CN113409907A - Intelligent pre-inquiry method and system based on Internet hospital - Google Patents
Intelligent pre-inquiry method and system based on Internet hospital Download PDFInfo
- Publication number
- CN113409907A CN113409907A CN202110813795.8A CN202110813795A CN113409907A CN 113409907 A CN113409907 A CN 113409907A CN 202110813795 A CN202110813795 A CN 202110813795A CN 113409907 A CN113409907 A CN 113409907A
- Authority
- CN
- China
- Prior art keywords
- inquiry
- information
- questions
- disease
- trained
- 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
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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to an intelligent pre-inquiry method and system based on an internet hospital, which are characterized in that input chief complaint information is converted into word vectors, pre-trained Bi-LSTM-CRF models and pre-trained GCNN models are utilized to obtain disease information, a first inquiry mode is triggered according to the disease information, a plurality of first inquiry problems are generated based on the disease information configuration in the first inquiry mode to realize intelligent pre-inquiry, and an electronic medical record is automatically generated according to the inquiry problems and corresponding feedback information thereof by collecting the feedback information of a user to the first inquiry problems, so that a doctor can know the illness state of a patient in advance, the inquiry process is simplified, and the inquiry efficiency is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an intelligent pre-inquiry method and system based on an internet hospital.
Background
The existing inquiry method mainly inquires patients step by step through the experience of doctors to obtain necessary diagnosis information; for necessary inquiry questions, doctors need to repeatedly inquire each patient in each inquiry process, the inquiry takes long time, and the inquiry efficiency is low.
Disclosure of Invention
The embodiment of the application provides an intelligent pre-inquiry method and system based on an internet hospital, which can perform intelligent pre-inquiry on a patient and generate an electronic medical record, so that the inquiry efficiency is improved.
In a first aspect of the embodiments of the present application, an intelligent pre-inquiry method based on an internet hospital is provided, which includes the following steps:
responding to the inquiry request, acquiring input main complaint information and converting the main complaint information into a plurality of word vectors; the complaint information is information which is input by a user and describes the disease condition;
acquiring key information by utilizing a pre-trained Bi-LSTM-CRF model based on the plurality of word vectors; wherein the key information includes symptoms, diseases and drug names;
acquiring disease information by utilizing a pre-trained GCNN model based on the key information and the word vectors;
triggering a first inquiry mode based on the disease information, configuring and generating a plurality of first inquiry questions based on the disease information in the first inquiry mode, and acquiring first feedback information of a user for answering the plurality of first inquiry questions;
and generating an electronic medical record according to the plurality of first inquiry questions and the first feedback information.
In a second aspect of the embodiments of the present application, an intelligent pre-inquiry system based on an internet hospital is provided, which includes:
the word vector acquisition module is used for responding to the inquiry request, acquiring the input main complaint information and converting the main complaint information into a plurality of word vectors; the complaint information is information which is input by a user and describes the disease condition;
the key information acquisition module is used for acquiring key information by utilizing a pre-trained Bi-LSTM-CRF model based on the word vectors; wherein the key information includes symptoms, diseases and drug names;
the disease information acquisition module is used for acquiring disease information by utilizing a pre-trained GCNN model based on the key information and the word vectors;
the inquiry module is used for triggering a first inquiry mode based on the disease information, generating a plurality of first inquiry questions based on the disease information configuration in the first inquiry mode, and acquiring first feedback information of a user for answering the plurality of first inquiry questions;
and the intelligent pre-inquiry module based on the Internet hospital is used for generating the electronic medical record according to the plurality of first inquiry questions and the first feedback information.
In a third aspect of the embodiments of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, the computer program, when being executed by a processor, implementing the steps of the internet hospital-based intelligent pre-interrogation method as described in any one of the above.
In a fourth aspect of the embodiments of the present application, there is provided a computer device, comprising a memory, a processor and a computer program stored in the memory and executable by the processor, wherein the processor executes the computer program to implement the steps of the internet hospital-based intelligent pre-interrogation method according to any one of the above.
In the embodiment of the application, the input chief complaint information is converted into word vectors, the pre-trained Bi-LSTM-CRF model and the pre-trained GCNN model are used for acquiring disease information, a first inquiry mode is triggered according to the disease information, a plurality of first inquiry questions are generated based on the disease information configuration in the first inquiry mode to realize intelligent pre-inquiry, and the electronic medical records are automatically generated according to the inquiry questions and the corresponding feedback information of the inquiry questions by collecting the feedback information of the user on the plurality of first inquiry questions, so that the doctor can know the illness state of the patient in advance, the inquiry process is simplified, and the inquiry efficiency is improved.
For a better understanding and practice, the invention is described in detail below with reference to the accompanying drawings.
Drawings
Fig. 1 is a schematic view of an application scenario of an internet hospital-based intelligent pre-inquiry method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for Internet hospital-based intelligent pre-interrogation in accordance with an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an internet hospital-based intelligent pre-inquiry system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
It should be understood that the embodiments described are only some embodiments of the present application, and not all embodiments. All other examples, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments in the present application, belong to the scope of protection of the embodiments in the present application.
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the present application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the application, as detailed in the appended claims. In the description of the present application, it is to be understood that the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not necessarily used to describe a particular order or sequence, nor are they to be construed as indicating or implying relative importance. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
In addition, in the description of the present application, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
The intelligent pre-inquiry method based on the Internet hospital can be applied to the application environment shown in fig. 1. In which a terminal 101 communicates with a server 102 via a network. The terminal 101 is configured to obtain the chief complaint information and the inquiry request input by the user, and send the chief complaint information and the inquiry request to the server 102 through the network, and the server 102 is configured to perform data processing on the chief complaint information and the inquiry request and generate an electronic medical record.
The terminal 101 may be various personal computers, notebook computers, smart phones, tablet computers, portable wearable devices, or other devices that can communicate with the server 101 through a network, and the server 102 may be an independent server or a server cluster formed by a plurality of servers.
As shown in fig. 2, the invention provides an intelligent pre-inquiry method based on an internet hospital, which comprises the following steps:
step S1: responding to the inquiry request, acquiring input main complaint information and converting the main complaint information into a plurality of word vectors;
the chief complaint information is information describing disease condition input by the user, and can be input on a terminal with a text input function. Specifically, the complaint information may include medicine information and disease information; the drug information includes, but is not limited to, drug name information, drug action information, drug type information, and the like, which can determine the related drug. The disease information includes, but is not limited to, information of name of disease, information of symptom corresponding to disease, information of location of disease, information of disease degree, and the like, which can identify related disease.
Word Embedding (Word Embedding) refers to a method for converting words in a text into digital vectors, a high-dimensional space with a dimension of all Word quantities is embedded into a continuous vector space with a much lower dimension, each Word or Word group is mapped into a vector on a real number domain, so that Word vectors are generated, the similarity of words corresponds to the distance of the vectors in the vector space, and similar operations such as 'diarrhea', 'King-' man + 'woman' ═ and 'queen', and the like can be realized after vectorization of words. Specifically, the main complaint information can be divided into a plurality of words by using a word segmentation tool such as jieba, and then the plurality of words after word segmentation can be converted into a plurality of word vectors by using a common word embedding method such as one-hot coding, TF-IDF algorithm, word-context matrix construction and the like.
In one embodiment, the step of converting the complaint information into a word vector comprises:
segmenting the chief complaint information into a plurality of words;
converting the plurality of words into a plurality of word vectors using a pre-trained BERT model.
Specifically, the chief complaint information may be segmented into a plurality of words by using a jieba-like segmentation tool.
The BERT model (Bidirectional Encoder reproduction from transformations) is an advanced pre-training word vector model, further enhances the generalization of the word vector model, fully describes the character level, the word level, the sentence level and even the inter-sentence relation characteristics, and can better represent syntax and semantic information of different contexts. The BERT model is used for generating high-quality word vectors, so that the extraction and classification of disease information are facilitated, and the accuracy of generating the electronic medical record is improved.
Step S2: obtaining key information by using a pre-trained Bi-LSTM-CRF model; wherein the key information includes symptoms, diseases and drug names;
named entity recognition refers to a process of recognizing entities with specific meanings from texts and dividing the entities into specified categories, and mainly includes recognition of names of people, places, organizations, proper nouns and the like. In the embodiment of the application, the identification of symptoms, diseases and drug names in the text vector is realized by using a pre-trained Bi-LSTM-CRF model. The Bi-LSTM-CRF model mainly comprises an input feature layer, a Bi-LSTM intermediate layer and a CRF output layer, wherein firstly, word vectors are used as the input of the model, the Bi-LSTM intermediate layer adopts an LSTM neural network layer containing forward and backward directions to model an input text sequence, and finally, the CRF output layer is adopted to generate a corresponding category label sequence. For example, for the user entered complaint information: "do doctors feel a headache, fever, and a runny nose, but not a cold? ' the key information of ' headache fever ', ' cold ' and the like is extracted by using a pre-trained Bi-LSTM-CRF model, wherein the ' headache fever ' belongs to symptoms, and the ' cold ' belongs to diseases.
In the embodiment of the present application, the Bi-LSTM-CRF model is a model that is trained in advance using a large amount of training texts and has a training precision meeting a preset requirement, and specifically, before the step of inputting the word vector into the pre-trained Bi-LSTM-CRF model, the method further includes:
acquiring a training text from a database;
pre-training the Bi-LSTM-CRF model by using the training text to obtain the training precision of the Bi-LSTM-CRF model;
and adjusting the model parameters of the Bi-LSTM-CRF model until the training precision of the Bi-LSTM-CRF model reaches the preset requirement.
The training text can be medical text data marked with labels such as symptoms, diseases and drug names; the training text can be extracted from a pre-constructed medical knowledge graph, and the medical knowledge graph comprises a plurality of medical entities and the interrelation among the medical entities.
The training precision requirement of the Bi-LSTM-CRF model can be set according to the actual requirement of a user,
step S3: acquiring disease information by utilizing a pre-trained GCNN model based on the key information and the word vectors;
the GCNN model (Gated Convolutional Neural networks) is characterized in that a gating unit is added in a traditional Convolutional layer, compared with a traditional CNN model, the GCNN model retains the nonlinear capacity through the gating unit, can filter out useless information, relieve gradient propagation, reduce gradient diffusion and better extract useful characteristics. In the embodiment of the application, the GCNN model is trained by using a text training set comprising various kinds of disease information, after the accuracy of the GCNN model is improved, the pre-trained GCNN model is used for carrying out disease classification according to key information and text vectors to obtain the disease information.
Step S4: triggering a first inquiry mode based on the disease information, configuring and generating a plurality of first inquiry questions based on the disease information in the first inquiry mode, and acquiring first feedback information of a user for answering the plurality of first inquiry questions;
the first inquiry mode is inquiry of relevant inquiry questions based on disease information, and can be triggered according to the disease names in the disease information. In one embodiment, when the first inquiry mode is triggered, each inquiry question may be configured as an inquiry window or an inquiry dialog, and the display is output to the user through the display of the electronic device, so as to obtain the feedback information input by the user for each inquiry question, thereby implementing intelligent pre-inquiry for the user.
In one embodiment, the step of generating a number of first interrogation questions based on the disease information configuration comprises:
and inputting the disease information into a pre-trained text generation model, generating a plurality of first inquiry questions and sequentially configuring the questions according to a preset sequence.
In one embodiment, the text generation model is based on a Seq2Seq algorithm, and is obtained by corpus training including a large amount of disease and symptom information and query sentences, and the Seq2Seq algorithm includes an encoder and a decoder, wherein the encoder encodes an input sequence, converts the sequence according to a preset conversion function, and decodes the sequence in the decoder to obtain output sequences in different forms. In the embodiment of the application, the corresponding inquiry questions are generated and configured by acquiring trigger words such as disease names, drug names or symptom names in the input information and utilizing the pre-trained text generation model,
in one embodiment, the internet hospital-based intelligent pre-inquiry method further comprises the following steps:
and when the feedback information of the last first inquiry question is acquired, ending the first inquiry mode.
After the first inquiry mode is finished, the inquiry questions and the corresponding feedback information are integrated and counted to generate the electronic medical record, so that the online inquiry efficiency of the internet hospital is greatly improved, the waiting time of a patient is reduced, and the repeated labor of a doctor is reduced.
Step S5: and generating an electronic medical record according to the plurality of first inquiry questions and the first feedback information.
In one embodiment, each inquiry question and the corresponding feedback information thereof can be combined in sequence according to the configuration sequence of each inquiry question to generate the electronic medical record. In other embodiments, the inquiry questions and the corresponding feedback information may be combined according to the importance ranking of the preset rules, or may be specifically set according to the actual situation of the user.
In the embodiment of the application, the input chief complaint information is converted into word vectors, the pre-trained Bi-LSTM-CRF model and the pre-trained GCNN model are used for acquiring disease information, a first inquiry mode is triggered according to the disease information, a plurality of first inquiry questions are generated based on the disease information configuration in the first inquiry mode to realize intelligent pre-inquiry, and the electronic medical records are automatically generated according to the inquiry questions and the corresponding feedback information of the inquiry questions by collecting the feedback information of the user on the plurality of first inquiry questions, so that the doctor can know the illness state of the patient in advance, the inquiry process is simplified, and the inquiry efficiency is improved.
In one embodiment, after the step of obtaining the disease information by using the pre-trained GCNN model, the method further comprises:
if the pre-trained GCNN model is not used for acquiring the disease information, a second inquiry mode is triggered, and a plurality of second inquiry questions are acquired from the database and configured in the second inquiry mode;
acquiring second feedback information of the user on the plurality of second inquiry questions;
and generating an electronic medical record according to the plurality of second inquiry questions and the second feedback information.
The second inquiry mode is used for implementing inquiry of general inquiry questions, wherein the second inquiry questions are a plurality of general inquiry questions stored in the database in advance, and may include a plurality of general inquiry questions obtained by analyzing and processing a large number of medical records in advance.
In one embodiment, the step of configuring the number of second interrogation questions comprises:
sequentially configuring each second inquiry question according to a preset sequence;
and when the feedback information of the last second inquiry question is acquired, ending the second inquiry mode.
In one embodiment, the step of collecting second feedback information of the user on the second plurality of inquiry questions comprises:
preferably, in the step of sequentially configuring each second inquiry question, after the feedback information of the user to the current inquiry question is acquired, the next second inquiry question is configured according to a preset sequence until the feedback information of the last second inquiry question is acquired, and at this time, the second inquiry mode is ended. The sequence of the second inquiry questions can be sorted according to the importance or the popularity, or can be set according to the actual situation of the user.
When the pre-trained GCNN model does not acquire disease information, judging that the chief complaint of the user cannot be identified, entering a second inquiry mode to execute a general inquiry process, calling a plurality of second inquiry questions from a database and configuring, collecting second feedback information of the user answering the plurality of second inquiry questions, and generating an electronic medical record according to the collected inquiry questions and the corresponding second feedback information, so that pre-inquiry in the general inquiry mode is realized, and the inquiry process is simplified.
In one embodiment, the method further comprises the following steps:
acquiring identity information of a user;
loading a historical electronic medical record corresponding to the identity information from a database;
when the current inquiry question is the same as the inquiry question in the historical electronic medical record, displaying historical feedback information corresponding to the inquiry question;
and when the clicking operation of the user is detected and falls within the display area of the historical feedback information, taking the historical feedback information as the feedback information of the current inquiry question.
The current inquiry question may be a first inquiry question in the first inquiry mode, or may be a second inquiry question in the second inquiry mode. Whether the user is an old user can be judged according to the identity information of the user, if the user is the old user, the system can load a historical electronic medical record of the user, the historical electronic medical record stores historical inquiry records of the user, common inquiry questions comprise user information (such as sex and age) and/or medical history information (allergy history, inoculation history and past history), and the user can select the historical feedback information to be used for the inquiry according to needs by displaying the historical feedback information, so that the problem of repeated inquiry is avoided, and the inquiry efficiency is improved.
As shown in fig. 3, an embodiment of the present application further provides an intelligent pre-inquiry system based on an internet hospital, including:
the word vector acquisition module 1 is used for responding to the inquiry request, acquiring the input chief complaint information and converting the chief complaint information into a plurality of word vectors; the complaint information is information which is input by a user and describes the disease condition;
the key information acquisition module 2 is used for acquiring key information by utilizing a pre-trained Bi-LSTM-CRF model based on the word vectors; wherein the key information includes symptoms, diseases and drug names;
the disease information acquisition module 3 is used for acquiring disease information by utilizing a pre-trained GCNN model based on the key information and the word vectors;
the inquiry module 4 is configured to trigger a first inquiry mode based on the disease information, generate a plurality of first inquiry questions based on the disease information configuration in the first inquiry mode, and acquire first feedback information of a user in response to the plurality of first inquiry questions;
and the intelligent pre-inquiry module 5 based on the internet hospital is used for generating the electronic medical record according to the plurality of first inquiry questions and the first feedback information.
It should be noted that, when the internet hospital-based intelligent pre-inquiry system provided in the foregoing embodiment executes the internet hospital-based intelligent pre-inquiry method, only the division of the functional modules is used for illustration, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the intelligent pre-inquiry system based on the internet hospital provided by the embodiment and the intelligent pre-inquiry method based on the internet hospital belong to the same concept, and the specific implementation process is detailed in the method embodiment and is not described herein again.
The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the internet hospital-based intelligent pre-inquiry method as described in any one of the above.
Embodiments of the present application may take the form of a computer program product embodied on one or more storage media including, but not limited to, disk storage, CD-ROM, optical storage, and the like, in which program code is embodied. Computer readable storage media, which include both non-transitory and non-transitory, removable and non-removable media, may implement any method or technology for storage of information. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of the storage medium of the computer include, but are not limited to: phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, may be used to store information that may be accessed by a computing device.
The embodiment of the present application further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the steps of the internet hospital-based intelligent pre-inquiry method as described in any one of the above when executing the computer program.
According to the intelligent pre-inquiry method based on the Internet hospital, the intelligent pre-inquiry is carried out on the chief complaint information input by the user, the feedback information of the user is obtained, the description of the user is converted into the electronic medical record according with the reading and writing habits of the doctor by using the natural language processing technology, the inquiry time and the inquiry process of the doctor are reduced, and the inquiry efficiency can be effectively improved.
The present invention is not limited to the above-described embodiments, and various modifications and variations of the present invention are intended to be included within the scope of the claims and the equivalent technology of the present invention if they do not depart from the spirit and scope of the present invention.
Claims (10)
1. An intelligent pre-inquiry method based on an internet hospital is characterized by comprising the following steps:
responding to the inquiry request, acquiring input main complaint information and converting the main complaint information into a plurality of word vectors; the complaint information is information which is input by a user and describes the disease condition;
acquiring key information by utilizing a pre-trained Bi-LSTM-CRF model based on the plurality of word vectors; wherein the key information includes symptoms, diseases and drug names;
acquiring disease information by utilizing a pre-trained GCNN model based on the key information and the word vectors;
triggering a first inquiry mode based on the disease information, configuring and generating a plurality of first inquiry questions based on the disease information in the first inquiry mode, and acquiring first feedback information of a user for answering the plurality of first inquiry questions;
and generating an electronic medical record according to the plurality of first inquiry questions and the first feedback information.
2. The intelligent internet hospital-based pre-interrogation method according to claim 1, wherein the step of generating a number of first interrogation questions based on the disease information configuration comprises:
and inputting the disease information into a pre-trained text generation model, generating a plurality of first inquiry questions and sequentially configuring the questions according to a preset sequence.
3. The intelligent internet hospital-based pre-inquiry method according to claim 2, further comprising the steps of:
and when the feedback information of the last first inquiry question is acquired, ending the first inquiry mode.
4. The intelligent internet hospital-based pre-inquiry method according to claim 1, further comprising, after the step of obtaining disease information using a pre-trained GCNN model:
if the pre-trained GCNN model is not used for acquiring the disease information, a second inquiry mode is triggered, and a plurality of second inquiry questions are acquired from the database and configured in the second inquiry mode;
collecting second feedback information of the user for answering the plurality of second inquiry questions;
and generating an electronic medical record according to the plurality of second inquiry questions and the second feedback information.
5. The internet hospital-based intelligent pre-interrogation method of claim 1, wherein the step of converting the chief complaint information into a plurality of word vectors comprises:
segmenting the chief complaint information into a plurality of words;
converting the plurality of words into a plurality of word vectors using a pre-trained BERT model.
6. The internet hospital-based intelligent pre-interrogation method of claim 1, further comprising, prior to the step of entering the word vector into a pre-trained Bi-LSTM-CRF model:
acquiring a training text from a database; the training text is corpus data including symptoms, diseases and drug name labels;
pre-training the Bi-LSTM-CRF model by using the training text to obtain the training precision of the Bi-LSTM-CRF model;
and adjusting the model parameters of the Bi-LSTM-CRF model until the training precision of the Bi-LSTM-CRF model reaches the preset requirement.
7. The internet hospital-based intelligent pre-interrogation method according to any one of claims 1-4, further comprising the steps of:
acquiring identity information of a user;
loading a historical electronic medical record corresponding to the identity information from a database;
if the current inquiry question is the same as the inquiry question in the historical electronic medical record, displaying historical feedback information corresponding to the inquiry question;
if the clicking operation of the user is detected and the clicking operation falls in a display area of historical feedback information, taking the historical feedback information as the feedback information of the current inquiry question; wherein the current inquiry question is a first inquiry question or a second inquiry question.
8. An intelligent pre-interrogation system based on internet hospitals, comprising:
the word vector acquisition module is used for responding to the inquiry request, acquiring the input main complaint information and converting the main complaint information into a plurality of word vectors; the complaint information is information which is input by a user and describes the disease condition;
the key information acquisition module is used for acquiring key information by utilizing a pre-trained Bi-LSTM-CRF model based on the word vectors; wherein the key information includes symptoms, diseases and drug names;
the disease information acquisition module is used for acquiring disease information by utilizing a pre-trained GCNN model based on the key information and the word vectors;
the inquiry module is used for triggering a first inquiry mode based on the disease information, generating a plurality of first inquiry questions based on the disease information configuration in the first inquiry mode, and acquiring first feedback information of a user for answering the plurality of first inquiry questions;
and the intelligent pre-inquiry module based on the Internet hospital is used for generating the electronic medical record according to the plurality of first inquiry questions and the first feedback information.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program when executed by a processor implements the steps of the internet hospital based intelligent pre-interrogation method as claimed in any one of claims 1 to 7.
10. A computer device, characterized by: comprising a memory, a processor and a computer program stored in said memory and executable by said processor, said processor implementing the steps of the internet hospital-based intelligent pre-interrogation method according to any one of claims 1 to 7 when executing said computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110813795.8A CN113409907A (en) | 2021-07-19 | 2021-07-19 | Intelligent pre-inquiry method and system based on Internet hospital |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110813795.8A CN113409907A (en) | 2021-07-19 | 2021-07-19 | Intelligent pre-inquiry method and system based on Internet hospital |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113409907A true CN113409907A (en) | 2021-09-17 |
Family
ID=77686893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110813795.8A Pending CN113409907A (en) | 2021-07-19 | 2021-07-19 | Intelligent pre-inquiry method and system based on Internet hospital |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113409907A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114155962A (en) * | 2022-02-10 | 2022-03-08 | 北京妙医佳健康科技集团有限公司 | Data cleaning method and method for constructing disease diagnosis by using knowledge graph |
| CN114300160A (en) * | 2021-11-16 | 2022-04-08 | 北京左医科技有限公司 | Inquiry dialogue method and system |
| 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 |
| CN117592567A (en) * | 2023-11-21 | 2024-02-23 | 广州方舟信息科技有限公司 | Medicine question-answer model training method, device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017097061A1 (en) * | 2015-12-07 | 2017-06-15 | 中兴通讯股份有限公司 | Smart response method and apparatus |
| CN111326251A (en) * | 2020-02-13 | 2020-06-23 | 北京百度网讯科技有限公司 | Method and device for outputting inquiry questions and electronic equipment |
| US20200227147A1 (en) * | 2019-01-10 | 2020-07-16 | 3M Innovative Properties Company | Automated generation of codes |
| CN112001177A (en) * | 2020-08-24 | 2020-11-27 | 浪潮云信息技术股份公司 | Electronic medical record named entity identification method and system integrating deep learning and rules |
| CN113051905A (en) * | 2019-12-28 | 2021-06-29 | 中移(成都)信息通信科技有限公司 | Medical named entity recognition training model and medical named entity recognition method |
-
2021
- 2021-07-19 CN CN202110813795.8A patent/CN113409907A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017097061A1 (en) * | 2015-12-07 | 2017-06-15 | 中兴通讯股份有限公司 | Smart response method and apparatus |
| US20200227147A1 (en) * | 2019-01-10 | 2020-07-16 | 3M Innovative Properties Company | Automated generation of codes |
| CN113051905A (en) * | 2019-12-28 | 2021-06-29 | 中移(成都)信息通信科技有限公司 | Medical named entity recognition training model and medical named entity recognition method |
| CN111326251A (en) * | 2020-02-13 | 2020-06-23 | 北京百度网讯科技有限公司 | Method and device for outputting inquiry questions and electronic equipment |
| CN112001177A (en) * | 2020-08-24 | 2020-11-27 | 浪潮云信息技术股份公司 | Electronic medical record named entity identification method and system integrating deep learning and rules |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114300160A (en) * | 2021-11-16 | 2022-04-08 | 北京左医科技有限公司 | Inquiry dialogue method and system |
| CN114155962A (en) * | 2022-02-10 | 2022-03-08 | 北京妙医佳健康科技集团有限公司 | Data cleaning method and method for constructing disease diagnosis by using knowledge graph |
| 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 |
| CN117592567A (en) * | 2023-11-21 | 2024-02-23 | 广州方舟信息科技有限公司 | Medicine question-answer model training method, device, electronic equipment and storage medium |
| CN117592567B (en) * | 2023-11-21 | 2024-05-28 | 广州方舟信息科技有限公司 | Medicine question-answer model training method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109906449B (en) | Searching method and device | |
| CN113409907A (en) | Intelligent pre-inquiry method and system based on Internet hospital | |
| CN112131393A (en) | Construction method of medical knowledge map question-answering system based on BERT and similarity algorithm | |
| CN108899064A (en) | Electronic health record generation method, device, computer equipment and storage medium | |
| CN112667799B (en) | Medical question-answering system construction method based on language model and entity matching | |
| CN110931137B (en) | Machine-assisted dialog systems, methods, and apparatus | |
| WO2023029506A1 (en) | Illness state analysis method and apparatus, electronic device, and storage medium | |
| WO2022227203A1 (en) | Triage method, apparatus and device based on dialogue representation, and storage medium | |
| CN114765075A (en) | Medicine recommendation method, device and system, electronic equipment and storage medium | |
| CN111651579B (en) | Information query method, device, computer equipment and storage medium | |
| CN110752027B (en) | Electronic medical record data pushing method, device, computer equipment and storage medium | |
| CN115714030A (en) | Medical question-answering system and method based on pain perception and active interaction | |
| CN112151187B (en) | Information query method, device, computer equipment and storage medium | |
| CN109299238B (en) | Data query method and device | |
| CN117542467A (en) | Automatic construction method of disease-specific standard database based on patient data | |
| CN117591655A (en) | Intelligent question-answering system based on traditional Chinese medicine knowledge graph | |
| CN112349367A (en) | Method and device for generating simulation medical record, electronic equipment and storage medium | |
| CN112037904A (en) | Online diagnosis and treatment data processing method and device, computer equipment and storage medium | |
| CN116861875A (en) | Text processing method, device, equipment and storage medium based on artificial intelligence | |
| Bandhu et al. | Health care chatbot using natural language processing with SGD and ADAM optimizer parameter optimization | |
| CN113761899A (en) | Medical text generation method, device, equipment and storage medium | |
| CN116226320A (en) | Method and device for predicting context information, electronic equipment and storage medium | |
| CN113807920A (en) | Artificial intelligence based product recommendation method, device, equipment and storage medium | |
| CN111816276A (en) | Method and device for recommending education courses, computer equipment and storage medium | |
| CN115714002B (en) | Training method for depression risk detection model, depression symptom early warning method and related equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210917 |
|
| RJ01 | Rejection of invention patent application after publication |