JPH05216887A - Device and method for chinese pronunciation notation/ chinese character conversion - Google Patents

Abstract

PURPOSE:To input pronunciation by utilizing any of plural kinds of notation method including the PinYin notation method and the ZhuYin notation method and to obtain Chinese character candidates including a desired Chinese character without inputting a tone or even when the input of the tone is erroneous. CONSTITUTION:Input data in the PinYin notation method are converted into corresponding sound codes by means of a PinYin/sound code conversion table 31, while the input data in the ZhuYin notation method are converted into the corresponding sound codes by means of a ZhuYin/sound code conversion table 32. A dictionary 35 stores Chinese character codes corresponding to a sound code train (corresponding to a word). The sound code train is prepared from the input data. The respective sound codes in the input sound code train is compared with the sound codes in the sound code train in the dictionary 35 through a filter masking a certain bit of the sound codes. Based on the comparison, the Chinese character codes corresponding to the coincident sound code train are read out of the dictionary 35 and the word (Chinese character) corresponding to the Chinese character codes are displayed.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus and method for converting Chinese phonetic notation input from a keyboard into corresponding Chinese characters and outputting the same, and is particularly preferably used in a Chinese word processor or work station. Apparatus and method.

[0002]

BACKGROUND ART Chinese is expressed using Chinese characters. There are several notations for writing the pronunciation of kanji. The representative one was promulgated by the Chinese government in 1958.

[Equation 1] Used before then, still used in Taiwan

[Equation 2] There is.

The pronunciation of a single Chinese kanji character is made up of a phonetic mother (Sheng Mu) corresponding to a consonant, and a Chinese mother (Yun Mu) corresponding to a vowel.
Four tones (Si Sheng) or tones (Sheng Dia)
o) can be divided into The combination of Kyoko and Kyoko is called Sheng Yun. Some kanji pronunciations have no intonation. The pronunciation of one Kanji is represented by one or less (one or zero) phonetic syllable and one cypress (using further tones as necessary).

There are the following four tone types. One voice (Yi Sheng
Or 1Sheng): High and flat.

[Equation 3] Two voices (Er Sheng or 2Sheng): Bass to treble.

[Equation 4] Three voices (Shan Sheng or 3Sheng): High to low, then high again.

[Equation 5] Four voices (Si Sheng or 4 Sheng): Decrease from treble to bass.

[Equation 6]

For example, the Chinese character “China” is Pin Yin
According to the law,

[Equation 7] Is written. Among these, "Zh" and "G" are the vocal mothers, and "ong" and "uo" are the female mothers. Also,
According to the Pin Yin method, the kanji "Japan" is

[Equation 8] Is written. "R" and "B" are voice carriers, and "i" and "en" are iron carriers.

Pin in a traditional Chinese word processor
Only input in Yin notation was allowed. The Pin Yin method is relatively new, so I know the Zhu Yin method, but Pin Yi
n Some people or generations do not know the law. Therefore, in order to get more people to use the Chinese word processor, we have to allow Zhu Yin input.

The Pin Yin system notation is defined with Mandarin as the standard language. In vast China, there are languages with pronunciations that differ from the tone of Mandarin. Depending on the region, even the vocal language may be different from Mandarin. Therefore, it becomes difficult for people who do not know or are familiar with Mandarin as the standard language to input the correct voice and tone,
Input errors often occur. Even if you are a Mandarin-speaking person,
It is not always possible to pronounce while paying attention to the distinction of tones, and it is necessary to perform input work into the word processor while remembering or thinking about the tone, and not only the input work is complicated, but also the correct tone is produced. Sometimes you can't enter.

In the conventional Chinese word processor, the correct Chinese character corresponding to the correct input is output only when the vocal and tone are correctly input, and the correct Chinese character cannot be obtained if there is an input error.

[0009]

DISCLOSURE OF THE INVENTION It is an object of the present invention to provide Chinese phonetic notation /
The Kanji conversion device enables pronunciations to be input using any of several types of notation including Pin Yin notation and Zhu Yin notation.

Another object of the present invention is to make it possible to obtain a candidate kanji including a desired kanji even if the tone is not input or there is an error in the tone input.

It is still another object of the present invention to obtain a kanji candidate corresponding to a pronunciation including a part of the pronunciation if at least a part of the pronunciation is accurate.

According to the first aspect of the present invention, the Chinese pronunciation notation / Kanji conversion apparatus according to the present invention is capable of inputting Chinese pronunciations according to a plurality of kinds of notations,
A plurality of conversion tables and sounds provided for each of a plurality of types of notations that can be input using the above-mentioned input device, for converting input data according to each notation into a sound code corresponding to the pronunciation represented by the input data. A dictionary in which a code and a Kanji code indicating a Kanji having a pronunciation represented by the phonetic code are stored in association with each other, and input data input from the input device is stored using one of the plurality of conversion tables. Convert to sound code,
The control means for searching the dictionary for the kanji code corresponding to the converted phonetic code is provided.

In a preferred embodiment, the apparatus of the present invention is further provided with input mode selection means for selecting one of a plurality of types of notation. Then, the input data is converted into a sound code by using a conversion table related to the notation selected by the input mode selection means.

The notation may be automatically determined based on the input data input from the input device, and the conversion table to be used may be selected according to this determination.

The input device is a device for converting an input voice into an electric signal, and recognizes pronunciation based on the voice electric signal,
It can also be configured with a voice recognition device that converts an input voice into a sound code.

When the device according to the present invention is applied to a Chinese word processor or the like, the means for converting the retrieved Kanji code into display data representing the Kanji indicated by the Kanji code, and the display data are used. Further, a device for displaying kanji is provided.

This device is further provided with a designation input means for designating one of the displayed kanji candidates and a memory for storing a kanji code indicating the designated kanji.

In order to apply to a more realistic word processor, each conversion table described above is configured to convert input data into a phonetic code for one Chinese character. On the other hand, the dictionary is configured to store a phonetic code string and a kanji code in association with each other for a word consisting of one kanji or a plurality of kanji. A series of input data input from the input device is divided into each kanji character and converted into a sound code. The converted one or more sound codes are arranged in word units to form a sound code string. The Kanji code corresponding to this phonetic code string is searched in the dictionary.

The present invention is based on the recognition that one phonetic code (kanji reading) can be associated with one phonetic code. Even if there are multiple types of notations such as Pin Yin notation and Zhu Yin notation, the pronunciations expressed by these notations can always be converged into one phonetic chord if they have the same pronunciation. .. Therefore, it suffices to prepare a dictionary for kanji (or words) that is searched using phonetic codes. In this way, according to the present invention, the pronunciation can be input using any of a plurality of types of notation, and the input pronunciation is converted into the kanji having the pronunciation.

In the embodiment of the present invention, it is possible to obtain a kanji character candidate including a desired kanji character even if the tone is not correctly input or the phonetic transcription has some error. To this end, the device according to the invention further comprises filtering means for masking the predetermined one or more bits that make up the sound code. Then, the control means filters the sound code corresponding to the input data and the sound code of the dictionary by using the filtering means and then compares them to determine a sound code matching the sound code corresponding to the input data. Search in the above dictionary.

The features of this embodiment will be fully clarified in view of the second feature of the invention described below.

According to the second aspect of the present invention, the Chinese pronunciation notation / Kanji conversion apparatus converts the input data representing the Chinese pronunciation into a sound code corresponding to the pronunciation, and a sound code. And a kanji code indicating a kanji having a pronunciation represented by the sound code are stored in association with each other, filtering means for masking a predetermined one or more bits constituting the sound code, and the conversion means. By filtering the sound code and the sound code in the dictionary using the filtering means and comparing them with each other, a sound code matching the sound code obtained from the converting means is searched in the dictionary,
The control means is provided for reading the kanji code corresponding to the matching phonetic code from the dictionary.

The above sound chord is, in one embodiment,
It is configured so as to include a bit representing a phonetic character, a bit representing a vowel, and a bit representing a tone. In this case, the filtering means is configured as a mask for a bit representing a voice vowel, a bit indicating a vowel vowel, or a bit indicating a tone.

It is to be understood that the filtering means include those that allow the sound chords to pass through as they are.

Search mode selecting means for selecting whether or not to use the filtering means or for selecting one of the plurality of filtering means is further provided, if necessary.

Like the first feature of the present invention described above,
You may further provide the input device which can input Chinese pronunciation according to the multiple types of notation. In this case, the conversion means is provided for each of a plurality of types of notation that can be input using the input device, and the input data according to each notation is converted into a sound code corresponding to the pronunciation represented by the input data. It will have a plurality of conversion tables for converting to.

Instead of the above input means and conversion means,
A voice recognition means may be provided for recognizing a pronunciation based on a voice input signal and outputting a sound code corresponding to the pronunciation.

In order to realize a more realistic word processor, a means for converting the read kanji code into display data representing the kanji indicated by the kanji code, and a device for displaying the kanji based on the display data. , A designation input means for designating one of the displayed kanji candidates and a memory for storing a kanji code indicating the designated kanji will be provided.

Further, while the conversion means is configured to convert the input data into a phonetic code for one Kanji, the above dictionary has a phonetic code string and a Kanji code for a word consisting of one Kanji or a plurality of Kanji. And are associated and stored. Then, a series of input data is divided into each Kanji character and converted into a sound code, and one or a plurality of converted sound codes are arranged in word units to form a sound code string. The Kanji code corresponding to this phonetic code string is searched in the dictionary.

According to the present invention, the sound code representing the input data and the sound code in the dictionary are both filtered and then compared. Since the filter masks the part (one or more bits) of the sound code that should be matched or unmatched, the masked part is not subject to comparison processing.

Therefore, when it is desired to make the tones unquestioned, by using a filter suitable for them, regardless of whether the tones match or not, or even when the tones are not input,
In the other part (Voice), one or a plurality of Chinese character candidates corresponding to the sound code corresponding to the input data can be obtained. In this way, candidates for kanji (words) including a desired kanji (word) can be output even if no tone is input or there is an error in tone input.

The type of filter can be set arbitrarily.
Therefore, it is also possible to search for kanji under the condition that only the phonetic mother or only the Chinese mother is matched. That is, if at least part of the pronunciation is correct, it is possible to obtain candidates for kanji (words) corresponding to the pronunciation including the pronunciation.

The present invention further includes the above-mentioned first and second
It provides a phonetic transcription / kanji conversion method for Chinese corresponding to each device according to the above features.

In the method according to the first feature, Chinese pronunciation can be input according to a plurality of types of notation, and for each of the plurality of types of notations that can be input, the input data according to each notation is converted into the input data. A dictionary is prepared in advance that stores a plurality of conversion tables for converting into the phonetic codes corresponding to the pronunciations represented by, and the phonetic codes and the Kanji codes representing the Kanjis with the pronunciations represented by the phonetic codes in association with each other. The input data is converted into a sound code using any of the plurality of conversion tables, and the Kanji code corresponding to the converted sound code is searched in the dictionary.

In the method according to the second feature, a dictionary in which a phonetic code and a kanji code indicating a kanji having a pronunciation represented by the phonetic code are stored in association with each other is prepared in advance, and the input Chinese Data representing a word pronunciation is converted into a sound code corresponding to the pronunciation, and the sound code obtained by the conversion and the sound code in the dictionary are masked with one or more predetermined bits constituting the sound code. The sound codes that match the sound codes obtained by the conversion are searched in the dictionary, and the Kanji codes corresponding to the matching sound codes are read from the dictionary.

Other features and advantages of the present invention will be apparent from the following description of the embodiments with reference to the drawings.

[0037]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 shows the configuration of a Chinese phonetic transcription / kanji conversion device. This device would typically be implemented as part of a Chinese word processor, work station, etc.

The phonetic transcription / kanji conversion device for Chinese includes a computer 10 including a central processing unit (CPU), a phonetic transcription,
Keyboard for entering various modes and other functions
20, memory device storing dictionary and various conversion tables
30 and a display device 14 for displaying converted Chinese characters and other information or data and its control device 12.

A commercially available general-purpose computer can be used as the computer 10. This computer 10 is programmed to execute the input, edit processing and Kanji search processing described later.

In this embodiment, there are the Pin Yin method and the Zhu Yin method as the phonetic notations that can be input. In addition, a complete phonetic transcription that includes the tone and a phonetic transcription that excludes the tone and that is performed using only the vocal cord are allowed.

On the keyboard 20, a Pin Yin key 21 for inputting phonetic notation by the Pin Yin method, a Zhu Yin key 22 for inputting phonetic notation by the Zhu Yin method, and a phonetic notation to be input also by the Pin Yin method. No. or Zhu Yin method input mode key 23, Kanji search with complete phonetic notation including tone (this is called first mode), A conversion mode key to select whether you want to search Kanji by phonetic notation (this is called the second mode), and a conversion key to instruct that the entered phonetic notation should be converted to Kanji,
A space key (if required) and a function key 25 for entering other functions are provided.

The data (or chord) representing the phonetic notation input from the keyboard 20 is the corresponding phonetic chord (Yin
Code). Pin Yin for this code conversion
A / sound code conversion table 31 and a Zhu Yin / sound code conversion table 32 are provided in the memory device 30. In order to display the input phonetic notation with that phonetic notation or another phonetic notation, the one that has been converted into a phonetic code is Pin Yi
Phonetic chord / Pin Yin table 33 for converting back to data (or chords) representing n notation or Zhu Yin notation
A sound code / Zhu Yin table 34 is provided in the memory device 30. Further, a dictionary 35 used for searching a code (Kanji code) representing a corresponding Kanji character based on the converted phonetic code, and a converted data area 36 for storing the converted Kanji code are memory devices. It is provided in 30. The memory device 30 is realized by a semiconductor memory (ROM or RAM), a magnetic memory (floppy disk or hard disk), or a combination thereof. For example, the conversion tables 31 to 34 are stored in the ROM, the floppy disk or the hard disk, the dictionary 35 is stored in the floppy disk or the hard disk, and the converted data area is set in the RAM.

As the display device 14, most commonly, C
An RT display device is used, but a plasma display device or a liquid crystal display device can also be used. The display controller 12 has a character generator 13 built-in. Character generator 13 is Pin Yin or Zh
u Yin data and Kanji code are converted to display data (dot data).

FIG. 2 is a diagram in which the configuration shown in FIG. 1 is arranged according to its function and processing flow. Switching circuit 1
5, the edit processing device 16 and the kanji search processing device 17 are substantially realized by the computer 10. Alternatively, the phonetic transcription / kanji conversion device can be configured to have the hardware architecture shown in FIG.

The switching circuit 15 selects the Pin Yin key 21 or the Zhu Yin key 22 according to the selection input through the input mode key 23.
Select. The data representing the Pin Yin or Zhu Yin notation input using the Pin Yin key 21 or the Zhu Yin key 22 is given to the edit processing device 16. Switching circuit 15 is Pin
It may be possible to automatically discriminate between Yin key input and Zhu Yin key input and select the input.

Some Chinese words are composed of one Kanji character, and some are composed of a plurality of (generally two or three) Kanji characters. The edit processing device 16 divides the input data string representing the Pin Yin or Zhu Yin notation into data representing one kanji character, and stores the separated data into the conversion table 31 or 32 selected by the input mode key 23. Refer to and convert to sound code. When there is an input from the conversion key included in the function key 25, the sound code string created from the data input so far is given from the edit processing device 16 to the kanji search processing device 17. Since the edit processing device 16 gives the data representing the input Pin Yin or Zhu Yin notation to the display control device 12, the characters in the input Pin Yin or Zhu Yin notation are input on the screen of the display device 14. It is displayed in order. In this case, the inverse conversion tables 33 and 34 are not necessary. The editing processor 16 converts the input data into sound chords, and then Pin Yin or Zhu Yin
The reverse conversion tables 33 and 34 are used when displaying by notation. These inverse conversion tables 33 and 34 are
Data input by the Pin Yin method (or Zhu Yin method)
It is effectively used when displaying in Zhu Yin notation (or Pin Yin notation). This is convenient because an operator who knows only Pin Yin notation can know Zhu Yin notation and an operator who knows only Zhu Yin notation can know Pin Yin notation.

The kanji search processor 17 searches the dictionary 35 according to the selection by the conversion mode key 24 based on the given phonetic code string, and one or a plurality of kanji having the pronunciation represented by the phonetic code string. The Kanji code representing "" is read and given to the display controller 12. The display control device 12 reads display data for displaying the kanji represented by the given kanji code from the character generator 13, and based on this, one or a plurality of kanji (candidates for kanji) on the display screen of the display device 14. Is displayed. When the operator sees this display and confirms or selects one of the displayed kanji by using the function key 25, the kanji code representing the confirmed or selected kanji is stored in the converted data area 36.

FIG. 3 shows an example of the Pin Yin / sound code conversion table, and FIG. 4 shows an example of the Zhu Yin / sound code conversion table.

About one type of pronunciation Pin Yin method and Zhu Yi
There are various phonetic notations such as the n system, but these notations always correspond to one type of pronunciation. One type of sound code (Yin Code) is assigned to one type of pronunciation. One Pin Yin notation always corresponds to one phonetic chord, and one Zhu Yin notation always corresponds to one phonetic chord. Pin Yin notation for one pronunciation and the same pronunciation
The Zhu Yin notation corresponds to one common chord. In this way, even if there are multiple types of phonetic notation used for phonetic input, the same phonetic representation is expressed using one phonetic code. Whether the input is made using the Pin Yin method or the Zhu Yin method, as long as they have the same pronunciation, they will be converted into one sound code, so the sound code will be the only pronunciation inside the device. Can be used uniformly as a code representing. Therefore, it is not necessary to prepare a dictionary for each phonetic notation, such as a dictionary for the Pin Yin method and a dictionary for the Zhu Yin method, and a dictionary searched using a phonetic code common to all the notations is used. All you have to do is prepare.

For example, the pronunciation in Pin Yin notation shown in the first line of FIG. 3 and the pronunciation in ZhuYin notation of the first line in FIG. 4 correspond to the same sound code 52f8 (hexadecimal notation). The pronunciation of the other lines is the same. 3 and 4, the leftmost columns are represented by Pin Yin notation and Zhu Yin notation respectively for the sake of clarity, but these notations are represented by binary data in the conversion table. Needless to say.

FIG. 5 (A) shows the data format of the sound code. In this embodiment, the sound code is composed of 2 bytes. The high-order 1 byte mainly represents Yibo, and the low-order 1
The bytes mainly represent the voice mother. The data "0" of the most significant bit (f) in the upper 1 byte and the data "1" of the most significant bit (7) in the lower 1 byte distinguish between the upper 1 byte and the lower 1 byte constituting one sound code. It is also used to distinguish it from other data (in particular, other sound codes in the sound code string).

The least significant bit (8th bit) of the upper 1 byte indicates the presence or absence of a tone. This is because some pronunciations have no tone. No tone is represented by "0", and tone is represented by "1". The lower 2 bits (0th to 1st bits) of the lower 1 byte represent a tone. As shown in FIG. 5 (B), one voice, two voices, three voices, and four voices are “00”, “01”, “10”,
It is represented by "11".

The middle 6 bits of the upper 1 byte (9th to eth)
Bits) represent the mother, and the middle 5 bits (2nd to 6th bits) of the lower 1 byte represent the mother. Since there are 37 different types of syllabary and 24 types of vowels, this number of bits is sufficient.

A filter is used in the Chinese character search processing described later. This filter also consists of 2 bytes,
The bit, the first bit and the eighth bit are set to "0" and the other bits are set to "1". If this filter is expressed in hexadecimal, it becomes "FEFC".

FIG. 6 shows the procedure of the input and edit processing by the computer 10 or the operation of the edit processing device 16.
The computer 10 or the editing processor 16 is provided with a key data buffer as shown in FIG. 7 and a tone code string buffer as shown in FIG.

First, using the input mode key 23, Pin Yi
It is determined whether the n method or the Zhu Yin method is set (step 41). If the Pin Yin method is selected, the Pin Yin / sound chord conversion table 31 is selected (step 42) and the Zhu Yin method is selected. Zhu Yi if law is selected
n / sound chord conversion table 32 is selected (step 4
3).

Then, the conversion mode key 24
It is determined whether the mode or the second mode is selected (step 44). When the first mode is selected, no processing is required, but when the second mode is selected, "FEFC" is set in the filter (implemented by the register or memory area). (Step 45). When the first mode is selected, the data "FFF" consisting of all 1's as a filter
F "may be set.

Each time character or symbol data representing a phonetic transcription is input from the Pin Yin key 21 or Zhu Yin key 22, these data are stored in the key data buffer (step 47). As shown in FIG. 7, when one character is input, the terminal symbol data “φ” is stored in the subsequent stage of the character. This is because the data representing the phonetic notation is variable length data, and it is necessary to clearly indicate the end of the data. FIG. 7 shows how the pronunciation “Zhong” in Pin Yin notation is input according to the second mode.

It is determined whether key data for one Chinese character has been input (step 48). There are various methods for this determination. The first is to have the operator press the space key at the end of key data input for one Chinese character. When the space key is pressed, it is determined that the input for one kanji has been completed. The second is effective in the case of the first mode, and is to allow the operator to input the tone with the numbers 1, 2, 3, 4 after inputting the phonetic symbols. For example, if the pronunciation is “Zhong” and has one voice intonation, “Zhong1” is input. If there is a numeric key input, it is determined that the input of data for one kanji has been completed. The third is to make a determination by automatic recognition by syllable division. Since there is a certain law in the description of pronunciation by the Pin Yin method, by using this law, it is possible to determine where in the entered key data string the notation for one Kanji character ends. Similarly, the Zhu Yin method can be used because there is a certain law.

In any case, when the key data for one Chinese character is input, the input key is referred to with reference to the previously selected PinYin / sound code conversion table 31 or Zhu Yin / sound code conversion table 32.・ Data (Pin Yin or Zh
u Yin notation) is converted into the corresponding sound code.
This sound code is stored in the sound code string buffer (step 49).

The above-mentioned processing of step 47 is repeatedly continued until the input of key data for one Chinese character is completed (step 48), and the processing of steps 47 to 49 is repeatedly executed until the conversion key is pressed (step 46). ). Then, when the conversion key is input, the sound code string stored in the sound code string buffer is passed to the kanji search process starting from FIG. 9 (step 50).

For example, when "Zhong Guo" is input in the second mode by the Pin Yin method, the key input data "Zhong" is converted into the sound code "52f8" and "G".
"uo" is converted into the sound code "66b4", respectively, and the sound code string "52f866b4" is obtained.

It is also possible to specify the second mode and then input the pronunciation including the tone. For example, "Zhong1 G
You can enter "uo2". In this case, "53
The sound code string "f867b5" is generated. Since the second mode is specified, the filter "FEF
"C" is set (step 45), and the second mode search, which will be described in detail later, is executed.

9 to 11 particularly show the procedure of the kanji search processing in the second mode. By setting the filter to "FFFF", this processing is also applied as it is to the Kanji search processing in the first mode. Also,
This processing may be executed by the computer 10 shown in FIG. 1 or the kanji search processing device 17 shown in FIG.

Before explaining this kanji search processing, the dictionary 35
The structure of will be described with reference to FIGS. 12 and 13. Figure
As shown in FIG. 12, the dictionary 35 is provided with an index I table, an index II table, and a phonetic code string / kanji code correspondence table.

As shown in FIG. 13, the phonetic code string / Kanji code correspondence table associates a phonetic code string with a Kanji code representing one or a plurality of Chinese characters forming a word having a pronunciation represented by the phonetic code string. It is something to remember. For the sake of clarity, FIG. 13 shows the kanji itself instead of the kanji code, but it should be understood that the code represented by a binary number is actually stored.

Since the word "Chinese" is composed of three Chinese characters, the sound code string is composed of 6 bytes. A 4-byte sound code string corresponds to a word composed of two Chinese characters (for example, "China"). A 2-byte sound code string corresponds to one Kanji character. in this way,
Words that share the same Chinese character at the beginning (“middle” in the above example) are arranged close to each other, and arranged so that the value indicating the relative address becomes smaller as the number of bytes in the phonetic code string that constitutes the word becomes smaller. Has been. In FIG. 13, there is always a symbol "φ" representing "0000" at the end of the sound code string.

One pronunciation may express two or more kanji. For example, the tone code strings of the relative addresses 102 and 103 are both “53f8”, which corresponds to the Chinese characters “middle”, “tada”, and the like.

The relative address of the phonetic code string / Kanji code correspondence table is represented by p. Further, the tone code string of the relative address p is expressed by Y0 (p, 1), Y0 (p, 2), ..., φ. Y0 (p, 1), Y0 (p, 2), etc. are generally represented by Y0 (p, C) (C = 1, 2, ...). The Kanji code of the relative address p is represented by KA (p) (variable length).

The phonetic code string / Kanji code correspondence table stores as many words as possible (preferably, almost all words used in China). The order of arranging these words is arbitrary except the above-mentioned rules. Therefore, it is possible to arrange a pair of a phonetic code string and a Kanji code in any memory location. Let M be the number of words arranged in the phonetic code string / Kanji code correspondence table.

Returning to FIG. 12, the index I table and the index II table store the sound code strings in the randomly arranged sound code string / kanji code correspondence table,
This is so that the search can be performed in the order of the numerical value represented by the sound code string.

The index I table has N Ins.
dexI (i) are arranged in a fixed order. Ind
exI (i) is a pointer (indicating the relative address of the index II table) to the corresponding element in the index II table. N is the number of different sound code strings in the sound code string / Kanji code correspondence table.
As described above, since two or more words may correspond to one phonetic code string, N ≦ M is generally established.

The index II table has M storage locations, and each storage location has three types of elements, F1 (k) and F1.
2 (k) and F3 (k) are stored. F3 (k)
Is a pointer (indicating the relative address of the correspondence table) to the corresponding sound code sequence in the sound code sequence / Kanji code correspondence table. F2 (k) is the relative location of another storage location in the index II table that has F3 (k) that points to the same sound code sequence as the sound code sequence that F3 (k) points to in the same storage location. Address). As a result, both the words "medium" and "tada" can be searched for the sound code string 53f8. When there is no other same tone code string, F2 (k) = φ is set.
F1 (k) is the same memory location as F3 (k)
F3 that points to a sound code string that includes a sound code string that is the same as the sound code string that points to
FIG. 7 shows (relative address of) another storage location in the Index II table with (k). As a result, when "China" is searched, "Chinese" including "China" and having more kanji characters than this is automatically searched.

Inde in the index I table
xI (i) is pre-sorted in ascending order of the numerical value represented by the sound code string in the sound code string / Kanji code correspondence table. Therefore, even if the arrangement of the sound code strings in the sound code string / Kanji code correspondence table is random, when viewed through the index I table, it is as if the sound code string is represented in the sound code string / Kanji code correspondence table. It looks as if the numbers are arranged in ascending order.

In the Kanji search processing shown in FIGS. 9 to 11, a binary search (dichotomizing) method is used.

Several variables are used in this Kanji search processing. These variables are START, END,
find, etc. The variables START and END are used to access the Index I table.
find is used to indicate the memory location of the kanji code buffer (see FIG. 14) that stores the found kanji code. These variables are implemented as data stored in registers or memory areas.

Input / edit processing (FIG. 6) or input sound code string given from the edit processing device 16 to the kanji search processing or kanji search processing device 17 is x (1), x (2), x
(3), ..., φ. For example, when “Zhong1 Guo2” is input by the Pin Yin notation, the input sound chord sequence is “53f8 67b5 φ”. That is, x (1) = 53f8, x (2) = 67b
It is 5. The sound code counter C is used to indicate the position of each sound code forming the input sound code string in the input sound code string. For example, x
(1) is represented by x (C) (C = 1).

In FIG. 9, first, the sound chord counter C
Are initialized to 1 (C = 1, step 51). As a result, the sound code x (1) at the head of the input sound code string is designated.

Subsequently, the variable START is initialized to 0, END is initialized to (N-1), and find is initialized to 0 (step 52).

Using the variables START and END, the relative address of the index I table is (START + EN
It is calculated as D) / 2 and is set as i (step 54). This is a process for obtaining the relative address located exactly in the center of the relative address of the index I table. The binary search method divides a series of relative addresses (generally speaking, a group of items) into two parts,
This is a search method of reaching (finding) a target relative address (item) by selecting one of them and further dividing the selected part into two.

The index I table is accessed using the calculated relative address i, and the relative address i
The IndexI (i) stored in the storage location having is read. This IndexI (i) is placed as k (step 55).

Subsequently, the index II table is accessed using IndexI (i) = k as a relative address, and the elements F1 (k), F2 (k), F3 (k stored in the storage location having the relative address are accessed. ) Are read out and placed as p1, p2 and p3, respectively (step 56).

Referring to FIG. 10, the tone code string / Kanji code correspondence table is accessed using the third element F3 (k) = p3 read from the index II table as a relative address, and the relative address The tone code Y0 (p3, C) stored in the memory location having the is read. FILT when the second mode is selected
ER = FEFC is set (Fig. 6, Step 4
Five). This FILTER and the read sound code Y0
An AND logical operation with (p3, C) is performed. Also,
The AND logic operation of the sound code x (C) designated by the sound code counter C of the input sound code string and the FILTER is executed. It is compared whether these two AND logical operation results are equal and which is larger (steps 63 and 64).

As described above, looking at the sound code string / Kanji code correspondence table through the index I table, the sound code strings in the sound code string / Kanji code correspondence table are arranged in ascending numerical order. Therefore, the fact that FILTER AND x (C) <FILTER AND Y0 (p3, C) is satisfied means that the input tone code x (C) is better than the read tone code Y0 (p3, C). It means that x (C) which is small, that is, to be searched for is stored in a memory location having a relative address smaller than that of Y0 (p3, C). In order to get closer to x (C), it is necessary to access a memory location with a smaller relative address. That is, it is necessary to access the upper half of the index I table. Then, i is substituted for the variable END (step 67), and the process returns to step 54 via step 53.

FILTER AND x (C)> FILTER AND Y0 (p3, C) In the case of Expression 2, i is substituted into the variable START (step
68), and similarly return to step 54.

In this way, according to the binary search method, the sound code that matches the input sound code x (C) is searched in the sound code string / Kanji code correspondence table.

Finally, FILTER AND x (C) = FILTER AND Y0 (p3, C) When Expression 3 is established, it means that the memory location storing the target sound code x (C) is found in the correspondence table. ..

If C = 1, then the second (C
= 2) input sound code x (C) and the second sound code Y0 (p3, C) of the sound code string in the correspondence table match, the sound counter C is incremented ( Step 66).

If the expression 3 is not satisfied in the incremented C, the search is again performed according to the binary search method depending on whether the expression 1 or the expression 2 is satisfied (step 64). , 67, 68). If C = 1 holds, it means that the target chord string exists near Y0 (p3, C) found in the correspondence table, so it is not necessary to use the binary search method. , You may search for the neighborhood. Further, as will be described later, the search can be performed using the element F1 (k).

Sound code Y0 (p3, C) for which expression 3 holds
As a result of incrementing the sound chord counter C while finding out, the search is completed for all the sound chords in the input sound chord string, and finally x (C) = φ (step 61), the action is taken. It is checked whether Y0 (p3, C) = φ holds in the sound chords of the sound chord string in the table (step 69). Where Y
If it becomes ES, it means that a sound code string that matches the input sound code string is found, and the process moves to the process shown in FIG. If the sound code Y0 (p3, C) is not φ, the target sound code string exists at a position having a relative address larger than that storage location, so the search is continued for storage locations larger than the relative address. This will be the case (step 70). However, since the sound code string that includes all the input sound code strings was found (as if "Chinese" was found in an attempt to find "China"), the target sound was found in the immediate vicinity. Since there should be a chord sequence, if the relative addresses in the correspondence table are incremented one by one, the intended chord sequence should be found immediately.

Further, when the read sound code Y0 (p3, C) becomes φ even though x (C) is not φ yet (while searching for "China", "Is found (step 62), the process moves to the search for a memory location with a smaller relative address (step 65). In this case as well, since the target character code string should exist in the immediate vicinity of the reached memory location,
By decrementing the relative addresses of the correspondence table one by one, it will be possible to quickly find the target character code string.

Here, the meaning of FILTER = FEFC will be described with reference to FIG. For example, "Zhon
When an AND of any one of the one-to-four-tone sound code having the voice g and the FILTER = FEFC is calculated, the tone code is converted into a sound code representing the voice "Zhong". Therefore, when a kanji search is performed under the second mode, all kanji with the same vocal gram can be found regardless of the tone. This is shown in FIG. Whether inputting with a tone such as "Zhong1 Guo2" or without inputting a tone such as "Zhong Guo", the input sound code is filtered to obtain the expression "3" for the word "China". Holds (in both C = 1 and C = 2), the word is found. This is the meaning of passing the filter in the processing of steps 63 and 64.

In the first mode, it is not always necessary to use the filter, and the input sound code and the sound code in the correspondence table may be directly compared. FILTER = F
If FFF is used, steps 63, 64 and equations 1 to 3 can be used as they are.

When a tone code string that matches the input tone code string (through a filter) is found (step 69), referring to FIG. 11, the variable find is incremented to specify the storage location of the Kanji code buffer. Kanji code KA (p stored in correspondence with the found sound code string
3) is read out from the phonetic code string / Kanji code correspondence table and stored in the memory location designated by the variable find of the Kanji code buffer (step 71).

Then, by using the second element F2 (k) of the index II table, the element F3 (k) of another storage location of the index II table that points to the note code string of the corresponding table having the same pronunciation. ), The corresponding kanji code having the same pronunciation stored therein is stored in the kanji code buffer after incrementing the variable find to specify a new storage location (step 73). ). The Kanji codes having the same pronunciation linked by the element F2 (k) are sequentially read out and stored in the Kanji code buffer (repeat steps 73 and 74). As a result, in addition to "Medium"
Will be found as a candidate for kanji.

When F2 (k) = p2 = φ is satisfied (step
72), a sound code string that includes and is longer than the input sound code string is searched using the element F1 (k) = p1. The Kanji code accessed by the element F3 (k) stored in the other (second) storage location in the index II table pointed to by the element F1 (k) is read from the correspondence table and the variable find is used. Is incremented and stored in the Kanji code buffer (step 76). Element F1 (k) of second memory location
If there are other memory locations linked by, in the same way, the element F3 of the further memory location described above.
The kanji code accessed by (k) is read and stored in the kanji code buffer (steps 75 to 7).
7). If F1 (k) = p1 = φ, all processing is finished (step 75).

Moreover, the binary search is repeated and finally START is started.
If + 1 ≧ END, it means that the sound code string corresponding to the input sound code string has not been found, and the Kanji search processing ends (step 53).

FIG. 17 shows a hardware architecture for realizing the above-mentioned processing, and shows an example of the configuration of the kanji search processing device 17.

The sound code string / Kanji code correspondence table 81 is the same as that shown in FIG. 12 or FIG. The retrieval / readout circuit 82 reads out the tone code sequence from this correspondence table sequentially or by referring to the input tone code sequence. In the filter register 83A, the data FFFF is
The data FEFC is stored in the register 83B. In response to the conversion mode selection by the conversion mode key 24, the multiplexer 84 selects the register 83A in the first mode and the register 83B in the second mode, and selects the filter data stored therein as A
It is given to the ND circuits 85 and 86.

In the AND circuit 85, the input tone code string is
The tone code strings read from the correspondence table 81 are given to the D circuits 86, respectively. The AND circuits 85 and 86 respectively filter the input sound code string and the sound code string, and the output data of them are compared in the comparison circuit 87. The comparison circuit 87 outputs the coincidence signal only when the two input data coincide. This match signal enables the gate 88. Further, the coincidence signal is given to the search and read circuit 82, and the search and read circuit 82 reads all the kanji codes corresponding to the matched sound chords from the correspondence table and gives them to the gate 88. Therefore, this kanji code passes through the gate 88. It will be stored in the Kanji code buffer 89.

In the above embodiment, the first mode and the second mode
There is a mode, and the Kanji search including the tone and ignoring the tone is performed by using the filters FFFF and FEFC, but it is also possible to perform the Kanji search of other modes by using other filters. it can. For example, if you use the filter 00FC in hexadecimal notation,
It will be possible to search for all kanji whose phonetic code matches the input phonetic code.

The input device is not limited to the keyboard but may be a device for inputting the pronunciation itself. In this case, a voice recognition device which converts an electric signal representing pronunciation into a corresponding sound code may be used.

[Brief description of drawings]

FIG. 1 is a block diagram showing an electrical configuration of a Chinese phonetic transcription / kanji conversion device.

FIG. 2 is a block diagram showing a hardware configuration of a main part of a Chinese phonetic transcription / kanji conversion device, or a configuration viewed from a functional point of view.

FIG. 3 shows an example of a Pin Yin / sound code conversion table.

FIG. 4 shows an example of a Zhu Yin / sound code conversion table.

5A shows a data format of a tone code, and FIG. 5B shows a code representing a tone.

FIG. 6 is a flow chart showing a procedure of input / edit processing.

FIG. 7 shows how key input data is stored in a key data buffer.

FIG. 8 shows how a sound code is stored in a sound code string buffer.

FIG. 9 is a flow chart showing a kanji search processing procedure.

FIG. 10 is a flow chart showing a kanji search processing procedure.

FIG. 11 is a flow chart showing a kanji search processing procedure.

FIG. 12 shows the structure of a dictionary.

FIG. 13 shows an example of a phonetic code string / Kanji code correspondence table.

FIG. 14 shows a Kanji code buffer.

FIG. 15 shows how a sound code is converted by filtering.

FIG. 16 shows a state of kanji search using a filter.

FIG. 17 is a block diagram showing the hardware architecture of a kanji search device or focusing on the function of kanji search processing.

[Explanation of symbols]

 10 Computer 12 Display control device 13 Character generator 14 Display device 15 Switching circuit 16 Edit processing device 17 Kanji search processing device 20 Keyboard 21 Pin Yin key 22 Zhu Yin key 23 Input mode key 24 Conversion mode key 25 Other function keys 30 Memory device 31 Pin Yin / Sound code 32 Zhu Yin / Sound code 33 Sound code / Pin Yin 34 Sound code / Zhu Yin 35 Dictionary 36 Data after conversion 81 Sound code string / Kanji code correspondence table 82 Search / read circuit 83A, 83B Filter・ Register 84 Multiplexer 85, 86 AND circuit 87 Comparison circuit 88 Gate 89 Buffer

Claims (21)

[Claims] 1. An input device capable of inputting Chinese pronunciations according to a plurality of types of notations, and a plurality of types of notations that can be input using the input device, respectively, and input data according to each notation is provided. , A plurality of conversion tables for converting into a sound code corresponding to the pronunciation represented by the input data, a dictionary storing the sound code and the Kanji code indicating the Kanji having the pronunciation represented by the sound code in association with each other, And control means for converting the input data input from the input device into a sound code using any of the plurality of conversion tables and searching the dictionary for a Kanji code corresponding to the converted sound code. Chinese phonetic transcription / kanji conversion device. 2. An input mode selection means for selecting one of a plurality of types of notation is further provided, and the control means inputs using a conversion table relating to the notation selected by the input mode selection means. The apparatus according to claim 1, which converts data into sound codes. 3. The apparatus according to claim 1, wherein the control means determines a notation based on input data input from the input device, and selects a conversion table to be used according to the determination. 4. The input device comprises a device for converting an input voice into an electric signal and a voice recognition device for recognizing pronunciation based on the voice electric signal and converting the input voice into a sound code. The apparatus according to Item 1. 5. The method according to claim 1, further comprising means for converting the retrieved Kanji code into display data representing the Kanji indicated by the Kanji code, and a device for displaying the Kanji based on the display data. apparatus. 6. The apparatus according to claim 5, further comprising: a designation input means for designating one of the displayed kanji candidates, and a memory for storing a kanji code indicating the designated kanji. . 7. Each of the conversion tables converts input data into a phonetic code for one Kanji character, and the dictionary associates a phonetic code string and a Kanji code with each other for a word consisting of one Kanji character or a plurality of Kanji characters. The control means divides the input data input from the input device into each kanji character and converts it into a sound code, and arranges the converted sound code in word units to create a sound code string. The device according to claim 1, wherein the dictionary is searched for a Kanji code corresponding to this phonetic code string. 8. Further comprising filtering means for masking a predetermined one or a plurality of bits constituting a sound code,
The control means filters the sound code corresponding to the input data and the sound code of the dictionary by using the filtering means, and then compares the sound code corresponding to the input data with the sound code corresponding to the input data. The apparatus of claim 1, located in. 9. A conversion means for converting input data representing a Chinese pronunciation into a sound code corresponding to the pronunciation.
From a dictionary in which a phonetic code and a kanji code indicating a kanji having a pronunciation represented by the phonetic code are stored in association with each other, filtering means for masking a predetermined one or more bits constituting the phonetic code, and the conversion means The obtained sound code and the sound code in the dictionary are filtered by the filtering means and compared with each other, thereby searching the sound code in the dictionary for a sound code that matches the sound code obtained from the conversion means, and matching the sound code. A Chinese phonetic transcription / Kanji conversion device comprising control means for reading out a Kanji code corresponding to a phonetic code from the dictionary. 10. The apparatus according to claim 9, wherein the phonetic code includes a bit representing a voice vowel, a bit representing a claw vowel, and a bit representing a tone. 11. The apparatus according to claim 10, wherein said filtering means masks a bit representing a vocal vowel, a bit representing a vowel or a bit representing a tone. 12. The apparatus according to claim 9, wherein the filtering means includes one that allows a sound code to pass through. 13. The apparatus further comprises an input device capable of inputting Chinese pronunciations according to a plurality of types of notations, and the conversion means is provided for each of a plurality of types of notations that can be input using the input device. 10. The apparatus according to claim 9, further comprising a plurality of conversion tables for converting input data according to each notation into sound codes corresponding to pronunciations represented by the input data. 14. The apparatus according to claim 9, wherein the conversion means is a voice recognition means for recognizing a pronunciation based on a voice input signal and outputting a sound code corresponding to the pronunciation. 15. The apparatus according to claim 9, further comprising search mode selection means for selecting whether to use the filtering means or to select one of the plurality of filtering means. 16. An input mode selecting means for selecting one of a plurality of types of notation is further provided, and the converting means inputs using a conversion table relating to the notation selected by the input mode selecting means. 14. The device according to claim 13, which converts data into phonetic chords. 17. The method according to claim 9, further comprising means for converting the read Kanji code into display data representing the Kanji indicated by the Kanji code, and a device for displaying the Kanji based on the display data. Equipment. 18. The apparatus according to claim 17, further comprising a designation input means for designating one of the displayed kanji candidates, and a memory for storing a kanji code indicating the designated kanji. . 19. The conversion means converts input data for one Chinese character into a phonetic code, and the dictionary stores a phonetic code string and a Chinese character code in association with one Chinese character or a word consisting of a plurality of Chinese characters. The control means controls the conversion means so that the input data is divided into each kanji and converted into a sound code, and the converted sound code is arranged in word units to create a sound code string. 10. The apparatus according to claim 9, wherein the dictionary is searched for a kanji code corresponding to this phonetic code string. 20. Chinese pronunciation can be input according to a plurality of types of notations, and for each of the plurality of types of notations that can be input, the input data according to each notation corresponds to the pronunciation represented by the input data. A plurality of conversion tables for converting to sound codes, and sound codes,
Prepare a dictionary that stores the Kanji code that indicates the Kanji that has the pronunciation represented by the phonetic code in correspondence with each other, and convert the input data to a phonetic code using one of the above conversion tables A phonetic transcription / kanji conversion method for Chinese, in which a kanji code corresponding to the selected phonetic code is searched in the dictionary. 21. A dictionary in which a phonetic code and a Kanji code indicating a Kanji having a pronunciation represented by the phonetic code are stored in association with each other is prepared in advance, and input data representing the Chinese pronunciation is stored. , Converted to the sound code corresponding to the pronunciation, and the sound code obtained by the conversion,
The sound code in the dictionary is filtered by masking one or more bits that make up the sound code and then compared with each other, and a sound code matching the sound code obtained by the conversion is searched in the dictionary. Then, the Chinese phonetic transcription / Kanji conversion method that reads the Kanji code corresponding to the matching phonetic code from the above dictionary.