CN110085316A - A kind of hypertension question answering system and its system method for building up based on deep learning - Google Patents

A kind of hypertension question answering system and its system method for building up based on deep learning Download PDF

Info

Publication number
CN110085316A
CN110085316A CN201910391205.XA CN201910391205A CN110085316A CN 110085316 A CN110085316 A CN 110085316A CN 201910391205 A CN201910391205 A CN 201910391205A CN 110085316 A CN110085316 A CN 110085316A
Authority
CN
China
Prior art keywords
hypertension
module
answer
question
language
Prior art date
Application number
CN201910391205.XA
Other languages
Chinese (zh)
Inventor
李宇欣
裘实
Original Assignee
北京康健数字化健康管理研究院
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 北京康健数字化健康管理研究院 filed Critical 北京康健数字化健康管理研究院
Priority to CN201910391205.XA priority Critical patent/CN110085316A/en
Publication of CN110085316A publication Critical patent/CN110085316A/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/26Speech to text systems
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20ICT 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
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H80/00ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring

Abstract

The invention discloses a kind of hypertension question answering system and its system method for building up based on deep learning reply module the system comprises voice pick device, voice paraphrase module, language and characters library, hypertension medical knowledge base, question and answer knowledge base, reasoning diagnosis and reply feedback module;Voice pick device is used to being converted to the voice messaging of user into electric signal, inputs question answering system;The problem of voice paraphrase module utilizes the language message in language and characters library, the language message inputted for analyzing user, analyzes user content;Reasoning diagnosis replies the problem of module receives language paraphrase module content, retrieves hypertension medical knowledge base and question and answer knowledge base according to problem, sends a reply to answer feedback module according to search result;Feedback module is replied for that will reply through language, text or photo feedback to user.Solve the problems, such as that existing time-consuming by search engine acquisition medical knowledge and information accuracy difficulty is sentenced.

Description

A kind of hypertension question answering system and its system method for building up based on deep learning

Technical field

The present invention relates to a kind of medical question answering systems, and in particular to a kind of hypertension question answering system based on deep learning and Its system method for building up.

Background technique

In the past, in such a way that search engine obtains knowledge, user's a large amount of time is on the one hand wasted;On the other hand it is curing The field of disease inquiry is treated, the good and bad jumbled together for information source, and user's resolving ability is limited, and there are misguided possibilities.Traditional asks Answering community needs human-edited's answer, and period of reservation of number is longer, along with the development of the artificial intelligence technologys such as NLP, knowledge mapping, Instant Health information service is provided in the form of question and answer for user to be possibly realized.

So needing a novel intelligent Answer System, which can satisfy user to specific hypertension medical field Question and answer demand, can recognize that the answer of inquiry is expressed and quickly can correctly be provided to the colloquial style of user.

Summary of the invention

The purpose of the present invention is to provide a kind of hypertension question answering system and its system method for building up based on deep learning, To solve the problems, such as that existing time-consuming by search engine acquisition medical knowledge and information accuracy difficulty is sentenced.

In order to solve the above technical problems, the present invention adopts the following technical scheme:

A kind of hypertension question answering system based on deep learning, the system comprises voice pick devices, voice paraphrase module, language Sound literal pool, hypertension medical knowledge base, question and answer knowledge base, reasoning diagnosis reply module and reply feedback module;

The voice pick device is used to being converted to the voice messaging of user into electric signal, inputs voice paraphrase module;

The voice paraphrase module utilizes the language message in language and characters library, for analyzing the language message of user's input, analysis Content the problem of user out;

The reasoning diagnosis replies the problem of module receives language paraphrase module content, retrieves hypertension medical knowledge according to problem The diagnosis input content of missing is sent to answer feedback module when lacking dependent diagnostic input by library and question and answer knowledge base, when After obtaining complete diagnosis input, reasoning diagnosis replies module and obtains the highest answer of confidence level, is sent to answer feedback module;

The answer feedback module will be for that will reply through language, text or photo feedback to user.

Preferably, above-mentioned voice pick device includes the microphone of the microphone of smart machine, the microphone of mobile phone and computer.

Preferably, the problem of above-mentioned voice paraphrase module analysis comes out content include blood pressure values, symptom, special population and Dietetic variety.

Preferably, above-mentioned answer feedback module by the microphone of smart machine or display, mobile phone loudspeaker or Screen, the loudspeaker of computer or screen are by language, text or photo feedback to user.

A kind of hypertension question answering system method for building up based on deep learning, method for building up specifically comprise the following steps:

Step1: voice pick device needed for establishing system operation and the hardware for replying feedback module, realize system and user it Between information interaction;

Step2: the language and characters library based on existing maturation constructs voice paraphrase module, writing system software;

Step3: the existing medical knowledge relevant to hypertension of typing constructs hypertension medical knowledge base, and in system operation In constantly improve the hypertension medical knowledge base constructed;

Step4: being based on existing network question and answer relevant to hypertension, constructs question and answer knowledge base;

Step5: in system operation, tissue doctor is reviewed modification to system replies result, and system passes through doctor's Modification is checked, constantly improve and updates hypertension knowledge library and question and answer knowledge base.

Preferably, existing medical knowledge relevant to the hypertension source in above-mentioned Step3 include books, periodical and High-level meeting paper.

Preferably, the existing network question and answer relevant to hypertension in above-mentioned Step4 include the question and answer of professional forum, hospital The medical software information of webpage and profession.

The present invention has the advantage that

It takes the present invention is based on after the scheme of the hypertension question answering system of deep learning, realizes to existing medical knowledge and question and answer The combination of system realizes the consulting to user and is correctly identified;Integrate the base of existing medical system and question answering system knowledge On plinth, in conjunction with the Real-time Feedback synchronous refresh knowledge base of doctor, completes and the system Construction correctly replied is provided to user's question and answer, User is allowed to obtain reliable medical advice or answer in time by the system.

Detailed description of the invention

Fig. 1 is a kind of work flow diagram of the hypertension question answering system embodiment based on deep learning of the present invention;

Fig. 2 is a kind of process of construction process of the hypertension question answering system method for building up embodiment based on deep learning of the present invention Figure.

Specific embodiment

Embodiments of the present invention are illustrated by particular specific embodiment below, those skilled in the art can be by this explanation Content disclosed by book is understood other advantages and efficacy of the present invention easily.

It should be clear that this specification structure depicted in this specification institute accompanying drawings, ratio, size etc., only to cooperate specification to be taken off The content shown is not intended to limit the invention enforceable qualifications so that those skilled in the art understands and reads, therefore Do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the present invention Under the effect of can be generated and the purpose that can reach, it should all still fall in disclosed technology contents and obtain the model that can cover In enclosing.Meanwhile cited such as "upper", "lower", " left side ", the right side in this specification ", the term of " centre ", be merely convenient to chat That states is illustrated, rather than to limit the scope of the invention, relativeness is altered or modified, and is changing skill without essence It is held in art, when being also considered as the enforceable scope of the present invention.

Embodiment 1

Referring to Fig. 1, a kind of hypertension question answering system based on deep learning, the system comprises voice pick device, voices to release Adopted module, language and characters library, hypertension medical knowledge base, question and answer knowledge base, reasoning diagnosis reply module and reply feedback module; Voice pick device includes the microphone of the microphone of smart machine, the microphone of mobile phone and computer, for turning the voice messaging of user It is changed to electric signal, inputs voice paraphrase module;Voice paraphrase module utilizes the language message in language and characters library, for analyzing user The language message of input, the problem of analyzing user content, analyze the problem content come include blood pressure values, it is symptom, special Crowd and dietetic variety;Reasoning diagnosis replies the problem of module receives language paraphrase module content, retrieves hypertension according to problem It is anti-to be sent to answer when lacking dependent diagnostic input by medical knowledge base and question and answer knowledge base for the diagnosis input content of missing Module is presented, after obtaining complete diagnosis input, reasoning diagnosis replies module and obtains the highest answer of confidence level, is sent to answer Feedback module;It replies feedback module and passes through the microphone of smart machine or display, the loudspeaker of mobile phone or screen, computer Perhaps photo feedback is anti-by language, text or photo for that will reply to user by language, text for loudspeaker or screen Feed user.

In embodiment, the method for the voice messaging of above-mentioned voice paraphrase module analysis user input, first is that using nature language Speech technology carries out profound understanding to problem, understanding content include be intended to analysis, name Entity recognition, interdependent syntactic analysis, Word sense disambiguation etc.;It is included into different classifications second is that puing question to user by Question Classification, is enabled a system to for different problem classes Type obtains candidate answers set using different answer feedback mechanism;Third is that extracting main completion customer problem by problem focus Information requirement accurate positioning, obtain accurate user put question to the problem of content.

Referring to fig. 2, a kind of hypertension question answering system method for building up based on deep learning, method for building up specifically includes as follows Step:

Step1: voice pick device needed for establishing system operation and the hardware for replying feedback module, realize system and user it Between information interaction;

Step2: the language and characters library based on existing maturation constructs voice paraphrase module, writing system software;

Step3: (existing medical knowledge relevant with hypertension source includes figure to the existing medical knowledge relevant to hypertension of typing Book, periodical and high-level meeting paper) building hypertension medical knowledge base, and structure is constantly improve in system operation The hypertension medical knowledge base built;

Step4: based on existing network question and answer relevant to hypertension, (existing network question and answer relevant with hypertension include profession opinion The medical software information of altar, the question and answer webpage of hospital and profession), construct question and answer knowledge base;

Step5: in system operation, tissue doctor is reviewed modification to system replies result, and system passes through doctor's Modification is checked, constantly improve and updates hypertension knowledge library and question and answer knowledge base, the machine learning frame increased income using Google TensorFlow, which improve to hypertension knowledge library and question and answer knowledge base, to be updated and completes to diagnose reasoning the mould for replying module Type training.

Take the present invention is based on after the scheme of the hypertension question answering system of deep learning, realizing to existing medical knowledge and The combination of question answering system realizes the consulting to user and is correctly identified;Integrate existing medical system and question answering system knowledge On the basis of, in conjunction with the Real-time Feedback synchronous refresh knowledge base of doctor, completes and the system correctly replied is provided to user's question and answer Construction allows user to obtain reliable medical advice or answer in time by the system.

In actual use, with the increase of number of users, the rising of question and answer number checks result with doctor, The answer accuracy and reliability of system is gradually increasing, and obtains more accurate and reliable diagnosis capability with the development of medical treatment.

Although above having used general explanation and specific embodiment, the present invention is described in detail, at this On the basis of invention, it can be made some modifications or improvements, this will be apparent to those skilled in the art.Therefore, These modifications or improvements without departing from theon the basis of the spirit of the present invention are fallen within the scope of the claimed invention.

Claims (7)

1. a kind of hypertension question answering system based on deep learning, it is characterised in that: the system comprises voice pick devices, language Sound paraphrase module, language and characters library, hypertension medical knowledge base, question and answer knowledge base, reasoning diagnosis reply module and reply feedback Module;
The voice pick device is used to being converted to the voice messaging of user into electric signal, inputs voice paraphrase module;
The voice paraphrase module utilizes the language message in language and characters library, for analyzing the language message of user's input, analysis Content the problem of user out;
The reasoning diagnosis replies the problem of module receives language paraphrase module content, retrieves hypertension medical knowledge according to problem The diagnosis input content of missing is sent to answer feedback module when lacking dependent diagnostic input by library and question and answer knowledge base, when After obtaining complete diagnosis input, reasoning diagnosis replies module and obtains the highest answer of confidence level, is sent to answer feedback module;
The answer feedback module will be for that will reply through language, text or photo feedback to user.
2. a kind of hypertension question answering system based on deep learning according to claim 1, it is characterised in that: the voice Pick device includes the microphone of the microphone of smart machine, the microphone of mobile phone and computer.
3. a kind of hypertension question answering system based on deep learning according to claim 1, it is characterised in that: the voice The problem of paraphrase module analysis comes out content includes blood pressure values, symptom, special population and dietetic variety.
4. a kind of hypertension question answering system and its system method for building up based on deep learning according to claim 1, It is characterized in that: the microphone or display, the loudspeaker of mobile phone or screen, electricity for replying feedback module and passing through smart machine The loudspeaker or screen of brain are by language, text or photo feedback to user.
5. a kind of hypertension question answering system method for building up based on deep learning, which is characterized in that method for building up specifically include as Lower step:
Step1: voice pick device needed for establishing system operation and the hardware for replying feedback module, realize system and user it Between information interaction;
Step2: the language and characters library based on existing maturation constructs voice paraphrase module, writing system software;
Step3: the existing medical knowledge relevant to hypertension of typing constructs hypertension medical knowledge base, and in system operation In constantly improve the hypertension medical knowledge base constructed;
Step4: being based on existing network question and answer relevant to hypertension, constructs question and answer knowledge base;
Step5: in system operation, tissue doctor is reviewed modification to system replies result, and system passes through doctor's Modification is checked, constantly improve and updates hypertension knowledge library and question and answer knowledge base.
6. a kind of hypertension question answering system method for building up based on deep learning according to claim 5, it is characterised in that: institute Stating the relevant medical knowledge source of the existing and hypertension in Step3 includes books, periodical and high-level meeting paper.
7. a kind of hypertension question answering system method for building up based on deep learning according to claim 5, it is characterised in that: institute State the medical treatment that the question and answer relevant to hypertension of the existing network in Step4 include professional forum, the question and answer webpage of hospital and profession Software information.
CN201910391205.XA 2019-05-11 2019-05-11 A kind of hypertension question answering system and its system method for building up based on deep learning CN110085316A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910391205.XA CN110085316A (en) 2019-05-11 2019-05-11 A kind of hypertension question answering system and its system method for building up based on deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910391205.XA CN110085316A (en) 2019-05-11 2019-05-11 A kind of hypertension question answering system and its system method for building up based on deep learning

Publications (1)

Publication Number Publication Date
CN110085316A true CN110085316A (en) 2019-08-02

Family

ID=67419752

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910391205.XA CN110085316A (en) 2019-05-11 2019-05-11 A kind of hypertension question answering system and its system method for building up based on deep learning

Country Status (1)

Country Link
CN (1) CN110085316A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130116128A (en) * 2012-04-14 2013-10-23 윤재민 Question answering system using speech recognition by tts, its application method thereof
CN106202301A (en) * 2016-07-01 2016-12-07 武汉泰迪智慧科技有限公司 A kind of intelligent response system based on degree of depth study
CN106557653A (en) * 2016-11-15 2017-04-05 合肥工业大学 A kind of portable medical intelligent medical guide system and method
CN109545391A (en) * 2018-10-26 2019-03-29 曾警卫 A kind of intelligent medical automatically request-answering system and application method based on deep learning

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130116128A (en) * 2012-04-14 2013-10-23 윤재민 Question answering system using speech recognition by tts, its application method thereof
CN106202301A (en) * 2016-07-01 2016-12-07 武汉泰迪智慧科技有限公司 A kind of intelligent response system based on degree of depth study
CN106557653A (en) * 2016-11-15 2017-04-05 合肥工业大学 A kind of portable medical intelligent medical guide system and method
CN109545391A (en) * 2018-10-26 2019-03-29 曾警卫 A kind of intelligent medical automatically request-answering system and application method based on deep learning

Similar Documents

Publication Publication Date Title
US10884503B2 (en) VPA with integrated object recognition and facial expression recognition
Vaismoradi et al. Theme in qualitative content analysis and thematic analysis
Baskarada Qualitative case study guidelines
US9753914B2 (en) Natural expression processing method, processing and response method, device, and system
Mårtensson et al. Evaluating research: A multidisciplinary approach to assessing research practice and quality
Gunnarsson et al. The construction of professional discourse
Wang Why students choose STEM majors: Motivation, high school learning, and postsecondary context of support
Beatty-Martínez et al. Bilingual experience shapes language processing: Evidence from codeswitching
US10402501B2 (en) Multi-lingual virtual personal assistant
Miller Measuring up to speech intelligibility
Broom Using qualitative interviews in CAM research: a guide to study design, data collection and data analysis
WO2018040501A1 (en) Man-machine interaction method and apparatus based on artificial intelligence
Bowers et al. Local and global structuring of computer mediated communication: Developing linguistic perspectives on CSCW in COSMOS
US20190295699A1 (en) Targeted sensation of touch
Bornstein et al. Mother-infant contingent vocalizations in 11 countries
O'dea et al. A linguistic analysis of suicide-related Twitter posts.
Hirschheim et al. Information systems development and data modeling: conceptual and philosophical foundations
Tan Grounded theory in practice: Issues and discussion for new qualitative researchers
CN104991965B (en) For asking the creation method and apparatus that extension is asked based on standard
US20170161619A1 (en) Concept-Based Navigation
Boger et al. Principles for fostering the transdisciplinary development of assistive technologies
US9431003B1 (en) Imbuing artificial intelligence systems with idiomatic traits
Bunt The DIT++ taxonomy for functional dialogue markup
US20130132308A1 (en) Enhanced DeepQA in a Medical Environment
US20190108316A1 (en) Personal assistant computing system monitoring

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