JPH0394332A - Diagnostic knowledge arranging method for expert system - Google Patents
Diagnostic knowledge arranging method for expert systemInfo
- Publication number
- JPH0394332A JPH0394332A JP1233691A JP23369189A JPH0394332A JP H0394332 A JPH0394332 A JP H0394332A JP 1233691 A JP1233691 A JP 1233691A JP 23369189 A JP23369189 A JP 23369189A JP H0394332 A JPH0394332 A JP H0394332A
- Authority
- JP
- Japan
- Prior art keywords
- knowledge
- matrix
- hypothesis
- event
- diagnostic
- 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 description 13
- 239000011159 matrix material Substances 0.000 claims abstract description 40
- 208000024891 symptom Diseases 0.000 claims description 2
- 201000010099 disease Diseases 0.000 abstract description 10
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 10
- 210000002345 respiratory system Anatomy 0.000 abstract description 2
- 210000002249 digestive system Anatomy 0.000 abstract 1
- 238000007689 inspection Methods 0.000 abstract 1
- 238000003745 diagnosis Methods 0.000 description 11
- 230000008520 organization Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003814 drug Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Devices For Executing Special Programs (AREA)
Abstract
Description
【発明の詳細な説明】
〔産業上の利用分野〕
本発明はエキスパートシステムの診断型知識整理方法に
関し、特に知識ベースを構築するための専門的知識の「
収集・整理」工程を提供するエキスパートシステムの診
断型知識整理方法に関する。[Detailed Description of the Invention] [Industrial Field of Application] The present invention relates to a diagnostic type knowledge organization method for an expert system, and in particular, to a method for organizing expert knowledge for building a knowledge base.
This paper relates to a diagnostic knowledge organization method using an expert system that provides a "collection and organization" process.
従来のエキスパートシステムの診断型知識整理方法には
、事象（Ｓｙｍｐｔｏｍ）と仮説（Ｈｙｐｏｔｈｅｓｉ
ｓ）との関係を表わすルール型知識をその確信度ととも
に単独の事象・仮説マトリックスに表現する手段として
の実願昭６３−７２５６２号明ａ書「知識獲得・検証支
援装置ｊがある。Conventional expert system diagnostic knowledge organization methods include phenomena and hypotheses.
There is a knowledge acquisition/verification support device j described in Utility Model Application No. 1983-72562 (a) as a means of expressing rule-type knowledge representing the relationship between the rules and the knowledge in a single event/hypothesis matrix along with its confidence level.
上述した従来のエキスパートシステムの診断型知識整理
方法では、全ルールを１つのマトリックス上に表わすた
めに、全知識が同一のレベルで画一的に羅列されること
となる。また、知識量の増大に伴って事象・仮説マトリ
ックスの巨大化が避けられない。In the conventional expert system diagnostic knowledge organizing method described above, all rules are represented on one matrix, so all knowledge is uniformly listed at the same level. Furthermore, as the amount of knowledge increases, the size of the event/hypothesis matrix becomes unavoidable.
したがって、従来のエ−キスパートシステムの診断型知
識整理方法は、事象・仮説マトリックスを利用するに当
っての知識の収集もれ・重複・矛盾の回避及び知識の一
覧が可能なことによる知識の検証の効率化という本来の
目的が、知識量の増大に伴って果たせなくなってしまう
という欠点を有している。Therefore, the diagnostic knowledge organization method of the conventional expert system avoids omissions, duplications, and contradictions in collecting knowledge when using the event/hypothesis matrix, and verifies knowledge by making it possible to list the knowledge. The drawback is that the original purpose of increasing the efficiency of knowledge becomes impossible as the amount of knowledge increases.
本発明のエキスパートシステムの診断型知識整理方法は
、複数の事象・仮説マトリックスを用いるとともに、親
マトリックスとなる前記事象・仮説マトリックスの仮説
部に子マトリックスとなる前記事象・仮説マトリックス
のマトリックス名を記述することにより、複数の前記事
象・仮説マトリックスの階層づけを行い、階層化された
複数の前記事象・仮説マトリックスに、発現する症状で
ある「事象」とその原因として考えられる「仮説」と間
の相関関係を示すとともに、概要から詳細に至る診断レ
ベルで分類した診断型知識をその診断のレベルとマトリ
ックスの階層とを対応させた分割を行って格納すること
により構成されている．
〔実施例〕
次に、本発明の実施例について図面を参照して説明する
。The diagnostic knowledge organization method of the expert system of the present invention uses a plurality of event/hypothesis matrices, and the matrix name of the event/hypothesis matrix that is a child matrix is written in the hypothesis part of the event/hypothesis matrix that is a parent matrix. By describing the above-mentioned event/hypothesis matrices, the plurality of event/hypothesis matrices are layered, and the "events" that are symptoms that occur and the "hypotheses" that are considered to be the causes are In addition to showing the correlation between `` and ``, it is constructed by dividing and storing diagnostic knowledge classified by diagnostic level ranging from summary to detailed, by making the diagnostic level correspond to the hierarchy of the matrix. [Example] Next, an example of the present invention will be described with reference to the drawings.
第１図は本発明のエキスパートシステムの診断型知識整
理方法における事象・仮説マトリックスの階層構造の一
例を示す階層構造説明図である。FIG. 1 is a hierarchical structure explanatory diagram showing an example of the hierarchical structure of an event/hypothesis matrix in the diagnostic knowledge organization method of the expert system of the present invention.
第１図に示すように、事象・仮説マトリックスである「
総合診断」マトリックス１は、仮説として外科診断１−
Ａ，内科診断１−Ｂを有しているが、これらは、１階層
下の事象・仮説マトリックス３である「外科診断」マト
リックス２，「内科診断」マトリックス３にそれぞれ対
応している。As shown in Figure 1, the event/hypothesis matrix “
Comprehensive diagnosis matrix 1 is based on the hypothesis that surgical diagnosis 1-
A, internal diagnosis 1-B, which respectively correspond to the "surgical diagnosis" matrix 2 and the "internal diagnosis" matrix 3, which are the event/hypothesis matrix 3 one level below.
同様に、「内科診断」マトリックス１−Ｂの下には、「
消化器系」マトリックス４，「呼吸器系」マトリックス
５，「循環器系」マトリックス６があり、「総合診断」
マトリックス１からこれらの事象・仮説マトリックスま
で３階層の階層構造となっている。Similarly, under “Internal Diagnosis” Matrix 1-B, “
There are ``digestive system'' matrix 4, ``respiratory system'' matrix 5, ``circulatory system'' matrix 6, and ``comprehensive diagnosis''.
It has a three-layer hierarchical structure from matrix 1 to these event/hypothesis matrices.
そして、各事象・仮説マトリックスに格納する各ルール
型知識は、そのレベルとカデゴリーとにより、分類・整
理されている。Each rule type knowledge stored in each event/hypothesis matrix is classified and organized according to its level and category.
すなわち、最上位の「総合診断」マトリックス１は、大
まかに外科疾患か内科疾患かの判断ができる程度のルー
ル型知識から戒っている。また、第２Ｐ１層の「外科診
断」マトリックス２および「内科診断」マトリックス３
は、それぞれ外科疾患に関するルール型知識および内科
疾患に関するルール型知識を格納している。さらに、第
３階層では、内科疾患の中でも、特に消火器系，呼吸器
系，循環器系のそれぞれに関するルール型知識をそれぞ
れの事象・仮説マトリックスごとに格納している。That is, the top-level "comprehensive diagnosis" matrix 1 prescribes rule-based knowledge to the extent that it is possible to roughly judge whether the disease is a surgical disease or a medical disease. In addition, "surgical diagnosis" matrix 2 and "internal medicine diagnosis" matrix 3 of the 2nd P1 layer
store rule-type knowledge regarding surgical diseases and rule-type knowledge regarding internal diseases, respectively. Further, in the third layer, rule-based knowledge regarding the fire extinguisher system, respiratory system, and circulatory system among internal medical diseases is stored for each event/hypothesis matrix.
このように、事象・仮説マトリックスの階層が下がるほ
ど、知識の診断レベルが深まり、より詳細レベルの診断
を行うための知識が格納されることになる。また、同レ
ベルの知識はその診断分野ごとに分類されている。In this way, the lower the hierarchy of the event/hypothesis matrix, the deeper the diagnostic level of knowledge becomes, and the more knowledge that is stored for performing diagnosis at a more detailed level. In addition, knowledge at the same level is categorized by its diagnostic field.
以上説明したように、本発明のエキスパートシステムの
診断型知識整理方法は、複数の事象・仮説マトリックス
に階層構造をもたせることにより、収集した診断型知識
のレベル別整理とモジュール化とを実現して、一つの事
象・仮説マトリックスの巨大化を防ぐとともに、知識自
身が持つ階層構造に即した形での知識整理が可能となり
、作業効率を向上させるという効果を有している。As explained above, the diagnostic knowledge organizing method of the expert system of the present invention realizes the level-by-level organization and modularization of collected diagnostic knowledge by providing a hierarchical structure to multiple event/hypothesis matrices. This has the effect of not only preventing a single event/hypothesis matrix from becoming too large, but also making it possible to organize knowledge in accordance with the hierarchical structure of the knowledge itself, improving work efficiency.
第１図は本発明のエキスパートシステムの診断型知識整
理方法における事象・仮説マトリックスの階層構造の一
例を示す階層構造説明図である。FIG. 1 is a hierarchical structure explanatory diagram showing an example of the hierarchical structure of an event/hypothesis matrix in the diagnostic knowledge organization method of the expert system of the present invention.
Claims (1)
トリックスとなる前記事象・仮説マトリックスの仮説部
に子マトリックスとなる前記事象・仮説マトリックスの
マトリックス名を記述することにより、複数の前記事象
・仮説マトリックスの階層づけを行い、階層化された複
数の前記事象・仮説マトリックスに、発現する症状であ
る「事象」とその原因として考えられる「仮説」と間の
相関関係を示すとともに、概要から詳細に至る診断レベ
ルで分類した診断型知識をその診断のレベルとマトリッ
クスの階層とを対応させた分割を行って格納することを
特徴とするエキスパートシステムの診断型知識の整理方
法。By using multiple event/hypothesis matrices and writing the matrix name of the event/hypothesis matrix that will be the child matrix in the hypothesis section of the event/hypothesis matrix that will be the parent matrix, you can create multiple event/hypothesis matrices. The matrix is stratified, and the multiple hierarchized event/hypothesis matrices show the correlation between the "event" that is a symptom that occurs and the "hypothesis" that is considered to be its cause, and also provides a summary to detailed information. A method for organizing diagnostic knowledge in an expert system, characterized in that diagnostic knowledge classified by diagnostic level leading to the above is divided and stored in a manner that corresponds the diagnostic level to the hierarchy of a matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP1233691A JPH0394332A (en) | 1989-09-07 | 1989-09-07 | Diagnostic knowledge arranging method for expert system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP1233691A JPH0394332A (en) | 1989-09-07 | 1989-09-07 | Diagnostic knowledge arranging method for expert system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPH0394332A true JPH0394332A (en) | 1991-04-19 |
Family
ID=16959033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP1233691A Pending JPH0394332A (en) | 1989-09-07 | 1989-09-07 | Diagnostic knowledge arranging method for expert system |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH0394332A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100606176B1 (en) * | 2003-10-01 | 2006-08-01 | 박경희 | Crank rocking propulsion vehicle |
| JP2009211344A (en) * | 2008-03-04 | 2009-09-17 | Hitachi Electronics Service Co Ltd | Method for specifying supposed problem by hierarchical causality matrix |
-
1989
- 1989-09-07 JP JP1233691A patent/JPH0394332A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100606176B1 (en) * | 2003-10-01 | 2006-08-01 | 박경희 | Crank rocking propulsion vehicle |
| JP2009211344A (en) * | 2008-03-04 | 2009-09-17 | Hitachi Electronics Service Co Ltd | Method for specifying supposed problem by hierarchical causality matrix |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Berg | Medical work and the computerbased patient record: A sociological perspective | |
| Cimino et al. | Designing an introspective, multipurpose, controlled medical vocabulary | |
| Warner et al. | HELP? A program for medical decision-making | |
| Adlassnig et al. | Temporal representation and reasoning in medicine: Research directions and challenges | |
| Grimnes et al. | A two layer case-based reasoning architecture for medical image understanding | |
| CN103235881B (en) | A kind of nuclear reactor fault monitoring system based on minimal cut set | |
| CN1755700A (en) | Methods, systems for hierarchical organization of data associated with medical events in databases | |
| Southwick | Explaining reasoning: an overview of explanation in knowledge-based systems | |
| CN107361743A (en) | Traditional Chinese medical science intelligent diagnosis system and method | |
| Bylander et al. | CSRL: A language for expert systems for diagnosis | |
| DE2426435C2 (en) | Computer system | |
| JPH0394332A (en) | Diagnostic knowledge arranging method for expert system | |
| Chuang et al. | Rethinking preparedness planning in disaster emergency care: lessons from a beyond-surge-capacity event | |
| Abiola et al. | Expert system for Lassa fever diagnosis using rule based approach | |
| Scheerer | Towards a history of cognitive science. | |
| Gierl et al. | ICONS: Cognitive basic functions in a case-based consultation system for intensive care | |
| Hosseinzadeh | A rule-based system for vital sign monitoring in intensive care | |
| Burge et al. | Integrating design rationale with a process model | |
| Zheng et al. | Discovering additional complex NCIt gene concepts with high error rate | |
| Asbeh et al. | Creating consistent diagnoses list for developmental disorders using UMLS | |
| JPH0245832A (en) | Operation expert system | |
| Barzdins et al. | Modeling and query language for hospitals | |
| Sharif et al. | 6 Identification of Asthma Severity in the Emergency Department Using Fuzzy Rule Based Model | |
| Ientile et al. | Emergency medical service information system: The ARES 118 experience | |
| Mosseveld et al. | HYPERCRITIC: A critiquing system for hypertension |