CN116864151A - Method, device, equipment and medium for evaluating inquiry dialogue model - Google Patents

Method, device, equipment and medium for evaluating inquiry dialogue model Download PDF

Info

Publication number
CN116864151A
CN116864151A CN202310792082.7A CN202310792082A CN116864151A CN 116864151 A CN116864151 A CN 116864151A CN 202310792082 A CN202310792082 A CN 202310792082A CN 116864151 A CN116864151 A CN 116864151A
Authority
CN
China
Prior art keywords
patient
dialogue
score
model
keywords
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
CN202310792082.7A
Other languages
Chinese (zh)
Inventor
刘佳瑞
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.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen 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 Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN202310792082.7A priority Critical patent/CN116864151A/en
Publication of CN116864151A publication Critical patent/CN116864151A/en
Pending legal-status Critical Current

Links

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
    • G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
    • 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
    • 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
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • 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
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Public Health (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Pathology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The invention relates to the field of artificial intelligence and digital medical treatment, and discloses a consultation dialogue model evaluation method, a device, electronic equipment and a storage medium, which can be used for evaluating a medical knowledge layer of a consultation dialogue model in the medical industry, wherein the method comprises the following steps: acquiring basic information of a patient and a dialogue model to be checked, and generating doctor-patient dialogue data according to the basic information of the patient and the dialogue model to be checked; the symptom keywords, the diagnosis result keywords and the prescription keywords in the doctor-patient dialogue data are respectively extracted, and a first score, a second score and a third score of a to-be-tested consultation dialogue model are calculated according to the patient symptoms, the patient diagnosis results and the patient disease prescriptions in the basic patient information; and carrying out weighted average on the first score, the second score and the third score according to the preset weight ratio to obtain the total score of the dialog model of the inquiry to be tested. The invention can improve the intelligent degree and accuracy of the assessment of the inquiry dialogue model.

Description

Method, device, equipment and medium for evaluating inquiry dialogue model
Technical Field
The invention relates to the field of artificial intelligence and digital medical treatment, in particular to a method and a device for evaluating a consultation dialogue model, electronic equipment and a readable storage medium.
Background
The current common evaluation indexes of the medical inquiry dialogue model are divided into two types, the first is frequency calculation according to co-occurrence word pairs of two sentences output by a virtual patient model and a doctor dialogue model, and the method can only evaluate the medical inquiry dialogue model from the level of smoothness or richness of texts and cannot evaluate medical knowledge of the inquiry dialogue model; the second method is based on manual evaluation of medical staff, and the method can evaluate the consultation dialogue model at the medical knowledge level, but consumes a great deal of manpower and material resources, and has low intelligent degree, so that the model evaluation efficiency is low.
Disclosure of Invention
The invention provides a method, a device, electronic equipment and a readable storage medium for evaluating a consultation dialogue model, which aim to improve the intelligent degree and the evaluation efficiency of the evaluation of the consultation dialogue model, ensure the accuracy of medical knowledge during the evaluation of the consultation dialogue model and reduce the working pressure of a doctor in the consultation process.
In order to achieve the above object, the present invention provides a method for evaluating a consultation dialogue model, the method comprising:
acquiring basic information of a patient and a dialogue model to be checked, and generating doctor-patient dialogue data according to the basic information of the patient and the dialogue model to be checked;
Extracting symptom keywords in the doctor-patient dialogue data, and calculating a first score of the to-be-tested consultation dialogue model according to patient symptoms in the patient basic information and the symptom keywords;
extracting diagnosis result keywords in the doctor-patient dialogue data, and calculating a second score of the to-be-tested consultation dialogue model according to the diagnosis result of the patient in the basic information of the patient and the diagnosis result keywords;
extracting prescription keywords in the doctor-patient dialogue data, and calculating a third score of the to-be-tested consultation dialogue model according to the patient disease prescription in the patient basic information and the prescription keywords;
and carrying out weighted average on the first score, the second score and the third score according to a preset weight ratio to obtain the total score of the dialog model of the to-be-tested inquiry.
Optionally, the generating doctor-patient dialogue data according to the patient basic information and the to-be-tested consultation dialogue model includes:
generating patient complaints according to the patient basic information, and taking the patient basic information as a character model of a virtual patient dialogue model in the to-be-tested consultation dialogue model;
According to the patient complaints, a doctor dialogue model in the to-be-tested consultation dialogue model is utilized to conduct reply statement prediction, and doctor first dialogue data are obtained;
according to the character model and the doctor first dialogue data, carrying out reply sentence prediction by utilizing the virtual patient dialogue model to obtain patient first dialogue data;
and according to the first dialogue data of the patient, carrying out reply sentence prediction by using the doctor dialogue model to obtain doctor dialogue data until the doctor dialogue data contains preset sentence content, stopping the reply sentence prediction of the to-be-tested consultation dialogue model, and integrating the virtual patient dialogue model and dialogue data output by the doctor dialogue model according to time sequence to obtain doctor-patient dialogue data.
Optionally, the calculating the first score of the dialog model for inquiry to be tested according to the patient symptoms and the symptom keywords in the patient basic information includes:
comparing the symptom keywords with the patient symptoms in the patient basic information, and calculating the number of overlapping keywords of the symptom keywords and the patient symptoms;
calculating the precision of the symptom keywords according to the number of the overlapped keywords and the number of the symptom keywords corresponding to the symptom keywords;
Calculating recall ratios of the symptom keywords according to the number of the overlapped keywords and the number of the patient symptoms corresponding to the patient symptoms;
and calculating a first score of the dialog model to be tested by using an F1 measurement calculation method according to the precision rate and the recall ratio.
Optionally, the calculating the first score of the dialog model for inquiry to be tested according to the precision and the recall, by using an F1 metric calculation method includes:
calculating a first score F1 of the dialog model to be tested by using the following formula:
wherein, A refers to the precision; the B refers to recall.
Optionally, the calculating the second score of the dialog model for inquiry to be tested according to the diagnosis result of the patient in the patient basic information and the diagnosis result keyword includes:
judging whether the diagnosis result keywords are consistent with the diagnosis results of the patients in the basic information of the patients;
when the diagnosis result keywords are inconsistent with the diagnosis results of the patients in the basic information of the patients, judging that the second score of the dialogue model to be tested is zero;
and when the diagnosis result keywords are consistent with the diagnosis results of the patients in the basic information of the patients, judging that the second score of the dialogue model to be tested is one.
Optionally, the extracting symptom keywords in the doctor-patient dialogue data includes:
matching doctor dialogue data in the doctor-patient dialogue data with a pre-constructed candidate word template to obtain a symptom candidate word set of the doctor dialogue data;
scoring each symptom candidate word in the symptom candidate word set by utilizing a key information extraction algorithm to obtain a candidate word score of each symptom candidate word;
and taking the symptom candidate words with the word segmentation of the candidate words being larger than a preset threshold value as keywords of the doctor-patient dialogue data.
Optionally, the weighted average is performed on the first score, the second score and the third score according to a preset weight ratio to obtain a total score of the to-be-tested inquiry dialogue model, which includes:
respectively calculating the first score, the second score and the third score weight value according to a preset weight ratio to obtain a first weight value, a second weight value and a third weight value;
and adding the first weight value, the second weight value and the third weight value to obtain the total score of the dialog model to be tested.
In order to solve the above problems, the present invention also provides a query dialogue model evaluation device, the device comprising:
The doctor-patient dialogue data generation module is used for acquiring basic information of a patient and a to-be-checked dialogue model and generating doctor-patient dialogue data according to the basic information of the patient and the to-be-checked dialogue model;
the doctor-patient dialogue data scoring module is used for extracting symptom keywords in the doctor-patient dialogue data, calculating a first score of the to-be-tested consultation dialogue model according to patient symptoms and the symptom keywords in the patient basic information, extracting diagnosis result keywords in the doctor-patient dialogue data, calculating a second score of the to-be-tested consultation dialogue model according to patient diagnosis results and the diagnosis result keywords in the patient basic information, extracting prescription keywords in the doctor-patient dialogue data, and calculating a third score of the to-be-tested consultation dialogue model according to patient disease prescriptions and the prescription keywords in the patient basic information;
and the inquiry dialogue model scoring module is used for carrying out weighted average on the first score, the second score and the third score according to a preset weight ratio to obtain the total score of the inquiry dialogue model to be tested.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
A memory storing at least one computer program; and
And the processor executes the computer program stored in the memory to realize the inquiry dialogue model evaluation method.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored therein at least one computer program that is executed by a processor in an electronic device to implement the above-mentioned inquiry dialogue model evaluation method.
According to the embodiment of the invention, the symptom keywords in the doctor-patient dialogue data are extracted, the first score of the to-be-tested consultation dialogue model is calculated according to the patient symptoms and the symptom keywords in the patient basic information, the diagnosis result keywords in the doctor-patient dialogue data are extracted, the second score of the to-be-tested consultation dialogue model is calculated according to the patient diagnosis results and the diagnosis result keywords in the patient basic information, the prescription keywords in the doctor-patient dialogue data are extracted, the third score of the to-be-tested consultation dialogue model is calculated according to the patient disease prescriptions and the prescription keywords in the patient basic information, and the evaluation scoring is carried out on the to-be-tested consultation dialogue model from the disease symptom latitude, the disease diagnosis latitude and the disease prescription latitude, so that the occupation coefficient of traditional Chinese medical therapy knowledge is improved, in addition, the artificial participation degree in evaluation of the to-be-tested consultation dialogue model is reduced, and the intelligent degree and the evaluation efficiency of the consultation dialogue model are improved. Therefore, the assessment method, the device, the equipment and the storage medium of the inquiry dialogue model can improve the intelligent degree and the assessment efficiency of the inquiry dialogue model assessment, ensure the accuracy of medical knowledge during the inquiry dialogue model assessment and reduce the working pressure of doctors in the inquiry process.
Drawings
FIG. 1 is a flowchart illustrating a method for evaluating a consultation dialogue model according to an embodiment of the present application;
FIGS. 2 and 3 are flowcharts illustrating a detailed implementation of one of the steps in the assessment method of the inquiry dialogue model according to an embodiment of the present application;
FIG. 4 is a schematic block diagram of an evaluation device for a consultation dialogue model according to an embodiment of the present application;
fig. 5 is a schematic diagram of an internal structure of an electronic device for implementing a method for evaluating a consultation dialogue model according to an embodiment of the present application;
the achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides a method for evaluating a consultation dialogue model. The execution subject of the inquiry dialogue model evaluation method includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the inquiry dialogue model evaluation method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The server may include an independent server, and may also include a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flowchart of a method for evaluating a query dialogue model according to an embodiment of the invention is shown, where in the embodiment of the invention, the method for evaluating a query dialogue model includes:
s1, acquiring basic information of a patient and a dialogue model to be checked, and generating doctor-patient dialogue data according to the basic information of the patient and the dialogue model to be checked.
In the embodiment of the present invention, the patient basic information includes information such as a name of a disease of the patient, symptoms of the patient when the patient is ill, causes of the disease of the patient, and prescriptions of the disease of the patient, for example, the patient basic information of the patient with the urticaria, which is small, includes a disease name of "urticaria"; the symptoms of skin itch at the time of onset are that red or pale wind clusters with different sizes appear rapidly at the itching part; disease causes of virus infection, emotional tension, eating of toluate, sulfite and the like; the prescription of the disease is antihistamine, tripterygium glycosides tablet and other medicines. The to-be-tested consultation dialogue model can be a combined model formed by a virtual patient dialogue model and a doctor dialogue model, wherein the virtual patient dialogue model and the doctor dialogue model are both trained circulating neural networks or bidirectional circulating neural networks. The doctor-patient session data may be patient session data output by the virtual patient session model and doctor session data output by the doctor session model.
In an alternative embodiment of the invention, the basic information of the patient can be obtained by crawling the network patient example through the web crawler script written in advance or retrieving the patient data in the server patient database, and the comparison data is provided for the evaluation of the to-be-tested consultation dialogue model, so that the accuracy of the evaluation of the consultation dialogue model is ensured.
According to the embodiment of the invention, doctor-patient dialogue data are generated according to the basic patient information and the to-be-tested consultation dialogue model, evaluation data are provided for evaluation of the consultation dialogue model, smooth evaluation of the consultation dialogue model is ensured, and evaluation efficiency of the consultation dialogue model is improved.
Further, as an optional embodiment of the present invention, referring to fig. 2, the generating doctor-patient dialogue data according to the patient basic information and the to-be-tested consultation dialogue model includes:
s11, generating patient complaints according to the basic patient information, and taking the basic patient information as a character model of a virtual patient dialogue model in the to-be-tested consultation dialogue model;
s12, according to the patient complaints, carrying out reply statement prediction by utilizing a doctor dialogue model in the to-be-tested consultation dialogue model to obtain doctor first dialogue data;
S13, according to the character model and the doctor first dialogue data, performing reply sentence prediction by using the virtual patient dialogue model to obtain patient first dialogue data;
s14, according to the first dialogue data of the patient, performing reply sentence prediction by using the doctor dialogue model to obtain doctor dialogue data, stopping the reply sentence prediction of the to-be-tested consultation dialogue model until the doctor dialogue data contains preset sentence content, and integrating the virtual patient dialogue model and dialogue data output by the doctor dialogue model in time sequence to obtain doctor-patient dialogue data.
In the embodiment of the invention, the patient complaint can be the self symptoms or (and) signs, properties, duration and the like of the patient. The character model may be a fictitious patient representing a patient population. The preset sentence content may be a sentence that the doctor dialogue model set by the healthcare worker summarizes according to dialogue data of the virtual patient dialogue model, for example: "according to your situation, consider: or suggest that you can take according to your situation: "etc.
In an alternative embodiment of the invention, the character model is built for the virtual patient dialogue model in the to-be-tested consultation dialogue model, so that the virtual patient dialogue model is guided to reply to the problems of the doctor dialogue model, the accuracy of output sentences of the virtual patient dialogue model is ensured, and the problem of evaluation errors of the consultation dialogue model caused by inaccurate output of the virtual patient dialogue model is avoided.
S2, extracting symptom keywords in the doctor-patient dialogue data, and calculating a first score of the to-be-tested consultation dialogue model according to the patient symptoms and the symptom keywords in the patient basic information.
In the embodiment of the invention, the symptom keywords can be keywords related to disease symptom characteristics, disease attack time, disease causes and the like.
According to the embodiment of the invention, the symptom keywords in the doctor-patient dialogue data are extracted, and the inquiry dialogue model is evaluated from the latitude of the symptom of the patient, so that the occupation ratio degree of the medical knowledge level during evaluation of the inquiry dialogue model is improved.
In detail, as an alternative embodiment of the present invention, referring to fig. 3, the extracting symptom keywords in the doctor-patient dialogue data includes:
S21, matching doctor dialogue data in the doctor-patient dialogue data with a pre-constructed candidate word template to obtain a symptom candidate word set of the doctor dialogue data;
s22, scoring each symptom candidate word in the symptom candidate word set by utilizing a key information extraction algorithm to obtain a candidate word score of each symptom candidate word;
s23, taking the symptom candidate words with the candidate word segmentation larger than a preset threshold value as keywords of the doctor-patient dialogue data.
In the embodiment of the invention, the pre-constructed candidate word template can be a word set formed by elements such as symptoms, causes and the like of various diseases. The keyword information extraction algorithm can be a TF-IDF algorithm, a textRank algorithm or an LDA algorithm and other keyword extraction algorithms.
In an alternative embodiment of the present invention, the keyword extraction algorithm may be divided into a supervised keyword extraction algorithm and an unsupervised keyword extraction algorithm, where the TF-IDF algorithm, the TextRank algorithm, or the LDA algorithm belong to the unsupervised keyword extraction algorithm, and in addition, the present invention may also use the supervised keyword extraction algorithm to extract symptom keywords in the doctor-patient dialogue data, for example: obtaining a large amount of training data related to disease symptoms, carrying out model training on a preset keyword extraction model by using the training data to obtain a trained keyword extraction model, and further extracting symptom keywords in the doctor-patient dialogue data by using the trained keyword extraction model.
According to the embodiment of the invention, the first score of the to-be-tested inquiry dialogue model is calculated according to the patient symptoms and the symptom keywords in the patient basic information, the inquiry dialogue model is evaluated from the latitude of the patient symptoms, and the medical knowledge level occupation ratio during evaluation of the inquiry dialogue model is improved.
In an alternative embodiment of the present invention, in order to evaluate the model generalization ability of the inquiry dialogue model, performance measurement needs to be performed on the inquiry dialogue model, where the performance measurement may be determined by calculating the precision and recall of the model, for example, the model generalization ability of the inquiry dialogue model at the symptom latitude of the patient may be determined by calculating the precision and recall of the symptom of the patient in the inquiry dialogue model.
Thus, as an optional embodiment of the present invention, the calculating the first score of the dialog model for questioning to be tested according to the patient symptoms and the symptom keywords in the patient basic information includes:
comparing the symptom keywords with the patient symptoms in the patient basic information, and calculating the number of overlapping keywords of the symptom keywords and the patient symptoms;
calculating the precision of the symptom keywords according to the number of the overlapped keywords and the number of the symptom keywords corresponding to the symptom keywords;
Calculating recall ratios of the symptom keywords according to the number of the overlapped keywords and the number of the patient symptoms corresponding to the patient symptoms;
and calculating a first score of the dialog model to be tested by using an F1 measurement calculation method according to the precision rate and the recall ratio.
In an alternative embodiment of the present invention, the precision a and recall ratio B may be calculated according to the number z of overlapping keywords, the number x of symptom keywords corresponding to the symptom keywords, and the number y of patient symptoms corresponding to the patient symptoms by using the following formulas:
further, in an optional embodiment of the present invention, the calculating, according to the precision and the recall, a first score of the dialog model to be tested by using an F1 metric calculation method includes:
calculating a first score F1 of the dialog model to be tested by using the following formula:
wherein, A refers to the precision; the B refers to recall.
And S3, extracting diagnosis result keywords in the doctor-patient dialogue data, and calculating a second score of the to-be-tested consultation dialogue model according to the diagnosis result of the patient in the patient basic information and the diagnosis result keywords.
In the embodiment of the invention, the diagnosis result keywords can be keywords related to disease names or disease categories and the like.
In an alternative embodiment of the present invention, the step of extracting the keywords of the diagnosis result in the doctor-patient dialogue data is similar to the step of extracting the keywords of the symptoms in the doctor-patient dialogue data, and the keyword extraction may be performed by using an unsupervised keyword extraction method or a supervised keyword extraction method, so that details are omitted.
According to the embodiment of the invention, the second score of the to-be-detected consultation dialogue model is calculated according to the patient diagnosis result and the diagnosis result keywords in the patient basic information, and the consultation dialogue model is evaluated from the latitude of the patient disease diagnosis, so that the occupation ratio degree of the medical knowledge level during the evaluation of the consultation dialogue model is further improved.
Further, in an alternative embodiment of the present invention, the accuracy of the diagnosis dialogue model in the latitude of the diagnosis of the patient disease may be determined by comparing the patient diagnosis result in the patient basic information with the diagnosis result keyword, so as to improve the accuracy of the evaluation of the diagnosis dialogue model.
In detail, as an optional embodiment of the present invention, the calculating the second score of the dialog model for questioning to be tested according to the diagnosis result of the patient in the patient basic information and the diagnosis result keyword includes:
Judging whether the diagnosis result keywords are consistent with the diagnosis results of the patients in the basic information of the patients;
when the diagnosis result keywords are inconsistent with the diagnosis results of the patients in the basic information of the patients, judging that the second score of the dialogue model to be tested is 0;
and when the diagnosis result keywords are consistent with the diagnosis results of the patients in the basic information of the patients, judging that the second score of the dialogue model to be tested is 1.
In an alternative embodiment of the present invention, since the patient diagnostic results are unique, there are only 0 and 1 scores when calculating the second score for the interview session model under test.
And S4, extracting prescription keywords in the doctor-patient dialogue data, and calculating a third score of the to-be-tested consultation dialogue model according to the patient disease prescription and the prescription keywords in the patient basic information.
In the embodiment of the invention, the prescription keywords can be keywords related to the therapeutic drugs or therapeutic modes of the diseases of the patients.
In an alternative embodiment of the present invention, the step of extracting the prescription keyword in the doctor-patient dialogue data is similar to the step of extracting the symptom keyword in the doctor-patient dialogue data, and the keyword extraction may be performed by using an unsupervised keyword extraction method or a supervised keyword extraction method, so that details are omitted.
According to the embodiment of the invention, the third score of the to-be-tested consultation dialogue model is calculated according to the patient disease prescription and the prescription keywords in the patient basic information, and the consultation dialogue model is evaluated from the latitude of patient disease treatment, so that the occupation ratio degree of the medical knowledge layer during evaluation of the consultation dialogue model is further improved, the participation degree of medical workers in evaluating the medical knowledge layer of the consultation dialogue model is reduced, and the intelligent degree and the efficiency of evaluation of the consultation dialogue model are improved.
Further, in an alternative embodiment of the present invention, the accuracy of the query dialogue model in the latitude of the patient disease treatment may be determined by comparing the patient disease prescription in the patient basic information with the prescription keyword, so as to improve the accuracy of the evaluation of the query dialogue model.
In an optional embodiment of the present invention, since the patient disease prescription has uniqueness, the step of calculating the third score of the to-be-tested inquiry dialogue model according to the patient disease prescription and the prescription keyword in the patient basic information is similar to the step of calculating the second score of the to-be-tested inquiry dialogue model according to the patient diagnosis result and the diagnosis result keyword in the patient basic information, which is not repeated.
And S5, carrying out weighted average on the first score, the second score and the third score according to a preset weight ratio to obtain the total score of the dialog model of the to-be-tested inquiry.
In the embodiment of the present invention, the preset weight ratio may be a first score ratio, a second score ratio, and a third score ratio obtained by calculating the patient disease symptoms, the patient disease diagnosis, and the importance degree of the patient disease treatment according to the medical knowledge of the medical practitioner.
In an alternative embodiment of the present invention, in order to obtain the evaluation score of the interview session model in the medical knowledge layer more accurately, the first score, the second score and the third score are weighted and averaged according to a preset weight ratio, so as to improve the accuracy of the evaluation of the interview session model.
In detail, as an optional embodiment of the present invention, the weighted average of the first score, the second score and the third score according to a preset weight ratio is performed to obtain a total score of the dialog model for inquiry to be tested, which includes:
respectively calculating the first score, the second score and the third score weight value according to a preset weight ratio to obtain a first weight value, a second weight value and a third weight value;
And adding the first weight value, the second weight value and the third weight value to obtain the total score of the dialog model to be tested.
According to the embodiment of the invention, the first score, the second score and the third score are weighted and averaged, so that the importance degree of three latitudes of patient disease symptoms, patient disease diagnosis and patient disease treatment in the evaluation of the inquiry dialogue model is reflected, the evaluation score of the medical knowledge layer is provided for the evaluation of the inquiry dialogue model, the evaluation result of the inquiry dialogue model is more reliable and real, and the evaluation accuracy of the inquiry dialogue model is improved.
According to the embodiment of the invention, the symptom keywords in the doctor-patient dialogue data are extracted, the first score of the to-be-tested consultation dialogue model is calculated according to the patient symptoms and the symptom keywords in the patient basic information, the diagnosis result keywords in the doctor-patient dialogue data are extracted, the second score of the to-be-tested consultation dialogue model is calculated according to the patient diagnosis results and the diagnosis result keywords in the patient basic information, the prescription keywords in the doctor-patient dialogue data are extracted, the third score of the to-be-tested consultation dialogue model is calculated according to the patient disease prescriptions and the prescription keywords in the patient basic information, and the evaluation scoring is carried out on the to-be-tested consultation dialogue model from the disease symptom latitude, the disease diagnosis latitude and the disease prescription latitude, so that the occupation coefficient of traditional Chinese medical therapy knowledge is improved, in addition, the artificial participation degree in evaluation of the to-be-tested consultation dialogue model is reduced, and the intelligent degree and the evaluation efficiency of the consultation dialogue model are improved. Therefore, the assessment method of the inquiry dialogue model can improve the intelligent degree and the assessment efficiency of the inquiry dialogue model assessment, ensure the accuracy of medical knowledge during the inquiry dialogue model assessment, and reduce the working pressure of a doctor in the inquiry process.
FIG. 4 is a functional block diagram of the inquiry dialogue model assessment apparatus according to the present invention.
The inquiry dialogue model evaluation apparatus 100 of the present invention may be installed in an electronic device. Depending on the implementation, the evaluation device 100 of the interview dialogue model may include a doctor-patient dialogue data generating module 101, a doctor-patient dialogue data scoring module 102, and an interview dialogue model scoring module 103, where the modules may also be referred to as units, and refer to a series of computer program segments that can be executed by a processor of an electronic device and can perform a fixed function, and are stored in a memory of the electronic device.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the doctor-patient dialogue data generating module 101 is configured to obtain basic patient information and a to-be-examined consultation dialogue model, and generate doctor-patient dialogue data according to the basic patient information and the to-be-examined consultation dialogue model.
The doctor-patient dialogue data scoring module 102 is configured to extract symptom keywords in the doctor-patient dialogue data, calculate a first score of the to-be-diagnosed dialogue model according to patient symptoms and the symptom keywords in the patient basic information, extract diagnosis result keywords in the doctor-patient dialogue data, calculate a second score of the to-be-diagnosed dialogue model according to patient diagnosis results and the diagnosis result keywords in the patient basic information, extract prescription keywords in the doctor-patient dialogue data, and calculate a third score of the to-be-diagnosed dialogue model according to patient disease prescriptions and the prescription keywords in the patient basic information.
The scoring module 103 is configured to weight average the first score, the second score, and the third score according to a preset weight ratio, so as to obtain a total score of the dialog model to be tested.
According to the embodiment of the invention, the symptom keywords in the doctor-patient dialogue data are extracted, the first score of the to-be-tested consultation dialogue model is calculated according to the patient symptoms and the symptom keywords in the patient basic information, the diagnosis result keywords in the doctor-patient dialogue data are extracted, the second score of the to-be-tested consultation dialogue model is calculated according to the patient diagnosis results and the diagnosis result keywords in the patient basic information, the prescription keywords in the doctor-patient dialogue data are extracted, the third score of the to-be-tested consultation dialogue model is calculated according to the patient disease prescriptions and the prescription keywords in the patient basic information, and the evaluation scoring is carried out on the to-be-tested consultation dialogue model from the disease symptom latitude, the disease diagnosis latitude and the disease prescription latitude, so that the occupation coefficient of traditional Chinese medical therapy knowledge is improved, in addition, the artificial participation degree in evaluation of the to-be-tested consultation dialogue model is reduced, and the intelligent degree and the evaluation efficiency of the consultation dialogue model are improved. Therefore, the assessment device for the inquiry dialogue model can improve the intelligent degree and the assessment efficiency of the assessment of the inquiry dialogue model, ensure the accuracy of medical knowledge during the assessment of the inquiry dialogue model, and reduce the working pressure of a doctor in the inquiry process.
Fig. 5 is a schematic structural diagram of an electronic device for implementing the assessment method of the inquiry dialogue model according to the present invention.
The electronic device may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a interview session model evaluation program, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 11 may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only for storing application software installed in an electronic device and various types of data, such as codes of a interview session model evaluation program, but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing Unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, and executes various functions of the electronic device and processes data by running or executing programs or modules (e.g., a consultation dialogue model evaluation program, etc.) stored in the memory 11, and calling data stored in the memory 11.
The communication bus 12 may be a peripheral component interconnect standard (PerIPheral ComponentInterconnect, PCI) bus, or an extended industry standard architecture (Extended IndustryStandard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The communication bus 12 is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
Fig. 5 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 5 is not limiting of the electronic device and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
Optionally, the communication interface 13 may comprise a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices.
Optionally, the communication interface 13 may further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The interview session model evaluation program stored by the memory 11 in the electronic device is a combination of a plurality of computer programs that, when run in the processor 10, can implement:
acquiring basic information of a patient and a dialogue model to be checked, and generating doctor-patient dialogue data according to the basic information of the patient and the dialogue model to be checked;
extracting symptom keywords in the doctor-patient dialogue data, and calculating a first score of the to-be-tested consultation dialogue model according to patient symptoms in the patient basic information and the symptom keywords;
Extracting diagnosis result keywords in the doctor-patient dialogue data, and calculating a second score of the to-be-tested consultation dialogue model according to the diagnosis result of the patient in the basic information of the patient and the diagnosis result keywords;
extracting prescription keywords in the doctor-patient dialogue data, and calculating a third score of the to-be-tested consultation dialogue model according to the patient disease prescription in the patient basic information and the prescription keywords;
and carrying out weighted average on the first score, the second score and the third score according to a preset weight ratio to obtain the total score of the dialog model of the to-be-tested inquiry.
In particular, the specific implementation method of the processor 10 on the computer program may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
Further, the electronic device integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. The computer readable medium may be non-volatile or volatile. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
Embodiments of the present invention may also provide a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, may implement:
acquiring basic information of a patient and a dialogue model to be checked, and generating doctor-patient dialogue data according to the basic information of the patient and the dialogue model to be checked;
extracting symptom keywords in the doctor-patient dialogue data, and calculating a first score of the to-be-tested consultation dialogue model according to patient symptoms in the patient basic information and the symptom keywords;
extracting diagnosis result keywords in the doctor-patient dialogue data, and calculating a second score of the to-be-tested consultation dialogue model according to the diagnosis result of the patient in the basic information of the patient and the diagnosis result keywords;
extracting prescription keywords in the doctor-patient dialogue data, and calculating a third score of the to-be-tested consultation dialogue model according to the patient disease prescription in the patient basic information and the prescription keywords;
and carrying out weighted average on the first score, the second score and the third score according to a preset weight ratio to obtain the total score of the dialog model of the to-be-tested inquiry.
Further, the computer-usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
In the embodiments provided in the present invention, it should be understood that the disclosed electronic device, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims (10)

1. A method of evaluating a consultation dialogue model, the method comprising:
acquiring basic information of a patient and a dialogue model to be checked, and generating doctor-patient dialogue data according to the basic information of the patient and the dialogue model to be checked;
extracting symptom keywords in the doctor-patient dialogue data, and calculating a first score of the to-be-tested consultation dialogue model according to patient symptoms in the patient basic information and the symptom keywords;
extracting diagnosis result keywords in the doctor-patient dialogue data, and calculating a second score of the to-be-tested consultation dialogue model according to the diagnosis result of the patient in the basic information of the patient and the diagnosis result keywords;
Extracting prescription keywords in the doctor-patient dialogue data, and calculating a third score of the to-be-tested consultation dialogue model according to the patient disease prescription in the patient basic information and the prescription keywords;
and carrying out weighted average on the first score, the second score and the third score according to a preset weight ratio to obtain the total score of the dialog model of the to-be-tested inquiry.
2. The method for evaluating a interview session model according to claim 1, wherein generating doctor-patient session data from the patient basic information and the interview session model to be tested comprises:
generating patient complaints according to the patient basic information, and taking the patient basic information as a character model of a virtual patient dialogue model in the to-be-tested consultation dialogue model;
according to the patient complaints, a doctor dialogue model in the to-be-tested consultation dialogue model is utilized to conduct reply statement prediction, and doctor first dialogue data are obtained;
according to the character model and the doctor first dialogue data, carrying out reply sentence prediction by utilizing the virtual patient dialogue model to obtain patient first dialogue data;
and according to the first dialogue data of the patient, carrying out reply sentence prediction by using the doctor dialogue model to obtain doctor dialogue data until the doctor dialogue data contains preset sentence content, stopping the reply sentence prediction of the to-be-tested consultation dialogue model, and integrating the virtual patient dialogue model and dialogue data output by the doctor dialogue model according to time sequence to obtain doctor-patient dialogue data.
3. The method for evaluating a dialogue model according to claim 1, wherein the calculating a first score of the dialogue model to be tested according to the patient symptoms and the symptom keywords in the patient basic information comprises:
comparing the symptom keywords with the patient symptoms in the patient basic information, and calculating the number of overlapping keywords of the symptom keywords and the patient symptoms;
calculating the precision of the symptom keywords according to the number of the overlapped keywords and the number of the symptom keywords corresponding to the symptom keywords;
calculating recall ratios of the symptom keywords according to the number of the overlapped keywords and the number of the patient symptoms corresponding to the patient symptoms;
and calculating a first score of the dialog model to be tested by using an F1 measurement calculation method according to the precision rate and the recall ratio.
4. The method for evaluating a query dialog model as claimed in claim 3, wherein calculating a first score of the query dialog model to be tested using an F1 metric calculation method based on the precision and recall, comprises:
calculating a first score F1 of the dialog model to be tested by using the following formula:
Wherein, A refers to the precision; the B refers to recall.
5. The method for evaluating a dialogue model according to claim 1, wherein the calculating a second score of the dialogue model to be tested based on the patient diagnosis result and the diagnosis result keyword in the patient basic information comprises:
judging whether the diagnosis result keywords are consistent with the diagnosis results of the patients in the basic information of the patients;
when the diagnosis result keywords are inconsistent with the diagnosis results of the patients in the basic information of the patients, judging that the second score of the dialogue model to be tested is zero;
and when the diagnosis result keywords are consistent with the diagnosis results of the patients in the basic information of the patients, judging that the second score of the dialogue model to be tested is one.
6. The method of claim 1, wherein the extracting symptom keywords in the doctor-patient dialogue data comprises:
matching doctor dialogue data in the doctor-patient dialogue data with a pre-constructed candidate word template to obtain a symptom candidate word set of the doctor dialogue data;
scoring each symptom candidate word in the symptom candidate word set by utilizing a key information extraction algorithm to obtain a candidate word score of each symptom candidate word;
And taking the symptom candidate words with the word segmentation of the candidate words being larger than a preset threshold value as keywords of the doctor-patient dialogue data.
7. The method for evaluating a dialog model for a consultation according to claim 1, wherein the step of weighted averaging the first score, the second score and the third score according to a preset weight ratio to obtain a total score of the dialog model for a consultation to be tested includes:
respectively calculating the first score, the second score and the third score weight value according to a preset weight ratio to obtain a first weight value, a second weight value and a third weight value;
and adding the first weight value, the second weight value and the third weight value to obtain the total score of the dialog model to be tested.
8. A consultation dialogue model assessment apparatus, the apparatus comprising:
the doctor-patient dialogue data generation module is used for acquiring basic information of a patient and a to-be-checked dialogue model and generating doctor-patient dialogue data according to the basic information of the patient and the to-be-checked dialogue model;
the doctor-patient dialogue data scoring module is used for extracting symptom keywords in the doctor-patient dialogue data, calculating a first score of the to-be-tested consultation dialogue model according to patient symptoms and the symptom keywords in the patient basic information, extracting diagnosis result keywords in the doctor-patient dialogue data, calculating a second score of the to-be-tested consultation dialogue model according to patient diagnosis results and the diagnosis result keywords in the patient basic information, extracting prescription keywords in the doctor-patient dialogue data, and calculating a third score of the to-be-tested consultation dialogue model according to patient disease prescriptions and the prescription keywords in the patient basic information;
And the inquiry dialogue model scoring module is used for carrying out weighted average on the first score, the second score and the third score according to a preset weight ratio to obtain the total score of the inquiry dialogue model to be tested.
9. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the interview session model evaluation method of any one of claims 1 to 7.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the interview session model evaluation method according to any one of claims 1 to 7.
CN202310792082.7A 2023-06-29 2023-06-29 Method, device, equipment and medium for evaluating inquiry dialogue model Pending CN116864151A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310792082.7A CN116864151A (en) 2023-06-29 2023-06-29 Method, device, equipment and medium for evaluating inquiry dialogue model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310792082.7A CN116864151A (en) 2023-06-29 2023-06-29 Method, device, equipment and medium for evaluating inquiry dialogue model

Publications (1)

Publication Number Publication Date
CN116864151A true CN116864151A (en) 2023-10-10

Family

ID=88222731

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310792082.7A Pending CN116864151A (en) 2023-06-29 2023-06-29 Method, device, equipment and medium for evaluating inquiry dialogue model

Country Status (1)

Country Link
CN (1) CN116864151A (en)

Similar Documents

Publication Publication Date Title
CN108492887B (en) Medical knowledge map construction method and device
CN109670054B (en) Knowledge graph construction method and device, storage medium and electronic equipment
US8285734B2 (en) Comparison of documents based on similarity measures
CN112700838A (en) Big data-based medication scheme recommendation method and device and related equipment
CN113724848A (en) Medical resource recommendation method, device, server and medium based on artificial intelligence
CN112216361A (en) Follow-up plan list generation method, device, terminal and medium based on artificial intelligence
CN113782125B (en) Clinic scoring method and device based on artificial intelligence, electronic equipment and medium
CN114781805B (en) Nursing staff nursing skill assessment method, system and device based on big data
CN113674858A (en) Online medical prescription medication intelligent checking method, device, equipment and storage medium
WO2023178978A1 (en) Prescription review method and apparatus based on artificial intelligence, and device and medium
CN116578704A (en) Text emotion classification method, device, equipment and computer readable medium
WO2022227171A1 (en) Method and apparatus for extracting key information, electronic device, and medium
Chandra et al. Natural language Processing and Ontology based Decision Support System for Diabetic Patients
CN114334175A (en) Hospital epidemic situation monitoring method and device, computer equipment and storage medium
Wallin et al. The multiple sclerosis surveillance registry: a novel interactive database within the veterans health administration
CN116895357A (en) Electronic medical record generation method, device, equipment and medium
CN112530602A (en) Method and device for analyzing side effect of medicine, electronic equipment and computer storage medium
CN116483976A (en) Registration department recommendation method, device, equipment and storage medium
CN116525053A (en) Patient report generation method, device, electronic equipment and medium
Xue et al. Differential diagnosis of heart disease in emergency departments using decision tree and medical knowledge
CN113689924B (en) Similar medical record retrieval method and device, electronic equipment and readable storage medium
CN116864151A (en) Method, device, equipment and medium for evaluating inquiry dialogue model
Wingrove et al. Using machine learning to predict primary care and advance workforce research
Rivera et al. Falls with Injury in Hospitalized Adults: Solving the Problem with an EHR-scored Fall Risk Tool.
CN114864032B (en) Clinical data acquisition method and device based on HIS system

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