CN106294608A - A kind of framework method of clinical medicine commonsense knowledge base - Google Patents

A kind of framework method of clinical medicine commonsense knowledge base Download PDF

Info

Publication number
CN106294608A
CN106294608A CN201610617905.2A CN201610617905A CN106294608A CN 106294608 A CN106294608 A CN 106294608A CN 201610617905 A CN201610617905 A CN 201610617905A CN 106294608 A CN106294608 A CN 106294608A
Authority
CN
China
Prior art keywords
data
knowledge
module
clinical medicine
framework method
Prior art date
Application number
CN201610617905.2A
Other languages
Chinese (zh)
Inventor
荆改丽
曹世霞
Original Assignee
郑州工业应用技术学院
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 郑州工业应用技术学院 filed Critical 郑州工业应用技术学院
Priority to CN201610617905.2A priority Critical patent/CN106294608A/en
Publication of CN106294608A publication Critical patent/CN106294608A/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21Design, administration or maintenance of databases

Abstract

The invention discloses the framework method of a kind of clinical medicine commonsense knowledge base, comprise the steps: to be completed by human-machine operation module and webcrawler module the input of data;Labelling and the typesetting of data is completed by knowledge point labelling type-setting module;The content of conflicting between redundant content and inputted data with the legacy data in data base existed between data is eliminated by knowledge point processing module;Completed the examination & verification of data after processing by human expert module;It is in data base, to find suitable position by the data after auditing by knowledge point locating module, and finds similarity number strong point for it, set up the relation between itself and similarity number strong point.The present invention carries out the importing of data by the way of user automatically enters and system inquires about clinical medicine knowledge general knowledge automatically, then the process function carried by system, complete process and the examination & verification of data, while realizing data base's real-time update, avoid the repetition of data, conflict, also achieve sharing of data simultaneously.

Description

A kind of framework method of clinical medicine commonsense knowledge base

Technical field

The present invention relates to clinical medicine domain, be specifically related to the framework method of a kind of clinical medicine commonsense knowledge base.

Background technology

The general knowledge of medical science was all the medium using analog form in the past, and such as paper, film etc. carry out conserving case distribution.With The foundation of datumization information system, medical science general knowledge has stepped into the electronic epoch, but the conserving case of these data controls The LAN form in units of hospital that is substantially exists, and does not has unified form and standard, between data and data often Repetition, conflict etc. can be there is, easily cause a certain degree of misleading to healthcare givers, be also easily caused due to Data duplication relatively Many, and the generation of the situation of the inquiry of required information cannot be rapidly performed by, also cannot realize sharing of knowledge general knowledge, office simultaneously Sex-limited greatly.

Summary of the invention

For solving the problems referred to above, the invention provides the framework method of a kind of clinical medicine commonsense knowledge base, pass through user Automatically enter and system is automatically inquired about the mode of clinical medicine knowledge general knowledge and carried out the importing of data, then carried by system Process function, complete process and the examination & verification of data, while realizing data base's real-time update, it is to avoid the repetition of data, Conflict;Also achieve sharing of data simultaneously.

For achieving the above object, the technical scheme that the present invention takes is:

The framework method of a kind of clinical medicine commonsense knowledge base, comprises the steps:

After S1, user carry out account login by human-machine operation module, complete the input of data to be stored;By timing mould Block controls the webcrawler module related data in online enquiries Yu clinical medicine general knowledge, and the related data that will inquire It is sent to knowledge point labelling type-setting module;

S2, knowledge point labelling type-setting module receive the data and and these data are right with it of man-machine operation module input Carry out typesetting according to default template after the accounts information labelling answered, be sent to data point processing module;And by climbing of receiving After the related data that erpoglyph block is inquired carries out typesetting according to default template, it is sent to knowledge point processing module;

S3, by knowledge point processing module eliminate received by data between exist redundant content and inputted number According to the content of conflicting between legacy data in data base;

S4, complete, to the examination & verification of data after processing, auditing result to be sent out with the form of letter in station by human expert module Deliver to the account of correspondence, and the data that examination & verification is passed through are sent to knowledge point locating module;

S5, by knowledge point locating module be by examination & verification after data in data base, find suitable position, and be It finds similarity number strong point, sets up the relation between itself and similarity number strong point.

Wherein, described human-machine operation module includes word input module, voice input module and picture input module.

Wherein, described voice input module uses mike, and word input module uses handwriting pad and keyboard, described picture Input module uses scanner and photographic head.

Wherein, in described human-machine operation module, it is additionally provided with modular converter, for removing the speckle noise in image, extracts figure Eigenvalue in sheet, and eigenvalue is converted into text data;It is additionally operable to convert voice data to text data.

Wherein, described knowledge point locating module realizes Knowledge positioning based on facet technology, by calculating different knowledge art Facet distance between language is accurately positioned knowledge;When knowledge of orientation point, under the constraint of known facet, select corresponding term, Complete the description to required knowledge with this, if chosen successfully, then return corresponding knowledge;If selecting unsuccessful, it is then Unite according to synonymicon and the similarity of concept distance map calculating term, form new location information.

Wherein, described step S5 is associated by calculating the similarity degree between two knowledge points.

Wherein, described clash handle module uses EKA algorithm and AKF algorithm.

Wherein, in described step S3, redundant content is logical uses redundancy function to be purged, concrete, In redundancy function, respectively by k1And k2In knowledge element take out e1And e2, so by e1And e2In X, Y and relation R Taking-up compares and contrasts xe respectively1, xe2, ye1, ye2, the element entry with identical content is deleted, and retains original pass It is r value, relation is merged with not being deleted item.

The method have the advantages that

The importing of data is carried out by the way of user automatically enters and system inquires about clinical medicine knowledge general knowledge automatically, Then the process function carried by system, is completed process and the examination & verification of data, while realizing data base's real-time update, keeps away The repetition of data, conflict are exempted from;The input of data can be voice, can also be picture, text, and system carries translation function, Greatly facilitate the use of user;Also achieve sharing of data simultaneously.

Accompanying drawing explanation

Fig. 1 is the flow chart of the framework method of the embodiment of the present invention a kind of clinical medicine commonsense knowledge base.

Detailed description of the invention

In order to make objects and advantages of the present invention clearer, below in conjunction with embodiment, the present invention is carried out further Describe in detail.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not used to limit this Bright.

As it is shown in figure 1, embodiments provide the framework method of a kind of clinical medicine commonsense knowledge base, including as follows Step:

After S1, user carry out account login by human-machine operation module, complete the input of data to be stored;By timing mould Block controls the webcrawler module related data in online enquiries Yu clinical medicine general knowledge, and the related data that will inquire It is sent to knowledge point labelling type-setting module;

S2, knowledge point labelling type-setting module receive the data and and these data are right with it of man-machine operation module input Carry out typesetting according to default template after the accounts information labelling answered, be sent to data point processing module;And by climbing of receiving After the related data that erpoglyph block is inquired carries out typesetting according to default template, it is sent to knowledge point processing module;

S3, by knowledge point processing module eliminate received by data between exist redundant content and inputted number According to the content of conflicting between legacy data in data base;

S4, complete, to the examination & verification of data after processing, auditing result to be sent out with the form of letter in station by human expert module Deliver to the account of correspondence, and the data that examination & verification is passed through are sent to knowledge point locating module;

S5, by knowledge point locating module be by examination & verification after data in data base, find suitable position, and be It finds similarity number strong point, sets up the relation between itself and similarity number strong point.

Described human-machine operation module includes word input module, voice input module and picture input module.

Described voice input module uses mike, and word input module uses handwriting pad and keyboard, and described picture inputs Module uses scanner and photographic head.

It is additionally provided with modular converter in described human-machine operation module, for removing the speckle noise in image, extracts in picture Eigenvalue, and eigenvalue is converted into text data;It is additionally operable to convert voice data to text data.

Described knowledge point locating module realizes Knowledge positioning based on facet technology, by calculating between different knowledge term Facet distance is accurately positioned knowledge;When knowledge of orientation point, under the constraint of known facet, select corresponding term, come with this Complete the description to required knowledge, if chosen successfully, then return corresponding knowledge;If selecting unsuccessful, then system is by root Calculate the similarity of term according to synonymicon and concept distance map, form new location information.

Described step S5 is associated by calculating the similarity degree between two knowledge points.

Described clash handle module uses EKA algorithm and AKF algorithm.

In described step S3, redundant content is logical uses redundancy function to be purged, concrete, at redundancy In function, respectively by k1And k2In knowledge element take out e1And e2, so by e1And e2In X, Y and relation R take out compare Relatively and respectively contrast xe1, xe2, ye1, ye2, the element entry with identical content is deleted, and retains original relation r value, will close It is and is not deleted item and merges.

The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art For Yuan, under the premise without departing from the principles of the invention, it is also possible to make some improvements and modifications, these improvements and modifications also should It is considered as protection scope of the present invention.

Claims (8)

1. the framework method of a clinical medicine commonsense knowledge base, it is characterised in that comprise the steps:
After S1, user carry out account login by human-machine operation module, complete the input of data to be stored;By time block control Webcrawler module processed is at the related data of online enquiries Yu clinical medicine general knowledge, and is sent by the related data inquired To knowledge point labelling type-setting module;
S2, knowledge point labelling type-setting module receive the data of man-machine operation module input and and by its correspondence of these data Carry out typesetting according to default template after accounts information labelling, be sent to data point processing module;And the reptile mould that will receive After the related data that block is inquired carries out typesetting according to default template, it is sent to knowledge point processing module;
S3, by knowledge point processing module eliminate received by data between exist redundant content and inputted data and Conflict content between legacy data in data base;
S4, complete, to the examination & verification of data after processing, auditing result to be sent to the form of letter in station by human expert module Corresponding account, and the data that examination & verification is passed through are sent to knowledge point locating module;
S5, by knowledge point locating module be by examination & verification after data in data base, find suitable position, and look for for it To similarity number strong point, set up the relation between itself and similarity number strong point.
The framework method of a kind of clinical medicine commonsense knowledge base the most as claimed in claim 1, it is characterised in that described man-machine behaviour Word input module, voice input module and picture input module is included as module.
The framework method of a kind of clinical medicine commonsense knowledge base the most as claimed in claim 2, it is characterised in that described voice is defeated Entering module and use mike, word input module uses handwriting pad and keyboard, and described picture input module uses scanner and takes the photograph As head.
The framework method of a kind of clinical medicine commonsense knowledge base the most as claimed in claim 1, it is characterised in that described man-machine behaviour It is additionally provided with modular converter in making module, for removing the speckle noise in image, extracts the eigenvalue in picture, and by eigenvalue It is converted into text data;It is additionally operable to convert voice data to text data.
The framework method of a kind of clinical medicine commonsense knowledge base the most as claimed in claim 1, it is characterised in that described knowledge point Locating module realizes Knowledge positioning based on facet technology, is accurately positioned by calculating the facet distance between different knowledge term Knowledge;When knowledge of orientation point, under the constraint of known facet, select corresponding term, complete required knowledge is retouched with this State, if chosen successfully, then return corresponding knowledge;If selecting unsuccessful, then system will be according to synonymicon and concept Distance map calculates the similarity of term, forms new location information.
The framework method of a kind of clinical medicine commonsense knowledge base the most as claimed in claim 1, it is characterised in that described step S5 It is associated by calculating the similarity degree between two knowledge points.
The framework method of a kind of clinical medicine commonsense knowledge base the most as claimed in claim 1, it is characterised in that at described conflict Reason module uses EKA algorithm and AKF algorithm.
The framework method of a kind of clinical medicine commonsense knowledge base the most as claimed in claim 1, it is characterised in that described step S3 Middle redundant content is logical uses redundancy function to be purged, concrete, in redundancy function, respectively by k1And k2 In knowledge element take out e1And e2, so by e1And e2In X, Y and relation R take out compare and contrast xe respectively1, xe2, ye1, ye2, the element entry with identical content is deleted, and retains original relation r value, relation is merged with not being deleted item.
CN201610617905.2A 2016-08-02 2016-08-02 A kind of framework method of clinical medicine commonsense knowledge base CN106294608A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610617905.2A CN106294608A (en) 2016-08-02 2016-08-02 A kind of framework method of clinical medicine commonsense knowledge base

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610617905.2A CN106294608A (en) 2016-08-02 2016-08-02 A kind of framework method of clinical medicine commonsense knowledge base

Publications (1)

Publication Number Publication Date
CN106294608A true CN106294608A (en) 2017-01-04

Family

ID=57663679

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610617905.2A CN106294608A (en) 2016-08-02 2016-08-02 A kind of framework method of clinical medicine commonsense knowledge base

Country Status (1)

Country Link
CN (1) CN106294608A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106980960A (en) * 2017-02-13 2017-07-25 广东小天才科技有限公司 The preparation method and device of a kind of knowledge point system
CN107230102A (en) * 2017-05-13 2017-10-03 吉林工程技术师范学院 A kind of electronic publication publishing system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101470714A (en) * 2007-12-27 2009-07-01 上海岱嘉医学信息系统有限公司 Architecture method for medicine general knowledge base
US20130066870A1 (en) * 2011-09-12 2013-03-14 Siemens Corporation System for Generating a Medical Knowledge Base
US8655679B2 (en) * 2010-08-06 2014-02-18 Sunjay Berdia System and methods for an intelligent medical practice system employing a learning knowledge base
CN105095969A (en) * 2015-09-25 2015-11-25 沈阳农业大学 Self-learning model facing knowledge sharing
CN105447106A (en) * 2015-11-10 2016-03-30 河南师范大学 Mathematical operation system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101470714A (en) * 2007-12-27 2009-07-01 上海岱嘉医学信息系统有限公司 Architecture method for medicine general knowledge base
US8655679B2 (en) * 2010-08-06 2014-02-18 Sunjay Berdia System and methods for an intelligent medical practice system employing a learning knowledge base
US20130066870A1 (en) * 2011-09-12 2013-03-14 Siemens Corporation System for Generating a Medical Knowledge Base
CN105095969A (en) * 2015-09-25 2015-11-25 沈阳农业大学 Self-learning model facing knowledge sharing
CN105447106A (en) * 2015-11-10 2016-03-30 河南师范大学 Mathematical operation system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106980960A (en) * 2017-02-13 2017-07-25 广东小天才科技有限公司 The preparation method and device of a kind of knowledge point system
CN107230102A (en) * 2017-05-13 2017-10-03 吉林工程技术师范学院 A kind of electronic publication publishing system

Similar Documents

Publication Publication Date Title
Zhang et al. Variational neural machine translation
DE112017004397T5 (en) System and method for classifying hybrid speech recognition results with neural networks
AU2016277675B2 (en) Video-voice preparation of electronic tax return
US9002066B2 (en) Methods, systems and processor-readable media for designing a license plate overlay decal having infrared annotation marks
US20180204562A1 (en) Method and device for image recognition
US8626512B2 (en) Cooperative processing for portable reading machine
TWI541676B (en) Method, machine-readable medium and system for picture gesture authentication
CN105096935B (en) A kind of pronunciation inputting method, device and system
Ryckman The reign of relativity: philosophy in physics 1915-1925
US9400806B2 (en) Image triggered transactions
US8284999B2 (en) Text stitching from multiple images
Bigham et al. VizWiz:: LocateIt-enabling blind people to locate objects in their environment
US8711188B2 (en) Portable reading device with mode processing
US7607078B2 (en) Paper and electronic recognizable forms
US7627142B2 (en) Gesture processing with low resolution images with high resolution processing for optical character recognition for a reading machine
JP6429945B2 (en) Method and apparatus for processing audio data
US10402501B2 (en) Multi-lingual virtual personal assistant
CN106796788A (en) Automatic speech recognition is improved based on user feedback
KR101870093B1 (en) Method and device for processing voiceprint authentication
US7844896B2 (en) Layout-rule generation system, layout system, layout-rule generation program, layout program, storage medium, method of generating layout rule, and method of layout
CN107735833A (en) Automatic accent detection
EP3123359A1 (en) Computer generated natural language outputs in question answer systems
US9236043B2 (en) Document mode processing for portable reading machine enabling document navigation
US7505056B2 (en) Mode processing in portable reading machine
US20150043822A1 (en) Machine And Method To Assist User In Selecting Clothing

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170104