JPH096762A - Device and method for converting kanji for chinese - Google Patents

Abstract

PURPOSE: To improve conversion efficiency and input speed by performing suitable clause partition in the case of a Chinese character (KANJI) converting input due to the phonetic symbol input of Chinese. CONSTITUTION: A phonetic symbol sequence to be the reading of a KANJI string composed of plural clauses to be inputted is inputted from a key input part 1. A CPU 2 partitions the phonetic symbol sequence into respective clauses while referring to a conversion dictionary 8 based on the inputted phonetic symbol sequence and outputs a KANJI string to be a candidate for each clause onto a display part 4. Besides, when partitioning the phonetic symbol sequence into the respective clauses, the CPU 2 retrieves the conversion dictionary 8 so that the sum of characters in the KANJI strings respectively corresponding to two continuous clauses can be maximum. In this case, a long KANJI string corresponds to the second clause, there is possibility for the first clause to be partitioned at the first character. Therefore, possibility to perform clause partition according to the grammer of Chinese having possibility for the first clause to be defined as one clause at the first character is improved.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a Chinese-Kanji conversion apparatus and Chinese-Kanji conversion method for converting a phonetic symbol string input from a keyboard capable of inputting phonetic symbols into Kanji in Chinese input processing. Regarding

[0002]

2. Description of the Related Art Generally, in the process of inputting Chinese characters, a phonetic symbol (Pinyin) string composed of alphabets is input, and a kanji corresponding to the input phonetic symbol string is retrieved from a dictionary and output. It is like this. That is, similar to the input processing of Japanese characters, in the input processing of Chinese characters, a Kanji conversion device (so-called FEP (front end)
processor)) is required.

Conventionally, in a kanji conversion device for Chinese,
If a phonetic symbol string corresponding to a Kanji string consisting of multiple Kanji phrases is input and then converted collectively, the dictionary is searched and the corresponding Kanji phrase is sequentially converted from the beginning of the phonetic symbol string. It is supposed to do.

At this time, first, a dictionary is searched for a kanji idiom corresponding to the beginning of an arbitrary length of the phonetic symbol string.
Then, when a plurality of Kanji phrases are searched and the searched Kanji phrases have different numbers of characters, the long Kanji phrase having the largest number of characters is preferentially selected. The beginning portion of the phonetic symbol string corresponding to the selected kanji compound word is set as one bunsetsu.

Next, in the phonetic symbol string excluding the head part corresponding to the kanji idiom retrieved from the phonetic symbol string, the above-mentioned processing is performed and all the parts of the phonetic symbol string are converted into kanji. The above process is repeated. In other words, when a phonetic symbol string corresponding to a Kanji string consisting of multiple Kanji compound words is collectively converted, the phonetic symbol string will be divided into multiple phrases in order from the beginning. The maximum number of characters in one bunsetsu is performed so that the number of characters in the kanji character string that makes up the character is maximized.

The above-mentioned maximum processing for the number of characters in one phrase is performed as follows. For example, in a kanji input device, a phonetic symbol string of "Chinese people" is displayed as "zhong gu o ur min min".
g "is input, and the following Table 1 is added to the dictionary.
It is assumed that the Kanji compound words shown in are registered.

[0007] In this case, "zhong guoo ren min
When a kanji string corresponding to the beginning part of an arbitrary length of “g” is searched from the dictionary, “medium”, “China”, “Chinese”, and “Chinese people” are included in the search range.

Here, since the bunsetsu is divided based on the kanji string having the largest number of characters among the kanji strings corresponding to the beginning part of the input phonetic symbol string of any length, "Chinese people"
Is a phonetic symbol string corresponding to "zhong guar
"en ming" is one clause.

[0009] Then, "zhong" is regarded as one clause.
If only Chinese people are registered in the dictionary as a kanji string corresponding to "guo ren ming", the Chinese people are output to the above phonetic symbol string.

Since there are many Kanji characters with the same sound, when the phonetic symbol string is divided into Kanji characters and converted into Kanji characters, many Kanji characters that are candidates are output in each divided portion. It takes a lot of time to select a desired kanji from the same kanji and it takes a long time for the conversion process.

Therefore, by dividing the phonetic symbol string into the longest possible phrases as described above, the number of kanji strings corresponding to each divided part can be significantly narrowed down. Labor saving the process of selecting
The time required for the conversion process can be reduced.

In the above-mentioned kanji conversion device, the phonetic symbol string is divided into bunsetsu, but it is divided into bunsetsu at a position different from the intended delimiter position of the bunsetsu, and the kanji string to be input is included in the conversion candidates. If not, the operator needs to change the segment delimiter position and perform the conversion process again.

Further, in the pronunciation of Chinese, even words represented by phonetic symbols of the same alphabet have different meanings depending on the pitch of pronunciation, and the kanji corresponding to these words also differ. There is. Therefore, in the phonetic symbols in Chinese, the phonetic symbols indicated by the above-mentioned alphabets are provided with tone symbols indicating the pitch up and down when being pronounced.

If a phonetic symbol with the above-mentioned tone symbol is input to the kanji conversion device, it is possible to reduce homonyms and improve conversion efficiency.
When a phonetic symbol with a tone symbol is input from the keyboard, a keyboard for Chinese phonetic symbols is required and the input speed is reduced.

The above-mentioned kanji conversion method is an example in which a phonetic symbol having no tone symbol is used.

The Kanji compound word is one Kanji string for one phonetic symbol string registered in the dictionary and is not necessarily the same as a Japanese compound word. For example, one phonetic symbol string in a dictionary. On the other hand, if one Kanji character is registered, this one Kanji character also becomes a Kanji compound word.

[0017]

By the way, in Chinese, a single kanji compound word is a subject (for example, me, etc.), a preposition (for example, is, through, or ...), and a negative word (for example, im ... ), As a modifier (for example, ...) It is highly likely that it will appear in the first phrase of one sentence, so the first phrase of the input character string is often a single character.

However, in the above-mentioned maximum processing of the number of characters in one bunsetsu, the number of characters in the leading bunsetsu of the input phonetic symbol string is determined based on the longest kanji compound word of the kanji compound words corresponding to the beginning part of the phonetic symbol string. Since it has been decided, there is a high possibility that the first phrase will be two or more characters.

Therefore, in terms of Chinese grammar, the first phrase is often one character, but in the conventional Chinese-Kanji conversion device, there is a high possibility that the first phrase will be two or more characters. The phrase break position may be incorrect.

That is, when a phonetic symbol string consisting of a plurality of clauses is input to the Chinese-to-Chinese character conversion apparatus described above, an inappropriate clause delimiter is performed as described above and the Chinese character to be input at the first conversion. There is a high possibility that a Kanji string different from the string will be output, resulting in a decrease in conversion efficiency.

Further, as described above, when the kanji character string different from the kanji character string to be input is output as a candidate because the punctuation position of the phrase is inappropriate, the kanji character string with the same sound is output from the dictionary for each verse. Even if you search, there is a high possibility that the kanji string with the same sound does not contain the desired kanji string. In this case, the Kanji character string to be input cannot be searched unless re-conversion is performed after changing the delimiter position of the bunsetsu, resulting in a decrease in input speed.

For example, in the conventional kanji conversion device, as a phonetic symbol string of "not knowing unknown", "zaibu zhi bu"
It is assumed that the user has entered "jue zhong". The correct bunsetsu "unknowingly unknown" is as follows when the bunsetsu segmentation position is indicated by :.

: Alive: Unknown Unknown: Medium: In addition, it is assumed that the kanji compound words shown in Table 2 below are registered in the dictionary.

[0024] In the conversion of the kanji conversion device in this case, the phonetic symbol string "zai bu z
The first phrase is divided based on the longest kanji string among the kanji strings of arbitrary number of characters registered in the dictionary corresponding to the head part of "hi bu ju zhong".

In this case, "zai bu zhi bu"
As the kanji character string corresponding to the beginning part of "jue zhong", the presence and the re-mistake are registered, but since the re-mistake has a larger number of characters, "zai bu" is regarded as the first phrase corresponding to the re-mistake. The kanji string that is the first candidate for the bunsetsu no kanji is rewritten.

Also, for the remaining phonetic symbol strings except the first bunsetsu, when the bunsetsu division and the kanji string which is the first candidate of each bunsetsu are output based on the above-mentioned one bunsetsu character number maximum processing, for example, It becomes a "re-branch section excellence".

Note that the phrase delimiter positions of the "non-re-branch species" are shown below. : Re: Branch: Absolute: (: zai bu: zhi bu: zhong :) As described above, when the first bunsetsu break position is inappropriate, the bunsetsu break position after that is also inappropriate. Next to
Kanji strings in each bunsetsu will not be converted correctly. In addition, as described above, even if the Kanji string corresponding to the Kanji string to be input is searched from the Kanji strings that are candidates for the same phoneme for each syllable of the phonetic symbol string, the target Kanji string may not be searched. Is high.

Therefore, it is necessary for the operator to change the phrase segmentation position to the correct position and perform the conversion again. An object of the present invention is to improve the conversion efficiency and the input speed of Kanji conversion input by performing phrase segmentation that matches Chinese grammar as much as possible in a Chinese character conversion device.

[0029]

According to a first aspect of the present invention, there is provided a kanji conversion device for Chinese characters in which a kanji character string corresponding to a phonetic symbol string is registered and a phonetic symbol string indicating the pronunciation of the kanji character string. The input means for inputting, and the conversion means for converting the input phonetic symbol string into a kanji character string for each phrase based on the dictionary and outputting the kanji character string. When it consists of multiple bunsetsu, the kanji string is searched from the above dictionary so that the sum of the number of characters in the kanji string converted from two consecutive syllabaries from the beginning of the input phonetic symbol string becomes the maximum. It is characterized by

In the Chinese character conversion method for Chinese according to claim 2 of the present invention, the inputted phonetic symbol string is converted into a Chinese character string based on a dictionary in which the phonetic symbol string and the Chinese character string are associated with each other. A method for converting Chinese characters in a Chinese-Kanji converting device for Chinese, wherein a first Chinese character string corresponding to the beginning portion of an input phonetic symbol string having an arbitrary length is searched from the dictionary and input. The second kanji string corresponding to the beginning part of the arbitrary length of the remaining phonetic symbol string excluding the part corresponding to the first kanji string retrieved from the phonetic symbol string is searched from the dictionary, and When a plurality of sets of one kanji string and a second kanji string are searched, the number of characters of the first kanji string and the second kanji string is selected from the plurality of sets of the first and second kanji strings. Select the first and second kanji strings that maximize the sum and select the selected first and second kanji strings. And outputs as a candidate Chinese character string to be input to string.

[0031]

According to the structure described in claim 1, the kanji character string is searched from the dictionary so that the number of characters of the kanji character string of each phrase is maximized in order from the beginning of the input phonetic symbol string as in the conventional case. Instead, the two kanji strings are searched from the dictionary so that the sum of the numbers of characters of the two kanji strings consecutive in order from the beginning of the input phonetic symbol string becomes the maximum.

Therefore, even if two or more Kanji idioms corresponding to the beginning portion of the input phonetic symbol string of any length are registered in the dictionary, depending on the length of the next clause, the phonetic symbol string may be generated. There is a possibility that a Kanji compound word of one character will be output as a candidate for the beginning part of, and the possibility that the Kanji compound word of one character will be converted to be at the beginning of the sentence will be higher than in the conventional Kanji conversion device.

Further, since the sum of the numbers of characters of two consecutive bunsetsu is maximized, even if the first bunsetsu is a single kanji idiom, the second bunsetsu becomes a long kanji idiom.
Since the ratio of long Kanji compound words to the whole sentence is large, select a Kanji compound word from a large number of homophone Kanji compound words registered in the dictionary corresponding to short phrases such as when the sentence is divided into short phrases. The input speed will not be reduced due to.

According to the configuration of claim 2, when a plurality of sets of the first and second kanji strings are searched, the maximum sum of the numbers of characters of the first kanji string and the second kanji string is the maximum. By selecting the first and second kanji character strings that are to be output and outputting the selected first and second kanji character strings as candidates for the kanji character string to be input, similar to the configuration according to claim 1, A kanji string that maximizes the sum of the numbers of characters of the two clauses is searched, and the conversion efficiency and the input speed can be improved.

[0035]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the Chinese character conversion device and Chinese character conversion method of the present invention will be described below with reference to the drawings. FIG. 1 shows a Chinese character conversion device of this embodiment. It should be noted that the Chinese-Kanji conversion device of this embodiment is incorporated in a computer system (for example, a general-purpose computer system, a word processor-dedicated machine, a computer typesetting system, or any other system) to input, for example, an ASCII code. It enables Chinese input to a computer system using a possible keyboard.

As shown in FIG. 1, the Chinese-Kanji conversion apparatus of this embodiment has a key input unit 1 capable of inputting Chinese phonetic symbols consisting of alphabets, and an input phonetic symbol for Chinese Kanji characters. CPU to convert to and output (central pr
ocessing unit) 2, a display memory 3 that stores the shape of characters such as phonetic symbols and Chinese characters output from the CPU 2 as image data (font data), and image data such as phonetic symbols and Chinese characters stored in the display memory 3. , A printing unit 5 for printing phonetic symbols and Chinese characters output from the CPU 2, data necessary for the processing of the CPU 2, such as the font data of the Chinese characters and phonetic symbols, and the CP.
External storage unit 6 for storing data output from U2
And a work memory 7 for temporarily storing data necessary for processing of the CPU 2 and data output from the CPU 2.
And a conversion dictionary 8 in which a phonetic symbol string and a Kanji compound word corresponding to the phonetic symbol string are registered.

The key input unit 1 is a so-called alphabet keyboard, and can input Chinese phonetic symbols without tone symbols. Also, the key input unit 1
Can input instructions such as conversion, change of segmentation position, and confirmation. The work memory 7 temporarily stores data necessary for converting phonetic symbols into kanji, and has an area as shown in FIG.

That is, the work memory 7 is necessary for searching the input buffer area IB in which the phonetic symbol string input from the key input unit 1 is stored and the conversion dictionary 8 of the input phonetic symbol string. And a search kanji character string region SC in which a kanji string of the first candidate searched based on the phonetic symbol string stored in the search pronunciation symbol region PY is stored. First phrase size area S1 in which the number of characters in the retrieved first phrase kanji string is stored
And a second bunsetsu size area S2 in which the number of characters in the searched second bunsetsu kanji string is stored, and when one or more sets of first and second bunsetsu kanji strings are searched, A clause size set stack area SK in which the clause sizes stored in the one clause size area S1 and the second clause size area S2 are stored, and a confirmed kanji character string area FC in which a confirmed kanji string is stored. Is secured.

The first phrase and the second phrase are the two phrases that are consecutive in sequence from the beginning of the input phonetic symbol string, and the first phrase is the first phrase and the second phrase is the second phrase. It is what The conversion dictionary 8 is a general kanji conversion dictionary. In Chinese, a kanji string used with a certain frequency is registered as a kanji compound word and corresponds to the registered kanji compound word. A phonetic symbol string that is the reading of the Kanji phrase is registered.

The conversion dictionary 8 also stores data such as the priority order of homophones and kanji compound words. The conversion dictionary 8 can be used to search for kanji compound words from phonetic symbol strings. It should be noted that the above-mentioned Kanji string and Kanji compound word include one Kanji character. That is, in the conversion dictionary, one kanji character is also registered as one kanji string (kanji compound word).

As will be described later, the CPU 2 searches the conversion dictionary 8 based on the phonetic symbol string input from the key input unit 1, divides the phonetic symbol string into phrases, and divides each phrase portion into Chinese characters. It has the function of converting to a column.

Next, a method of converting Chinese characters into Chinese characters by the Chinese character converting apparatus as described above will be explained. The flowchart of FIG. 3 illustrates the Chinese character conversion method for Chinese in this embodiment. In this embodiment, the Chinese character conversion method for Chinese is used to divide phonetic segments into Kanji characters by dividing the bunsetsu by the maximum processing of the number of two-segment characters described later. It is converted into and input.

First, in the Chinese character conversion method for Chinese,
The operator inputs a phonetic symbol string indicating the reading of a kanji string of an arbitrary number of characters to be entered from the key input unit 1 (step S1). Here, as shown in FIG. 6 (A), the phonetic symbol string "zai" is read as the reading of the Chinese character string "Absolutely unknown".
It is assumed that "buzijujuzhong" is input.

The phonetic symbol string input from the key input unit 1 is stored in the input buffer area IB as shown in FIG. Further, the phonetic symbol string stored in the input buffer area IB is stored in the display memory 3 with its shape information and displayed on the display unit 4 as shown in FIG. 6 (A). In FIG. 6, the inside of a rectangular frame shows the display on the display screen of the display unit 4.

Next, as shown in FIG. 6B, the operator inputs the (conversion) key to start the Kanji conversion process. First, the input phonetic symbol string is converted into a conversion dictionary 8
(Step S2), and it is determined whether or not the input phonetic symbol string can be converted into a kanji string based on the dictionary (step S3).

If a phonetic symbol string that cannot be converted into Kanji has been input, the process advances to step S19 to notify the operator of an input error and the process ends.
If the input phonetic symbol string can be converted into a Chinese character string, the process proceeds to the next maximum processing for the number of two-section lexical characters.

Then, the Kanji character string corresponding to the beginning portion of the input phonetic symbol string of an arbitrary number of characters is searched from the conversion dictionary 8 (step S4). Then, the number of characters in the kanji string (longest idiom) having the longest number of characters among the searched kanji strings is set as the number of characters in the first phrase, and this number of characters is stored in the first phrase size area S1 (step S5).

Here, "zaibuhibujuue"
It is assumed that the "re-non" searched from "zaibu", which is the beginning part of "zhong", is the longest idiom, and the beginning part "zaibu" corresponding to the longest idiom of the inputted phonetic symbol string is shown in FIG. As shown in A), the phonetic symbol string “zai” stored in the search phonetic symbol area PY is stored.
The first candidate kanji string (here, "re-non") among the homophone kanji compound words searched based on "bu" is searched and stored in the search kanji character string area SC.

Further, the number of characters 2 of the first phrase is stored in the first phrase size area S1. Next, when the phonetic symbol string of the first phrase is removed from the input phonetic symbol string, it is determined whether or not there are remaining phonetic symbol strings (step S6).

If there is no remaining phonetic symbol string, that is, if all of the inputted phonetic symbol strings are converted into one kanji string registered in the dictionary, the operator will have phonetic symbols for only one phrase. It's likely that you've entered a column, and it's unlikely that the bunsetsu delimiter is inadequate, so
It can be judged that it is not necessary to perform the following maximum processing for the number of two-segment characters.

Therefore, if there is no remaining phonetic symbol string, that is, if all of the inputted phonetic symbol strings are converted into one kanji string registered in the dictionary, this kanji string is used as a candidate kanji character. The column size is determined and the phrase size is determined (step S7), and the process proceeds to step S18.

The confirmation here does not mean to finally determine the kanji character string to be input, but to decide the candidate kanji character string to be presented to the operator as the first candidate. Therefore, when there is no remaining phrase, after the candidate kanji string of the first phrase is confirmed, the candidate kanji string is displayed on the display unit 4,
The operator will be asked to determine whether it matches the Kanji string to be entered.

When there are remaining phonetic symbol strings,
Next, it is determined whether or not the number of characters in the first phrase (first phrase size) is one character (step S8). If the first phrase size is one character, the process proceeds to step S7 as in the case where there is no remaining phonetic symbol string.

Then, the size of the first phrase is fixed to one character, and the kanji character string which is the first candidate for one character is fixed to the candidate kanji character string. In addition, this maximum processing of the number of characters in two phrases
When the correct first phrase size of the kanji string to be input is one character, it is to prevent the first phrase size from becoming two or more characters like the one phrase character number maximum process. If the first phrase size is set to one character, it is not necessary to continue the process for maximizing the number of characters in two phrases, so the process proceeds to step S18.

In addition, the phonetic symbol string "zaibuzhi"
In the case of “bujuezhong”, the kanji character string of the first bunsetsu is “re-non”, and there are remaining phonetic symbols, and since the number of characters in the first bunsetsu is 2, the process proceeds to step S9. Searches the conversion dictionary 8 on the basis of the beginning portion of the phonetic symbol string of any length other than the first phrase (step S9).

The number of characters in the kanji string (longest idiom) having the longest number of characters among the searched kanji strings is set as the number of characters in the second phrase, and this number of characters is stored in the second phrase size area S2. (Step S10). Here, the phonetic symbol string "z
"Kanji string searched from" zhibu "which is the head part of" zhibujuezhong "excluding aibu"
It is assumed that "Branch" was the longest phrase.

Then, as shown in FIG. 4B, the head part "zhibu" corresponding to the longest idiom of the inputted phonetic symbol string is stored in the search phonetic symbol area PY, and the stored phonetic symbol string "zhibu" is stored. The first candidate kanji string (here, the branch) of the homophone kanji compound words searched based on "is searched and stored in the search kanji character string area SC together with the above-mentioned" re-unsupport "as" re-support ".

Further, the number of characters 2 of the second phrase is stored in the second phrase size area S2. Then, the phrase sizes (S1, S2) of the first and second phrases are stored in the phrase size set stack area SK (step S11).

Here, as shown in FIG.
Is stored in the phrase size group stack area SK. next,
1 is subtracted from the phrase size (S1) of the first phrase to make it the size of the first phrase (step S12).

Then, it is determined whether or not the size of the new first phrase becomes 0 (step S13). Note that, here, since the case where the first phrase size is already one character is excluded, the size of the first phrase never becomes 0, but since the process of step S12 is repeated, The size of the first phrase becomes 0.

Also, here, the first phrase is "re-unavailable" and the first phrase size is 2, so the first phrase size is 1. If the first phrase is not 0, the conversion dictionary 8 is searched for a kanji string having the number of characters of the first phrase size and corresponding to the beginning portion of the input phonetic symbol string of any length. S14).

Next, it is determined whether or not the Kanji string satisfying the above conditions has been retrieved from the conversion dictionary 8 (step S15). If the kanji string cannot be retrieved, step S1
Returning to step 2, the process after step S12 of subtracting 1 from the first phrase size is repeated.

Here, the phonetic symbol string "zaibuz" is used.
It is assumed that the presence "zai" is searched as a Kanji compound word of one character corresponding to the beginning part of "hibujuezhong". And the beginning part "zai" corresponding to the first phrase size (1) of the input phonetic symbol string. Is stored in the search phonetic symbol area PY as shown in FIG. 4C, and the kanji string which is the first candidate among the homophone kanji idioms searched based on the stored phonetic symbol string "zai" (here Then "A"
Is stored in the search kanji character string area SC.

The number 1 of characters of the first phrase is stored in the first phrase size area S1. Then, when the Chinese character string of the above condition can be retrieved from the conversion dictionary 8 as described above, the process returns to step S9 to retrieve the second phrase, and the processes from step S9 are repeated.

That is, in step S9, the remaining phonetic symbol string "buzhib" excluding the first phrase "zai".
The conversion dictionary 8 is searched for a kanji string corresponding to the beginning part of an arbitrary length of "ujuezhong". Next, step S
The number of characters in the kanji string (longest idiom) having the longest number of characters among the kanji strings searched in 10 is set as the number of characters in the second phrase, and this number of characters is stored in the second phrase size area S2.

Here, "buzhibujuzeho"
It is assumed that "ignorance unknowingness" retrieved from "buzhibujue" which is the head part of "ng" is the longest idiom, and the head part "buzhibujue" corresponding to the longest idiom of the inputted phonetic symbol string is shown in FIG. As shown in (D), the kanji string that is the first candidate among the homophone kanji compound phrases stored in the search phonetic symbol area PY and searched based on the stored phonetic symbol string "buzhibujue" (here, "unknown"). Search "Kaku""and search Kanji character string area S
It is stored in C as "absence" together with "absence".

The number of characters in the second phrase, 4 is stored in the second phrase size area S2. Then, in step S11, new first and second phrase sizes (S1, S2) are additionally stored in the phrase size set stack area SK.

Here, as shown in FIG. 5D, in addition to the first 2 and 2, 1 and 4 are the phrase size group stack area SK.
Stored in. Next, in step S12, 1 is subtracted from the first phrase size. Here, the first phrase is "
Since the phrase size is 1 and the phrase size is 1, the first phrase size becomes 0 when 1 is subtracted, so step S1
Proceed to 6.

If the first phrase size is not 0, the above process is repeated again. Then, from the first and second phrase sizes registered in the phrase size group stack area SK, the first and second phrase sizes having the largest sum of the first phrase size and the second phrase size are obtained and obtained. Based on the first and second phrase sizes, the number of characters in the candidate kanji string of the first phrase and the number of characters in the candidate kanji string of the second phrase are determined (step S16).

Here, the sum of the first phrase size and the second phrase size in the case of "re-unknown: branch" is set to 2 + 2 = 4, and the first phrase size and the second phrase in the case of "presence: ignorance". The sum of the sizes is 1 + 4 = 5. Therefore, when the sum of the first bunsetsu size and the second bunsetsu size is "5", the sum of the bunsetsu sizes is the largest, so the first bunsetsu size is "
1 "and the second phrase size is" 2 ".

Next, in the first phrase and the second phrase, the kanji character string having the determined phrase size and having the highest priority in the conversion dictionary is selected from the kanji character strings corresponding to the phonetic symbol strings. , Is determined as a candidate kanji string (step S17).

In this case, since "absence: ignorance unawareness" is the first candidate of the first bunsetsu and the second bunsetsu in the bunsetsu size, "absence: ignorance unawareness" is a candidate kanji string for the first and second bunsetsu. It is confirmed and stored in the confirmed kanji character string area FC as shown in FIG.

Next, it is determined whether or not there are remaining phonetic symbols in the first phrase and the second phrase (step S18).
If there are remaining phonetic symbols, the process returns to step 4, and the same process as the above-described process performed on the inputted phonetic symbol string is performed.

If there is no remaining phonetic symbol string,
It is assumed that the phrase sizes of all the phrases of the input phonetic symbol string and the candidate kanji strings of each phrase have been fixed (step S18).
Proceed to. If there is no remaining phonetic symbol string, all the phonetic symbol strings input in step S6 are converted into one kanji string and it is determined that there is no phonetic symbol string remaining. This also includes the case where the bunsetsu size of the bunsetsu and the candidate kanji character string are confirmed and the process proceeds to step S18.

Here, the input phonetic symbol string "zai" is input.
The bunsetsu sizes and candidate kanji strings of the first and second bunsetsus of "buzhijujuzhong" are determined. That is, "zaibuzhibuj" of the above phonetic symbol strings.
up to ue ”is established, and the phonetic symbol string“ zhong ”remains. Therefore, the process returns to step S4, and at step S4, the phonetic symbol string“ zhong ”of any length is selected. The conversion dictionary 8 is searched for the Kanji string corresponding to the head portion.

Here, it is assumed that the Chinese character string "middle" is searched for the phonetic symbol string "zhong", and the Chinese character string longer than the single character Chinese character string is not searched. In this case, it is determined in step S6 that there is no remaining phonetic symbol string, and in step S7 the phrase size and candidate of the first phrase of the remaining phonetic symbol string (the third phrase of the input phonetic symbol string). The kanji string is confirmed, and the process proceeds to step S18.

That is, as shown in FIG.
"Medium" is confirmed and this "Medium" is confirmed Kanji character string area FC
In addition to the above "absence of ignorance", it is stored as "during ignorance". Then, even in step S18, it is determined that there is no remaining phonetic symbol string, and the process proceeds to step S19.

When the phrase sizes of all the phrases of the inputted phonetic symbol string and the candidate kanji strings of each phrase are confirmed, the candidate kanji strings are displayed on the display unit 4 as shown in FIG. 6 (B).
Is displayed (step S19). Then, when the displayed candidate kanji string matches the kanji string to be input, the operator confirms the displayed candidate kanji string to end the input of the kanji string.

If the candidate Kanji string does not match the Kanji string to be input, the target Kanji string is searched from the other candidate Kanji strings for each phrase, or the phrase position is changed. It is necessary to re-convert it. As mentioned above,
According to the Chinese-Kanji conversion device and Chinese-Kanji conversion method of this embodiment, when determining the phrase of the converted Kanji string for the input phonetic symbol string, the phrase size of the first phrase and two Since the bunsetsu is determined so that the sum of the bunsetsu size and the bunsetsu size is maximized, the first bunsetsu is not always the longest one based on the kanji string registered in the dictionary. Instead, there is a high possibility that the first phrase will be a single Kanji compound word consisting of a single Kanji string.

In the Chinese grammar, a single kanji compound as a noun, a single kanji compound as a preposition, a negative kanji compound or a modifier, a single kanji at the first paragraph of a sentence. Idioms are often arranged. And
In the conventional maximal processing of the number of characters in one bunsetsu, when a kanji string corresponding to the beginning part of the input phonetic symbol string is searched from the dictionary, a kanji string of two or more characters may be searched in the first bunsetsu of the sentence. Is high.

On the other hand, in the case of this embodiment, since the length of the second bunsetsu as well as the first bunsetsu is analyzed as described above, the first bunsetsu is a kanji string of one character and a kanji string of two or more characters. Even if and can be searched, if the long kanji string can be converted to the second phrase when the first phrase is one character, the first phrase may be a one-character kanji string.

Particularly, in the inputted phonetic symbol string, when it is grammatically appropriate that the first phrase is a one-character phrase, the first phrase is set to one character so that the start position of the second phrase can be changed. Since it is in the correct position, it is more likely that a traditional long kanji string registered in the dictionary will be assigned to the second phrase, but if the first phrase is made up of two or more characters, Since the start position is incorrect, it is unlikely that the corresponding long kanji string is registered in the dictionary, and the short kanji string will be searched as a candidate kanji string for the second phrase. .

Therefore, in the inputted phonetic symbol string,
When it is grammatically valid to make the first phrase a single-character phrase, the phrase size of the first phrase and the first phrase can be one character and two or more characters. Comparing the size of the sum of the second bunsetsu and the bunsetsu size, it is more likely that the sum of the bunsetsu sizes will be larger when the first bunsetsu is one character. Therefore, if it is correct in the Chinese grammar that the first phrase is one character, the first phrase is likely to be one character when the above-described two-phrase character number maximum process is used.

From the above, the kanji conversion device of this embodiment is more effective than the conventional kanji conversion device when the correct phonetic symbol string is input when the first phrase is one character.
The conversion efficiency can be improved because the first phrase is made up of two or more characters and the conversion efficiency is less likely to decrease.

Further, according to the kanji conversion device of this embodiment, although it is correct to make the first phrase one character as in the conventional kanji conversion device, the first phrase is made up of two or more characters, and as described above. There is no need to change the bunsetsu delimiter position and delay the input process of Kanji, in order to match the candidate Kanji string with the Kanji string that should be input. As a result, the input speed can be increased. In the above embodiment, the phonetic symbols have no tone code, but tone symbols may be used.

[0086]

According to the Chinese-Kanji conversion device of the first aspect of the invention, the bunsetsu delimiter position is set for each two consecutive bunsetsus from the beginning of the inputted phonetic symbol string, and at the same time, two bunsetsus are set. The bunsetsu delimiter positions are set so that the sum of the numbers of characters in the kanji strings registered in each dictionary that applies to each bunsetsu is maximized, so the maximum number of characters in the kanji string registered in a dictionary that applies to one bunsetsu is maximized. Compared with the processing, the probability of applying a one-character kanji string to the first phrase is higher.

Therefore, it is possible to divide the bunsetsu according to the Chinese grammar in which it is highly likely that one kanji compound word comes in the first bunsetsu of the sentence, and the correct one bunsetsu size of the input phonetic symbol string is one character. , It is less likely that the first paragraph will be more than one character at the time of conversion, improving the conversion efficiency and reducing the possibility that the operator has to change the bunsetsu delimiter position at the time of conversion to improve the input speed. be able to.

According to the Chinese character conversion apparatus for claim 2 described above, like the Chinese character conversion apparatus for Chinese according to claim 1, the number of consecutive two-section characters from the beginning of the phonetic symbol string to be input. Since the clauses are set so that the sum of is maximum, the conversion efficiency and the input speed can be improved.

[Brief description of drawings]

FIG. 1 is a block diagram showing a basic configuration of a Chinese-Kanji conversion device according to an embodiment of the present invention.

FIG. 2 is a drawing for explaining a work memory of the Chinese character conversion device of the embodiment.

FIG. 3 is a flowchart for explaining a Chinese character conversion method in the Chinese character conversion apparatus.

FIG. 4 is a diagram for explaining a storage state of data in a work memory of the Chinese character conversion device.

FIG. 5 is a diagram for explaining a data storage state in a work memory of the Chinese-Kanji conversion apparatus.

FIG. 6 is a diagram for explaining a Chinese character conversion operation in the Chinese character conversion apparatus.

[Explanation of symbols]

 1 key input unit (input means) 2 CPU (converting means) 8 conversion dictionary (dictionary)

Claims (2)

[Claims] 1. A dictionary in which kanji strings are registered corresponding to phonetic symbol strings, input means for inputting phonetic symbol strings indicating pronunciation of kanji strings, and input phonetic symbol strings based on the dictionary. And a conversion means for converting and outputting each kanji character string. When the kanji character string to be converted is composed of a plurality of clauses, the conversion means continuously from the beginning of the inputted phonetic symbol string. A Chinese character conversion device for Chinese, which searches a Chinese character string from the above dictionary so that the sum of the numbers of characters of the Chinese character string converted from each of the two clauses becomes maximum. 2. A Chinese-Kanji conversion method for a Chinese-Kanji conversion device for converting an inputted phonetic symbol string into a Kanji string based on a dictionary in which a phonetic symbol string and a Kanji string are associated with each other. In addition to searching the first kanji string corresponding to the beginning part of the input phonetic symbol string of any length from the above dictionary, the first kanji string searched from the input phonetic symbol string The dictionary is searched for a second Kanji string corresponding to the beginning part of the phonetic symbol string of any length excluding the corresponding part, and multiple sets of the first Kanji string and the second Kanji string are combined. From these multiple sets of first and second kanji strings, the first and second kanji strings that maximize the total number of characters in the first and second kanji strings when retrieved Select and output the selected first and second kanji strings as candidates for kanji strings to be input. Chinese for Kanji conversion method comprising the door.