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...
Saved in:
Main Authors | , |
---|---|
Format | Patent |
Language | English Japanese |
Published |
22.12.2016
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |