JPH1196141A - Device and method for chinese input conversion processing, and recording medium recording chinese input conversion processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To efficiently obtain a conversion result by removing the ambiguity and uncertainty of pin-in notation such as a miss of a pin-in input, the oscillation of the four tones of Chinese characters due to differences between the notation of a sentence and usual spoken language and phoneme changes in pronunciation. SOLUTION: A word dictionary 14 is retrieved based on pin-in inputted by an input part 11. When a corresponding KANJI (Chinese character) can not be obtained, a pin-in error detection part 15 detects an error of the pin-in and alarms the pin-in error to a user. When pin-in having a sound change speciphic in Chinese pronunciation is inputted, a pin-in sound change correction part 17 corrects the inputted pin-in to reference notation and then dictionary retrieval is executed. At the time of inputting pin-in having four-tone oscillation specific in Chinese pronunciation, a four-tone oscillation detection/correction part 16 corrects the voice information to reference tone information and then dictionary retrieval is executed.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a Chinese input conversion processing device such as a Chinese word processor used for creating a Chinese document, a Chinese input conversion processing method, and a recording medium on which a Chinese input conversion processing program is recorded. .

[0002]

2. Description of the Related Art Conventionally, a Chinese input conversion processing device such as a Chinese word processor uses a dictionary in which Chinese kanji and phonetic symbols (hereinafter referred to as pinyin) representing their readings are associated with each other. It is equipped with a function to input the Yomi reading in Pinyin, convert it into Kanji and output it. This is called the Pinyin Kanji conversion function (corresponding to the Kana-Kanji conversion function of a Japanese word processor).

As a prior art having such a Pinyin kanji conversion function, for example, Japanese Patent Laid-Open No. 9-44476 is known. According to this publication, when displaying a kanji converted from an input pinyin, a tone code is attached to the kanji near the kanji depending on the mode setting, or the kanji is displayed near the kanji according to the mode setting. It is disclosed that the information is displayed with an affixed to it.

In this prior art, when displaying a kanji obtained as a result of conversion, a device such as adding a tone code to the pinyin of the kanji is devised, but the ambiguity and uncertainty of the Pinyin notation are given. No effort has been made to remove it.

[0005]

In Chinese, the pronunciation of one kanji is always one syllable. One syllable is further composed of a leading consonant called "vowel" (a consonant at the beginning of a syllable) and a portion excluding "vowel" called "final vowel" (including vowels, diphthongs, and nasal vowels). Have been. There is also a tone called "four voices" (similar to Japanese accents) that represents the inflection of syllables.

Examples of vowels: b, p, m, f, d, t, n, l, zh, c
h, sh, ... Examples of rhyme: a, o, e, i, u, ai, en, ang,
one, one of the features of the notation is that, unlike the consonant vowel of the Japanese Roman alphabet, the length of the Roman alphabet is not constant.

[0007] In the conventional Chinese input device, consideration for such Pinyin characters and four voices is insufficient. In addition,
When syllable boundaries become ambiguous (especially for syllables without vowels), the user is required to enter special symbols to separate syllables, or to take measures to determine syllable boundaries on the device side. Is there.

[0008] Further, in Chinese sounds, phenomena such as fluctuation of four voices and phonological change of pronunciation occur due to the difference between the written notation and the everyday spoken language. If the phonological change of the four voices or pronunciation is incorrect, conversion may not be possible even if the pinyin reading is correct.

[0009] As described above, unless special consideration is given to pinyin, which is peculiar to Chinese, and the fluctuations of the four voices and the change in pronunciation phonology, the user can correctly input Chinese pinyin, There is a problem that it is difficult to efficiently convert to a desired kanji.

SUMMARY OF THE INVENTION The present invention has been made in view of the above-mentioned points, and is ambiguous in Pinyin notation such as an error in Pinyin input, a fluctuation of four voices due to a difference between a notation in a sentence and a daily spoken language, and a change in phoneme of pronunciation. Remove the gender and uncertainty,
An object of the present invention is to provide a Chinese input conversion processing device having a higher performance input conversion function, a Chinese input conversion processing method, and a recording medium storing a Chinese input conversion processing program capable of efficiently obtaining a conversion result. And

[0011]

According to a first aspect of the present invention, there is provided a Chinese input conversion processing apparatus for inputting a pinyin indicating the reading of Chinese kanji, and converting the input pinyin into a kanji. An input conversion processing device, comprising: input means for inputting pinyin, a word dictionary storing pinyin and a corresponding kanji, and dictionary search means for searching for the word dictionary based on pinyin input by the input means. A pinyin error detecting means for detecting the input pinyin error when the corresponding kanji is not obtained by the dictionary search means; and a warning means for warning the input pinyin error detected by the pinyin error detecting means. And characterized in that:

[0012] According to a second aspect of the present invention, there is provided the Chinese input conversion processing device according to the first aspect, further comprising a table in which all patterns in Pinyin notation are described. The Pinyin error detecting means checks the notation of the input Pinyin with reference to the table, and determines that the input Pinyin is an error if the notation does not exist in the table.

According to such a configuration, when a Chinese kanji reading is input by pinyin, a dictionary search is performed based on the input pinyin. At this time, if the dictionary search fails, the notation of the input pinyin is checked, and a warning is issued if an error is detected in the notation.

As described above, when the user inputs a non-existent pinyin, a warning to that effect is issued, so that erroneous conversion due to a pinyin input such as a key touch mistake can be prevented.

A Chinese input conversion processing device according to a third aspect of the present invention is a Chinese input conversion processing device for inputting pinyin indicating the reading of Chinese kanji and converting the input pinyin into kanji. Input means for inputting pinyin, a word dictionary storing pinyin and the corresponding kanji, a dictionary search means for searching the word dictionary based on pinyin input by the input means, and a dictionary search means. If the corresponding kanji is not obtained,
Sound change determining means for determining whether or not the input pinyin is a pinyin with a possibility of sound change; and if the input pinyin is a pinyin with a possible sound change, the pinyin And a control means for performing a dictionary search by the dictionary search means based on the input pinyin corrected by the sound change correction means. It is characterized by having done.

According to a fourth aspect of the present invention, there is provided the Chinese input conversion processing device according to the third aspect, further comprising a table describing a correspondence relationship between a special pinyin notation regarding a sound change and a pinyin notation before the sound change. The sound change determination means checks the notation of the input pinyin with reference to the table, and determines that there is a possibility of a sound change if the notation is a special pinyin notation existing in the table. The sound change correction means refers to the table and replaces the special pinyin notation in the input pinyin with the pinyin notation before the sound change.

According to such a configuration, when a Chinese kanji reading is input by pinyin, a dictionary search is performed based on the input pinyin. At this time, if the dictionary search fails, it is determined whether the input pinyin is a pinyin with a possibility of sound change. If there is a possibility of sound change,
It is corrected to the standard notation handled in the text, and the dictionary search is performed again based on the corrected input pinyin.

Therefore, for example, for an input of a pinyin having a sound change peculiar to Chinese pronunciation, such as an r-type sound,
The conversion can be performed correctly, which can increase the conversion efficiency.

According to a fifth aspect of the present invention, there is provided a Chinese input conversion apparatus for inputting Pinyin indicating reading of Chinese kanji with tone information and converting the input Pinyin into Kanji. A processing device, input means for inputting Pinyin with tone information, Pinyin and corresponding Chinese characters, a word dictionary storing tone information of the Chinese characters,
Dictionary search means for searching the word dictionary based on the pinyin and tone information input by the input means,
When the corresponding kanji is not obtained by the dictionary search means, the four-tone shaking determination means for determining whether the tone information added to the input pinyin is tone information with a possibility of four-tone shaking, If the tone information added to the input pinyin is tone information that may possibly cause a four-tone swing as a result of the four-tone swing determination means, the tone information is corrected to standard tone information handled in the text. It is characterized by comprising voice fluctuation correction means, and control means for performing a dictionary search by the dictionary search means based on the input pinyin and tone information corrected by the four voice fluctuation correction means.

According to a sixth aspect of the present invention, in the Chinese input conversion processing device of the fifth aspect, there is provided a table in which a pattern in which four voice fluctuations occur is described. The four-tone shaking determination means refers to the table, checks tone information added to the input pinyin, and determines that there is a possibility of four-voice shaking if the tone information matches the pattern in the table. The four-tone shaking correction means refers to the table and replaces the tone information added to the input pinyin with a light tone or another four-tone tone.

According to such a configuration, when a Chinese kanji reading is input using pinyin with tone information, a dictionary search is performed based on the input pinyin and tone information.
At this time, if the dictionary search fails, it is determined whether or not the tone information added to the input pinyin is tone information with a possibility of four-tone shaking. If there is a possibility of four voice swings,
It is corrected to standard tone information handled in the text, and the dictionary search is performed again based on the corrected input pinyin abdomen tone information.

Therefore, in the case of inputting pinyin with a tone, it is possible to correctly convert even input of pinyin with four voices peculiar to Chinese pronunciation.
Thereby, the conversion efficiency can be increased.

[0023]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing a configuration of a Chinese input conversion processing device according to the present invention. In addition, this device
For example, it is realized by a computer which reads a program recorded on a recording medium such as a magnetic disk and the operation of which is controlled by the program.

In FIG. 1, an input unit 11 is composed of, for example, a keyboard, and inputs Chinese kanji readings by pinyin and gives a conversion instruction. The control unit 12 controls the entire apparatus. The control unit 12 includes a conversion engine that performs conversion processing from input Pinyin to Kanji (pinyin Kanji conversion processing).

The dictionary search unit 13 searches the word dictionary 14 based on the input pinyin, and extracts a kanji corresponding to the input pinyin. The word dictionary 14 is provided in an external storage device such as a ROM or a magnetic disk device, and stores various information necessary for Pinyin kanji conversion processing, such as Pinyin and its corresponding kanji, and kanji tone.

The Pinyin error detecting section 15 detects the correctness of the notation of the input Pinyin while referring to the Pinyin composition rule table 19. The four-voice fluctuation detection and correction unit 16 detects and corrects the four-voice fluctuation in the input four-tone information (tone information) in the pinyin while referring to the four-voice fluctuation detection correction rule 20. I do. The Pinyin sound change correction unit 17 performs a process of correcting a special notation having a sound change into a convertible notation while referring to the Pinyin sound change correction rule table 21 for the input Pinyin.

The rule table storage unit 18 is, for example, a ROM
Or, provided in an external storage device such as a magnetic disk device,
A Pinyin composition rule table 19, a four-voice fluctuation detection correction rule table 20, and a Pinyin sound change correction rule table 21 are stored.

The Pinyin composition rule table 19 describes each Pinyin pattern (Pinyin spelling rule), which is a Chinese phonetic notation, in a format such as an initial matrix / final matrix. The four-voice sway detection correction rule table 20 describes rules for four-voice sway based on differences between sentence notation and everyday spoken language. Pinyin sound change correction rule table 21
Is a special Pinyin notation for sound changes (eg, r
It describes the correspondence between ((Al) -generated sound) and Pinyin notation before sound change.

Note that the r (al) -generated sound means that the er [child] of the sling vowel is combined with another syllable as a suffix.
This is a sound change that is conventionally described by simply omitting [e] and only [r].

The output unit 22 is, for example, a CRT (Cathode Rad).
y Tube) and LCD (Liquid Crystal Display), etc., which display the input Pinyin character string and the kanji obtained as a conversion result.

FIG. 2 is a diagram showing a configuration (part) of the Pinyin configuration rule table 19. In the Pinyin composition rule table 19, all the patterns of Pinyin (Chinese pronunciation notation) (Pinyin spelling composition rules) are described in the form of a matrix of initials and finals. In the figure, “○” indicates a notation that exists as a syllable, and “x” indicates a notation that does not exist as a syllable.

That is, in Chinese sounds, one syllable is generally one.
Although it is expressed by a combination of one initial and one final, some combinations are not actually used. For example, there is no syllable [fe} composed of a combination of [f] and [e].

FIG. 3 shows a four-voice shake detection / correction rule table 20.
FIG. 3 is a diagram showing the configuration of FIG. The four-voice sway detection correction rule table 20 describes rules for four-voice sway based on differences between sentence notation and everyday spoken language.

Here, the Chinese tone will be described. The Chinese sound is one syllable per letter, and the tone is attached to the kanji here. There are four basic tones, and these are called four tones. Of these, the one that extends the sound at the same pitch is called the first voice, the one that raises the sound is the second voice, the one that bends it is the third voice, and the one that lowers it is the fourth voice. If the tone of the same syllable is different, the kanji and meaning will be different. For example, syllable [qi] is as follows.

First voice: [period] Second voice: [odd] Third voice: [ki] Fourth voice: [vessel] In the following description, the tones of the first to fourth voices are 1-4. And should be attached after the syllable. For example, the readings of [period], [odd], [ki], and [vessel] are represented as [qi1], [qi2], [qi3], and [qi4], respectively.

By the way, in the Chinese sound, there is a phenomenon that the tone of the kanji changes according to a certain rule. This is called four-tone swing (or tone swing). The four-voice fluctuation rule is shown in the four-voice fluctuation detection correction rule table 20.

For example, a kanji normally pronounced with the third voice,
If the same kanji of the third voice follows, the tone of the kanji changes to the second voice. When a kanji pronounced as [ba] comes to the end or at the end of a sentence, the tone of the kanji is light. The light voice is a special tone that does not belong to the first to fourth voices, and is lightly pronounced. In the case of a light voice, a number 0 or 5 is added after the syllable.

Next, the operation of the present apparatus will be described. FIG. 4 is a flowchart showing the conversion processing operation according to the first embodiment of the present invention. The first embodiment is characterized in that an error in the notation of the input pinyin is detected, and this is warned to the user.

When the Chinese kanji reading is input in pinyin (alphabet character string) through the input unit 11,
The control unit 12 compares the input pinyin with the dictionary search unit 1
3 (step A11).

Here, when the conversion key is pressed by the user and a conversion instruction is issued, the dictionary search unit 13 searches the word dictionary 14 for a kanji corresponding to the input pinyin (step A12).

If the dictionary search is successful, that is, if the kanji corresponding to the input pinyin can be searched from the word dictionary 14 (Yes in step A13), the control unit 12 sets the kanji as a conversion candidate for the input pinyin. After obtaining and performing a conversion process such as determining the output order of the conversion candidates (step A14), this is sent to the output unit 22 as a conversion result (step A15). As a result, the output unit 22 displays the input pinyin instead of the Chinese character.

On the other hand, if the dictionary search fails, that is,
If the Chinese character corresponding to the input pinyin cannot be searched from the word dictionary 14 (No in step A13), the control unit 12 sends the input pinyin to the pinyin error detection unit 15. The Pinyin error detection section 5 refers to the Pinyin configuration rule table 19 stored in the rule table storage section 18 as shown in FIG. 2 and checks the sent character string of the input Pinyin (vowel final) (step A16). ).

As a result, if the character string of the input Pinyin does not exist in the Pinyin composition rule table 19 (No in step A17), it means that the character string as Pinyin is incorrect. Therefore, upon receiving the check result, the control unit 12 presents a warning to the user via the output unit 22 that the pinyin does not exist (step A18).

If the input pinyin exists in the pinyin composition rule table 19 (Yes in step A17)
s) Since the dictionary could not be searched for other reasons, the control unit 12 performs an error process such as displaying an error message, and terminates the process (step A19).

FIG. 5 shows a specific example. As shown in FIG. 5A, for example, it is assumed that a pinyin consisting of a character string such as [shifenanbian] has been input. By pressing the conversion key, a dictionary search is performed based on the input pinyin, and a conversion result as shown in FIG.

In this case, [fe] in the character string corresponds to FIG.
Does not exist in the Pinyin composition rule table 19 shown in FIG. Therefore, it is determined that the input is erroneous, the character string portion is not converted, and a warning message as shown in FIG.

As described above, when the user inputs a non-existent pinyin, a warning to that effect is issued, so that erroneous conversion due to pinyin input such as a key touch mistake can be prevented.

However, other than the key touch mistake, there is an erroneous input of the Pinyin character string. For example, it is a phenomenon such as an r sound. This is expressed as [r] when the pinyin character string [er] is originally combined with another syllable as a suffix.

By the way, phenomena such as r-consonants are merely spoken words, and there is no clear regulation on how to handle them when writing a document, and it is expected that individual differences exist.
For this reason, it is desired that the system can convert any of these sound changes peculiar to Chinese pronunciation regardless of which one is input.

Hereinafter, as a second embodiment of the present invention, processing for such a sound change of pinyin will be described. FIG. 6 is a flowchart showing the conversion processing operation according to the second embodiment of the present invention.

When the Chinese kanji reading is input in pinyin (alphabet character string) through the input unit 11,
The control unit 12 compares the input pinyin with the dictionary search unit 1
3 (step B11).

Here, when the conversion key is pressed by the user and a conversion instruction is issued, the dictionary search unit 13 searches the word dictionary 14 for a kanji corresponding to the input pinyin (step B12).

If the dictionary search is successful, that is, if the kanji corresponding to the input pinyin can be searched from the word dictionary 14 (Yes in step B13), the control unit 12 sets the kanji as a conversion candidate for the input pinyin. After obtaining and performing conversion processing such as determining the output order of the conversion candidates (step B14), this is sent to the output unit 22 as a conversion result (step B15). As a result, the output unit 22 displays the input pinyin instead of the Chinese character.

On the other hand, if the dictionary search fails, that is,
When the Chinese character corresponding to the input pinyin cannot be searched from the word dictionary 14 (No in step B13), the control unit 12 sends the input pinyin to the pinyin sound change correction unit 17. The pinyin sound change correction unit 17 refers to the pinyin sound change correction rule table 21 based on the input pinyin and checks whether or not there is a pinyin with a possibility of a sound change (for example, r sound) (step). B16).

In this case, the Pinyin sound change correction rule table 21 describes the correspondence between a special Pinyin notation relating to a sound change and the Pinyin notation before the sound change. By checking the notation of the input pinyin with reference to the pinyin sound change correction rule table 21, if the notation is a special pinyin notation existing in the pinyin composition rule table, it is determined that there is a possibility of a sound change. I do.

When it is determined that the input pinyin may have a sound change (Yes in step B17), the pinyin sound change correction unit 17 refers to the pinyin sound change correction rule table 21 to check the input pinyin. By changing the notation to the Pinyin notation before the sound change, the notation is corrected to a standard notation handled in the text (step B18).

When the sound change of the pinyin is corrected in this way, the control unit 12 passes the corrected pinyin to the dictionary search unit 13 and performs a dictionary search again (step B).
12).

If the input pinyin is not a pinyin with a possibility of sound change (No in step B17), the dictionary cannot be searched for other reasons. Error processing such as display is performed, and the processing here ends (step B19).

FIG. 7 shows a specific example. As shown in FIG. 7A, it is assumed that a pinyin consisting of a character string such as [nikunaer] is input. When a dictionary search is performed based on the input pinyin by pressing the conversion key, the word dictionary 14 does not have [nikunaer] but [ni]
quinar] is registered, so that the search fails.

Therefore, the input pinyin is checked with reference to the pinyin sound change correction rule table 21, and if it is determined that there is a possibility of a sound change, the notation of the pinyin is corrected.

In this case, as shown in FIG. 9B, since an input pinyin has an r-format sound [er], [er] is corrected to [r] in accordance with the Pinyin sound change correction rule. Input pinyin [niqunar] after this correction
Is performed again to obtain a conversion result as shown in FIG.

As described above, even when a pinyin having a sound change peculiar to Chinese pronunciation, such as an r-type sound, is input, the conversion can be correctly performed, thereby increasing the conversion efficiency.

In the above description, the r-shaped sound is taken as an example. However, there are other pinyins having sound changes other than the r-shaped sound. Can be applied.

Incidentally, such a difference between the pronunciation and the notation is not limited to the sound change such as the above-mentioned r-formed sound, and the fluctuation of the four-voice information often occurs. For example, there is a tone called light tone, and a word or a sentence (both at the end of a sentence) loses its unique tone and may be pronounced lightly and shortly (light tone).

As an example, the reading "intention" is [yi4sil] in sentence notation, but the actual pronunciation is [yi4si]. Thus, the second character [si
l] is a light tone [si]. Note that the notation is [s
i5] or [si0].

The tone of the third voice, [yil]
(1) There is a phenomenon that the tone of [bu4] (not) changes to another tone when used in a word or a sentence. For such fluctuations in tone information, the problem can be solved by registering all patterns when registering the dictionary. However, in that case, a plurality of records are originally registered in a dictionary for one word, which causes a problem that memory space consumption and dictionary search efficiency are reduced.

Therefore, in the third embodiment of the present invention, a four-tone shaking detection correction rule is provided, the tone information in the input pinyin information is checked, and when the four voices to be corrected are detected, Is corrected.

Hereinafter, a third embodiment of the present invention will be described. FIG. 8 is a flowchart showing the conversion processing operation according to the third embodiment of the present invention.

When the reading of Chinese kanji is input as pinyin (character string of alphabet) with tone information (numerals indicating four tones) through the input unit 11, the control unit 12 controls the input pinyin and tone information. To the dictionary search unit 13 (steps C11 and C12).

Here, when the conversion key is pressed by the user and a conversion instruction is issued, the dictionary search unit 13 searches the word dictionary 14 for a kanji corresponding to the input pinyin and tone information (step C13).

When the dictionary search is successful, that is, when the kanji corresponding to the input pinyin and tone information can be searched from the word dictionary 14 (Yes in step C14), the control unit 12 stores the kanji for the input pinyin. After acquiring as conversion candidates and performing a conversion process such as determining the output order of the conversion candidates (step C15), this is sent to the output unit 22 as a conversion result (step C16). As a result, the output unit 22 displays the input pinyin instead of the Chinese character.

On the other hand, if the dictionary search fails, that is,
If the kanji corresponding to the input pinyin and tone information cannot be retrieved from the word dictionary 14 (No in step C14), the control unit 12 sends the input pinyin and tone information to the four-voice fluctuation detection correction unit 16. The four-voice fluctuation detection / correction unit 16 refers to the four-voice fluctuation detection / correction rule table 20 based on the input pinyin and tone information sent,
It is checked whether the tone information added to the input pinyin is tone information with a possibility of four-tone shaking (step C1).
7).

In this case, the four-voice fluctuation detection correction rule table 20 describes the four-voice fluctuation pattern. By checking the tone information added to the input pinyin with reference to the four-tone shaking detection / correction rule table 20, if the tone information matches a pattern according to the four-tone shaking detection / correction rule, the four-tone shaking detection / correction rule is used. Is determined to be possible.

If it is determined that the tone information added to the input pinyin may have a four-voice fluctuation (Yes in step C18), the four-voice fluctuation detection / correction unit 16 outputs the four-voice fluctuation detection correction rule table. With reference to 20, the tone information added to the input pinyin is replaced with a light tone or another four tone, so that the tone information is corrected to standard tone information handled in the text (step C19).

When the four-tone fluctuation is corrected in this way, the control unit 12 passes the pinyin having the corrected tone information to the dictionary search unit 13 and performs a dictionary search again (step C13).

If the tone information added to the input piny has no possibility of four-tone shaking (N in step C18)
o) Since the dictionary could not be searched for other reasons, the control unit 12 performs error processing such as displaying an error message, and terminates the processing here (step C20).

FIG. 9 shows a specific example. As shown in FIG. 9A, it is assumed that a pinyin consisting of a character string such as [zhuolzi3] is input with tone information. When a dictionary search is performed based on the input pinyin and tone information by pressing the conversion key, [zhu
Since only [zhuolzi5] is registered instead of [olzi3], the search fails.

Therefore, the tone information added to the input pinyin is checked with reference to the four-voice fluctuation detection correction rule table 20 as shown in FIG. And the tone information added to the input pinyin is converted to a light voice or another four voices (for example, to the second voice) in accordance with the four voice fluctuation detection correction rule.
To be corrected.

In this case, [z
Since [i] is at the end of the word, it is determined that there is a possibility of four-voice fluctuation, and as shown in FIG. 3B, [zi3] is changed to [zi5] (light voice) according to the four-voice fluctuation detection and correction rule. Will be corrected. The input pinyin after this correction [zhuolz
By performing a dictionary search again using [i5], a conversion result as shown in FIG.

As described above, in the case of inputting a pinyin with a tone, even if a pinyin with four voice fluctuations peculiar to Chinese pronunciation is input, the conversion can be correctly performed, thereby increasing the conversion efficiency. Can be.

Although the Pinyin error detection processing, the Pinyin sound change correction processing, and the four-voice shaking correction processing of the present invention have been described separately for each embodiment, it goes without saying that these processings can be executed as a series of processing. No.

The methods described in each of the above-described embodiments include, for example, a magnetic disk (floppy disk, hard disk, etc.), an optical disk (CD-ROM,
It is also possible to write the data on a recording medium such as a DVD or a semiconductor memory and apply it to various devices, or to transmit it via a communication medium and apply it to various devices. A computer that realizes the present apparatus reads the program recorded on the recording medium, and executes the above-described processing by controlling the operation of the program.

[0083]

As described above, according to the first and second aspects of the present invention, when the user inputs a pinyin that does not exist, a warning to that effect is given. Erroneous conversion can be prevented.

According to the third and fourth aspects of the present invention, when a pinyin having a sound change peculiar to Chinese pronunciation, such as an r-type sound, is input, the input pinyin is handled in a sentence. Therefore, the conversion process can be performed using the corrected input pinyin, and the conversion efficiency can be improved.

According to the fifth and sixth aspects of the present invention, when inputting pinyin with a tone,
If you input a pinyin with a four-tone fluctuation peculiar to Chinese pronunciation, the tone information added to the input pinyin is corrected to standard tone information handled in the text, so the corrected input pinyin and tone The conversion process can be performed using the information, and thereby the conversion efficiency can be increased.

As described above, according to the present invention, the ambiguity and uncertainty of Pinyin notation such as erroneous Pinyin input, fluctuation of four voices due to difference between written notation and everyday spoken language, and phonetic change of pronunciation are eliminated. Thus, a conversion result can be obtained efficiently.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a Chinese input conversion processing device of the present invention.

FIG. 2 is a diagram showing a configuration (part) of a Pinyin configuration rule table provided in the Chinese input conversion processing device;

FIG. 3 is a view showing a configuration of a four-voice fluctuation detection correction rule table provided in the Chinese input conversion processing device.

FIG. 4 is a flowchart showing a conversion processing operation according to the first embodiment of the present invention.

FIG. 5 is a specific example for explaining a conversion processing operation according to the first embodiment.

FIG. 6 is a flowchart showing a conversion processing operation according to a second embodiment of the present invention.

FIG. 7 is a specific example for explaining a conversion processing operation according to the second embodiment.

FIG. 8 is a flowchart showing a conversion processing operation according to a third embodiment of the present invention.

FIG. 9 is a specific example for explaining a conversion processing operation as the third embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 11 ... Input part 12 ... Control part 13 ... Dictionary search part 14 ... Word dictionary 15 ... Pinyin error detection part 16 ... Four voice fluctuation detection correction part 17 ... Pinyin sound change correction part 18 ... Rule table storage part 19 ... Pinyin composition rule table 20: Four voice fluctuation detection correction rule table 21: Pinyin sound change correction rule table

Claims (12)

[Claims] 1. A Chinese input conversion processing device for inputting pinyin indicating reading of Chinese kanji and converting the input pinyin into kanji, comprising: input means for inputting pinyin; A word dictionary storing kanji to be input; a dictionary search means for searching the word dictionary based on the pinyin input by the input means; and an input pinyin when the corresponding kanji is not obtained by the dictionary search means. 3. A Chinese input conversion processing device comprising: a Pinyin error detecting means for detecting an error in the input; and a warning means for warning the input Pinyin error detected by the Pinyin error detecting means. 2. The apparatus according to claim 1, further comprising: a table describing all the patterns of the Pinyin notation, wherein the Pinyin error detecting means checks the notation of the input Pinyin with reference to the table, and if the notation does not exist in the table, 2. The Chinese input conversion processing device according to claim 1, wherein it is determined that the error is an error. 3. A Chinese input conversion processing device for inputting pinyin indicating reading of Chinese kanji and converting the input pinyin into kanji, comprising: input means for inputting pinyin; A word dictionary storing kanji to be input; a dictionary search means for searching the word dictionary based on the pinyin input by the input means; and an input pinyin when the corresponding kanji is not obtained by the dictionary search means. A sound change determining means for determining whether or not the input pinyin is a pinyin with a possibility of a sound change. As a result of the sound change determination means, when the input pinyin is a pinyin with a possibility of a sound change, the notation of the pinyin is Sound change correction means for correcting to a standard notation handled in the text, and the dictionary search based on the input pinyin corrected by the sound change correction means And a control means for performing a dictionary search by the means. 4. A table which describes a correspondence relationship between a special Pinyin notation related to a sound change and a Pinyin notation before a sound change, wherein the sound change determining means refers to the table to determine the notation of the input Pinyin. If the notation is a special Pinyin notation that exists in the table, it is determined that there is a possibility of a sound change. 4. The Chinese input conversion processing device according to claim 3, wherein the Pinyin notation is replaced with a Pinyin notation before a sound change. 5. A Chinese input conversion processor for inputting Pinyin indicating Chinese kanji reading with tone information and converting the input Pinyin into Kanji, wherein the Pinyin is input with tone information. Input means, a word dictionary storing pinyin and corresponding kanji, and tone information of the kanji; a dictionary search means for searching the word dictionary based on the pinyin and tone information input by the input means; A four-voice shaking determining means for determining whether the tone information added to the input pinyin is tone information having a possibility of four-voice shaking when the corresponding kanji is not obtained by the searching means; If the tone information added to the input pinyin as a result of the shaking determination means is tone information that may cause a four-voice shaking, the tone information is treated as a standard voice to be handled in a sentence. And a control means for performing a dictionary search by the dictionary search means based on the input pinyin and tone information corrected by the four-voice shake correction means. Chinese input conversion processor. 6. A table in which a pattern in which four-tone fluctuations occur is described, wherein the four-tone fluctuation determination means checks tone information added to the input pinyin with reference to the table, and determines the tone information. If the pattern matches the pattern in the table, it is determined that there is a possibility of four-tone shaking, and the four-tone shaking correction means refers to the table and converts the tone information added to the input pinyin into a light tone or another four tone. 6. The Chinese input conversion processing device according to claim 5, wherein the voice is converted into a voice. 7. A Chinese input conversion processing method for inputting pinyin indicating reading of Chinese kanji and converting the input pinyin to kanji, comprising the steps of: inputting pinyin; Searching for a word dictionary storing pinyin and the corresponding kanji, and detecting an error in the input pinyin if a corresponding kanji is not obtained, and warning the input pinyin error. Chinese input conversion processing method. 8. A Chinese input conversion method for inputting a pinyin indicating a Chinese kanji reading and converting the input pinyin into a kanji, comprising the steps of: inputting the pinyin; Then, a word dictionary storing pinyin and the corresponding kanji is searched, and if the corresponding kanji cannot be obtained, it is determined whether or not the input pinyin is a pinyin with a possibility of sound change. Is a Chinese character, which corrects the notation of the Pinyin to a standard notation handled in the text when the Pinyin has a possibility of sound change, and performs a dictionary search based on the corrected input Pinyin Word input conversion processing method. 9. A Chinese input conversion processing method for inputting Pinyin indicating Chinese kanji reading with tone information, and converting the input Pinyin into Kanji, comprising inputting Pinyin with tone information. Based on the input pinyin and tone information, a pinyin and a corresponding kanji, and a word dictionary storing the tone information of the kanji are searched, and if the corresponding kanji is not obtained, it is added to the input pinyin. It is determined whether or not the tone information thus obtained is tone information with a possibility of four-tone shaking. If the tone information added to the input pinyin is tone information with a possibility of four-tone shaking, the tone information is determined. A Chinese input conversion processing method comprising correcting to standard tone information handled in a sentence and performing a dictionary search based on the corrected input pinyin and tone information. 10. A recording medium which records a Chinese input conversion processing program for inputting Pinyin indicating Chinese kanji reading and converting the input Pinyin to Kanji, and comprising the steps of: inputting Pinyin; Based on the input Pinyin, a procedure for searching a word dictionary storing Pinyin and the corresponding Kanji, and a procedure for detecting an error in the input Pinyin when the corresponding Kanji cannot be obtained; A computer-readable recording medium that records a program for causing a computer to execute a procedure for warning an error of Pinyin. 11. A recording medium which records a Chinese input conversion processing program for inputting Pinyin indicating reading of Chinese kanji and converting the input Pinyin into Kanji, wherein a procedure for inputting Pinyin is provided. Based on the input Pinyin, a procedure for searching a word dictionary storing Pinyin and the corresponding Kanji, and if the corresponding Kanji is not obtained, whether the input Pinyin may have a sound change A procedure for determining whether or not the input pinyin is a pinyin with a possibility of sound change, and a procedure for correcting the notation of the pinyin to a standard notation handled in the text. And a computer-readable recording medium that records a program for causing a computer to execute a dictionary search procedure based on a computer. 12. A recording medium recording a Chinese input conversion processing program for inputting Pinyin indicating Chinese kanji reading with tone information and converting the input Pinyin into Kanji, wherein the Pinyin is converted to tone. A step of searching based on the input pinyin and tone information, a step of searching a pinyin, a corresponding kanji, and a word dictionary storing tone information of the kanji, and a step in which the corresponding kanji cannot be obtained. In the case where the tone information added to the input pinyin is determined to be tone information having a possibility of four-tone shaking, a step of determining whether the tone information added to the input pinyin is In the case of certain tone information, a procedure for correcting the tone information to standard tone information handled in the text, and based on the input pinyin and the tone information after the correction. A computer-readable recording medium a program for executing the procedure for writing the search to a computer.