JPS6373462A - Input device for japanese word - Google Patents

Abstract

PURPOSE:To output Japanese words according to selection of an operator not to the interpreted words after the first selection, by learning information on the presence/absence of additional words of the final paragraph of an interpreted character string. CONSTITUTION:A deciding part 13 decides whether the final paragraph of a KANJI (Chinese character) - KANA (Japanese syllabary) character string includes an additional word or not. This information is informed to a learning part 14. Hereafter, the part 14 is retrieved when a KANJI-KANA character string is outputted through a converting part 12. Thus a mastered form is turned into an original form. For instance, 'JINJIKA' (KANJI-KANA) is outputted from the part 12 to an input character string 'JINJIKA' (KANA). In such a case, the part 13 informs the presence of an additional word to the part 14. Then an operator has a correction to 'JINJIKA' (KANJI) and therefore the part 13 informs the absence of additional words to the part 14. Then a character string 'NAKANO' (KANA) is inputted and the part 12 refers to the part 14 to select 'NAKANO' (KANJI) out of two interpreted words 'NAKANO' (KANJI) and 'NAKANO' (KANJI-KANA) and outputs it.

Description

DETAILED DESCRIPTION OF THE INVENTION Field of Industrial Application The present invention relates to a Japanese input device equipped with a so-called kana-kanji conversion function that converts an input kana character string into a character string containing kanji.

BACKGROUND OF THE INVENTION Conventionally, various methods have been considered for the kana-kanji conversion function installed in this type of Japanese input device. and,
When the same input string has two interpretations, one where the interpretation ends with an independent word and the other where the interpretation ends with an attached word, each machine decides which interpretation to give priority to. Ta. Furthermore, if the operator selects an interpretation different from the one prioritized by the machine, learning is performed only on the selected word, and even this method is not effective when using the same word a second time. Ta.

Problems to be Solved by the Invention However, in the above-mentioned learning method using the conventional Japanese language input device, only the words used by the operator are effective. For example, when creating a directory or the like, it is common to give priority to interpretations in which the final clause of a compound word ends with an independent word. Therefore, the operator had to make corrections for each newly input word.

Therefore, the present invention is intended to solve the above-mentioned conventional problems, and it not only learns the words used, but also
The present invention aims to provide a Japanese input device that can also learn the form of used sentences.

Means for solving the problems and technical means of the present invention for solving the above problems include means for inputting kana, means for converting the input kana character string into a character string containing kanji, It is equipped with a means for determining the presence or absence of an adjunct in the final clause of the converted character string, and a means for learning information on the presence or absence of the adjunct. It is configured to convert a kana character string into a character string containing kanji by referring to the presence/absence information.

For production The effects of the above technical means are as follows.

In other words, by learning the presence/absence information of adjuncts in the final clause of the interpreted character string, once one of the two interpretations is selected, the operator's decision from the second time onwards is independent of the interpreted word. It is possible to output according to the selection.

EXAMPLES Hereinafter, examples of the present invention will be described with reference to the drawings.

The figure is a block diagram showing one embodiment of the present invention.

In the figure, 11 is an input section for inputting a kana character string;
13 is a conversion unit that converts an input kana character string into a kanji-mixed character string; 13 is a judgment unit that determines whether or not the final clause includes an adjunct; and 14 is a learning unit that learns information on the presence or absence of an adjunct. It is.

Next, the operation of the above embodiment will be explained. A conversion unit 12 converts a kana character string inputted from an input unit 11 into a character string mixed with kanji. At this time, the judgment unit 13 uses the information about the presence or absence of an adjunct in the final clause of the character string containing kanji to the learning unit 14.
Notify. From then on, when the converting unit 12 outputs a character string containing kanji, it searches the learning unit 14 and converts it based on the learned form. For example, when the input character string "jinjika" On the other hand, when the conversion unit 12 outputs “Human Resources”, the judgment unit 13 notifies the learning unit 14 of the information with attached words.
When corrected, the judgment unit 13 notifies the learning unit 14 (-) of the information without adjuncts.Next, when the character string “Nakano” is sent from the input unit 11 to the conversion unit 12, the conversion unit 12 Now, with reference to the learning unit 14, "Nakano" is selected and outputted from among the two interpretations of "Nakano" and "Nakano".

Effects of the Invention As is clear from the above, according to the present invention, there is provided a means for determining the presence or absence of an adjunct of the final clause in a character string converted to a character string containing kanji, and a means for learning information on the presence or absence. In addition to learning the words used, the students also try to learn the form of the sentences used. Therefore, it is possible to output a character string that matches the format of the input text.

[Brief explanation of the drawing]

The figure is a block diagram of a Japanese language input device according to an embodiment of the present invention. 11... Input unit, 12... Conversion unit, 13... Judgment unit, 14... Learning unit.

Claims (1)

[Claims] A means for inputting kana, a means for converting the input kana character string into a character string containing kanji, a means for determining the presence or absence of an adjunct in the final clause of the converted character string, and information on the presence or absence of the adjunct. , and is configured to convert a kana character string into a character string containing kanji by referring to the learning information of the character string used and the presence or absence information of the adjunct word learned above. Japanese input device.