Phonetic data-to-kanji character converter with a syntax analyzer to alter priority order of displayed kanji homonyms

• US 4,777,600 A
• Filed: 07/28/1986
• Issued: 10/11/1988
• Est. Priority Date: 08/01/1985
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Nakasato, Shigemi, Kawada, Tsutomu, Kusumoto, Tatsuji, Saito, Hiroyoshi, Takeda, Kimihito
• Primary Examiner(s): Smith, Jerry
• Assistant Examiner(s): Jablon, Clark A.
• Application Number:
  US06/889,761
• Time in Patent Office: 806 Days
• Field of Search: 364/200 MS File, 364/900 MS File, 364/419, 434/157, 400/110
• US Class Current: 715/234
• CPC Class Codes: G06F 3/018 Input/output arrangements for oriental characters
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/53 Processing of non-Latin text kana-to-kanji conversion G06F40/129; vowelisation G06F40/232

Abstract

An input processing system inputs character string data including kanji characters and corresponding to phonetic data by entering phonetic data. An input device sequentially inputs phonetic data and sentence end data. A conversion section includes a conversion processor, a syntactic analyzer, and a priority order alterator. The conversion processor sequentially converts character string data in a predetermined conversion unit. If single phonetic data includes a plurality of conversion possibilities in the predetermined conversion unit, character string data is selected according to a predetermined priority order, thereby obtaining character string data (including kanji characters) corresponding to input phonetic data. The syntactic analyzer performs syntactic analysis of a sentence consisting of the character string data in response to sentence end data. The priority alterator alters the priority orders of the conversion possibilities corresponding to identical phonetic data for the conversion processor according to syntactic analysis results, and alters the already selected possibilities as needed. The character string data from the conversion processor in the conversion section is displayed on a diplay.

Claims

1. A phonetic data-to-kanji characters converter for converting character string data including Kanji characters, comprising:

input means for inputting phonetic data and sentence end data representing an end of a sentence;

conversion processing means for sequentially converting the phonetic data input by said input means into character string data in a predetermined train of the phonetic data, selecting character string data having the highest priority according to a predetermined priority order in the predetermined train of the phonetic data if a plurality of conversion possibilities are present, and obtaining the character string data which corresponds to the phonetic data;

storing means for storing, in accordance with said priority order, all of the character string data obtained by said conversion processing means;

syntactic analyzing means for analyzing syntactic relations in the character string data from said conversion processing means in response to the sentence end data from said input means;

priority order altering means for altering, based on the analyzed syntactic relations, the priority order of the plurality of conversion possibilities corresponding to homonymic data during the processing of said conversion processing means, and altering selection of the character string data according to an altered priority order; and

output means for sequentially displaying the character string input from said conversion processing means.

2. A system according to claim 1, wherein said syntactic analyzing means includes means for selecting a conversion possibility whose semantic relation with other words in the character string data is not defined, among conversion possibilities as homonyms obtained in character string data from said conversion processing means, and said priority altering means includes means for lowering a priority order of the conversion possibility whose semantic relation with other words in the character string data is not defined and which is selected by said syntactic analyzing means.

3. A system according to claim 1, wherein said conversion processing means comprises means for converting the phonetic data into the character string in units of words or clauses.

4. A system according to claim 1, wherein said input means comprises means for inputting a full stop or a parenthesis as sentence end data.

5. A system according to claim 1, wherein said input means comprises means for inputting a phonetic alphabetic character string as phonetic data.

6. A system according to claim 1, wherein said input means comprises means for inputting a phonetic kana character string as the phonetic data.

7. A system according to claim 1, wherein said input means comprises a keyboard for inputting character data.

8. A system according to claim 1, wherein said conversion processing means comprises means for selecting a last selected conversion possibility as a conversion possibility having the highest priority for the phonetic data having a plurality of conversion possibilities.

9. A system according to claim 1, wherein said conversion processing means includes means for selecting a conversion possibility having the highest previous selection frequency as a conversion possibility having the highest priority for the phonetic data having a plurality of conversion possibilities.

10. A system according to claim 1, wherein said conversion processing means includes a dictionary means comprising a data base for obtaining the character string data corresponding to the phonetic data.

11. A system according to claim 1, wherein said conversion processing means includes dictionary means consisting of a data base for obtaining the character string data corresponding to the phonetic data and syntactic data for performing syntactic analysis, and said syntactic analyzing means includes means for performing the syntactic analysis on the basis of the syntactic data from said dictionary means.

12. A system according to claim 1, wherein said conversion processing means comprises means for converting Japanese phonetic data into character string data including kanji characters.

13. A system according to claim 1, wherein said conversion processing means comprises means for converting Chinese phonetic data into character string data including kanji characters.

14. A system according to claim 1, wherein said input means includes means for inputting conversion possibility alteration data for designating selection and alteration of the conversion possibilities, and said conversion processing means includes means for altering the conversion possibility to another conversion possibility having a second highest priority in response to the conversion possibility alteration data.