JPH11134331A - Document preparing device and kana/chinese character converting method and recording medium for recording kana/chinese character conversion program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To output a converted result intended by a user by outputting the replacement candidate of an erroneous input by using the key sequence of a user. SOLUTION: A read character string is inputted through an inputting part 21. A controlling part 22 detects an erroneous input character in the read character string through an erroneous input automatic correcting part 23. When the erroneous input character is detected, the erroneous input automatic correcting part 23 extracts plural replacement candidates for the erroneous input character from an erroneous input dictionary 25 based on the erroneous input character and a previous character. The erroneous input dictionary 25 stores plural replacement candidates whose priority order is decided according to the key sequence of the erroneous input character to be corrected and the previous character. A KANA/Chinese character converting part 24 operates the KANA/Chinese character conversion of the read character string by using those replacement candidates. A controlling part 22 outputs plural conversion candidates obtained by the KANA/Chinese character converting part 24 through an outputting part 27.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a document creation device such as a personal computer or a word processor equipped with word processing software, and more particularly to a document creation device having an erroneous input automatic correction function and a kana-kanji conversion method used in the device. And a recording medium storing a kana-kanji conversion program.

[0002]

2. Description of the Related Art In a kana-kanji conversion system used in a document creation device such as a personal computer or a word processor, a kana character string input from an input device such as a keyboard is converted into a character string mixed with kanji to input Japanese characters. Has been realized.

In this case, kana input for kana-kanji conversion is performed by inputting a kana character string as it is, or by inputting it in romaji and converting it into kana by the system. In some cases, a kana is erroneously entered, in which case the result of the kana-to-kanji conversion is also incorrect.

Conventionally, such an input error is corrected by replacing it with a key near the key. For example, in the Roman character input mode, when the user inputs “ko” where “ko” is to be input, the user searches for a vowel character key near the “l” key and “ko” Is corrected. By correcting such erroneous input, a correct conversion result can be obtained without the user correcting the input.

[0005]

However, in the conventional erroneous input correction method as described above, the replacement candidate for the erroneous input character is uniquely determined to a key near the erroneous input key. When there are a plurality of candidates, they cannot be distributed. For this reason, there is a problem that the conversion result intended by the user cannot always be output.

SUMMARY OF THE INVENTION The present invention has been made in view of the above points, and a conversion result intended by a user is output by using a key sequence of the user to select replacement candidates for erroneous input. An object of the present invention is to provide a document creation device, a kana-kanji conversion method, and a recording medium on which a kana-kanji conversion program is recorded, which can smoothly perform subsequent input / conversion / editing operations.

[0007]

According to a first aspect of the present invention, there is provided a document creating apparatus, comprising: input means for inputting a character string to be converted; and erroneous input characters in the character string input by the input means. Erroneous input detection means for detecting a erroneous input character and a key sequence of a character immediately before the erroneous input character detected by the erroneous input detection means, and a plurality of replacement candidate generation means for generating a plurality of replacement candidates for the erroneous input character And conversion means for converting the erroneous input character to kana-kanji using each replacement candidate created by the replacement candidate creation means, and output means for outputting a plurality of conversion candidates obtained by the conversion means. Features.

According to such a configuration, when a character string to be converted is input, an erroneous input character in the character string is detected, and the erroneous input character and the key of the character immediately before the erroneous input character are detected. A plurality of replacement candidates for the erroneous input character are created based on the sequence, and a plurality of conversion candidates are output by kana-kanji conversion using these replacement candidates.

As described above, when an erroneous input character is detected, kana-kanji conversion is performed using a plurality of replacement candidates determined by a key sequence with the immediately preceding character. You will be able to get results.

According to a second aspect of the present invention, in the first aspect, there is provided an erroneous input dictionary storing a plurality of replacement candidates whose priorities are determined by a key sequence of a character to be corrected and a preceding character. The replacement candidate creating means extracts a plurality of replacement candidates for the erroneous input character from the erroneous input dictionary in a priority order based on the detected erroneous input character and a character immediately preceding the erroneous input character. .

According to such a configuration, a plurality of replacement candidates for erroneous input characters are extracted from the erroneous input dictionary in order of priority according to the key sequence, and a more probable conversion candidate is obtained by Kana-Kanji conversion using the replacement candidates. Output preferentially. As a result, the number of candidate selection operations can be reduced.

According to a third aspect of the present invention, in the second aspect, the output means changes the output form of each conversion candidate obtained by the conversion means based on the priority of each replacement candidate. I do.

According to such a configuration, the output form of the plurality of conversion candidates obtained by the Kana-Kanji conversion is changed according to the priority of each of the replacement candidates. Therefore, when the conversion candidates are selected, their priorities are changed. It can be judged visually.

[0014]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing a system configuration of a document creation device according to an embodiment of the present invention.
The document creation apparatus according to the present embodiment is realized by a computer that reads a program recorded on a recording medium such as a magnetic disk and the operation of which is controlled by the program.

As shown in FIG. 1, a document creation device according to the present embodiment includes a CPU 11, a memory 12, an input device 1
3, display device 14, external storage device 15, printing device 16,
The communication device 17 is provided.

The CPU 11 controls the entire operation of the present apparatus, and operates by activating a program stored in the memory 12. Functions realized based on the program stored in the memory 12 include a word processor by an application program, a kana-kanji conversion system (IME: input method editor) by a kana-kanji conversion program, and the like.

The memory 12 is composed of, for example, a ROM or a RAM, and stores programs and data used in the present apparatus. The memory 12 has a program area 12a for storing an application program for realizing a word processor, a kana-kanji conversion program for realizing a kana-kanji conversion system, an input buffer 12b, a replacement candidate buffer 12c, a conversion candidate buffer 12d, and a document. A buffer 12e and the like are provided.

The input buffer 12b stores a reading character string input for document creation. The replacement candidate buffer 12c stores a character string obtained by correcting an erroneously input character in the read character string with a plurality of replacement candidates. The conversion candidate buffer 12d stores a plurality of conversion candidates obtained by the Kana-Kanji conversion. The document buffer 12e stores document data composed of character strings mixed with kana-kanji obtained by the kana-kanji conversion function.

The input device 13 is composed of a keyboard and is used to input instructions and data to the apparatus. The input device 13 reads a character string for creating a document, and instructs a kana-kanji conversion of the input character string (" It is used for inputting an instruction) by operating the "Convert" key.

The display device 14 is, for example, a CRT (Cathode
It comprises a Ray Tube) and an LCD (Liquid Crystal Display), and displays data such as a read character string and a Kana-Kanji conversion result input through the input device 13.

The external storage device 15 is, for example, an HDD (Hard
Disk Drive) and CD-ROM (Compact Disc Read On)
ly Memory) and stores various programs and data. In this case, in addition to the application program and the Kana-Kanji conversion program for realizing the Kana-Kanji conversion system, the documents generated by the Kana-Kanji conversion system and the data of the Kana-Kanji conversion dictionary that the Kana-Kanji conversion system refers to when performing the Kana-Kanji conversion are also included. It is.

The printing device 16 is used for printing a document or the like. The printing device 16 may be built in the printing apparatus or may be connected externally. The communication device 17 is, for example, a private LAN (Local
It controls the transmission and reception of data with external devices via an Area Network) or a communication network.

Next, a description will be given of a functional configuration of the document creating apparatus realized by the system configuration shown in FIG. FIG. 2 is a block diagram showing a functional configuration of the document creating apparatus realized by the system configuration of FIG. As shown in FIG. 2, the document creation device according to the present embodiment includes an input unit 21,
Control unit 22, erroneous input automatic correction unit 23, kana-kanji conversion unit 2
4, erroneous input dictionary 25, kana-kanji conversion dictionary 26, output unit 2
7 functions.

The input unit 21 controls data such as a read character string input by operating the input device 13 and an instruction for kana-kanji conversion. The data of the read character string input under the control of the input unit 21 is stored in the input buffer 12 of the memory 12.
b and is subjected to kana-kanji conversion. In addition, the instruction of the kana-kanji conversion is notified to the kana-kanji conversion unit 24.

The control unit 22 controls the entire function of the kana-kanji conversion system, and controls each processing unit in accordance with input data from the input unit 21, an instruction for kana-kanji conversion, and the like.

The erroneous input automatic correction unit 23, which is one function of the kana-kanji conversion system,
By referring to the result of the Roman character conversion or the Kana-Kanji conversion dictionary 26, it is checked whether or not the target of the Kana-Kanji conversion is an error. Further, when it is determined that the input is incorrect, a plurality of replacement candidates for the erroneous input character are created with reference to the erroneous input dictionary 25. The character string corrected using these replacement candidates is stored in the replacement candidate buffer 1 of the memory 12.
2c.

The Kana-Kanji conversion unit 24 converts the input read character string into Kana-Kanji characters with reference to the Kana-Kanji conversion dictionary 26 and returns the conversion result (Kanji-mixed character string) to the control unit 22. In this case, when a plurality of replacement candidates for the erroneous input character are created by the erroneous input automatic correction unit 23, the input reading character string is converted into Kana-Kanji characters using these replacement candidates, and the conversion result is obtained. Control unit 2 converts each conversion candidate
Return to 2. These conversion candidates are stored in a conversion candidate buffer 12d of the memory 12.

The erroneous input dictionary 25 is a dictionary in which information for correcting erroneous input characters is stored. In this embodiment, the precedence is determined by the character to be corrected for erroneous input and the key sequence of the immediately preceding character. A plurality of predetermined replacement candidates are stored. The key sequence is an input order of each key when a user inputs a character string according to a key arrangement on a keyboard.

The kana-kanji conversion dictionary 26 stores information necessary for kana-kanji conversion processing, such as readings and headings (conversion words) corresponding to the readings. The output unit 27 includes the control unit 22
Character string input via the PC or an erroneous input automatic correction unit 2
3, the character string converted by the kana-kanji conversion unit 24 and the like are output to the display device 14.
Create output data to the application.

FIG. 3 is a diagram showing the configuration of the erroneous input dictionary 25. The erroneous input dictionary 25 stores a character to be corrected for erroneous input and a plurality of replacement candidates whose priorities are determined by the key sequence of the character immediately preceding the character.

That is, for example, when the character to be corrected is “k”, the character immediately before that is “q”, “a”,
"Z", "w", "s", "x", "e", "d",
"C", "r", "f", "v", "t", "g",
When a key arranged on the left side of the keyboard, such as "b", "y", "h", "n", is input, "l",
There is a high possibility that keys are input in the order of "i", ",", "o", "u", "j", "m". These characters are stored in the erroneous input dictionary 25 as replacement candidates in the order of priority.

Note that "l", "i", ",", "o",
The priority of each candidate such as “u”, “j”, “m”
The appearance frequency of the character following "k" is statistically obtained and determined in the order of appearance frequency.

Also, for the same "k", the preceding character is "[", "]", "@", ":", "@", "p",
When a key arranged on the left side of the keyboard such as ";", "/", "o", "l", "." ,
There is a high possibility that keys are input in the order of "j", "i", ",", "o", "u", "m". These characters are stored in the erroneous input dictionary 25 as replacement candidates in the order of priority.

Note that "l", "j", "i", ",",
The priority of each candidate such as “o”, “u”, “m”
The appearance frequency of the character following "k" is statistically obtained and determined in the order of appearance frequency.

FIG. 4 is a diagram showing a key arrangement of a keyboard used as the input device 13. On the keyboard,
Various keys for inputting characters (kana characters, English characters), numbers, symbols, and the like are arranged in accordance with JIS standards.
This standard mainly specifies a two-handed key arrangement used in a kana-kanji conversion type Japanese sentence input device. In addition to the character keys shown here, various keys such as a cursor key, a shift key, a conversion key, and a next candidate key are arranged at predetermined locations.

Next, the operation of the embodiment will be described. FIG.
9 is a flowchart showing an operation of a kana-kanji conversion process in the embodiment. Here, it is assumed that the apparatus is operable as a word processor by activating an application, and a kana-kanji conversion of a reading character string is performed by a kana-kanji conversion system under the application to create a document.

In the input mode, there are a "kana input mode" for directly inputting Japanese readings and a "romanized input mode" for reading and inputting Roman characters. The following description assumes that a reading character string is input.

The input unit 21 receives a read character string or a conversion key input by the input device 13 composed of a keyboard, and passes it to the control unit 22 (step A11).
The read character string input at this time is converted into Roman characters, then stored in the input buffer 12b of the memory 12, and displayed at the cursor position on the display screen of the display device 14.

Here, if the conversion key is pressed after the input of the reading character string (Yes in step A12), the control unit 22
First, the erroneous input is automatically checked for the read character string stored in the input buffer 12b through the erroneous input automatic correction unit 23 (step A13), and it is determined whether the erroneous input character exists in the read character string. Judge (Step A1)
4). This erroneous input check is performed by detecting characters that have not been converted to Roman characters.

As a result, if the read character string has been correctly converted to Roman characters, it is determined that there is no erroneous input character (Yes in step A14), and the control unit 22 converts the read character string into Kana-Kanji characters through the Kana-Kanji conversion unit 24. Processing is performed (step A16). In this case, the kana-kanji conversion unit 24 searches the kana-kanji conversion dictionary 26 to obtain a heading (conversion word) corresponding to the read character string stored in the input buffer 12b as a conversion candidate. The conversion candidates are stored in a conversion candidate buffer 12d of the memory 12.

When the conversion candidates are stored in the conversion candidate buffer 12d, the control unit 22 displays the conversion candidates on the display device 14 through the output unit 27 (Step A17). On the other hand, if there is a character that is not converted to Roman characters in the read character string, the character is determined to be an erroneously input character (step A14).
Yes), the control unit 22 performs an erroneous input correction process on the erroneously input character through the erroneous input automatic correction unit 23 (step A15).

Here, the present embodiment is characterized in that the erroneous input correction processing is performed based on the erroneous input character and the key sequence of the character immediately before the erroneous input character. FIG. 6 shows the operation of the erroneous input correction process at this time.

FIG. 6 is a flowchart showing the operation of the erroneous input correction processing in step A15. That is, when an erroneous input character is detected, the erroneous input automatic correction unit 23
Then, the erroneous input character and the character immediately before the erroneously input character from the read character string stored in the input buffer 12b are received from the control unit 22 (step B11).

The erroneous input automatic correcting section 23 sequentially extracts replacement candidates for erroneous input characters from the erroneous input dictionary 25 in accordance with the key sequence of these characters (step B1).
2). As shown in FIG. 3, the erroneous input dictionary 25 stores a plurality of replacement candidates whose priorities are determined by the key sequence of the character to be corrected for the erroneous input and the character immediately before the erroneous input.

When a replacement candidate is obtained from the erroneous input dictionary 25,
The erroneous input automatic correction unit 23 determines the validity of the replacement candidate (step B13). This is performed by checking whether Roman character conversion is possible with the character string corrected by the replacement candidate. As a result, if Roman character conversion is possible (Yes in step B13), the erroneous input automatic correction unit 23 determines the replacement candidate as a valid candidate, and stores the character string corrected by the replacement candidate in the memory 1.
2 is stored in the replacement candidate buffer 12c (step B).
14). This process is performed for all replacement candidates extracted from the erroneous input dictionary 25 (step B15).

Thus, the replacement candidate buffer 12
When the character string corrected by each replacement candidate is stored in c, the control unit 22 performs the kana-kanji conversion process through the kana-kanji conversion unit 24 (step A16). In this case, the kana-kanji conversion unit 24 searches the kanji conversion dictionary 26 for each character string corrected by each replacement candidate stored in the replacement candidate buffer 12c to obtain a plurality of conversion candidates. These conversion candidates are stored in a conversion candidate buffer 12d of the memory 12.

When the conversion candidates are obtained, the control unit 22 displays the conversion candidates on the display device 14 via the output unit 27 (step A17). Here, the present embodiment is characterized in that, when displaying conversion candidates, the read character string is displayed in a case where it is erroneously input corrected and a case where it is not erroneously input corrected. FIG. 7 shows the operation of the display process at this time.

FIG. 7 is a flowchart showing the operation of the display processing in step A17. That is, when displaying the conversion candidate, the output unit 27 determines whether or not the conversion candidate is obtained by correcting the read character string (step C11). As a result, when the conversion candidate is not obtained by correcting the read character string, that is, when there is no erroneous input automatic correction, the output unit 27 displays the conversion candidate on the display device 14 in a normal display form. It is displayed on the screen (step C12).

At this time, a plurality of conversion candidates (homophones)
Exists, and the display of the next candidate is instructed by pressing the next candidate key (Yes in step C13), the output unit 2
7 displays a list of these conversion candidates in another area on the display screen (step C14). By selecting a desired candidate from the candidate list, the user can determine the conversion result of the read character string.

On the other hand, when the conversion candidate is obtained by correcting the read character string, that is, when there is an erroneous input automatic correction, the output unit 27 changes the display color, for example, by changing the display color. The candidates are displayed on the display screen of the display device 14 in a display mode different from the normal display mode (step C1).
5).

At this time, a plurality of conversion candidates (homophones)
Exists, and the display of the next candidate is instructed by pressing the next candidate key (Yes in step C16), the output unit 2
7 displays a list of these conversion candidates in another area on the display screen, and distinguishes each candidate by changing the display color based on the priority of each replacement candidate determined by the key sequence at that time. It is displayed (step C17).
By selecting a desired candidate from the candidate list, the user can determine the conversion result of the read character string.

FIG. 8 shows a specific example. In the state where the “Roman character input mode” is set, the user sets “acknout”.
It is assumed that a reading character string such as "a" is input by a key and the conversion key is pressed. This read character string is converted into Roman characters and stored in the input buffer 12b as shown in FIG. In this case, since "k" in "aknowa" is incorrect, a read character string such as "ak no uta" is stored in the input buffer 12b by Roman character conversion.

Here, the input reading character string "akno
The character "k" which has not been converted to Roman characters in "uta" is determined to be an erroneous input character, and a plurality of replacement candidates are created by a key sequence with the character "a" immediately before the character.

That is, as shown in FIG. 3, if “k” is an erroneous input character and the character immediately preceding it is “a”, “l”, “i”, ",",
Characters such as "o", "u", "j", and "m" are sequentially extracted from the erroneous input dictionary 25.

When the erroneous input character "k" is corrected by these replacement candidates and converted into Roman characters, "i" and "o"
When "u" and "u" are used, Roman character conversion is possible. Therefore, this “i” is stored in the replacement candidate buffer 12c.
As shown in FIG. 8 (b), three candidates of “Aino Uta”, “Ao No Uta”, and “Au No Uta” are obtained as character strings obtained by correcting the read character string using “o” and “u”. Is stored. In this case, according to the priorities of the replacement candidates “i”, “o”, and “u”, “ainouta” → “aonouta” →
It is stored in the order of “a song”.

Next, a kana-kanji conversion process is performed for each character string stored in the replacement candidate buffer 12c. As a result, in the conversion candidate buffer 12d, as shown in FIG. 8 (c), "Ai no Uta" is changed to "Ai no Uta", "Ai no Uta", "Ai no Uta", and "Ao no Uta". On the other hand, a plurality of conversion candidates, such as "blue song", "Ao no Uta", and "a song" for "a song" are stored in order.

In addition to these candidates, non-conversion candidates such as "Aino Uta", "Ao No Uta", and "Au No Uta" are also stored. However, these non-conversion candidates are not necessarily required to be added as candidates.

When a plurality of conversion candidates are obtained in this way, first, the first candidate is displayed. In this case, since the display order of the conversion candidates follows the priority order of the replacement candidates, “Love Song” is displayed in the first place.

Note that, in a candidate group using the same replacement candidate, the priority order is determined based on frequency information and the like.
For example, in the candidate group using the replacement candidate “i”, the order is “love song” → “eye song” → “indigo song”.

When the user instructs to display the next candidate by pressing the next candidate key, a list of all conversion candidates is displayed. FIG. 9 shows an example of the display screen at this time. FIG. 9 is a diagram illustrating an input character string displayed on the display device 14 and a state of a conversion result. In the figure, 31 is an input character string, 32 is a conversion candidate, and 33 is a candidate list.

Character string 3 input through input device 13
1 is displayed at the cursor position on the display screen of the display device 14. When the conversion key provided on the input device 13 is pressed after the input of the character string 31, the kana-kanji conversion is performed after the error of the input character string 31 is automatically corrected, and the first conversion candidate obtained as the conversion result 32 is displayed. Also,
When the next candidate key is pressed, a list 33 of each conversion candidate is displayed in a window, and a desired candidate can be selected from the window.

Here, in the present embodiment, when displaying the conversion candidates 32 obtained by automatic correction, the conversion candidates 32 are displayed in a display mode different from the normal display mode, for example, without changing the display color. indicate. Thus, the user can visually determine whether or not the correction has been obtained.

In the candidate list 33, the display mode (for example, display color) of each candidate is changed according to the priority of each candidate according to the key sequence. In the example of FIG. 8 (c), the conversion candidates “love song”, “eye song” and “indigo song” using the replacement candidate “i” are blue, and the replacement candidate “o” is used. The conversion candidates are displayed in such a manner that the conversion candidates "blue song" and "Ao no Uta" are green, and the conversion candidate "matching song" using the replacement candidate "u" is red. This allows the user to visually determine the priority of each candidate when selecting the candidate.

The current candidate displayed as the conversion candidate 32 in the candidate list 33 is displayed by being distinguished from other candidates by, for example, reverse display. in this way,
When erroneous input characters are detected, Kana-Kanji conversion is performed using not only keys near the erroneous input characters but also a plurality of replacement candidates determined by a key sequence with the immediately preceding character as in the related art. Thus, the conversion result intended by the user can be obtained.

Although the above embodiment has been described on the assumption that a reading character string is input in the “Roman input mode”, the present invention is not limited to this, and the reading character string is input in the “Kana input mode”. Is input, the same method as described above can be applied. In this case, information according to the key sequence of the “kana input mode” is registered in the erroneous input dictionary 25, and the part of the read character string that could not be converted to the kana kanji is detected as an erroneous input character by referring to the kana-kanji conversion dictionary 26. Then, a replacement candidate for the erroneous input character may be extracted from the erroneous input dictionary 25.

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

[0067]

As described above, according to the first aspect of the present invention, when an erroneous input character is detected, a Kana-Kanji character is determined by using a plurality of replacement candidates determined by a key sequence with the immediately preceding character. Since the conversion is performed, a conversion result intended by the user can be obtained.

According to the second aspect, a plurality of replacement candidates for erroneous input characters are extracted from the erroneous input dictionary in order of priority using a key sequence, and Kana-Kanji conversion using these replacement candidates is performed. Conversion candidates are more likely to be output with priority, and the number of candidate selection operations can be reduced.

According to the third aspect, the output form of the plurality of conversion candidates obtained by the Kana-Kanji conversion is changed according to the priority of each replacement candidate. Can be visually judged.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a system configuration of a document creation device according to an embodiment of the present invention.

FIG. 2 is a block diagram showing a functional configuration of a document creation device realized by the system configuration of FIG. 1;

FIG. 3 is an exemplary view showing the configuration of an erroneous input dictionary according to the embodiment;

FIG. 4 is an exemplary view showing a key arrangement of a keyboard used as an input device in the embodiment.

FIG. 5 is an exemplary flowchart showing the operation of kana-kanji conversion processing in the embodiment.

FIG. 6 is an exemplary flowchart illustrating the operation of an erroneous input correction process in the embodiment.

FIG. 7 is an exemplary flowchart showing the operation of display processing in the embodiment.

FIG. 8 is a specific example for explaining erroneous input correction according to the present invention.

FIG. 9 is a view showing an input character string displayed on a display device and a state of a conversion result.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 11 ... CPU 12 ... Memory 12a ... Program area 12b ... Input buffer 12c ... Replacement candidate buffer 12d ... Conversion candidate buffer 12e ... Document buffer 13 ... Input device 14 ... Display device 15 ... External storage device 16 ... Printing device 17 ... Communication device 21 ... Input unit 22 ... Control unit 23 ... Automatic erroneous input correction unit 24 ... Kana-Kanji conversion unit 25 ... Error input dictionary 26 ... Kana-Kanji conversion dictionary 31 ... Input character string 32 ... Conversion candidate 33 ... Candidate list

 ──────────────────────────────────────────────────の Continued on the front page (72) Inventor Hirofumi Goto 1385 Shinmachi, Ome-shi, Tokyo Toshiba Software Engineering Co., Ltd. (72) Inventor Kunihiro Sakamoto 1385 Shinmachi, Ome-shi, Tokyo Toshiba Software Engineering Co., Ltd. Inside

Claims (5)

[Claims] An input unit for inputting a character string to be converted; an erroneous input detection unit for detecting an erroneous input character in the character string input by the input unit; Replacement candidate creating means for creating a plurality of replacement candidates for the erroneous input character based on the erroneous input character and the key sequence of the character immediately preceding the erroneous input character; and using each replacement candidate created by the replacement candidate creating means. A document creation apparatus, comprising: a conversion unit for converting the erroneous input character into a kana-kanji character; and an output unit for outputting a plurality of conversion candidates obtained by the conversion unit. 2. An erroneous input dictionary storing a character to be corrected and a plurality of replacement candidates of which priorities are determined by a key sequence of a character preceding the correction target dictionary, 2. The document creation apparatus according to claim 1, wherein a plurality of replacement candidates for the erroneous input character are extracted from the erroneous input dictionary in a priority order based on the erroneous input character and the character immediately preceding the erroneous input character. 3. The document creation apparatus according to claim 2, wherein said output means changes an output form of each conversion candidate obtained by said conversion means based on a priority order of each of said replacement candidates. 4. When a character string to be converted is input, an erroneous input character in the character string is detected, and the erroneous character is detected on the basis of the detected erroneous input character and the character immediately before the erroneous input character. Kana-kanji conversion characterized by creating a plurality of replacement candidates for an input character, converting the erroneous input character to kana-kanji using each created replacement candidate, and outputting a plurality of conversion candidates obtained by the kana-kanji conversion. Method. 5. A recording medium storing a kana-kanji conversion program for converting an input character string into kana-kanji characters, wherein when a character string to be converted is input, an erroneous input character in the character string is input. A step of generating a plurality of replacement candidates for the erroneous input character based on the detected erroneous input character and the character immediately preceding the detected erroneous input character; and A computer-readable storage medium storing a program for causing a computer to execute a procedure for converting an input character into kana-kanji characters and a procedure for outputting a plurality of conversion candidates obtained by the kana-kanji conversion.