JP2001216295A - Kana/kanji conversion method and device and recording medium having kana/kanji conversion program recorded thereon - Google Patents

Abstract

PROBLEM TO BE SOLVED: To highly efficiently convent a word from the Kana (Japanese syllabary) notation to the Kanji (Chinese character) notation. SOLUTION: Based on a ward extraction condition set in an extraction condition setting part 3, the Kanji notations of the plurals words pertinent to the Kana notation of the word inputted in an input part 1 and the intimacy of the word are extracted from a ward dictionary storage part 2 storing the pair of the Kana notation and Kanji notation of the word and the intimacy of the word in a word extraction part 4. The extracted Kanji notations of the words are rearranged in the descending order of the intimacy in a word rearrangement part 6 based on a rearrangement condition set in a rearrangement condition setting part 5 and the rearranged Kanji notations of the words are outputted in an output part 7.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a kana-kanji conversion method, a kana-kanji conversion apparatus, and a storage medium storing a kana-kanji conversion program for converting a kana character input into a kanji in a Japanese input of a computer or a word processor.

[0002]

2. Description of the Related Art Conventionally, in order to convert kana character notation into kanji notation, matching is performed with a dictionary using kana character notation as a search condition, and kanji notation of a word corresponding to the search condition is extracted. Was. If there are multiple words that match the search condition, display the kanji notation of those words one by one in order and select an appropriate kanji notation from among them. A method of displaying a list and selecting an appropriate kanji notation from the list was employed.

[0003]

In the prior art described above, when there are a plurality of words corresponding to a kana character notation, the order of displaying the kanji notation of those words is arbitrarily determined. Therefore, 1) In the method of displaying the kanji notation of a word one by one in order, the kanji notation of a target word may not be easily displayed. The display method has a property that the kanji notation of a target word may be displayed at the end of the list. Due to these properties, the conventional method has a disadvantage that it takes time to select a kanji notation of a target word, which is inefficient. For example, if the kanji notation of the target word is "feeling" with respect to the kana character notation "kanji", in the method 1), the kanji notation is "substitution", "inspector", "secretary", " Kanji ”,“ Kanji ”, and“ Feeling ”may be displayed in this order. In the method 2), the list of Kanji notation may be displayed as“ Substitution Auditor Secretary Kanji Kanji Kanji Feel ” Both are "feeling"
Is time consuming and inefficient. The cause of this drawback was that the order in which the kanji notation of words was displayed did not follow reasonable standards.

[0004] It is an object of the present invention to provide a method and apparatus for efficiently converting kana-kanji characters and a recording medium on which a kana-kanji conversion program is recorded.

[0005]

According to the kana-kanji conversion method of the present invention, the degree of familiarity with the kanji notation corresponding to each kana character notation, that is, the degree of familiarity, is stored in a word dictionary,
The input kanji notation of kanji and its familiarity are extracted from the word dictionary, and the extracted kanji notations are rearranged in descending order of familiarity and output.

The present invention is characterized by using the degree of familiarity of a word, that is, the degree of familiarity, as a rational criterion for displaying the kanji notation of the word. Here, “intimacy” is the average value of the scores given by many people on a 7-point scale ranging from 1 (unfamiliar) to 7 (familiar) with respect to how familiar a word is. It is. For example,
The familiarity of the familiar word “feel” is 6.188
The familiarity of the unfamiliar word "inspector" is low at 2.656. In general, the more familiar a word is, the more likely it is to be the target word in kana-kanji conversion.Therefore, displaying the kanji notation in descending order of the intimacy level allows the kanji notation of the target word to be displayed in a shorter time. You can choose.

A kana-kanji conversion device according to the present invention comprises an input means for receiving a kana character input, a kanji notation corresponding to each kana character notation, and a word dictionary storing familiarity of each kanji notation, that is, intimacy. A word extracting means for extracting the kanji notation word corresponding to the kana character notation received by the input means and the familiarity of each kanji notation word from the word dictionary; and a kanji notation word extracted by the word extracting means as a parent word. Word sorting means for sorting words in descending order of density and output means for outputting sorted words in kanji notation.

[0008]

Next, embodiments of the present invention will be described with reference to the drawings.

Referring to FIG. 1, a kana-kanji conversion apparatus according to an embodiment of the present invention comprises an input unit 1, a dictionary storage unit 2, an extraction condition setting unit 3, a word extraction unit 4, a sorting condition setting unit 5, and a word sorting unit 6. And an output unit 7.

The input unit 1 accepts kana character input. The dictionary storage unit 2 stores the kana character notation and kanji notation of each word, and the degree of familiarity of each kanji notation, that is, the familiarity. In the extraction condition setting unit 3, a range of the intimacy level of words to be extracted from the dictionary storage unit 2 and the number of words to be extracted are set. The word extraction unit 4 is a kanji notation of a plurality of words corresponding to the kana notation of the word input by the input unit 1 within the range of the familiarity set by the extraction condition setting unit 3 and the number of kanji of the word. Extract the notation and its familiarity. The rearrangement condition setting unit 5 sets that the kanji notation is rearranged from a word having a high degree of familiarity to a word having a low degree of familiarity. Word rearranger 6
Sorts the kanji notations extracted by the word extraction unit 4 according to the sorting condition set by the sorting condition setting unit 5, that is, in descending order of intimacy. The output unit 7 outputs (displays) the rearranged word notations on a display.

In general, a word with a higher degree of intimacy is more likely to be a target word in Kana-Kanji conversion, that is, a word to be converted. Thus, the kanji notation of the target word can be selected in a shorter time, and the kana-kanji conversion with high efficiency which is the object of the present invention can be realized.

Further, since the extraction condition setting unit 3 sets conditions for limiting the range of intimacy of words to be extracted and conditions for limiting the number of words to be extracted, it is possible to avoid extraction of unnecessary words. Thus, the number of kanji notations of words extracted by the word extracting unit 4 can be reduced. As a result, the number of kanji notations of words that are finally output in the output unit 7 can be reduced, so that more efficient kana-kanji conversion can be performed.

In the rearrangement condition setting unit 5, it is possible to combine a condition for rearranging the kanji notation in descending order of the familiarity word with another rearrangement condition. For example, if a condition that the kanji notation is arranged in the younger order as the number of Kana-Kanji conversions of each word so far is larger is added as a rearrangement condition, the words that frequently perform the Kana-Kanji conversion are rearranged in the word rearranger 6. It is more likely to appear at the beginning of a kanji list. This enables efficient Kana-Kanji conversion in a short time.

Here, a specific example of this embodiment will be described.

The dictionary storage unit 2 stores the familiarity of 79,834 words and the kana and kanji representations of the words. In the extraction condition setting unit 3, an extraction condition for setting the intimacy of words in the entire range and setting the number of words to infinity is set. In the rearrangement condition setting unit 5, a condition for rearranging the kanji notation in order from words having higher intimacy to words having lower intimacy is set.
Under the above-mentioned conditions, the human kana-kanji conversion device was used by 20 subjects, and the work of converting kana-kanji into kanji-notation was performed on 1000 randomly selected words. The average was 30 minutes.

On the other hand, when the subject according to the prior art was used by 20 subjects, and the operation of converting kana notation into kanji notation was performed for 1000 randomly selected words, the time required to complete the operation was obtained. Averaged 45 minutes. Therefore, according to the present embodiment, the working time can be reduced by about 33% as compared with the conventional technique.

Referring to FIG. 2, a kana-kanji conversion device according to another embodiment of the present invention includes an input device 11 and storage devices 12, 1.
3, display device 14, recording medium 15, and data processing device 16
It is composed of

The input device 11 inputs, for example, a kana character notation of a word using a keyboard, and sets extraction conditions and rearrangement conditions. The storage device 12 is the dictionary storage unit 2 of FIG.
And a word dictionary is stored. The storage device 13 is a hard disk. The output device 14 is a display (CRT, LCD, or the like) that displays the rearranged Chinese characters. The recording medium 15 receives the input kana character notation, the set extraction condition, and the rearrangement condition.
It is a recording medium such as a floppy disk, a CD-ROM, a magneto-optical disk, etc., on which a kana-kanji conversion program comprising the processing of the word extraction unit 4, word rearrangement unit 6, and output unit 7 is recorded. The data processing device 16 includes a CPU, reads a kana-kanji conversion program from the recording medium 15, and executes the program.

[0019]

As described above, according to the present invention,
The conversion from the kana character notation to the kanji notation of a word can be performed efficiently.

[Brief description of the drawings]

FIG. 1 is a configuration diagram of a kana-kanji conversion device according to an embodiment of the present invention.

FIG. 2 is a configuration diagram of a kana-kanji conversion device according to another embodiment of the present invention.

[Explanation of symbols]

 Reference Signs List 1 input unit 2 dictionary storage unit 3 extraction condition setting unit 4 word extraction unit 5 sorting condition setting unit 6 word sorting unit 7 output unit 11 input device 12, 13 storage device 14 output device 15 recording medium 16 data processing device

Claims (10)

[Claims] 1. A kana-kanji conversion method for extracting a kanji-notation word corresponding to a search condition from a word dictionary storing kanji-notation words corresponding to each kana-letter notation as a search condition. The degree of familiarity of the kanji notation corresponding to the notation, that is, the familiarity, that is, the degree of familiarity, is stored in the word dictionary, and the kanji notation of the input kana character notation and the familiarity are extracted from the word dictionary. A Kana-Kanji conversion method characterized by sorting and outputting Kanji notation in descending order of familiarity. 2. The method according to claim 1, wherein a kanji notation of a familiarity in a preset range and the familiarity are extracted from the word dictionary. 3. The method according to claim 1, wherein a kanji notation and its familiarity are extracted from the word dictionary based on a preset number of words to be extracted in addition to the familiarity. 4. The method according to claim 1, wherein when rearranging the kanji notation, another rearrangement condition is used together. 5. An input means for receiving kana character input, a kanji notation corresponding to each kana character notation, and a word dictionary storing familiarity of each kanji notation, that is, a degree of familiarity, Word extraction means for extracting the kanji notation word corresponding to the katakana notation and the intimacy degree of each kanji notation word from the word dictionary; and the kanji notation words extracted by the word extraction means in descending order of intimacy degree. A kana-kanji conversion device having a word rearranging means for rearranging and an output means for outputting the rearranged words in kanji notation. 6. The apparatus according to claim 5, further comprising extraction condition setting means for setting a range of intimacy of words in kanji notation extracted by said word extraction means. 7. The extraction condition setting means further sets the number of words to be extracted, and the word extraction means determines the number of words to be extracted from the word dictionary based on the number of words to be extracted in addition to the degree of intimacy. Extract the words in the notation and their intimacy,
The device according to claim 6. 8. An input process for receiving a kana character input, a kanji notation corresponding to each kana character notation, and a degree of familiarity of each kanji notation, that is, a word dictionary storing familiarity, that is, an input process for receiving the kana character notation. A word extraction process for extracting the familiarity of each kanji notation word corresponding to the kana character notation and each kanji notation word; and a word for rearranging the kanji notation words extracted in the word extraction process in descending order of familiarity. A recording medium storing a kana-kanji conversion program for causing a computer to execute a rearrangement process and a process of outputting the rearranged words in kanji notation to a display device. 9. The recording medium according to claim 8, wherein said input process further accepts a range of intimacy, and said word extraction process extracts words in kanji notation and intimacy in the range of intimacy. 10. The input processing further receives the number of words to be extracted, and the word extraction processing extracts words in Chinese characters and their intimacy from the word dictionary based on the number of words to be extracted in addition to the intimacy. The recording medium according to claim 9,