JPH06290183A - Kanji conversion device - Google Patents

Abstract

PURPOSE:To improve the efficiency for correct conversion into the KANJI (Chinese syllabary writings) required by a user of the KANJI conversion device for preparing the Chinese sentences. CONSTITUTION:The syllable in which one of the inputted phonetic character string is not converted, is segmented as the object of the next KANJI conversion. Then, a dictionary retrieval section 17 retrieves whether or not the corresponding word is in a direction, by taking the syllable as a retrieval key. If there is no corresponding word, a consecutive word detecting section 20 detects whether or not the 1st syllable is consecutive characters such a preposition or conjunction. If it is the consecutive word, a dictionary retrieval section 17 takes the 2nd synllable as a retrieval key and retrieves whether or not word comprising the word having more number of KANJIs by integrating with the consecutive word in a dictionary section 18. If such a word is found, an expansion word generation section 19 combines the corresponding word with the consecutive word to make an expansion word with more KANJIs. Then, a conversion processing section 16 converts the expansion word into KANJI in prior to the word retrieved by the dictionary.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a kanji conversion device for converting a phonetic character string into kanji.

[0002]

2. Description of the Related Art There are more than 10,000 Chinese characters used in Chinese sentences. The most important issue in Chinese computer processing including a Chinese word processor is how to correctly and quickly input Chinese characters intended by Chinese sentence creators and to convert them into Chinese characters. Next, as conventional input means for the intended kanji conversion device, there are voice recognition, character recognition, a keyboard and the like. Of these, keyboard input is the most reliable, and therefore it is widely used.
Now, the kanji input method using the keyboard can be divided into the kanji reading input method and the kanji character input method. By the way, the former character-shaped input method requires that the input rules be memorized in advance, and that it requires a considerable amount of time for memorization and it takes time to get used to. On the other hand, the kanji reading input method is widely used in Japanese word processors, and it is natural and easy to learn, so it is expected to become the mainstream kanji input method in the future. The present invention also relates to a kanji conversion device that employs this reading-based input method.

By the way, as a conventional kanji conversion device using this reading as an input, for example, patent application number 7 of the Republic of China
There is one such as shown in 5105838. Figure 6
Is a block diagram of this kanji conversion device. In this figure, 1
00 is the Chinese sound that the Chinese text creator intended to convert to Kanji,
It is an input unit for inputting phonetic characters such as note and romaji, and can input any length (phonetic character number). 18
Reference numeral 0 denotes a dictionary unit in which a phonetic character string and a word for conversion corresponding thereto are registered (permanently stored) in association with each other. If more than one Chinese word corresponds to the same phonetic character string, the total number of strokes of the Chinese word, frequency of use, and if it consists of a single Kanji, the frequency of use of that Kanji, the order of character codes, etc. They are arranged according to each other, and they are converted in this order of priority. Of course, if the conversion result is not intended by the input person, the words and kanji of the next rank are output by a separate operation, as in the Japanese word processor. By the way, a phonetic character string is given a "string" because it is a principle that a plurality of phonetic characters are converted into one word or kanji character by their nature. It is a concept that also includes phonetic characters. This also applies to syllable strings and the like which will be described later. In addition, the word includes one kanji character and is not necessarily limited to a Chinese word such as “Japan” or “Tokyo”. Reference numeral 140 is an NCHAR register that stores the number of syllables of the input phonetic character string.
Reference numerals 120 and 130 respectively denote a PTR register and an NP register used when converting a phonetic character string into a word, and the PTR register 120 stores from which position of the input phonetic character string the kanji conversion is performed. , The NP register stores the converted word length when converting the input phonetic character string into words, that is, the number of kanji or syllables that compose the word (in Chinese, one kanji character is one syllable in principle). To do. 150 is the above N after the conversion processing of all the words having a certain length or the number of constituent kanji is performed.
This is a comparison unit that operates the conversion control unit so that when the value of the P register 130 is decreased by 1, the word having the next smaller number of Kanji characters is converted into Kanji with priority.
The reference numeral 160 is based on the number of constituent kanji, that is, the number of syllables of the word to be converted set in the NP register 130 by sequentially shifting the set position of the PTR register 120 backward from the first position of the input phonetic character string. It is checked whether or not there is a kanji-converted syllable, and if none of them have been converted yet and the corresponding word is registered in the dictionary unit 180, it is converted to the corresponding word. It is a conversion control unit. A dictionary search unit 170 searches the dictionary unit 180 using the syllable string sent from the conversion control unit 160 as a key. 190 is an output unit that outputs the result converted by the conversion control unit 160.

With the above configuration and operation, the Chinese word corresponding to the phonetic character string input by the input unit is the longest matching method, that is, first, the number of Chinese characters constituting the word is given priority, and second is input first. The converted syllables are sequentially converted into and displayed in kanji by the method of giving priority, and eventually Chinese sentences are created.

[0005]

However, in the Kanji conversion apparatus as described above, the words registered in the dictionary are used as the conversion unit and are converted by the longest matching method.
Therefore, the candidate words have the same length (the number of kanji that make up),
In addition, when a syllable in the input phonetic character string forms two corresponding words (preceding word and subsequent word) with the preceding and following syllables, respectively, the word corresponding to the preceding syllable entered earlier (Preceding word) is preferentially converted, and after converting the word, the syllable corresponding to the succeeding word is converted into a syllable excluding the syllable common to the preceding word, and in many cases, conversion is performed in units of one kanji character. Become. In this case, since the converted syllables are converted into Kanji characters, the following erroneous conversion occurs in the arrangement of Kanji characters for the same syllable in the dictionary. For example, when trying to enter "Yuichiten",
There is a kanji "Masu" with the same pronunciation as "I", so that the phonetic character string corresponding to the input "Yuichiten" has the words "beneficial" and "Iten". Therefore, the preceding word "beneficial" is preferentially converted, and after that, "heaven" is converted, so that an erroneous conversion of "beneficial heaven" occurs. In addition, when trying to output "murder-correction criminal", there is a kanji "Han" which has the same pronunciation as "criminal", and a kanji "show" which has the same pronunciation as "ye". Since the word "exemplary" constitutes the words before and after "exemplary" and "crime," the preceding word "exemplary" is converted first, and the same pronunciation as the kanji for "sin" is given. Since the kanji for "is" is present and arranged so that it is converted in preference to "sin", an erroneous conversion of "killer exemplification" will occur. In addition, the Chinese sentence "that feature" can be converted into the wrong "odd special conquest". On the other hand, it is practically difficult to register all the Chinese sentences that may cause such conversion in the dictionary. Therefore, it has been desired to realize a kanji conversion device capable of preventing such erroneous conversion. The present invention has been made for the purpose of solving such problems.

[0006]

In order to achieve the above object, the present invention first converts a syllable or a part of the syllable of an input phonetic character string that has not been converted into a word having the maximum number of characters. The second priority is to convert the previously input syllables, and then the number of syllables to be converted is successively reduced, and the syllables to be converted are sequentially shifted backward. A syllable segmentation unit for segmenting a syllable string to be converted, a dictionary unit in which phonetic character strings and Chinese words corresponding thereto are registered in advance, and a syllable to be converted segmented by the syllable segmentation unit. If the first syllable is a conjunctive character in the dictionary search unit that searches the dictionary unit to detect Chinese words by using the string as a search key, and in the syllable string that is the conversion target that is cut out by the syllable cutout unit. When a compound word detecting unit that detects the compound character in a fixed procedure and the corresponding compound character detecting unit detects the compound character, the second syllable of the syllable string that is currently the conversion target is used as the search key. The dictionary search unit searches the dictionary unit, and if there is a corresponding word, the extended word generation unit that generates the extended word having a larger number of constituent kanji by combining the compound word and the word, and the extended word generation unit. And a conversion processing unit that controls to convert the expanded word into a Kanji character prior to the word searched by the dictionary searching unit.

[0007]

With the above-described structure, the present invention gives priority to first converting the syllabic segmentation unit into a word having the maximum number of characters for the input phonetic character string that has not been converted or a part of the syllable. Secondly, the number of syllables to be converted is successively reduced while giving priority to the conversion of previously input syllables,
In addition, the syllables are sequentially shifted backward to cut out a syllable string that is the current target of kanji conversion. Phonetic character strings and corresponding Chinese words are registered in advance in the dictionary. The dictionary search unit searches the dictionary unit for a corresponding Chinese word using the syllable string cut out as a search key. In the syllable string to be converted, which is cut out by the syllable cutout unit, the compound word detecting unit detects the compound character in a predetermined procedure if the first syllable is a compound character. When the expanded word generation unit detects the corresponding collocation character by the collocation character detection unit, the dictionary search unit is searched by the dictionary search unit using the second and other syllables of the syllable string to be currently converted as search keys. , If there is a corresponding word, the compound word and the word are combined to generate a longer extended word. The conversion processing unit converts the expanded word generated by the expanded word generation unit into Kanji with priority over the word searched by the dictionary search unit.

[0008]

EXAMPLES The present invention will be described below based on examples.
FIG. 1 is a block diagram of an embodiment of a kanji conversion device according to the present invention. 2 to 4 are process flow charts of this embodiment. In FIG. 1, reference numeral 10 denotes an input unit for a Chinese sentence creator to input phonetic characters such as Chinese characters intended to be converted, syllabary sounds corresponding to sentences, peep sounds, and Roman characters. Reference numeral 18 denotes a dictionary unit in which phonetic character strings and Chinese words corresponding to the phonetic character strings are registered (previously permanently stored). When there are a plurality of words in one phonetic character string, these words are arranged in descending order of frequency of use, which gives priority to Kanji conversion. Reference numeral 14 is an NCHAR register representing the number of syllables of the input phonetic character string. In addition, since one Chinese character corresponds to one syllable in Chinese, the number of syllables of the input phonetic character string is the number of Chinese characters to be converted. 1
Reference numerals 2 and 13 respectively denote a PTR register and an NP register used when converting a phonetic character string into a word. Here, the PTR register 12 stores the conversion position from which position of the input phonetic character string the Kanji conversion is performed. N
The P register 13 stores the word length to be converted when converting the input phonetic character string into words, that is, the number of Chinese characters and syllables that compose the word. That is, if the contents of the above two registers are ptr and np, respectively, it means that np consecutive syllables from the ptr-th syllable of the input phonetic character string are search keys at the time of dictionary search ( Hereafter, nchar, np, ptr, and the nch that appears later
Let ar represent the values of the NP, PTR and NCHAR registers respectively). Reference numeral 11 is a register initialization unit. Although the details of the operation will be described later, the number of syllables nchar of the input phonetic character string is calculated, and the value is set in the NCHAR register 14, and if the value is registered in the dictionary unit 18. When the longest word, that is, the number of kanji of the most composed kanji is larger than max (8 in this embodiment), the above max is NP.
If the number is 8 or less in the register 13, the number of syllables of the input phonetic character string is set in the NP register 13, and the value of the PTR register 12 is set to 1. 15
Constantly checks whether (np + ptr)> (nchar + 1) is established, and if it is established, the value of the NP register 13 is decremented by 1 and the value of the PTR register 12 is re-set by 1.
Is a comparison unit set to. As a result, a word having one less Kanji character is subjected to Kanji conversion, and a word with the target number of Kanji characters is Kanji converted from the beginning of the input phonetic character. Reference numeral 21 is a compound word dictionary section for reading a special compound word and storing the character. 20
Is a compound word detecting unit that searches the compound word dictionary unit 21 using the ptr-th syllable of the input phonetic character string as a search key. When the compound word detecting unit 20 detects that there is a corresponding compound character, the dictionary searching unit 19 uses the np-1 syllables from the ptr + 1th phonogram of the input phonetic character string as a search key. Whether or not the corresponding word is registered in the dictionary unit 18 is searched, and if the corresponding word is registered, the input person originally intends to convert the word by combining the corresponding word with the compound word. This is an expanded word generation unit that generates a word that is being expanded, that is, an expanded word. Reference numeral 16 is a conversion processing unit. Although the detailed operation will be described later, of the inputted phonetic character strings, ptr-th consecutive np syllables are inspected for already converted syllables, and if there is a converted syllable, The value of the PTR register 12 is set to 1 in order to process the unconverted syllable in the rear.
Increase, if there are no converted syllables, and if
If there is a corresponding word, this will be converted into kanji,
Add np to ptr, and if there is no corresponding word, add 1 to ptr to process the next syllable string. Numeral 17 designates the corresponding word from the dictionary 18 as the search key, using the syllable sent from the conversion processor 16 or the expanded word generator 19 as the search key, and arranges the corresponding word first if there are a plurality of words. The word with the highest possibility is taken out, and this is converted into the conversion processing unit 16 or the expanded word generation unit 1 described above.
9 is a dictionary search unit for sending to 9. 22 is the conversion processing unit 1
An output unit that outputs the result converted by 6.

The operation flow of this embodiment will be described below.
Although FIGS. 2 to 4 are originally one sheet, they are divided into three figures due to the limitation of the screen size. Figure 2
Shows the flow of the register initialization operation, and this operation will be described with reference to this figure. (S1) First, the register for calculating the number of syllables is set to zero.

(S2) Input a phonetic character string. (S3) It is checked whether the currently input phonetic character is a tone key. If it is a tone key, go to (S4). If not, go to (S5). (S4) As the input syllable number increases, the content of the register for calculating the syllable number is incremented by 1 and the process returns to (S2).

(S5) It is checked whether the currently input phonetic character is the input end key. If it is an input end key, go to (S6) to convert kanji. If it is not an input key (S2)
Return to. (S6) It is checked whether the number of syllables currently input exceeds eight. If 9 or more, go to (S7). If it is 8 or less, go to (S8).

(S7) The value of the NP register is set to 8. (S8) The value of the NP register is set to the currently input syllable number. (S9) The value of the NCHAR register is set to the currently input syllable number. (S10) Set the value of the PTR register to 1. As a result, the initial setting of processing from the beginning of the input phonetic character string as a target of Kanji conversion from a word having a large number of syllables and a large number of Kanji characters is completed.

Next, FIGS. 3 and 4 focus on the operation of the conversion processing section, and this operation will be described with reference to this figure. (S11) Np consecutive syllables are cut out from the ptr-th phonetic character string. (S12) It is checked whether or not there is a converted syllable in the syllable cut out in (S11). If there are already converted syllables, go to (S16). At this time, syllables that have not been converted are targeted for conversion when the value of np becomes smaller. If there is no syllable that has already been converted, go to (S13).

(S13) It is searched whether or not the word corresponding to the syllable cut out in (S11) is stored in the dictionary.
If so, go to (S14), otherwise go to (S17). (S14) Convert np consecutive syllables starting from ptr-th of the input phonetic character string to the corresponding word detected in (S13),
Then go to (S15). (S15) Add np to the value of the PTR register. This is (S
This is because the syllable character string immediately after the Kanji conversion in 14) is to be processed in the next Kanji conversion.

(S16) Add 1 to the value of the PTR register.
This is because the next syllable character string having the same number of syllables is subjected to the kanji conversion processing. (S17) Compare the current value of the NP register with 2. If it is larger than 2, go to (S18), and if it is smaller, go to (S16). (S18) It is inspected by a predetermined procedure whether or not the first syllable cut out in (S11) is the reading of a compound character. if,
If it is the reading of compound words, go to (S19), otherwise go to (S16).

(S19) It is checked whether the words corresponding to np-1 syllables from the second syllable among the syllables extracted in (S11) are registered in the dictionary section. If registered, go to (S20). If not, go to (S16). (S20) Combined characters detected in (S18) and words extracted in (S19) are combined into an expanded word that is, so to speak, one word, and np syllables consecutive from the ptr of the input syllable. To an expanded word. Then go to (S15).

In (S21), the value of (np + ptr) and the value of (n
The value of (char + 1) is inspected. If the former is large, go to (S22). If it is smaller, go to (S11). (S22) The value of the NP register 13 is decremented by 1, the value of the PTR register 12 is set to 1, and the process goes to (S23). this is,
This is because a word having the number of constituent kanji less than one is processed as a target of kanji conversion from the first to the next in the input syllable character string.

At (S23), it is checked whether the value of the NP register 13 is zero. If it is zero, the Kanji conversion processing of the input phonetic character string is terminated. Otherwise (S11)
Return to. Next, the compound word dictionary part according to the main part of the present invention will be described. FIG. 5 is a conceptual diagram of the data structure of the compound word dictionary section of the present embodiment. This lexicon consists of basic phonetic reading sounds and corresponding compound word correspondence tables. In this embodiment, the Chinese prepositions "a", "從", "將", etc., also the conjunctions "rule", "young", "wa", "i", etc. , "No", "Yes" and the like, as well as the specifiers "the", "the" etc., are regarded as compound words. In addition, in Chinese, these compound words are connected with words to form a word having a larger number of kanji characters. In addition, the word comprised by such a combination is called the expansion word in this specification. For example, "three years old", "in Taipei", "unnecessary",
For example, "Yuichiten". These expanded words are regarded as one word (so-called idiom) in this embodiment. And
In the Kanji conversion device that uses the longest match method, the conversion will be performed with higher priority.

Next, the present embodiment configured as described above will be described with reference to words. (Less than,
Due to the limitation of the characters that can be used by the application through the electronic information processing system, in this specification, (a) of FIG.
The phonetic characters and symbols shown in (b), (c), (d), (e), and (f) are inventions intended for this Chinese word processor etc. even in the enforcement rules of electronic information processing systems. Therefore, it is assumed that it was not assumed that a large number of external characters would be used in a complicated manner, and in consideration of the readability of the specification, “sha”, “ren /”, which are similar to each other,
"Shi \", "fan \", "zui \", "de"
・ "Is substituted. ) "Sha ren / shi \ fan \ zui \
The operation of the input sequence "de." will be described. Below is a list of all possible conversion words stored in the dictionary corresponding to this input string.

"Sha ren / murder" "ren / shi \ personnel affairs" "fan \ zui \ example" "zui \ de / crime" It will be explained again based on the flow chart.

When the above phonetic character string is input (S2), the register initializing section obtains the number of syllables by dividing the input phonetic character string into syllables by tone signals (S3 to S3).
Five) . Since there are six syllables in the above input string, the syllable number 6 is set in the NCHAR register (S9). Since the value is smaller than the number of Chinese characters of the longest word in the dictionary section, which is 8 (8 in this embodiment) (S6), 6 is set as the initial value of the NP register (S8), and the value of the PTR register is set to 1. Set to
(S10). Here, the role of the NP register is to store the number of Kanji of the word currently obtained by the conversion. In this case, since 6 is input in the initial setting, the kanji conversion is performed in order from the word having the syllable number 6 which is made up. The value ptr in the PTR register indicates that the current start position of the dictionary search is the ptr-th syllable of the input phonetic character string. In this case, since 1 is input in the initial setting, the first syllable of the phonetic character string is sequentially converted into the Chinese character.

After the initial values of the PTR register, the NP register, and the NCHAR register are set based on the input syllable number, the conversion processing unit first sets the PTR register and the NP register.
Depending on the value of the register, the first to sixth consecutive syllable strings “sha ren /” of the phonetic character string sent from the input unit.
"shi \ fan \ zui \ de."
(S11), and then, it is checked whether or not there are syllables that have already been converted to Kanji (S12). If all syllables have not been converted yet, and these syllable strings have just been input and no Kanji conversion has been performed yet, all six syllables are sent as search keys to the dictionary search unit. The dictionary is searched (S13). Since there is no corresponding word and the value of the NP register is currently larger than 2 (S17), it is checked whether or not the first syllable is a reading of a compound word (S18). When it is determined that the first syllable is not a compound word, the value of the PTR register is incremented by 1 (S
16). At that time, the comparison unit determines that the value of (np + ptr) is (nc
Since it is larger than the value of (har + 1), it is judged (S21), and it is shown that other syllable strings cannot be cut out in order to convert the word having 6 syllables. Therefore, the value of the NP register is decremented by 1 to 5, and PT
The value of the R register is set to 1 again (S22). Since the value of the NP register is not zero (S23), the operation for cutting out the next consecutive syllable and converting kanji is started. Similarly, the "sha ren / s" originally clipped by the new value 1 in the PTR register and the value 5 in the NP register.
hi \ fan \ zui \ ", and because this is also not converted to kanji, prt is added by 1 to become 2 (S16), and then" ren / shi \ fa "is cut out.
"n \ zui \ de ..." (S11) is also a syllable that has not been converted yet (S12), but the corresponding word is not stored in the dictionary (S13). Since it is not (S18), the kanji conversion process is not performed. However, the value of the PTR register is incremented by 1 (S16).
"Ren / shi \ fan \ zui \ de."
After it is determined that is not the target of Kanji conversion (S13), 1 is further added to the value of the PTR register to become 3. In this case, the comparison unit calculates (np + ptr)> (nchar +
It is determined to be 1) (S21), and it is determined that it is no longer possible to cut out another syllable string in the rear in order to convert the word having the number of constituent kanjis of 5. Therefore, the value of the NP register is reduced by 1 to 4. Also, the value of the PTR register is newly set to 1 (S22). Since the value of the NP register is not zero (S23), the next consecutive syllable is cut out and the kanji conversion process is started. When the value of the NP register is 4, as in the case of 5, the continuous syllable string “sh” consisting of four pieces sequentially cut out from the input phonetic character string is selected according to the values of the PTR register and the NP register.
a ren / shi \ fan \ "," ren / s
Since all of "hi \ fan \ zui \" (S11) have not been converted yet (S12), the dictionary part is searched using them as search keys. There is no word corresponding to them (S13),
And since the first syllable is not the reading of compound words (S18),
These are not subject to Kanji conversion processing. At this stage, P
The value 2 in the TR register is further increased by 1 (S16). PTR
When the register value becomes 3, the third phonetic character string "sh
i \ fan \ zui \ de ... "is cut out.
(S11), which is also a syllable that has not yet been converted (S12)
. Now, at this stage, the word corresponding to this syllable string is not stored in the dictionary part (S13), and the value of the NP register is larger than 2 (S17), so the first syllable is the reading of the compound word. Whether or not it will be inspected (S18). Then, since the reading "shi \" is registered in the compound word dictionary part, it is searched whether or not the corresponding word is stored in the dictionary part for the other syllable "fan \ zui \ de." (S19). . However, since the corresponding word is not registered, neither Kanji conversion nor Kanji conversion is performed. Next, the value of the PTR register is incremented by 1 to 4
(S16). At this time, the comparison unit calculates (np + ptr)> (n
It is determined that (char + 1) (S21), and it is determined that another syllable string in the rear can no longer be cut out in order to convert a word having four syllables. Therefore, the value of the NP register is decreased by 1 to be 3. The value of the PTR register is set to 1 again (S22). In this case, since the value of the NP register is not zero (S23), the next continuous syllable is cut out and converted.

Even when the value of the NP register is 3, 6,
As in the case of Nos. 5 and 4, the syllable strings “sha ren / shi \”, “ren” that are continuous from the input phonetic character string are set depending on the operation and setting values of the PTR register and the NP register.
"/ Shi \ fan \" is sequentially cut out (S11).
In this case, all these syllables have not been converted yet (S
12) Then, the dictionary is searched using them as search keys, but there is no word corresponding to them (S13), and since the first syllable is not the reading of compound words (S18), there is no kanji conversion processing. Will not be done. However, the value of the PTR register will be sequentially incremented by 1 (S16). “Shi \ f” cut out when the value of the PTR register becomes 3
"an \ zui \" (S11) has not been converted yet (S11)
12) Moreover, since there is no corresponding word in the dictionary part (S13) and the value of the NP register is larger than 2 (S17), it is checked whether or not the first syllable is the reading of a compound word ( S1
8). By the way, in this case, there is a character “” corresponding to the reading “shi \” in the compound word dictionary part. Therefore, it is searched whether or not the corresponding word is registered in the dictionary for the other syllable "fan \ zui \" (S19).
. Since the corresponding word "crime" is registered, the extended word "correction" is generated by combining the combined word "" and the corresponding word "crime" (S20). And "s
"hi \ fan \ zui \" is converted to the extended word "death". Next, the value of the PTR register and the value of the NP register are added. As a result, the value of ptr becomes 6 (S15).
Therefore, the comparison unit calculates (np + ptr)> (ncha
r + 1) is determined (S21). This gives 3 syllables
It is determined that other syllable strings in the rear cannot be cut out in order to convert the word of, and the value of the NP register is decreased by 1 to 2. The value of the PTR register is set to 1 again (S22). In this case, since the value of the NP register is not zero (S23), the next consecutive syllable is cut out and the kanji conversion process is performed.

When the value of the NP register is 2 and the value of the PTR register is 1, the continuous syllable string "sha"
"ren /" is cut out (S11), and since it is a syllable that has not been converted yet (S12), the dictionary search unit searches the dictionary unit by using it as a search key. The corresponding word "murder" is stored in the dictionary, so "sha ren /"
Is converted to "murder" and the value of the NP register is added to the value of the PTR register to be 3 (S15). At this time, the comparison unit determines that (np + ptr) is smaller than (nchar + 1) (S21), and it is possible to cut out another syllable string in order to convert the word whose constituent kanji number is 2.
Continuous syllable syllables "shi \ fan \", "fa"
Cut out "n \ zui \" and "zui \ de." (S
11). However, since these syllables contain already converted syllables (S12), no processing is done.

Next, when the value of the NP register becomes 1, all the extracted syllables have been converted regardless of whether the value of the PTR register is 1, 2, 3, 4 or 5. Therefore, no processing will be performed. When the value of the PTR register becomes 6, the “de.” Cut out at this stage has not been converted yet, so it is sent to the dictionary search unit to search the dictionary unit. In Chinese sentences, the most frequent use of "target" is in the kanji corresponding to the sound of "de." It is arranged first, so this will be converted to kanji first.
"De" is converted to "target". Then, add the value of the NP register to the value of the PTR register to make 7 (S15).
. In this case, the comparison unit calculates (np + ptr) as (nc
It is determined that it is larger than (har + 1) (S21). Therefore, the value of the NP register is decreased by 1 and becomes 0. Up to this point, the conversion processing unit determines that the Kanji conversion processing of the input phonetic character string has been completed, and sends the conversion result “murder-killing criminal” to the output unit.

Although the present invention has been described above based on the embodiments, it goes without saying that the present invention is not limited to the above embodiments. That is, for example, it is not always necessary to start converting all phonetic character strings of the input phonetic character string into Kanji after the input end key is pressed, and when the tone key is input, that is, one syllable Each time is input, the input phonetic character string from the input end position of the previously input phonetic character string to the currently input phonetic character string may be converted. Instead of storing compound words independently in the compound word dictionary section, we decided to display these compound characters by a flag,
It may also be stored in the dictionary unit corresponding to this flag. For convenience of manufacture, each constituent part shown in the claims may be physically divided into a plurality of parts, or the plurality of constituent parts may be physically one, or these may be appropriately used. You may combine. For example, a part of the processing of the PTR register, the NP register, the comparison unit, and the conversion processing unit 16 in the embodiment corresponds to the processing of the syllable cutout unit. A phonetic character is a concept that includes not only the phoneme characters and syllabic characters illustrated but also phoneme symbols, and if it is subject to Kanji conversion, it is a character such as Japanese kana or Korean Hangul. Good. Needless to say, the usage includes a word processor for Chinese sentences in Japanese. Of course, a learning function or the like may be added.

[0027]

As described above, according to the present invention,
When converting the input syllable string into Chinese characters (Kanji), the syllable to be converted has Chinese prepositions, conjunctions,
For compound words that have characteristics such as affirmative words, negative words, and designated words, there is a reading of that character, and in subsequent consecutive syllables, a word with a large number of kanji characters is integrated with the compound word. If there is a word to be generated, the extended word having a larger number of Chinese characters and a larger number of syllables to be converted is generated by combining the compound word and the word. By the way, since kanji conversion is done preferentially from the words with a large number of kanji composed on this, "Ariichiten", which was difficult only with the conventional principle of simply prioritizing the number of composed kanji and the forward word, It is possible to easily resolve erroneous conversions such as "murder-correction criminal" and "its characteristics". For this reason, the accuracy rate at the time of converting Kanji in Chinese sentence creation is increased, and its technical effect is very large.

[Brief description of drawings]

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

FIG. 2 is a flow chart of an operation in the initial stage of the register in the above embodiment.

FIG. 3 is a flowchart mainly showing an operation of a conversion processing unit in the above embodiment.

FIG. 4 is a flow chart centering on the operation of a conversion processing unit in the above embodiment.

FIG. 5 is a conceptual diagram of a data structure of a compound word dictionary in the above embodiment.

FIG. 6 is a configuration diagram of a conventional kanji conversion device.

FIG. 7 is a list of phonetic character strings used to describe examples in the specification.

[Explanation of symbols]

 10 input unit 11 register initialization unit 12 PTR register 13 NP register 14 NCHAR register 15 comparison unit 16 conversion processing unit 17 dictionary search unit 18 dictionary unit 19 expanded word generation unit 20 compound word detection unit 21 compound word character unit 22 output unit

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Akinori Xie Taiwan Taipai She Tha An Che 10628 Ren Ile San Touan 136 Hao 10 Law Sun She Tien Chi Ji Shu Kai Kai Fu Ku Yu Feng Yu Sien Con Su (72) Inventor Kei Ken Hayashi Taiwan Taipai Shita Ann Qi 10628 Len I Le San Toh Ann 136 Hao 10 Lo Sun Sha Tien Chi Ji Shu Shu Kai Fah Kuu Feng Yu Inside Cien Con Sue

Claims (1)

[Claims] 1. For a syllable or a part of the syllable that has not been converted in the input phonetic character string, first of all, it is prioritized to convert the word into the maximum number of characters, and secondly, it is input first. Prioritizing the conversion of syllables, the number of syllables to be converted is successively reduced based on this, and the syllable extraction unit that cuts out the syllable string to be currently converted by sequentially shifting the syllables to be converted backward. , A dictionary unit in which phonetic character strings and Chinese words corresponding thereto are registered in advance, and a syllable string to be converted which is cut out by the syllable cutout unit is used as a search key to search the dictionary unit for Chinese. In the syllable string to be converted which is cut out by the syllable cutout unit, if the first syllable is a compound word, a compound word detection unit that detects the compound word in a predetermined procedure. And above When the corresponding compound word detecting unit detects the corresponding compound character, the dictionary searching unit searches the dictionary unit using the second syllable of the syllable string to be currently converted as a search key, and if there is a corresponding word, An extended word generation unit that generates an extended word having a larger number of constituent Kanji characters by combining the compound words and the words, and the extended word generated by the extended word generation unit have priority over the word searched by the dictionary search unit. And a conversion processing unit for controlling so as to convert the Kanji.