from the disease description text, and then the attribute question (and/or the medical history question) and the query manner thereof corresponding to the symptom to be asked may be queried from the pre-constructed question knowledge base, which are respectively used as the first question and the query manner of the first question, so that the query manner can show the display content of the first question on the pre-asked medical record generating device (for example, the first question and the candidate answer corresponding thereto) and the response manner (for example, multiple selection, single selection, dialing code, self organization language description, etc.) adopted by the medical applicant when answering the first question.
S3032: and generating inquiry display content of the first inquiry question according to the inquiry mode of the first inquiry question.
The inquiry display content of the first inquiry question refers to the content which needs to be displayed in the inquiry interaction process of the first inquiry question. In addition, the present embodiment does not limit the inquiry display content of the first inquiry question, for example, the inquiry display content of the first inquiry question may include at least one of the first inquiry question, a candidate answer corresponding to the first inquiry question, and a response prompt message corresponding to the first inquiry question. The answer prompt information corresponding to the first inquiry question is used for reminding the doctor seeking staff of an answer mode which should be adopted when answering the first inquiry question.
In addition, the generation process of the inquiry display content of the first inquiry question is not limited in the embodiments of the present application, for example, if the inquiry manner of the first inquiry question includes the display content corresponding to the first inquiry question and the reply manner adopted by the medical applicant when answering the first inquiry question, the generation process of the inquiry display content of the first inquiry question may specifically include: firstly, determining reply prompt information corresponding to the first inquiry question according to a reply mode adopted by medical personnel when answering the first inquiry question; and determining the display content corresponding to the first inquiry question and the response prompt message corresponding to the first inquiry question as the inquiry display content of the first inquiry question.
S3033: and displaying the inquiry display content of the first inquiry question to the user to be inquired.
In this embodiment of the application, after the inquiry display content of the first inquiry question is acquired, the inquiry display content of the first inquiry question may be displayed to the user to be inquired, so that the user to be inquired can know the first inquiry question and the answer mode of the first inquiry question from the inquiry display content, and thus the user to be inquired can reply to the first inquiry question according to the answer mode of the first inquiry question.
Based on the related contents of S3031 to S3033, after the disease description text of the user to be queried is obtained, a first query question corresponding to the user to be queried and an inquiry mode of the first query question may be determined according to the disease description text; and generating inquiry display content of the first inquiry question and displaying the inquiry display content to a user to be inquired according to an inquiry mode of the first inquiry question, so that the user to be inquired can obtain the first inquiry question and a response mode of the first inquiry question from the inquiry display content, the user to be inquired can accurately reply to the first inquiry question, a first inquiry answer corresponding to the first inquiry question is obtained, and the first inquiry answer can accurately express response information fed back by the user to be inquired to the first inquiry question.
S304: and acquiring a first inquiry answer input by the user to be inquired aiming at the first inquiry question.
The first inquiry answer refers to the reply content input by the user to be inquired aiming at the first inquiry question; moreover, the input manner of the first inquiry answer is not limited in the embodiments of the present application, for example, the input manner of the first inquiry answer may be a click manner (e.g., a single-selection manner, a multiple-selection manner, or a dial-up manner), or may be a statement manner (e.g., a statement manner by text, a statement manner by voice, a statement manner by video, a statement manner by image, etc.).
As can be seen, after the first inquiry question is displayed to the user to be inquired, the first inquiry answer input by the user to be inquired for the first inquiry question may be received, so that the basic information of the disease condition of the user to be inquired can be supplemented with information by using the first inquiry question and the corresponding first inquiry answer, so that the basic information of the disease condition of the user to be inquired, the first inquiry question and the corresponding first inquiry answer can comprehensively show the physical condition of the user to be inquired.
S305: and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question and the first inquiry answer.
The pre-inquiry medical record corresponding to the user to be inquired is used for recording the physical condition of the user to be inquired.
In addition, the embodiment of the present application does not limit the generation process of the pre-inquiry medical record, for example, in a possible implementation manner, the generation process of the pre-inquiry medical record may specifically include steps 41 to 42:
step 41: and acquiring a medical record template corresponding to the user to be inquired.
The medical record template corresponding to the user to be asked is not limited in the embodiment of the application, and for example, the medical record template corresponding to the user to be asked may include contents such as "chief complaint", "current medical history", "past history", "examination and" physical examination ".
In addition, the embodiment of the present application does not limit the acquisition manner of the medical record template corresponding to the user to be asked, and for example, the medical record template corresponding to the user to be asked may be preset.
In fact, different symptoms often correspond to different medical history templates, as the information that needs to be consulted varies from symptom to symptom. Based on this, the present application embodiment also provides a possible implementation manner of step 41, which may specifically include steps 411 to 412:
step 411: and determining the symptoms to be inquired of the user to be inquired according to the symptom description text of the user to be inquired.
It should be noted that the relevant content of step 411 is referred to the relevant content of step 31 above.
Step 412: obtaining a medical record template corresponding to a user to be inquired according to the symptoms to be inquired of the user to be inquired and a pre-constructed template knowledge base; the template knowledge base comprises the corresponding relation between the symptoms to be inquired and the medical record templates corresponding to the users to be inquired.
The template knowledge base is used for recording medical record templates corresponding to all symptoms. In addition, the embodiment of the present application does not limit the representation manner of the template knowledge base, for example, the template knowledge base may include a corresponding relationship between the g-th symptom and the g-th medical record template. Wherein g is a positive integer, g is less than or equal to H, and H is the total number of symptoms.
In addition, the embodiment of the present application does not limit the generation manner of the g-th medical record template, and for example, the g-th medical record template may be set manually. For another example, the g-th medical record template can be constructed according to the second historical medical record; and the construction process may specifically include steps 51-52:
step 51: and screening out a second history medical record with the g-th symptom from a plurality of second history medical records to be used as a template reference medical record corresponding to the g-th symptom.
In this embodiment of the application, for R second historical medical histories, if the ith second historical medical record has the g-th symptom, the R second historical medical record may be determined as the template reference medical record corresponding to the g-th symptom. Wherein R is a positive integer, R is not more than R, and R is a positive integer.
Step 52: and according to the template reference medical record corresponding to the g symptom, generating a g medical record template.
The embodiment of the present application is not limited to the implementation of step 52, for example, if the number of the template reference medical records corresponding to the g-th symptom is W, the format of the W template reference medical records corresponding to the g-th symptom may be integrated to obtain the g-th medical record template, so that the g-th medical record template can cover the format content in the W template reference medical records corresponding to the g-th symptom.
For another example, if the number of the template reference medical records corresponding to the g-th symptom is W, step 52 may include steps 521 to 523:
step 521: and performing statistical analysis on medical record formats of the W template reference medical records corresponding to the g-th symptom to determine the reference medical record format corresponding to the g-th symptom and the occurrence frequency of the reference medical record format.
The medical record format of the w template reference medical record corresponding to the g-th symptom refers to a format used by the w template reference medical record corresponding to the g-th symptom for describing the disease condition.
The reference medical record format corresponding to the g-th symptom is a medical record format which appears at least once in the medical record formats of the W template reference medical records corresponding to the g-th symptom.
The occurrence frequency of the reference medical record format corresponding to the g-th symptom refers to the occurrence frequency of the reference medical record format corresponding to the g-th symptom in the medical record formats of the W template reference medical records corresponding to the g-th symptom.
Step 522: and screening a common medical record format corresponding to the g symptom from medical record reference formats corresponding to the g symptom based on the occurrence frequency.
The common medical record format refers to a medical record format with relatively high use probability.
In addition, the screening process of the common medical record format corresponding to the g-th symptom is not limited in the embodiment of the present application, for example, the medical record reference formats corresponding to the g-th symptom may be sorted from high to low according to the frequency of occurrence, and the E medical record reference formats in the top of the sorting may be determined as the common medical record format corresponding to the g-th symptom. For another example, each medical record reference format whose occurrence frequency corresponding to the g-th symptom reaches a preset frequency threshold may be determined as a common medical record format corresponding to the g-th symptom.
Step 523: and integrating the format of the common medical record format corresponding to the g-th symptom to obtain a g-th medical record template, so that the g-th medical record template can cover the common medical record format corresponding to the g-th symptom.
Based on the related contents of the above steps 521 to 523, after obtaining each template reference medical record corresponding to the g-th symptom, a common medical record format corresponding to the g-th symptom can be screened from medical record formats of the template reference medical records, and then format integration is performed on the common medical record format corresponding to the g-th symptom to obtain the g-th medical record template, so that the g-th medical record template can cover the common medical record format corresponding to the g-th symptom.
Based on the relevant content of the step 412, since the template knowledge base is used to record the medical record templates corresponding to the symptoms, after the symptoms to be queried of the user to be queried are obtained, the medical record templates corresponding to the symptoms to be queried can be queried in the template knowledge base and serve as the medical record templates corresponding to the user to be queried, so that the pre-query medical record corresponding to the user to be queried can be constructed subsequently based on the medical record templates corresponding to the user to be queried.
Step 42: and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question, the first inquiry answer and the medical record template corresponding to the user to be inquired.
The embodiment of the present application is not limited to the implementation manner of step 42, for example, the basic information of the disease condition, the first inquiry question and the first inquiry answer are added to a medical record template corresponding to the user to be inquired, so as to obtain a pre-inquiry medical record corresponding to the user to be inquired.
In some cases, a doctor needs to perform disease diagnosis by combining one symptom and a symptom associated with the symptom, so in order to improve the accuracy of the pre-inquiry medical record, the user to be inquired can be inquired during the pre-inquiry process whether other symptoms besides the symptom to be inquired appear. Based on this, the present application embodiment also provides a possible implementation manner of step 42, which may specifically include steps 421 to 424:
step 421: and generating an initial medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question, the first inquiry answer and the medical record template corresponding to the user to be inquired.
The embodiment of the present application is not limited to the implementation manner of step 421, for example, step 421 may specifically be adding the basic information of the disease condition, the first inquiry question and the first inquiry answer to a medical record template corresponding to the user to be inquired, so as to obtain an initial medical record corresponding to the user to be inquired. For another example, step 421 may specifically be: extracting first semantic information from the first inquiry question and the corresponding first inquiry answer, and adding the first semantic information and the disease basic information into a medical record template corresponding to a user to be inquired to obtain an initial medical record corresponding to the user to be inquired. The first semantic information refers to semantic information recorded in the first inquiry question and the corresponding first inquiry answer.
Step 422: and generating a second inquiry question corresponding to the user to be inquired according to the initial medical record corresponding to the user to be inquired.
The second inquiry question is used for inquiring whether the user to be inquired has the symptoms to be supplemented corresponding to the initial medical record. The symptom to be supplemented corresponding to the initial medical record refers to a symptom which is not recorded in the initial medical record and has an association relation with the initial medical record.
In addition, the embodiment of the present application is not limited to the implementation of step 422, for example, in a possible implementation, step 422 may specifically include steps 4221 to 4224:
step 4221: and obtaining a similar medical record corresponding to the initial medical record according to the initial medical record corresponding to the user to be inquired and a pre-constructed medical record knowledge base. Wherein, the medical record knowledge base comprises similar medical records corresponding to the initial medical record.
The medical record knowledge base comprises the corresponding relation between the yth third medical record and the actual disease diagnosis result of the yth third medical record. Wherein Y is a positive integer, Y is less than or equal to Y, and Y is the number of the medical records in the third history.
The similar medical record refers to a medical record which is similar to the initial medical record corresponding to the user to be asked in the medical record knowledge base, and the similarity between the similar medical record and the initial medical record meets a preset similar condition.
The preset similarity condition may be preset, for example, the preset similarity condition may be that the similarity between the similar medical record and the initial medical record reaches a preset similarity threshold. For another example, if the similarities between all the third medical records in the medical record knowledge base and the initial medical record are sorted from high to low, the preset similarity condition may be that the arrangement position of the similarities between the similar medical records and the initial medical record is higher than the first preset position. For example, if the similarities between all the third medical records in the medical record knowledge base and the initial medical record are sorted from low to high, the preset similarity condition may be that the arrangement position of the similarities between the similar medical records and the initial medical record is lower than the second preset position.
In addition, the embodiment of the present application does not limit the process of acquiring similar medical records, for example, if the medical record knowledge base includes Y third medical records, the process of acquiring similar medical records may specifically be: and when the similarity between the initial medical record corresponding to the user to be asked and the y-th third medical record in the medical record knowledge base meets the preset similarity condition, determining the y-th third medical record as the similar medical record corresponding to the initial medical record. Wherein Y is a positive integer and is less than or equal to Y.
It should be noted that the embodiment of the present application is not limited to the implementation of calculating the similarity between two medical records, and may be implemented by using any existing or future method capable of calculating the similarity between two medical records.
Based on the related content in the step 4221, after the initial medical record corresponding to the user to be queried is obtained, similarity between the initial medical record and each third medical record in the medical record knowledge base can be calculated; and then determining each third history medical record with the corresponding similarity meeting the preset similarity condition as the similar medical record corresponding to the initial medical record, so as to determine the symptom to be supplemented corresponding to the initial medical record based on the similar medical records.
Step 4222: and determining a candidate disease diagnosis result corresponding to the initial medical record according to the actual disease diagnosis result of the similar medical record corresponding to the initial medical record.
The candidate disease diagnosis result corresponding to the initial medical record is a disease diagnosis result which can be determined based on the initial medical record corresponding to the user to be asked.
In the embodiment of the application, after all similar medical records corresponding to the initial medical record are obtained, the actual disease diagnosis result of each similar medical record can be determined as the candidate disease diagnosis result corresponding to the initial medical record, so that the symptom to be supplemented corresponding to the initial medical record can be determined according to the candidate disease diagnosis results.
Step 4223: and determining the symptom to be supplemented corresponding to the initial medical record according to the actual symptom corresponding to the candidate disease diagnosis result.
The actual symptoms corresponding to the candidate disease diagnosis result refer to symptoms that may appear in the patient having the candidate disease diagnosis result.
It should be noted that, for a candidate disease diagnosis, the candidate disease diagnosis may correspond to a plurality of actual symptoms, and different actual symptoms may have different degrees of importance for the candidate disease diagnosis. In addition, the higher the importance of an actual symptom to the candidate disease diagnosis, the higher the probability that the patient having the candidate disease diagnosis will present the actual symptom.
The embodiment of the present application is not limited to the implementation of step 4223, for example, in one possible implementation, when the number of candidate disease diagnosis results is T, and the number of actual symptoms corresponding to the tth candidate disease diagnosis result is NtIn this case, step 4223 may specifically include steps 42231 to 42233:
step 42231: corresponding N to the t-th candidate disease diagnosis resulttThe actual symptoms are all determined as candidate symptoms. Wherein T is a positive integer, T is less than or equal to T, T is a positive integer, NtIs a positive integer.
In this embodiment of the application, after T candidate disease diagnosis results are obtained, N corresponding to the 1 st candidate disease diagnosis result may be obtained1N corresponding to the actual symptom to the Tth candidate disease diagnosis resultTAll the actual symptoms are determined as candidate symptoms, so that the candidate symptoms corresponding to the initial medical record can be screened out later.
Step 42232: the question probability for each candidate symptom is calculated.
Wherein the inquiry probability refers to the possibility that the user to be inquired inquires whether the candidate symptom appears.
In addition, the embodiment of the present application does not limit the calculation process of the query probability, for example, in a possible implementation, the query probability of the u-th candidate symptom may be calculated by using formula (1).
Figure BDA0002921726440000251
In the formula, puThe question probability of the u-th candidate symptom;
Figure BDA0002921726440000252
(ii) the degree of significance of the u-th candidate symptom on the t-th candidate disease diagnosis; stSimilarity between a third history medical record corresponding to the u-th candidate symptom and an initial medical record corresponding to the user to be asked for diagnosis; u is a positive integer and is a negative integer,
Figure BDA0002921726440000253
if the u-th candidate symptom does not belong to the actual symptom corresponding to the t-th candidate disease diagnosis result, the importance degree of the u-th candidate symptom to the t-th candidate disease diagnosis result is set to 0. In addition, the embodiments of the present application are not limited to
Figure BDA0002921726440000261
The manner of acquisition of (a) may be, for example,
Figure BDA0002921726440000262
the obtaining method can be as follows: counting the co-occurrence probability of the u-th candidate symptom and the t-th candidate disease diagnosis result from a plurality of fourth historical medical records as
Figure BDA0002921726440000263
In addition, the embodiment of the present application does not limit the relationship between the first history medical record, the second history medical record, the third history medical record, and the fourth history medical record, and for example, the first history medical record, the second history medical record, the third history medical record, and the fourth history medical record may refer to the same history medical record or may refer to different history medical records.
Step 42233: according to the inquiry probability of each candidate symptom, from
Figure BDA0002921726440000264
And screening out the symptoms to be supplemented corresponding to the initial medical record from the candidate symptoms.
In the embodiment of the application, the acquisition
Figure BDA0002921726440000265
After the query probability for a candidate symptom, the symptom present in the initial medical record can be first queried from the candidate symptom
Figure BDA0002921726440000266
Deleting the candidate symptoms to obtain at least one remaining candidate symptom; and determining each residual candidate symptom with the corresponding inquiry probability meeting the preset inquiry condition as a to-be-supplemented symptom corresponding to the initial medical record. Wherein, the remaining candidate symptoms are candidate symptoms which do not appear in the initial medical record corresponding to the user to be asked for diagnosis.
It should be noted that the preset query condition may be preset, for example, the preset query condition may be that the query probability of the remaining candidate symptom is higher than a preset query threshold. For another example, if the query probabilities of all the remaining candidate symptoms are ranked from high to low, the preset query condition may be that the ranking position of the query probabilities of the remaining candidate symptoms is higher than the third preset position. For example, if the query probabilities of all the remaining candidate symptoms are ranked from low to high, the preset query condition may be that the ranking position of the query probabilities of the remaining candidate symptoms is lower than the fourth preset position.
Based on the relevant content of the step 4223, after each candidate disease diagnosis result is obtained, a to-be-supplemented symptom corresponding to the initial medical record can be screened from all actual symptoms corresponding to all candidate disease diagnosis results, so that the to-be-supplemented symptom can be used for perfecting the initial medical record corresponding to the user to be asked for consultation.
Step 4224: and determining a second inquiry question corresponding to the user to be inquired according to the symptom to be supplemented corresponding to the initial medical record.
In the embodiment of the application, after the D to-be-supplemented symptoms corresponding to the initial medical record are obtained, a D second inquiry question corresponding to the user to be inquired can be generated according to a D to-be-supplemented symptom corresponding to the initial medical record, so that the D second inquiry question is used for inquiring the user to be inquired whether the D to-be-supplemented symptom appears or not. Wherein D is a positive integer, D is less than or equal to D, and D is a positive integer.
Based on the related content in the above step 422, after the initial medical record corresponding to the user to be queried is obtained, the second query question corresponding to the initial medical record may be determined by using the third history medical record recorded in the medical record repository, so that the initial medical record may be subsequently refined based on the second query question.
Step 423: after the second inquiry question is displayed to the user to be inquired, second inquiry answers input by the user to be inquired for the second inquiry question are obtained.
The second inquiry answer refers to the reply content input by the user to be inquired aiming at the first inquiry question; and the second inquiry answer is used for indicating whether the user to be inquired has the symptoms to be supplemented corresponding to the initial medical record.
Step 424: and updating the initial medical record corresponding to the user to be queried by using the second query question and the second query answer, and returning to the step 422 until the preset stop condition is reached, and determining the pre-query medical record corresponding to the user to be queried according to the initial medical record corresponding to the user to be queried.
The embodiment of the present application does not limit the updating process of the initial medical record, for example, the second inquiry question and the corresponding second inquiry answer may be directly added to the initial medical record. For another example, the second semantic information can be extracted from the second inquiry question (e.g., if you are dizziness) and the corresponding second inquiry answer (e.g., yes), and the second semantic information is added to the initial medical record to obtain the updated initial medical record. The second semantic information refers to semantic information recorded in the second inquiry question and the corresponding second inquiry answer.
The preset stop condition may be preset, and the embodiment of the present application does not limit the preset stop condition. For example, the preset stop condition may be that the second inquiry question cannot be generated when step 422 is executed (i.e., the symptom to be supplemented corresponding to the initial medical record cannot be found when step 4223 is executed). For another example, the preset stop condition may be that the number of updates of the initial medical record reaches a preset number threshold.
Therefore, when the initial medical records of the current round are determined not to reach the preset stop condition, the initial medical records of the current round still need to be perfected, so that a second inquiry question corresponding to the initial medical records can be determined according to the initial medical records, and then the initial medical records are updated by utilizing the second inquiry question and a second inquiry answer corresponding to the second inquiry question, so that the updated initial medical records can record more complete disease information; however, when it is determined that the initial medical records of the current round reach the preset stop condition, it may be determined that the initial medical records of the current round have recorded relatively complete disease information, so to improve the inquiry efficiency, the initial medical records of the current round may be directly determined as the pre-inquiry medical records corresponding to the user to be inquired, so that the pre-inquiry medical records can accurately describe the physical condition of the user to be inquired, so that a subsequent doctor can perform subsequent operations (for example, perform detailed inquiry, or perform examination item arrangement, etc.) on the user to be inquired with reference to the pre-inquiry medical records.
Based on the relevant contents of S301 to S305, in the method for generating a medical record for pre-inquiry provided in the present application, after the input data carrying the disease condition information of the user to be inquired and input by the user to be inquired is obtained, the disease description text of the user to be inquired is generated according to the input data; generating the disease condition basic information of the user to be queried and a first query question corresponding to the user to be queried according to the disease condition description text, so as to obtain a first query answer input by the user to be queried for the first query question after the first query question is displayed to the user to be queried; and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question and the first inquiry answer.
It can be seen that, since the first inquiry question is used to inquire the user to be inquired about the disease condition supplementary information related to the disease condition basic information of the user to be inquired, the first inquiry answer input by the user to be inquired for the first inquiry question and the first inquiry question can accurately describe the disease condition supplementary information related to the disease condition basic information of the user to be inquired, so that the disease condition basic information, the first inquiry question and the first inquiry answer can comprehensively describe the body condition of the user to be inquired, and the pre-inquiry medical record generated based on the disease condition basic information, the first inquiry question and the first inquiry answer can accurately describe the body condition of the user to be inquired, so that the user to be inquired does not need to be manually diagnosed for a long time after the doctor obtains the pre-inquiry medical record (even does not need to manually ask the user to be inquired), therefore, the inquiry efficiency of doctors can be improved, and the medical efficiency can be improved.
Based on the method for generating the medical record for pre-inquiry provided by the embodiment of the method, the embodiment of the application also provides a device for generating the medical record for pre-inquiry, which is explained and explained below with reference to the accompanying drawings.
Device embodiment
The device embodiment introduces a device for generating a medical record for pre-inquiry, and please refer to the method embodiment for related contents.
Referring to fig. 4, the drawing is a schematic structural diagram of a medical record generation apparatus for pre-inquiry according to an embodiment of the present application.
The device 400 for generating a medical record for pre-inquiry provided by the embodiment of the application comprises:
a text generating unit 401, configured to generate a disease description text of a user to be asked according to input data of the user to be asked; wherein, the input data carries the self-stated disease information of the user to be asked;
a problem generating unit 402, configured to generate, according to the disease description text of the user to be asked, disease basic information of the user to be asked and a first inquiry problem corresponding to the user to be asked; the first inquiry question is used for inquiring condition supplementary information corresponding to the basic information of the disease condition from the user to be inquired;
an answer obtaining unit 403, configured to obtain a first inquiry answer input by the user to be inquired for the first inquiry question after the first inquiry question is displayed to the user to be inquired;
a medical record generating unit 404, configured to generate a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question, and the first inquiry answer.
In a possible implementation manner, the text generating unit 401 is specifically configured to: if the input data of the user to be asked for diagnosis comprises the voice to be recognized, performing voice recognition on the voice to be recognized to obtain a voice recognition result; determining a disease description text of the user to be asked according to the voice recognition result; if the input data of the user to be asked for diagnosis comprises an image to be identified, carrying out image identification on the image to be identified to obtain an image identification result; determining a disease description text of the user to be asked according to the image recognition result; if the input data of the user to be asked comprise a text to be processed, determining a disease description text of the user to be asked according to the text to be processed; if the input data of the user to be asked for a consultation comprises a video to be identified, carrying out image identification on each frame of video picture in the video to be identified to obtain a video identification result; and determining the disease description text of the user to be asked according to the video identification result.
In a possible implementation, the generation process of the basic information of the disease condition of the user to be asked for diagnosis includes:
carrying out entity labeling on the disease description text of the user to be asked for diagnosis to obtain a labeled text; determining the basic information of the disease symptoms of the user to be asked according to the labeling text;
alternatively, the first and second electrodes may be,
the generation process of the disease basic information of the user to be asked for diagnosis comprises the following steps:
semantic understanding is carried out on the disease condition description text of the user to be inquired to obtain a semantic understanding result corresponding to the disease condition description text; and determining the basic information of the disease symptoms of the user to be asked according to the semantic understanding result corresponding to the disease symptom description text.
In a possible implementation manner, the generating process of the first inquiry question corresponding to the user to be inquired includes:
determining the symptoms to be inquired of the user to be inquired according to the symptom description text of the user to be inquired;
determining a first inquiry question corresponding to the user to be inquired according to the symptom to be inquired of the user to be inquired and a pre-constructed question knowledge base; wherein the question knowledge base comprises a corresponding relationship between the symptoms to be interrogated and the first interrogation question.
In one possible implementation, the pre-inquiry medical record generating apparatus 400 further includes:
the mode generating unit is used for generating an inquiry mode of the first inquiry question according to the disease description text of the user to be inquired;
a content generating unit, configured to generate an inquiry display content of the first inquiry question according to an inquiry manner of the first inquiry question; wherein the interrogation display content of the first interrogation question comprises the first interrogation question;
and the question display unit is used for displaying the inquiry display content of the first inquiry question to the user to be inquired.
In one possible implementation, the pre-inquiry medical record generating apparatus 400 further includes:
the template acquisition unit is used for acquiring a medical record template corresponding to the user to be asked;
the medical record generating unit 404 is specifically configured to: and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question, the first inquiry answer and a medical record template corresponding to the user to be inquired.
In a possible implementation manner, the template obtaining unit is specifically configured to: determining the symptoms to be inquired of the user to be inquired according to the symptom description text of the user to be inquired; obtaining a medical record template corresponding to the user to be inquired according to the symptom to be inquired of the user to be inquired and a pre-constructed template knowledge base; the template knowledge base comprises a corresponding relation between the symptoms to be asked and the medical record templates corresponding to the users to be asked.
In a possible implementation manner, the medical record generating unit 404 includes:
a first generating subunit, configured to generate an initial medical record corresponding to the user to be asked according to the disease basic information, the first inquiry question, the first inquiry answer, and a medical record template corresponding to the user to be asked;
a second generation subunit, configured to generate a second inquiry question corresponding to the user to be inquired according to the initial medical record corresponding to the user to be inquired; the second inquiry question is used for inquiring whether the user to be inquired has the symptoms to be supplemented corresponding to the initial medical record;
an answer obtaining subunit, configured to obtain, after the second inquiry question is displayed to the user to be inquired, a second inquiry answer input by the user to be inquired for the second inquiry question;
and a medical record updating subunit, configured to update the initial medical record corresponding to the user to be asked by using the second inquiry question and the second inquiry answer, and return to the second generating subunit to execute the initial medical record corresponding to the user to be asked, so as to generate the second inquiry question corresponding to the user to be asked, until a preset stop condition is reached, and determine the pre-inquiry medical record corresponding to the user to be asked according to the initial medical record corresponding to the user to be asked.
In a possible implementation manner, the second generating subunit is specifically configured to: obtaining a similar medical record corresponding to the initial medical record according to the initial medical record corresponding to the user to be inquired and a pre-constructed medical record knowledge base; the similarity between the similar medical record and the initial medical record corresponding to the user to be asked for diagnosis meets a preset similarity condition; the medical record knowledge base comprises the similar medical records; determining a candidate disease diagnosis result corresponding to the initial medical record according to the actual disease diagnosis result of the similar medical record; determining the symptom to be supplemented corresponding to the initial medical record according to the actual symptom corresponding to the candidate disease diagnosis result; and determining a second inquiry question corresponding to the user to be inquired according to the symptom to be supplemented corresponding to the initial medical record.
Further, an embodiment of the present application further provides a device for generating a medical record for pre-inquiry, including: a processor, a memory, a system bus;
the processor and the memory are connected through the system bus;
the memory is configured to store one or more programs, the one or more programs including instructions, which when executed by the processor, cause the processor to perform any of the implementations of the pre-inquiry medical record generation method described above.
Further, an embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are run on a terminal device, the terminal device is caused to execute any implementation method of the pre-inquiry medical record generation method.
Further, an embodiment of the present application further provides a computer program product, which when running on a terminal device, enables the terminal device to execute any implementation method of the above pre-inquiry medical record generation method.
As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the above embodiment methods can be implemented by software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.
It should be noted that, in the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A method for generating a pre-inquiry medical record, the method comprising:
generating a disease description text of a user to be asked according to input data of the user to be asked; wherein, the input data carries the self-stated disease information of the user to be asked;
generating the disease basic information of the user to be inquired and a first inquiry question corresponding to the user to be inquired according to the disease description text of the user to be inquired; the first inquiry question is used for inquiring condition supplementary information corresponding to the basic information of the disease condition from the user to be inquired;
after the first inquiry question is displayed to the user to be inquired, acquiring a first inquiry answer input by the user to be inquired aiming at the first inquiry question;
and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question and the first inquiry answer.
2. The method according to claim 1, wherein the generation process of the basic information of the disease condition of the user to be asked for diagnosis comprises:
carrying out entity labeling on the disease description text of the user to be asked for diagnosis to obtain a labeled text; determining the basic information of the disease symptoms of the user to be asked according to the labeling text;
alternatively, the first and second electrodes may be,
the generation process of the disease basic information of the user to be asked for diagnosis comprises the following steps:
semantic understanding is carried out on the disease condition description text of the user to be inquired to obtain a semantic understanding result corresponding to the disease condition description text; and determining the basic information of the disease symptoms of the user to be asked according to the semantic understanding result corresponding to the disease symptom description text.
3. The method according to claim 1, wherein the generating process of the first inquiry question corresponding to the user to be inquired comprises:
determining the symptoms to be inquired of the user to be inquired according to the symptom description text of the user to be inquired;
determining a first inquiry question corresponding to the user to be inquired according to the symptom to be inquired of the user to be inquired and a pre-constructed question knowledge base; wherein the question knowledge base comprises a corresponding relationship between the symptoms to be interrogated and the first interrogation question.
4. The method of claim 1, further comprising:
generating an inquiry mode of the first inquiry question according to the disease description text of the user to be inquired;
generating inquiry display content of the first inquiry question according to the inquiry mode of the first inquiry question; wherein the interrogation display content of the first interrogation question comprises the first interrogation question;
the displaying the first inquiry question to the user to be inquired comprises:
and displaying the inquiry display content of the first inquiry question to the user to be inquired.
5. The method of claim 1, further comprising:
acquiring a medical record template corresponding to the user to be asked;
generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question and the first inquiry answer, wherein the pre-inquiry medical record comprises:
and generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question, the first inquiry answer and a medical record template corresponding to the user to be inquired.
6. The method according to claim 5, wherein the acquiring of the medical record template corresponding to the user to be asked comprises:
determining the symptoms to be inquired of the user to be inquired according to the symptom description text of the user to be inquired;
obtaining a medical record template corresponding to the user to be inquired according to the symptom to be inquired of the user to be inquired and a pre-constructed template knowledge base; the template knowledge base comprises a corresponding relation between the symptoms to be asked and the medical record templates corresponding to the users to be asked.
7. The method according to claim 5, wherein the generating a pre-inquiry medical record corresponding to the user to be inquired according to the disease basic information, the first inquiry question, the first inquiry answer and a medical record template corresponding to the user to be inquired comprises:
generating an initial medical record corresponding to the user to be asked according to the disease basic information, the first inquiry question, the first inquiry answer and a medical record template corresponding to the user to be asked;
generating a second inquiry question corresponding to the user to be inquired according to the initial medical record corresponding to the user to be inquired; the second inquiry question is used for inquiring whether the user to be inquired has the symptoms to be supplemented corresponding to the initial medical record;
after the second inquiry question is displayed to the user to be inquired, acquiring a second inquiry answer input by the user to be inquired aiming at the second inquiry question;
updating the initial medical record corresponding to the user to be asked by using the second inquiry question and the second inquiry answer, and returning to execute the step of generating the second inquiry question corresponding to the user to be asked according to the initial medical record corresponding to the user to be asked until a preset stop condition is reached, and determining the pre-inquiry medical record corresponding to the user to be asked according to the initial medical record corresponding to the user to be asked.
8. The method according to claim 7, wherein the generating a second inquiry question corresponding to the user to be inquired according to the initial medical record corresponding to the user to be inquired comprises:
obtaining a similar medical record corresponding to the initial medical record according to the initial medical record corresponding to the user to be inquired and a pre-constructed medical record knowledge base; the similarity between the similar medical record and the initial medical record corresponding to the user to be asked for diagnosis meets a preset similarity condition; the medical record knowledge base comprises the similar medical records;
determining a candidate disease diagnosis result corresponding to the initial medical record according to the actual disease diagnosis result of the similar medical record;
determining the symptom to be supplemented corresponding to the initial medical record according to the actual symptom corresponding to the candidate disease diagnosis result;
and determining a second inquiry question corresponding to the user to be inquired according to the symptom to be supplemented corresponding to the initial medical record.
9. A pre-interrogation medical record generation apparatus, the apparatus comprising:
the text generation unit is used for generating a disease description text of the user to be asked according to the input data of the user to be asked; wherein, the input data carries the self-stated disease information of the user to be asked;
the problem generation unit is used for generating the disease basic information of the user to be asked and the first inquiry problem corresponding to the user to be asked according to the disease description text of the user to be asked; the first inquiry question is used for inquiring condition supplementary information corresponding to the basic information of the disease condition from the user to be inquired;
the answer obtaining unit is used for obtaining a first inquiry answer input by the user to be inquired aiming at the first inquiry question after the first inquiry question is displayed to the user to be inquired;
and a medical record generating unit, configured to generate a pre-inquiry medical record corresponding to the user to be subjected to inquiry according to the disease basic information, the first inquiry question, and the first inquiry answer.
10. An apparatus, characterized in that the apparatus comprises: a processor, a memory, a system bus;
the processor and the memory are connected through the system bus;
the memory is to store one or more programs, the one or more programs comprising instructions, which when executed by the processor, cause the processor to perform the method of generating a pre-interrogation medical record of any of claims 1-8.
CN202110120160.XA 2021-01-28 2021-01-28 Pre-inquiry case history generation method and device Pending CN112837772A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110120160.XA CN112837772A (en) 2021-01-28 2021-01-28 Pre-inquiry case history generation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110120160.XA CN112837772A (en) 2021-01-28 2021-01-28 Pre-inquiry case history generation method and device

Publications (1)

Publication Number Publication Date
CN112837772A true CN112837772A (en) 2021-05-25

Family

ID=75930808

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110120160.XA Pending CN112837772A (en) 2021-01-28 2021-01-28 Pre-inquiry case history generation method and device

Country Status (1)

Country Link
CN (1) CN112837772A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114550863A (en) * 2022-02-25 2022-05-27 首都医科大学附属北京安贞医院 Medical record generation method, device, system, equipment and storage medium
CN116028603A (en) * 2022-06-07 2023-04-28 成都成电金盘健康数据技术有限公司 Intelligent pre-consultation method, device and system based on big data, and storage medium
CN116913450A (en) * 2023-09-07 2023-10-20 北京左医科技有限公司 Method and device for generating medical records in real time

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105912846A (en) * 2016-04-07 2016-08-31 南京小网科技有限责任公司 Intelligent medical aid decision making system on basis of cloud computing technique and medical knowledge base technique
CN109887557A (en) * 2018-12-29 2019-06-14 北京天鹏恒宇科技发展有限公司 A kind of pre- interrogation system of intelligent sound
CN111933239A (en) * 2020-09-17 2020-11-13 泰康保险集团股份有限公司 Data processing method, device, system and storage medium
CN112015917A (en) * 2020-09-07 2020-12-01 平安科技（深圳）有限公司 Data processing method and device based on knowledge graph and computer equipment

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105912846A (en) * 2016-04-07 2016-08-31 南京小网科技有限责任公司 Intelligent medical aid decision making system on basis of cloud computing technique and medical knowledge base technique
CN109887557A (en) * 2018-12-29 2019-06-14 北京天鹏恒宇科技发展有限公司 A kind of pre- interrogation system of intelligent sound
CN112015917A (en) * 2020-09-07 2020-12-01 平安科技（深圳）有限公司 Data processing method and device based on knowledge graph and computer equipment
CN111933239A (en) * 2020-09-17 2020-11-13 泰康保险集团股份有限公司 Data processing method, device, system and storage medium

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114550863A (en) * 2022-02-25 2022-05-27 首都医科大学附属北京安贞医院 Medical record generation method, device, system, equipment and storage medium
CN116028603A (en) * 2022-06-07 2023-04-28 成都成电金盘健康数据技术有限公司 Intelligent pre-consultation method, device and system based on big data, and storage medium
CN116028603B (en) * 2022-06-07 2023-12-19 成都成电金盘健康数据技术有限公司 Intelligent pre-consultation method, device and system based on big data, and storage medium
CN116913450A (en) * 2023-09-07 2023-10-20 北京左医科技有限公司 Method and device for generating medical records in real time
CN116913450B (en) * 2023-09-07 2023-12-19 北京左医科技有限公司 Method and device for generating medical records in real time

Similar Documents

Publication Publication Date Title
US9779211B2 (en) Computer-assisted abstraction for reporting of quality measures
US10541053B2 (en) Automated clinical indicator recognition with natural language processing
CN112837772A (en) Pre-inquiry case history generation method and device
US8612261B1 (en) Automated learning for medical data processing system
US8671112B2 (en) Methods and apparatus for automated image classification
KR102217457B1 (en) A chat service providing system that can provide medical consultation according to customer's needs with a chat robot
US20130138457A1 (en) Electronic health record system and method for patient encounter transcription and documentation
CN111489800A (en) Analysis method and system for identifying and storing medical record and report list images
CN113724848A (en) Medical resource recommendation method, device, server and medium based on artificial intelligence
CN108109689B (en) Diagnosis and treatment session method and device, storage medium and electronic equipment
CN117093679B (en) Large language model intelligent inquiry dialogue method, system, equipment and medium
CN109087688B (en) Patient information acquisition method, apparatus, computer device and storage medium
CN109871440B (en) Intelligent prompting method, device and equipment based on semantic analysis
CN113409907A (en) Intelligent pre-inquiry method and system based on Internet hospital
CN112349435A (en) Online inquiry method, device, server, medium and system
CN114613461A (en) Intelligent entry method and system for outpatient service medical record
CN109065015B (en) Data acquisition method, device and equipment and readable storage medium
CN109299238B (en) Data query method and device
CN114999676A (en) Method, system, apparatus and medium for automatically replying to medical consultation
KR20110048675A (en) Call center counsel method and counsel system using voice recognition and tagging
CN109599176B (en) Method and device for recommending inquiry skills and online auxiliary diagnosis system
CN113113093A (en) Clinical and image-based case data management system
CN111524515A (en) Voice interaction method and device, electronic equipment and readable storage medium
AU2020265819A1 (en) System and method for phrase comparison consolidation and reconciliation
CN116719840A (en) Medical information pushing method based on post-medical-record structured processing

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB03 Change of inventor or designer information

Inventor after: Wei Chengyong

Inventor after: He Zhiyang

Inventor after: Zhao Jinghe

Inventor after: Luxiaoliang

Inventor before: Wei Chengyong

CB03 Change of inventor or designer information
CB02 Change of applicant information

Address after: 230088 floor 23-24, building A5, No. 666, Wangjiang West Road, high tech Zone, Hefei, Anhui Province

Applicant after: Anhui Xunfei Medical Co.,Ltd.

Address before: 230088 18th floor, building A5, NO.666, Wangjiang West Road, high tech Zone, Hefei City, Anhui Province

Applicant before: ANHUI IFLYTEK MEDICAL INFORMATION TECHNOLOGY CO.,LTD.

CB02 Change of applicant information
CB02 Change of applicant information

Address after: 230000 floor 23-24, building A5, No. 666, Wangjiang West Road, high tech Zone, Hefei City, Anhui Province

Applicant after: IFLYTEK Medical Technology Co.,Ltd.

Address before: 230088 floor 23-24, building A5, No. 666, Wangjiang West Road, high tech Zone, Hefei, Anhui Province

Applicant before: Anhui Xunfei Medical Co.,Ltd.

CB02 Change of applicant information