JPS62190571A - Character selection system - Google Patents

Character selection system

Info

Publication number
JPS62190571A
JPS62190571A JP61032573A JP3257386A JPS62190571A JP S62190571 A JPS62190571 A JP S62190571A JP 61032573 A JP61032573 A JP 61032573A JP 3257386 A JP3257386 A JP 3257386A JP S62190571 A JPS62190571 A JP S62190571A
Authority
JP
Japan
Prior art keywords
character
word
rejected
next candidate
word dictionary
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
Application number
JP61032573A
Other languages
Japanese (ja)
Inventor
Toshiaki Morita
森田 敏昭
Tadashi Hirose
斉志 広瀬
Yoshio Kono
河野 義生
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sharp Corp
Original Assignee
Sharp Corp
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 Sharp Corp filed Critical Sharp Corp
Priority to JP61032573A priority Critical patent/JPS62190571A/en
Publication of JPS62190571A publication Critical patent/JPS62190571A/en
Pending legal-status Critical Current

Links

Landscapes

  • Character Discrimination (AREA)

Abstract

PURPOSE:To simplify operations and to shorten the processing time by automatically selecting a rejected character according to a word dictionary in terms of recognizing sentence information. CONSTITUTION:Word data is inputted through an input part 11 to read characters or as accumulated data, and a recognition part 12 recognizes the characters. A word buffer 13 temporarily stores the result obtained by recognizing input character data and character data selected by a rejected word selection part 16. A next candidate buffer 14 temporarily stores a next candidate if it is present by rejecting the recognized result. The word dictionary 15 stores a character string composed of words in Japanese alphabetical order of a top character. If no rejected character is found through the recognized result, the characters are outputted as they are from an output part 17. If the rejected character is present, the selection part 16 selects the rejected character in combination with a piece of next candidate information in the word dictionary 15 and in the next candidate buffer 14 according to presence or absence of the next candidate. The word dictionary 15 selects the rejected character and outputs it from the output part 17.

Description

【発明の詳細な説明】 〈産業上の利用分野) 本発明は文字認識や音声認識等において入力文字がリジ
ェクト(不合格)のときのこのリジェクト文字を自動的
に選択する文字選択方式に関する。
DETAILED DESCRIPTION OF THE INVENTION (Field of Industrial Application) The present invention relates to a character selection method that automatically selects a rejected character when an input character is rejected in character recognition, voice recognition, or the like.

〈従来の技術) 文字認識や音声認識等において、例えば「はんじつ」と
いう4文字からなる単語を入力し、認識結果として第3
図に示すように最後の4文字目がリジェクトになった場
合、この4文字目の「っ」を従来では使用者がキーボー
ド等がら手操作で入力していた。このため、操作が煩雑
化し、処理に時間を要するという問題があった。
(Prior art) In character recognition, voice recognition, etc., a word consisting of four letters, such as "hanjitsu", is input, and the third word is recognized as the recognition result.
As shown in the figure, when the last fourth character is rejected, conventionally the user manually inputs the fourth character "tsu" using a keyboard or the like. Therefore, there is a problem that the operation becomes complicated and the processing takes time.

(発明の目的〉 本発明は上記事情に鑑みてなされたものであり、リジェ
クト文字を自動的に選択して入力するようにした文字選
択方式の提供を目的とする。
(Objective of the Invention) The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a character selection method that automatically selects and inputs reject characters.

〈実施例〉 第1図は本実、絶倒の文字選択方式の機能構成を示す。<Example> FIG. 1 shows the functional configuration of the true and unbelievable character selection method.

入力部11は、文章情報を入力するためのタブレットあ
るいは文字読取器等からなる。認識部12は、入力文字
データを文字単位で公知の方法により認識する。単語バ
ッファ13は、入力文字データの認識結果及びリジェク
ト単語選択部16で選択された文字データを一時的に蓄
える。次候補バッファ14は、認識結果のりジェツト等
で次候補が在る場合にこの次候補を一時的に蓄える。単
語辞書15は、例えば先頭文字の五十音順に単語の文字
列を記憶する。リジェクト単語選択部16は、入力され
た単語データの認識過程で1文字以上のりジェツトが発
生した場合に、当該リジェクト文字を単語辞書15と次
候補バッファ14の内容を参照して選択する。出力部1
7は、表示装置またはプリンター等からなり、単語バッ
ファ13が記憶した文字データを出力する。制御部18
は、例えばCPUからなり、以上の各要素を制御プログ
ラムにしたがって制御する。
The input unit 11 includes a tablet, a character reader, or the like for inputting text information. The recognition unit 12 recognizes input character data character by character using a known method. The word buffer 13 temporarily stores recognition results of input character data and character data selected by the reject word selection section 16. The next candidate buffer 14 temporarily stores the next candidate when there is a next candidate in the recognition result paste or the like. The word dictionary 15 stores word strings in alphabetical order of the first letter, for example. The reject word selection section 16 selects the reject character by referring to the contents of the word dictionary 15 and the next candidate buffer 14 when one or more characters are duplicated during the recognition process of the input word data. Output section 1
7 consists of a display device, a printer, etc., and outputs the character data stored in the word buffer 13. Control unit 18
consists of, for example, a CPU, and controls each of the above elements according to a control program.

第2図はこの文字選択方式の処理手順を示す。FIG. 2 shows the processing procedure of this character selection method.

文字読取あるいは蓄積データとして単語データが入力さ
れる(ステップ532)と、認識処理を行ない(ステッ
プ533)、リジェクト文字が無ければそのまま認識結
果を出力する(ステップ838)。リジェクトが有ると
、次候補の有無により単語辞書15と次候補情報の組み
合せによりリジェクト文字を選択する(ステップ836
)かあるいは単語辞書15によりリジェクト文字を選択
する(ステップ537)。そして、結果を出力する(ス
テップ538)。
When word data is input as character reading or stored data (step 532), recognition processing is performed (step 533), and if there are no reject characters, the recognition result is output as is (step 838). If there is a reject character, a reject character is selected based on the combination of the word dictionary 15 and the next candidate information depending on whether there is a next candidate (step 836
) or select a reject character using the word dictionary 15 (step 537). Then, the result is output (step 538).

例えば、前述の「はんじつ」という文字列が入力され認
識結果として最後の4文字目の「つ」がリジェクト文字
になった場合、このリジェクト文字「つ」を導き出す手
順は以下の様になる。
For example, if the aforementioned character string "hanjitsu" is input and the recognition result is that the fourth and final character "tsu" is a rejected character, the procedure for deriving this reject character "tsu" is as follows.

i)入力されたのは4文字の単語であるので、単語辞書
15の検索は4文字列の単語に限定される。
i) Since the input word is a four-letter word, the search in the word dictionary 15 is limited to four-letter words.

1i)1文字目〜3文字目までの「はんし」は認識され
ている。
1i) The first to third characters of "hanshi" are recognized.

iii )単語辞書15の第4図に示す内容を参照し、
°正解文字列「はんじつ」を選択して出力する。この場
合、「はんじこ」などの他の文字列がでてきた場合は、
候補文字列の距離の小さい順に選択する。また、候補が
全く無い場合も正解文字列が選択される。
iii) Referring to the contents shown in FIG. 4 of the word dictionary 15,
°Select and output the correct character string "hanjitsu". In this case, if other character strings such as "Hanjiko" appear,
Select candidate strings in ascending order of distance. Furthermore, even if there are no candidates at all, the correct character string is selected.

〈発明の効果〉 以上説明したように本発明においては、文章情報の認識
においてリジェクト文字を単語辞書にもとづいて自動的
に選択するようしたので、操作を簡単化できるとともに
、処理時間の短縮が達成できる。
<Effects of the Invention> As explained above, in the present invention, reject characters are automatically selected based on a word dictionary when recognizing text information, which simplifies operation and reduces processing time. can.

【図面の簡単な説明】[Brief explanation of drawings]

第1図は本発明実施例の機能構成を示すブロック図、第
2図は本発明実施例の処理手順を示すフローチャート、
第3図は入力文字列の認識結果の一例を示す図、第4図
は本発明実施例の単語辞書の内容を示す図である。 11・−・入力部 12−・認識部 13・−・単語バッファ 14・−・次候補バッファ 15・−・単語辞書
FIG. 1 is a block diagram showing the functional configuration of the embodiment of the present invention, and FIG. 2 is a flowchart showing the processing procedure of the embodiment of the present invention.
FIG. 3 is a diagram showing an example of the recognition result of an input character string, and FIG. 4 is a diagram showing the contents of a word dictionary according to an embodiment of the present invention. 11--Input unit 12--Recognition unit 13--Word buffer 14--Next candidate buffer 15--Word dictionary

Claims (1)

【特許請求の範囲】[Claims] 入力された文章情報を認識した結果生じたリジェクト文
字を単語辞書にもとづいて選択することを特徴とする文
字選択方式。
A character selection method characterized in that reject characters generated as a result of recognizing input text information are selected based on a word dictionary.
JP61032573A 1986-02-17 1986-02-17 Character selection system Pending JPS62190571A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP61032573A JPS62190571A (en) 1986-02-17 1986-02-17 Character selection system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP61032573A JPS62190571A (en) 1986-02-17 1986-02-17 Character selection system

Publications (1)

Publication Number Publication Date
JPS62190571A true JPS62190571A (en) 1987-08-20

Family

ID=12362636

Family Applications (1)

Application Number Title Priority Date Filing Date
JP61032573A Pending JPS62190571A (en) 1986-02-17 1986-02-17 Character selection system

Country Status (1)

Country Link
JP (1) JPS62190571A (en)

Similar Documents

Publication Publication Date Title
JPS62190571A (en) Character selection system
JP3548372B2 (en) Character recognition device
JPH0256086A (en) Method for postprocessing for character recognition
JPS58123126A (en) Dictionary retrieving device
JPS61177575A (en) Forming device of japanese document
JPH0540853A (en) Post-processing system for character recognizing result
JPS6293776A (en) Information recognizing device
JPS62117060A (en) Character/voice input conversion system
JPS62224859A (en) Japanese language processing system
JPH01297768A (en) Document processor
JPH0512257A (en) Document preparation device
JP3273778B2 (en) Kana-kanji conversion device and kana-kanji conversion method
JPS63103393A (en) Word recognizing device
JPS63138479A (en) Character recognizing device
JPS62208169A (en) Sentence analytical processing system
JPS58123125A (en) Documentation device
JPH0778155A (en) Document recognizing device
JPH01166187A (en) Method for recognizing character
JPH06308994A (en) Japanese language voice recognizing method
JPH05204896A (en) Kana/kanji conversion system
JPS60207983A (en) Production system of dictionary for recognizing character
JPH06289890A (en) Natural language processor
JPS62247451A (en) Constituting method for word dictionary for japanese word processor
JPS60205687A (en) Character reading device
JPH11212976A (en) Morpheme analyzing device