CN114664431A - Artificial intelligence assisted question and answer method, device, equipment and medium - Google Patents
Artificial intelligence assisted question and answer method, device, equipment and medium Download PDFInfo
- Publication number
- CN114664431A CN114664431A CN202210253548.1A CN202210253548A CN114664431A CN 114664431 A CN114664431 A CN 114664431A CN 202210253548 A CN202210253548 A CN 202210253548A CN 114664431 A CN114664431 A CN 114664431A
- Authority
- CN
- China
- Prior art keywords
- disease
- keywords
- patient
- question
- text
- 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
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 41
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 210
- 201000010099 disease Diseases 0.000 claims abstract description 209
- 230000008569 process Effects 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 25
- 208000024891 symptom Diseases 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000003745 diagnosis Methods 0.000 abstract description 18
- 230000003750 conditioning effect Effects 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 11
- 210000003128 head Anatomy 0.000 description 6
- 206010019233 Headaches Diseases 0.000 description 4
- 208000002193 Pain Diseases 0.000 description 4
- 206010036790 Productive cough Diseases 0.000 description 4
- 206010039101 Rhinorrhoea Diseases 0.000 description 4
- 239000003814 drug Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 208000036071 Rhinorrhea Diseases 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 231100000869 headache Toxicity 0.000 description 3
- 206010011224 Cough Diseases 0.000 description 2
- 238000012905 input function Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 206010006002 Bone pain Diseases 0.000 description 1
- 206010008479 Chest Pain Diseases 0.000 description 1
- 208000008017 Hypohidrosis Diseases 0.000 description 1
- 208000019695 Migraine disease Diseases 0.000 description 1
- 206010028372 Muscular weakness Diseases 0.000 description 1
- 206010028748 Nasal obstruction Diseases 0.000 description 1
- 208000003251 Pruritus Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 208000002173 dizziness Diseases 0.000 description 1
- 206010013781 dry mouth Diseases 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 208000023406 head swelling Diseases 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007803 itching Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 206010027599 migraine Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000010753 nasal discharge Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000399 orthopedic effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 210000004243 sweat Anatomy 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- 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
-
- 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
-
- 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
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Pathology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and discloses an artificial intelligence assisted question-answering method, an artificial intelligence assisted question-answering device, a storage medium and a terminal, wherein the artificial intelligence assisted question-answering method comprises the following steps: receiving and analyzing a disease description text of a patient to be treated to generate a plurality of first disease keywords; inputting a plurality of first disease condition keywords into a pre-trained medical family judgment model, and outputting a target family corresponding to a patient to be treated; connecting a question-answer database corresponding to the target subject, and determining an optimal answer text according to the question-answer database; determining a plurality of second disease condition keywords according to the optimal reply text; and generating a final question-answering report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords. According to the method and the system, the collection and analysis of the patient information can be automatically completed to obtain a plurality of disease keywords, the final diagnosis report of the patient is obtained based on the plurality of disease keywords, and then the final diagnosis report is pushed to an artificial expert to make a comprehensive diagnosis and conditioning scheme, so that the inquiry process is accelerated, and the treatment efficiency is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence technology and natural language processing, in particular to an artificial intelligence assisted question answering method, an artificial intelligence assisted question answering device, artificial intelligence assisted question answering equipment and an artificial intelligence assisted question answering medium.
Background
Internet medical care is an important field of artificial intelligence applications. With the rapid development of technology, mobile medicine has moved towards the clinical level. In recent years, online inquiry is becoming more and more popular, the amount of single-day online inquiry breaks through the million-level daily average scale, the online doctor resources are insufficient, and the online inquiry service efficiency is not high, which becomes a prominent problem.
In the daily hospitalization of a patient, a common business scene requires a medical expert to collect basic information and disease information of the patient in a questioning mode, then the collected information is integrated to distinguish a disease and a syndrome according to a traditional Chinese medicine theory and clinical experience, and finally a scientific conditioning scheme is provided. In practice, the dialogues inquired by doctors in the same type of patients are basically similar, so that a large amount of time is wasted for the doctors to perform inquiry, the inquiry process is slowed down, and the treatment efficiency is reduced.
Disclosure of Invention
The invention provides an artificial intelligence assisted question answering method, an artificial intelligence assisted question answering device, artificial intelligence assisted question answering equipment and an artificial intelligence assisted question answering medium, which are used for solving the technical problems that a doctor wastes a large amount of time to perform inquiry, the inquiry process is slowed down, and meanwhile the treatment efficiency is reduced.
In a first aspect, an artificial intelligence assisted question-answering method is provided, which includes:
receiving and analyzing a disease description text of a patient to be treated to generate a plurality of first disease keywords;
inputting a plurality of first disease condition keywords into a pre-trained medical family judgment model, and outputting a target family corresponding to a patient to be treated;
connecting a question-answer database corresponding to the target subject, and determining an optimal answer text according to the question-answer database;
determining a plurality of second disease condition keywords according to the optimal reply text;
and generating a final question-answering report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords.
Optionally, receiving and parsing a disease description text of a patient to be treated to generate a plurality of first disease keywords, including:
receiving a disease description text of a patient to be treated;
invoking a natural language understanding service;
processing the disease description text according to a natural language understanding service to obtain patient state description information;
constructing a medical field dictionary, and segmenting the patient state description information based on the medical field dictionary to obtain a segmentation result;
and inputting the word segmentation results into a preset sliding window algorithm one by one to match with the symptom keywords, and outputting a plurality of first symptom keywords.
Optionally, the generating a pre-trained medical genus judgment model according to the following steps includes:
constructing a medical discipline judgment model by adopting an n-gram model;
collecting a plurality of medical description texts of different families in the medical field;
inputting a plurality of medical description texts of different subjects into a medical subject judgment model to obtain semantic vectors corresponding to the plurality of medical description texts of different subjects; the semantic vector is generated after a sentence vectorization module in the medical discipline judgment model processes each medical description text;
calculating a target loss value according to semantic vectors corresponding to a plurality of medical description texts of different families;
generating a pre-trained medical discipline judgment model according to the target loss value; wherein,
the semantic vector calculation formula of the medical description texts of different families is as follows:
Xivector representations corresponding to a plurality of medical description texts of different families.
Optionally, determining an optimal reply text according to the question-answer database includes:
analyzing the severity of the disease of the patient to be treated according to the plurality of first disease keywords;
acquiring a plurality of preset candidate reply text sets with different reply depths in a question-answer database;
determining a target candidate reply text set from a plurality of preset candidate reply text sets according to the severity of the illness of the patient to be treated;
calculating the similarity between the plurality of first disease condition keywords and each reply text in the target candidate reply text set;
and determining the reply text with the maximum similarity as the optimal reply text.
Optionally, determining a plurality of second disease condition keywords according to the optimal response text includes:
determining the language type of the patient to be treated according to the disease description text of the patient to be treated;
performing language conversion on the optimal reply text according to the language type of the patient to be processed to obtain a converted language text;
displaying the converted language text;
and receiving and analyzing the disease description texts input aiming at the displayed language texts to generate a plurality of second disease keywords.
Optionally, before receiving and parsing the disease description text of the patient to be treated, the method further includes:
loading patient information to be treated;
an initial question-answering report is created according to the information of the patient to be processed.
Optionally, generating a final question-and-answer report of the patient according to the plurality of first condition keywords and the plurality of second condition keywords comprises:
when the number of the keywords of the first disease condition keywords and the second disease condition keywords is larger than or equal to a preset threshold value, mapping and associating the first disease condition keywords and the second disease condition keywords into an initial question-answer report to obtain a final question-answer report of the patient;
or,
and when the number of the keywords of the first disease condition keywords and the second disease condition keywords is less than a preset threshold value, continuously executing the step of determining the optimal reply text according to the question-answer database.
In a second aspect, an artificial intelligence assisted question answering device is provided, which comprises:
the text analysis module is used for receiving and analyzing the disease description text of the patient to be processed and generating a plurality of first disease keywords;
the family judgment module is used for inputting a plurality of first disease condition keywords into a pre-trained medical family judgment model and outputting a target family corresponding to the patient to be treated;
the optimal reply text determination module is used for connecting the question-answer database corresponding to the target subject and determining an optimal reply text according to the question-answer database;
the keyword determining module is used for determining a plurality of second disease keywords according to the optimal reply text;
and the final question-answer report generating module is used for generating a final question-answer report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords.
In a third aspect, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the intelligent question-answering processing method are implemented.
In a fourth aspect, a computer-readable storage medium is provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the intelligent question-answering processing method.
According to the artificial intelligence assisted question-answering method, the artificial intelligence assisted question-answering device, firstly, a disease state description text of a patient to be processed is received and analyzed, a plurality of first disease state key words are generated, then the first disease state key words are input into a pre-trained medical subject judgment model, a target subject corresponding to the patient to be processed is output, then a question-answering database corresponding to the target subject is connected, an optimal answer text is determined according to the question-answering database, and finally a plurality of second disease state key words are determined according to the optimal answer text; and generating a final question-answering report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords. According to the method and the system, the collection and analysis of the patient information can be automatically completed to obtain a plurality of disease keywords, the final diagnosis report of the patient is obtained based on the plurality of disease keywords, and then the final diagnosis report is pushed to an artificial expert to make a comprehensive diagnosis and conditioning scheme, so that the inquiry process is accelerated, and the treatment efficiency is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a diagram of an implementation environment of an artificial intelligence assisted question answering method provided in an embodiment of the present application;
FIG. 2 is a schematic diagram of an internal structure of a computer device according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a method for artificial intelligence assisted question answering in one embodiment of the present application;
FIG. 4 is a schematic process diagram of an artificial intelligence assisted question answering process provided in one embodiment of the present application;
FIG. 5 is a schematic diagram of an apparatus for assisting a question answering device with artificial intelligence according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an optimal response text determination module according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another.
Fig. 1 is a diagram of an implementation environment of an artificial intelligence assisted question answering method provided in an embodiment, as shown in fig. 1, in the implementation environment, including a server 110 and a client 120.
The server 110 may be a server, which may specifically be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a web service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like, for example, a server device that stores a medical discipline judgment model and a question and answer database. When artificial intelligence assisted question answering is needed, the client 120 receives and analyzes a disease description text of a patient to be processed to generate a plurality of first disease keywords, the client 120 initializes a pre-trained medical department judgment model and relevant parameters of a question answering database from the server 110, the client 120 inputs the plurality of first disease keywords into the pre-trained medical department judgment model to output a target department corresponding to the patient to be processed, the client 120 is connected with the question answering database corresponding to the target department and determines an optimal answer text according to the question answering database, the client 120 determines a plurality of second disease keywords according to the optimal answer text, and the client 120 generates a final question answering report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords.
It should be noted that the client 120 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, and the like, but is not limited thereto. The server 110 and the client 120 may be connected through bluetooth, USB (Universal Serial Bus), or other communication connection methods, which is not limited herein.
FIG. 2 is a diagram showing an internal configuration of a computer device according to an embodiment. As shown in fig. 2, the computer device includes a processor, a medium, a memory, and a network interface connected by a system bus. The computer device comprises a medium, an operating system, a database and computer readable instructions, wherein the database can store control information sequences, and the computer readable instructions can enable a processor to realize an artificial intelligence assisted question-answering method when being executed by the processor. The processor of the computer device is used for providing calculation and control capability and supporting the operation of the whole device. The memory of the computer device may have stored therein computer readable instructions that, when executed by the processor, cause the processor to perform a method for artificial intelligence assisted question answering. The network interface of the computer device is used for connecting and communicating with the terminal. Those skilled in the art will appreciate that the architecture shown in fig. 2 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components. Wherein the medium is a readable storage medium.
The artificial intelligence assisted question answering method provided by the embodiment of the application will be described in detail below with reference to fig. 3-4. The method may be implemented by means of a computer program, which may be run on an artificial intelligence assisted question-answering device based on the von neumann architecture. The computer program may be integrated into the application or may run as a separate tool-like application.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence base technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
Please refer to fig. 3, which provides a schematic flow chart of an artificial intelligence assisted question answering method according to an embodiment of the present application. As shown in fig. 3, the method of the embodiment of the present application may include the following steps:
s101, receiving and analyzing a disease description text of a patient to be processed to generate a plurality of first disease keywords;
wherein, the disease description text is automatically generated by the client according to the information input by the patient. The disease key words are determined after analyzing the disease description texts.
In the embodiment of the application, firstly, a disease description text of a patient to be processed is received, then, natural language understanding service is called, the disease description text is processed according to the natural language understanding service to obtain state description information of the patient, secondly, a medical field dictionary is built, the state description information of the patient is segmented based on the medical field dictionary to obtain segmentation results, finally, the segmentation results are input into a preset sliding window algorithm one by one to be matched with symptom keywords, and a plurality of first disease keywords are output.
Specifically, the disease description text of the patient to be treated may be a voice description text or a text description text, and the voice description text may be a description text of multiple languages.
Specifically, when receiving a disease description text of a patient to be treated, a user can press a voice input function on the client, and after the pressing is triggered, the user performs voice description according to symptoms appearing in the user. Or, by clicking a text editing box of the client, the text inputs the symptoms appearing in the text. Finally, after the input is completed, the disease description text of the patient to be treated can be obtained.
Further, before receiving and parsing the disease description text of the patient to be treated, the patient information to be treated is loaded first, and then an initial question-and-answer report is created according to the patient information to be treated.
In a possible implementation mode, firstly, a patient inputs personal information for verification, after the verification is passed, a client loads the patient information, an initial question-answering report is created according to the patient information, then the patient inputs a disease description text of the patient by clicking a voice input function or a text editing function, and finally, a plurality of first disease keywords are obtained by analyzing the disease description text.
S102, inputting a plurality of first disease condition keywords into a pre-trained medical genus judgment model, and outputting a target genus corresponding to a patient to be processed;
the medical families are generic terms of different families in medicine, and the medical families can comprise internal medicine, surgery, orthopedics and the like, and the different families are responsible for treating different diseases. The medical discipline judgment model is a mathematical model that determines which discipline a patient belongs to based on the patient condition keyword.
In the embodiment of the application, when a pre-trained medical discipline judgment model is generated, firstly, a medical discipline judgment model is built by adopting an n-gram model, then, a plurality of medical description texts of different disciplines in the medical field are collected, then, the plurality of medical description texts of different disciplines are input into the medical discipline judgment model, and semantic vectors corresponding to the plurality of medical description texts of different disciplines are obtained, wherein the semantic vectors are generated after each medical description text is processed by a sentence vectorization module in the medical discipline judgment model; secondly, calculating a target loss value according to semantic vectors corresponding to a plurality of medical description texts of different subjects, and finally generating a pre-trained medical subject judgment model according to the target loss value. The semantic vector calculation formula of the medical description texts of different families is as follows:
Xivector representations corresponding to a plurality of medical description texts of different families.
Further, when a pre-trained medical discipline judgment model is generated according to the target loss value, when the target loss value reaches a preset threshold and the training times reach preset times, the pre-trained medical discipline judgment model is generated, or when the loss value does not reach the preset threshold and the training times do not reach the preset times, the loss value is propagated reversely to update parameters of the model, and the step of inputting a plurality of medical description texts of different disciplines into the medical discipline judgment model is continuously executed.
In a possible implementation manner, after obtaining a plurality of first disease condition keywords according to step S101, a pre-trained medical family judgment model may be called, then the plurality of first disease condition keywords are input into the pre-trained medical family judgment model for processing, and finally a target family corresponding to the patient to be processed may be output.
S103, connecting a question-answer database corresponding to the target subject, and determining an optimal answer text according to the question-answer database;
the question-answer database is a special answer database set for different departments, and each department can be provided with at least one question-answer database.
In general, when the target subject is determined based on step S102, the question-answer database corresponding to the target subject may be connected, and finally, the optimal response text is determined according to the question-answer database.
In the embodiment of the application, when the optimal reply text is determined according to the question-answer database, the disease severity of a patient to be treated is analyzed according to a plurality of first disease keywords, a plurality of preset candidate reply text sets with different reply depths in the question-answer database are obtained, a target candidate reply text set is determined from the preset candidate reply text sets according to the disease severity of the patient to be treated, the similarity between the plurality of first disease keywords and each reply text in the target candidate reply text set is calculated, and the reply text with the maximum similarity is determined as the optimal reply text.
For example, a plurality of first disease keywords are determined as "cough and fear of cold" respectively according to the disease description text of the patient, the content of the target department can be determined through a pre-trained medical department judgment model, then the client connects to the question-answer database of the department, and the optimal answer text can be determined according to the question-answer database of the department as to whether you are accompanied by expectoration and rhinorrhea symptoms? ".
S104, determining a plurality of second disease condition keywords according to the optimal reply text;
in a possible implementation manner, when a plurality of second disease condition keywords are determined according to the optimal reply text, firstly, the language type of the patient to be processed is determined according to the disease condition description text of the patient to be processed, then, the optimal reply text is subjected to language conversion according to the language type of the patient to be processed to obtain a converted language text, then, the converted language text is displayed, and finally, the disease condition description text input aiming at the displayed language text is received and analyzed to generate a plurality of second disease condition keywords.
And S105, generating a final question-answer report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords.
In one possible implementation manner, when a final question and answer report of a patient is generated according to a plurality of first disease condition keywords and a plurality of second disease condition keywords, when the number of the keywords of the plurality of first disease condition keywords and the plurality of second disease condition keywords is greater than or equal to a preset threshold value, the plurality of first disease condition keywords and the plurality of second disease condition keywords are mapped and associated to the initial question and answer report, and the final question and answer report of the patient is obtained; or when the number of the keywords of the first disease condition keywords and the second disease condition keywords is smaller than a preset threshold value, the step of determining the optimal reply text according to the question-answer database is continuously executed.
Further, the obtained multiple disease condition keywords also need to be cached in a preset slot position for temporary storage, when the multiple first disease condition keywords fill the preset slot position, the slot position needs to be filled, so that the number of the slot position is consistent with the number of the multiple first disease condition keywords and the number of the multiple second disease condition keywords, the keywords in the newly-built slot position can be identified by italics, such as ("cough", "cold feeling", "expectoration", "rhinorrhea"), the initial template has four slot positions, two slot positions are filled (non-italics), and two newly-built slot positions are to be filled (italics).
In one application scenario, the client and patient communicate as follows:
the user: i have headache;
a client: whether you are accompanied by these symptoms: headache is not cured for a long time, the headache is aggravated when encountering wind, the pain is relieved after the head is wrapped, the head top pain, migraine, head swelling and bone pain at the eyebrow growing position are caused;
the user: comprises the following steps of;
a client: whether you are accompanied by these symptoms: soreness of limbs, heaviness of the head, dizziness, and pharyngalgia;
the user: head weight;
a client: whether you are accompanied by these symptoms: nasal obstruction, nasal discharge, head pain, and itching throat;
the user: runny nose;
a client: whether you are accompanied by these symptoms: chest pain, heavy limbs, weakness of limbs, fear of wind blowing;
the user: cold feeling;
a client: whether you are accompanied by these symptoms: cold feeling, irresistible clothes addition, fever, expectoration and no sweat;
the user: expectoration;
a client: whether you are accompanied by these symptoms: hypohidrosis, distending pain in the head, prickling pain in the head, and dry mouth;
the user: … … are provided.
A plurality of keywords may be derived based on the communication to generate a patient question and answer report.
For example, as shown in fig. 4, fig. 4 is a schematic diagram of an artificial intelligence assisted question-answering process provided by the present application, which includes initializing patient information, collecting patient information, analyzing dialect information input by a patient by invoking natural language understanding (intention understanding, disease entity extraction) service to obtain keywords, determining a subject corresponding to the patient and connecting to a department database through the keywords, updating a patient state, determining an optimal answer text from the database, collecting information of a next step, and determining an information answer text until the keywords satisfy a set number, and generating a question-answering report.
In the embodiment of the application, the artificial intelligent auxiliary question-answering device firstly receives and analyzes a disease description text of a patient to be processed to generate a plurality of first disease keywords, then inputs the plurality of first disease keywords into a pre-trained medical subject judgment model, outputs a target subject corresponding to the patient to be processed, then connects a question-answering database corresponding to the target subject, determines an optimal answer text according to the question-answering database, and finally determines a plurality of second disease keywords according to the optimal answer text; and generating a final question-answering report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords. According to the method and the system, the collection and analysis of the patient information can be automatically completed to obtain a plurality of disease keywords, the final diagnosis report of the patient is obtained based on the plurality of disease keywords, and then the final diagnosis report is pushed to an artificial expert to make a comprehensive diagnosis and conditioning scheme, so that the inquiry process is accelerated, and the treatment efficiency is improved.
The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus of the present invention, reference is made to the embodiments of the method of the present invention.
Referring to fig. 5, a schematic structural diagram of an artificial intelligence assisted question answering apparatus provided by an exemplary embodiment of the present invention is shown, which is applied to a server. The artificial intelligence assisted question answering apparatus can be implemented as all or part of a device through software, hardware or a combination of both. The device 1 comprises a text analysis module 10, a family judgment module 20, an optimal reply text determination module 30, a keyword determination module 40 and a final question-answer report generation module 50.
The text analysis module 10 is used for receiving and analyzing the disease description text of the patient to be treated and generating a plurality of first disease keywords;
the family judgment module 20 is used for inputting a plurality of first disease keywords into a pre-trained medical family judgment model and outputting a target family corresponding to the patient to be processed;
the optimal reply text determination module 30 is used for connecting the question-answer database corresponding to the target subject and determining an optimal reply text according to the question-answer database;
a keyword determination module 40, configured to determine a plurality of second disease keywords according to the optimal reply text;
and a final question-answer report generating module 50, configured to generate a final question-answer report for the patient according to the plurality of first condition keywords and the plurality of second condition keywords.
Optionally, for example, as shown in fig. 6, the optimal reply text determination module 30 includes:
a disease severity analysis unit 301 for analyzing a disease severity of the patient to be treated based on the plurality of first condition keywords;
a reply text set obtaining unit 302, configured to obtain multiple preset candidate reply text sets with different reply depths in the question-and-answer database;
a target candidate reply text set determining unit 303, configured to determine a target candidate reply text set from a plurality of preset candidate reply text sets according to the severity of the illness of the patient to be treated;
a similarity calculation unit 304 for calculating a similarity between the plurality of first disorder keywords and each of the reply texts in the target candidate reply text set;
an optimal reply text determination unit 305 for determining the reply text with the largest similarity as the optimal reply text.
It should be noted that, when the high-voltage rear part identification device provided in the foregoing embodiment executes the high-voltage rear part identification method, only the division of the above functional modules is exemplified, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the above described functions. In addition, the high-pressure rear part identification device provided by the embodiment and the high-pressure rear part identification method embodiment belong to the same concept, and the detailed implementation process is shown in the method embodiment and is not described again.
The above-mentioned serial numbers of the embodiments of the present application are merely for description, and do not represent the advantages and disadvantages of the embodiments.
In the embodiment of the application, the artificial intelligent auxiliary question-answering device firstly receives and analyzes a disease description text of a patient to be processed to generate a plurality of first disease keywords, then inputs the plurality of first disease keywords into a pre-trained medical subject judgment model, outputs a target subject corresponding to the patient to be processed, then connects a question-answering database corresponding to the target subject, determines an optimal answer text according to the question-answering database, and finally determines a plurality of second disease keywords according to the optimal answer text; and generating a final question-answering report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords. According to the method and the system, the collection and analysis of the patient information can be automatically completed to obtain a plurality of disease keywords, the final diagnosis report of the patient is obtained based on the plurality of disease keywords, and then the final diagnosis report is pushed to an artificial expert to make a comprehensive diagnosis and conditioning scheme, so that the inquiry process is accelerated, and the treatment efficiency is improved.
In one embodiment, a computer device is provided, the device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: receiving and analyzing a disease description text of a patient to be treated to generate a plurality of first disease keywords; inputting a plurality of first disease condition keywords into a pre-trained medical family judgment model, and outputting a target family corresponding to a patient to be processed; connecting a question-answer database corresponding to the target subject, and determining an optimal answer text according to the question-answer database; determining a plurality of second disease condition keywords according to the optimal reply text; generating a final question-answer report of the patient according to the plurality of first disease condition keywords and the plurality of second disease condition keywords.
In one embodiment, the processor receives and parses a disease description text of a patient to be treated, and specifically performs the following operations when generating a plurality of first disease keywords: receiving a disease description text of a patient to be treated; invoking a natural language understanding service; processing the disease description text according to a natural language understanding service to obtain patient state description information; constructing a medical field dictionary, and segmenting the patient state description information based on the medical field dictionary to obtain a segmentation result; and inputting the word segmentation results into a preset sliding window algorithm one by one to match with the symptom keywords, and outputting a plurality of first symptom keywords.
In one embodiment, the processor generates the pre-trained medical genus judgment model by performing the following operations: constructing a medical discipline judgment model by adopting an n-gram model; collecting a plurality of medical description texts of different families in the medical field; inputting a plurality of medical description texts of different subjects into a medical subject judgment model to obtain semantic vectors corresponding to the plurality of medical description texts of different subjects; the semantic vector is generated after each piece of medical description text is processed by a sentence vectorization module in the medical discipline judgment model; calculating a target loss value according to semantic vectors corresponding to a plurality of medical description texts of different families; generating a pre-trained medical discipline judgment model according to the target loss value; the semantic vector calculation formula of the medical description texts of different families is as follows:
Xivector representation corresponding to a plurality of medical description texts of different families.
In one embodiment, when the processor determines the optimal reply text according to the question-answer database, the following operations are specifically performed: analyzing the severity of the disease of the patient to be treated according to the plurality of first disease keywords; acquiring a plurality of preset candidate reply text sets with different reply depths in a question-answer database; determining a target candidate reply text set from a plurality of preset candidate reply text sets according to the severity of the illness of the patient to be treated; calculating the similarity between the plurality of first disease condition keywords and each reply text in the target candidate reply text set; and determining the reply text with the maximum similarity as the optimal reply text.
In one embodiment, the processor, when determining the plurality of second disease condition keywords according to the optimal reply text, specifically performs the following operations: determining the language type of the patient to be treated according to the disease description text of the patient to be treated; performing language conversion on the optimal reply text according to the language type of the patient to be processed to obtain a converted language text; displaying the converted language text; and receiving and analyzing the disease description text input aiming at the displayed language text to generate a plurality of second disease keywords.
In one embodiment, the processor performs the following operations before receiving and parsing the condition description text of the patient to be treated: loading patient information to be treated;
an initial question-answering report is created according to the information of the patient to be processed.
In one embodiment, the processor performs the following operations when generating the final question-answering report of the patient according to the plurality of first condition keywords and the plurality of second condition keywords: when the number of the keywords of the first disease condition keywords and the second disease condition keywords is larger than or equal to a preset threshold value, mapping and associating the first disease condition keywords and the second disease condition keywords into an initial question-answer report to obtain a final question-answer report of the patient;
or,
and when the number of the keywords of the first disease condition keywords and the second disease condition keywords is less than a preset threshold value, continuously executing the step of determining the optimal reply text according to the question-answer database.
In the embodiment of the application, the artificial intelligent auxiliary question-answering device firstly receives and analyzes a disease description text of a patient to be processed to generate a plurality of first disease keywords, then inputs the plurality of first disease keywords into a pre-trained medical subject judgment model, outputs a target subject corresponding to the patient to be processed, then connects a question-answering database corresponding to the target subject, determines an optimal answer text according to the question-answering database, and finally determines a plurality of second disease keywords according to the optimal answer text; and generating a final question-answering report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords. According to the method and the system, the collection and analysis of the patient information can be automatically completed to obtain a plurality of disease keywords, the final diagnosis report of the patient is obtained based on the plurality of disease keywords, and then the final diagnosis report is pushed to an artificial expert to make a comprehensive diagnosis and conditioning scheme, so that the inquiry process is accelerated, and the treatment efficiency is improved.
In one embodiment, a medium is presented having computer-readable instructions stored thereon which, when executed by one or more processors, cause the one or more processors to perform the steps of: receiving and analyzing a disease description text of a patient to be treated to generate a plurality of first disease keywords; inputting a plurality of first disease condition keywords into a pre-trained medical family judgment model, and outputting a target family corresponding to a patient to be processed; connecting a question-answer database corresponding to the target subject, and determining an optimal answer text according to the question-answer database; determining a plurality of second disease condition keywords according to the optimal reply text; and generating a final question-answering report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords.
In one embodiment, the processor receives and parses a disease description text of a patient to be treated, and specifically performs the following operations when generating a plurality of first disease keywords: receiving a disease description text of a patient to be treated; invoking a natural language understanding service; processing the disease description text according to a natural language understanding service to obtain patient state description information; constructing a medical field dictionary, and segmenting the patient state description information based on the medical field dictionary to obtain a segmentation result; and inputting the word segmentation results into a preset sliding window algorithm one by one to match with the symptom keywords, and outputting a plurality of first symptom keywords.
In one embodiment, the processor, when generating the pre-trained medical discipline judgment model, specifically performs the following operations: constructing a medical discipline judgment model by adopting an n-gram model; collecting a plurality of medical description texts of different families in the medical field; inputting a plurality of medical description texts of different subjects into a medical subject judgment model to obtain semantic vectors corresponding to the plurality of medical description texts of different subjects; the semantic vector is generated after each medical description text is processed by a sentence vectorization module in the medical discipline judgment model; calculating a target loss value according to semantic vectors corresponding to a plurality of medical description texts of different families; generating a pre-trained medical discipline judgment model according to the target loss value; the semantic vector calculation formula of the medical description texts of different families is as follows:
Xivector representations corresponding to a plurality of medical description texts of different families.
In one embodiment, when the processor determines the optimal reply text according to the question-answer database, the following operations are specifically performed: analyzing the severity of the disease of the patient to be treated according to the plurality of first disease keywords; acquiring a plurality of preset candidate reply text sets with different reply depths in a question-answer database; determining a target candidate reply text set from a plurality of preset candidate reply text sets according to the severity of the illness of the patient to be treated; calculating the similarity between the plurality of first disease condition keywords and each reply text in the target candidate reply text set; and determining the reply text with the maximum similarity as the optimal reply text.
In one embodiment, the processor, when determining the plurality of second disease condition keywords according to the optimal reply text, specifically performs the following operations: determining the language type of the patient to be treated according to the disease description text of the patient to be treated; performing language conversion on the optimal reply text according to the language type of the patient to be processed to obtain a converted language text; displaying the converted language text; and receiving and analyzing the disease description text input aiming at the displayed language text to generate a plurality of second disease keywords.
In one embodiment, the processor performs the following operations before receiving and parsing the condition description text of the patient to be treated: loading patient information to be treated;
an initial question-answering report is created according to the information of the patient to be processed.
In one embodiment, the processor performs the following operations when generating the final question-answering report of the patient according to the plurality of first condition keywords and the plurality of second condition keywords: when the number of the keywords of the first disease condition keywords and the second disease condition keywords is larger than or equal to a preset threshold value, mapping and associating the first disease condition keywords and the second disease condition keywords into an initial question-answer report to obtain a final question-answer report of the patient;
or,
and when the number of the keywords of the first disease condition keywords and the second disease condition keywords is less than a preset threshold value, continuously executing the step of determining the optimal reply text according to the question-answer database.
In the embodiment of the application, the artificial intelligent auxiliary question-answering device firstly receives and analyzes a disease description text of a patient to be processed to generate a plurality of first disease keywords, then inputs the plurality of first disease keywords into a pre-trained medical subject judgment model, outputs a target subject corresponding to the patient to be processed, then connects a question-answering database corresponding to the target subject, determines an optimal answer text according to the question-answering database, and finally determines a plurality of second disease keywords according to the optimal answer text; and generating a final question-answering report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords. According to the method and the system, the collection and analysis of the patient information can be automatically completed to obtain a plurality of disease keywords, the final diagnosis report of the patient is obtained based on the plurality of disease keywords, and then the final diagnosis report is pushed to an artificial expert to make a comprehensive diagnosis and conditioning scheme, so that the inquiry process is accelerated, and the treatment efficiency is improved.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer readable medium, and when executed, can include the processes of the embodiments of the methods described above. The medium may be a non-volatile medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only show some embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An artificial intelligence assisted question answering method is characterized by comprising the following steps:
receiving and analyzing a disease description text of a patient to be treated to generate a plurality of first disease keywords;
inputting the first disease keywords into a pre-trained medical family judgment model, and outputting a target family corresponding to the patient to be processed;
connecting a question-answer database corresponding to the target subject, and determining an optimal answer text according to the question-answer database;
determining a plurality of second disease condition keywords according to the optimal reply text;
generating a final question-answering report of the patient according to the plurality of first disease keywords and the plurality of second disease keywords.
2. The method of claim 1, wherein receiving and parsing a condition description text of a patient to be treated to generate a plurality of first condition keywords comprises:
receiving a disease description text of a patient to be treated;
invoking a natural language understanding service;
processing the disease description text according to the natural language understanding service to obtain patient state description information;
constructing a medical field dictionary, and segmenting the patient state description information based on the medical field dictionary to obtain a segmentation result;
and inputting the word segmentation results into a preset sliding window algorithm one by one to match with the symptom keywords, and outputting a plurality of first symptom keywords.
3. The method of claim 1, wherein generating a pre-trained medical genus judgment model comprises:
constructing a medical discipline judgment model by adopting an n-gram model;
collecting a plurality of medical description texts of different families in the medical field;
inputting the medical description texts of different subjects into the medical subject judgment model to obtain semantic vectors corresponding to the medical description texts of different subjects;
calculating a target loss value according to semantic vectors corresponding to the medical description texts of different families; the semantic vector is generated after a sentence vectorization module in the medical discipline judgment model processes each medical description text;
generating a pre-trained medical discipline judgment model according to the target loss value; wherein,
4. The method of claim 1, wherein determining an optimal response text from the question-answer database comprises:
analyzing the severity of the disease of the patient to be treated according to the plurality of first disease keywords;
acquiring a plurality of preset candidate reply text sets with different reply depths in the question-answer database;
determining a target candidate reply text set from the plurality of preset candidate reply text sets according to the severity of the patient to be treated;
calculating the similarity between the plurality of first disease condition keywords and each reply text in the target candidate reply text set;
and determining the reply text with the maximum similarity as the optimal reply text.
5. The method of claim 1, wherein determining a plurality of second condition keywords from the optimal response text comprises:
determining the language type of the patient to be treated according to the disease description text of the patient to be treated;
performing language conversion on the optimal reply text according to the language type of the patient to be processed to obtain a converted language text;
displaying the converted language text;
and receiving and analyzing the disease description text input aiming at the displayed language text to generate a plurality of second disease keywords.
6. The method of claim 1, wherein prior to receiving and parsing the condition description text of the patient to be treated, further comprising:
loading patient information to be treated;
and creating an initial question-answer report according to the information of the patient to be processed.
7. The method of claim 6, wherein generating a patient final question-and-answer report based on the plurality of first condition keywords and the plurality of second condition keywords comprises:
when the number of the keywords of the first disease keywords and the second disease keywords is larger than or equal to a preset threshold value, mapping and associating the first disease keywords and the second disease keywords into the initial question-answer report to obtain a final question-answer report of the patient;
or,
and when the number of the keywords of the first disease condition keywords and the second disease condition keywords is less than a preset threshold value, continuously executing the step of determining the optimal reply text according to the question-answer database.
8. An artificial intelligence assisted question answering apparatus, characterized in that the apparatus comprises:
the text analysis module is used for receiving and analyzing the disease description text of the patient to be processed and generating a plurality of first disease keywords;
the family judgment module is used for inputting the first disease keywords into a pre-trained medical family judgment model and outputting a target family corresponding to the patient to be processed;
the optimal reply text determination module is used for connecting the question-answer database corresponding to the target subject and determining an optimal reply text according to the question-answer database;
a keyword determining module, configured to determine a plurality of second disease keywords according to the optimal reply text;
and the final question-answer report generating module is used for generating a patient final question-answer report according to the plurality of first disease keywords and the plurality of second disease keywords.
9. A computer storage medium, characterized in that it stores a plurality of instructions adapted to be loaded by a processor and to perform the method steps according to any one of claims 1 to 7.
10. A terminal, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210253548.1A CN114664431A (en) | 2022-03-15 | 2022-03-15 | Artificial intelligence assisted question and answer method, device, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210253548.1A CN114664431A (en) | 2022-03-15 | 2022-03-15 | Artificial intelligence assisted question and answer method, device, equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114664431A true CN114664431A (en) | 2022-06-24 |
Family
ID=82030374
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210253548.1A Pending CN114664431A (en) | 2022-03-15 | 2022-03-15 | Artificial intelligence assisted question and answer method, device, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114664431A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115238064A (en) * | 2022-09-20 | 2022-10-25 | 大安健康科技(北京)有限公司 | Keyword extraction method of traditional Chinese medicine medical record based on clustering |
CN117995347A (en) * | 2024-04-07 | 2024-05-07 | 北京惠每云科技有限公司 | Medical record content quality control method and device, electronic equipment and storage medium |
-
2022
- 2022-03-15 CN CN202210253548.1A patent/CN114664431A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115238064A (en) * | 2022-09-20 | 2022-10-25 | 大安健康科技(北京)有限公司 | Keyword extraction method of traditional Chinese medicine medical record based on clustering |
CN117995347A (en) * | 2024-04-07 | 2024-05-07 | 北京惠每云科技有限公司 | Medical record content quality control method and device, electronic equipment and storage medium |
CN117995347B (en) * | 2024-04-07 | 2024-06-21 | 北京惠每云科技有限公司 | Medical record content quality control method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109670179B (en) | Medical record text named entity identification method based on iterative expansion convolutional neural network | |
CN107729392B (en) | Text structuring method, device and system and non-volatile storage medium | |
CN109215754A (en) | Medical record data processing method, device, computer equipment and storage medium | |
CN108491486B (en) | Method, device, terminal equipment and storage medium for simulating patient inquiry dialogue | |
CN110931137B (en) | Machine-assisted dialog systems, methods, and apparatus | |
CN114664431A (en) | Artificial intelligence assisted question and answer method, device, equipment and medium | |
CN110427486B (en) | Body condition text classification method, device and equipment | |
CN112036154A (en) | Electronic medical record generation method and device based on inquiry dialogue and computer equipment | |
EP4361843A1 (en) | Neural network searching method and related device | |
CN111710383A (en) | Medical record quality control method and device, computer equipment and storage medium | |
Kavitha et al. | Chatbot for healthcare system using Artificial Intelligence | |
CN111191446B (en) | Interactive information processing method and device, computer equipment and storage medium | |
CN110750642A (en) | CNN-based Chinese relation classification method and system | |
CN111160049B (en) | Text translation method, apparatus, machine translation system, and storage medium | |
CN113326383B (en) | Short text entity linking method, device, computing equipment and storage medium | |
CN111429991A (en) | Medicine prediction method and device, computer equipment and storage medium | |
CN114490984A (en) | Question-answer knowledge extraction method, device, equipment and medium based on keyword guidance | |
CN112037904B (en) | Online diagnosis and treatment data processing method and device, computer equipment and storage medium | |
CN113657086A (en) | Word processing method, device, equipment and storage medium | |
CN113724830A (en) | Medicine taking risk detection method based on artificial intelligence and related equipment | |
CN110648754A (en) | Department recommendation method, device and equipment | |
JP2019082860A (en) | Generation program, generation method and generation device | |
CN116861875A (en) | Text processing method, device, equipment and storage medium based on artificial intelligence | |
JP2022089169A (en) | Method and device for decentralized supervised learning in nlp application | |
CN115579153A (en) | Inquiry evaluation method, inquiry evaluation device, electronic device, and readable storage medium |
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 |