MEASURE EXAMPLE INFORMATION REGISTRATION AND RETRIEVAL DEVICE, AND KEYWORD DETERMINATION METHOD

PROBLEM TO BE SOLVED: To make it possible to determine a key word in accordance with content of each example information file automatically.SOLUTION: A plurality of keyword candidates are stored in advance for each of the plurality of items in a keyword candidate storage unit 11. A text mining unit...

Full description

Saved in:
Bibliographic Details
Main Authors SHIRAI HIDETO, MANABE AKIRA
Format Patent
LanguageEnglish
Japanese
Published 22.12.2016
Subjects
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:PROBLEM TO BE SOLVED: To make it possible to determine a key word in accordance with content of each example information file automatically.SOLUTION: A plurality of keyword candidates are stored in advance for each of the plurality of items in a keyword candidate storage unit 11. A text mining unit 13 partitions a sentence in a measure example file into words and phrases through text mining processing. An appearance frequency discrimination unit 14 obtains the appearance frequency of each keyword candidate related to the item in a sentence in a measure example file for each item. A keyword determination unit 15 determines a keyword candidate having high appearance frequency among each keyword candidate related to the item for each item as a key word.SELECTED DRAWING: Figure 1 【課題】各事例情報ファイルの内容に応じたキーワードを、自動的に決定できる。【解決手段】キーワード候補記憶部１１には、予め、複数の項目毎にそれぞれ、複数のキーワード候補が記憶されている。テキストマイニング部１３が、テキストマイニング処理によって、対策事例ファイル中の文章を、単語／文節に区切る。出現回数判別部１４が、各項目毎に、その項目に係わる各キーワード候補の対策事例ファイル中の文章中における出現回数を求める。キーワード決定部１５が、各項目毎に、その項目に係わる各キーワード候補の中で出現回数が多いキーワード候補を、キーワードに決定する。【選択図】図１
Bibliography:Application Number: JP20150103239