JPH06236359A - Word processor - Google Patents

Abstract

PURPOSE:To output homonyms as conversion candidates in optimum priority order when KANJI(Chinese character)-KANA(Japanese syllabary) mixed document conversion. CONSTITUTION:A coordinate sequence of a handwritten character inputted from a coordinate input device 1 is stored in the character coordinate data buffer 23 of a controller 2. Then the coordinate sequence of the handwritten character is recognized by a handwritten character recognition part 12, whose recognition result is stored in an input character buffer 25. A KANJI-mixed KANA-KANJI conversion part 13 converts the input character string in the input character buffer 25 into a KANJI-mixed sentence by referring to a KANJI- mixed KANA-KANJI conversion dictionary 42. In the KANJI-mixed KANA- KANJI conversion dictionary 42, the use frequencies of input character strings are registered, pattern by pattern, so a conversion candidate operation part 14 rearranges conversion candidate words and phrases, obtained in a conversion candidate buffer 26 by the KANJI-mixed KANA-KANJI conversion, according to the use frequencies and then displays the conversion candidate word or phrase having the highest use frequency on a display device 3 thorugh a display part 15.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a document creation apparatus using a handwriting input method, and particularly to a conversion candidate for creating a kanji-kana mixed document by converting a kanji-kana mixed character string into kanji-kana mixed kanji. Regarding the output ranking of the.

[0002]

2. Description of the Related Art With the recent progress of pattern recognition technology, a device in which a transparent tablet and a display are laminated and integrated is used to recognize handwritten characters input with a stylus pen or the like,
It has become possible to develop a document creation device such as a handwritten word processor that creates an electronic Japanese document.

In the case of creating a document using a document creating apparatus capable of directly inputting such characters by handwriting, katakana, numbers, symbols, and simple kanji are directly entered by handwriting, and kanji with a large number of strokes, etc. Difficult characters tend to be entered in hiragana. If you create a document by performing Kanji-Kana Kana conversion on a Kanji-Kana Kana-Kana character string input by handwriting like this, efficient input is possible. The priority order of words is determined by the frequency information of headwords registered in the kanji conversion dictionary containing mixed kanji.

By the way, in the conventional kanji-kana-kanji conversion dictionary, one usage frequency is assigned to one word, so that it is irrelevant to what kind of kanji-kana-mixing pattern the word was input. Instead, the homophone priority order is uniformly determined by the frequency. However, in the case of kanji-kana-kana conversion, the priority order of homophones may not be appropriately determined with one piece of frequency information for each word. For example, conversion candidates for words with the reading "Inyou" include "quote" and "drinking". Considering the general frequency of use of both words, the frequency of "quoting" is higher than that of "drinking". large. However, when inputting “in use” and kanji mixed with kana, the input candidate is not “quotation” which is easier to write in kanji, but “drinking” including “drink” with a large number of strokes is the conversion candidate. In many cases, since it is expected, it is appropriate to estimate that the frequency of "drinking" is higher than that of "quoting".

In the case of kanji and kana conversion, for example, when "ka name" is converted, "kana" (kana) and "section name" are converted.
There is a property that words with different pronunciations are output as a kind of homophone. In the conventional kanji / kanji conversion dictionary, the frequency of "kana" is set to be larger than that of "section name" because of the general usage frequency. For this reason, when converting "kaname", conversion candidates are output in the order of "kana" and "section name", but the number of strokes of "kana" is relatively small.
Since it is often entered directly by handwriting, the input person is "section name"
It is presumed that there are many cases in which "Kaname" is entered in the hope that Therefore, when "ka name" is input, it is more appropriate to estimate that the "section name" is used more frequently than the "pseudonym", contrary to the conventional case. As described above, in kanji-kana-kana conversion, the frequency of use of words is not constant, and the use frequency according to the kanji-kana-mix input pattern that includes the word is adopted to avoid kanji-kana-kana conversion. Will not be able to convert properly.

[0006]

When converting a kanji-mixed kana character string input by handwriting as described above into a kanji-mixed kana-kanji character string, the kanji-mixed kana character string input like a conventional dictionary is used. Regardless of the pattern, if only a uniform frequency of use is registered for one word, the output priority of conversion candidate phrases in kanji conversion that mixes kanji is not necessarily appropriate, and conversion efficiency deteriorates. there were.

Therefore, the present invention eliminates the above-mentioned drawbacks and outputs the homophones in the conversion candidates when the Kanji-mixed kana-character string input by handwriting is converted into the kanji-mixed kana-character with the optimum priority. Accordingly, it is an object of the present invention to provide a document creation device capable of improving conversion efficiency.

[0008]

SUMMARY OF THE INVENTION The present invention recognizes a kanji-mixed kana character string input by handwriting and converts it into an input character string consisting of a character code, and then converts this input character string into kanji mixed kana-kanji character conversion. In the document creating apparatus for creating a document, a kanji-blending kanji conversion dictionary in which the frequency of use and conversion candidate words are registered for each of a plurality of character string patterns forming the input character string, and the input character string are When kana-kanji conversion is performed by referring to the kanji-kana-kana conversion dictionary, the frequency of use corresponding to the pattern of the input character string is obtained from the kanji-kana-kana conversion dictionary, and the kanji-kana-kana conversion is performed in the order of frequency of use. And a conversion unit that outputs a conversion candidate word obtained from the business dictionary.

[0009]

In the document creating apparatus of the present invention, the kanji-mixed kanji conversion dictionary has a usage frequency and conversion candidate words registered for each of a plurality of character string patterns forming an input character string. The conversion means obtains the frequency of use corresponding to the pattern of the input character string from the kanji / kana-kanji conversion dictionary when converting the input character string into kana / kanji by referring to the kanji / kana-kanji conversion dictionary. The conversion candidate words obtained from the Kanji conversion dictionary for kanji mixed with each other are output in order of frequency of use. Therefore, if the frequency of use registered for each of the input character string patterns corresponds to the frequency of use of the converted character string intended by the handwritten character input person, the conversion candidate phrase as intended by the handwritten character string input person is first displayed. Then, the conversion efficiency can be improved.

[0010]

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 an embodiment of a document creating apparatus of the present invention. Reference numeral 1 is a coordinate input device including, for example, a tablet and a stylus pen, 2 is a control device for controlling document creation, and includes an input control unit 11 and a handwritten character recognition unit 1.
2. Kana and Kana conversion unit 13, Kanji conversion operation unit 1
4. A processing unit including a display unit 15 and a buffer memory including a coordinate data buffer 21, a screen area coordinate buffer 22, a character coordinate data buffer 23, a recognized character type buffer 24, an input character buffer 25, and a conversion candidate buffer 26. There is. Reference numeral 3 denotes a display device including, for example, a liquid crystal display, which displays a handwriting input by the coordinate input device 1 and a plurality of conversion candidate character strings obtained as a result of kanji and kana / kanji conversion. An external storage device 4 such as a floppy disk stores a handwritten character recognition dictionary 41, a kanji / kana mixing conversion dictionary 42, data used for initialization of the control device 2, and the like.

FIG. 2 is a diagram showing a concrete configuration example of the coordinate input device 1, the control device 2 and the display device 3 shown in FIG. The coordinate input device 1 made of a transparent tablet is laminated on a display device 3 such as a liquid crystal display to integrally form an input display device. This input display device is the control device 2
When the operator attaches a character or the like on the transparent tablet 1 with the stylus pen 5, the control device 2 recognizes this and displays it on the liquid crystal display 3.

Next, the operation of this embodiment will be described. The input control unit 11 of the control device 2 stores the coordinate value input by the coordinate input device 1 in the coordinate data buffer 21, and the coordinate value and the character recognition frame on the screen stored in the screen area coordinate buffer 22. And position information such as kana-mixed kana conversion icon and recognition character type icon,
When the coordinate value is within the character recognition frame, the coordinate value is stored in the character coordinate data buffer 23, and then the handwritten character recognition unit 12 is activated. If the coordinate values are in the kanji conversion icon containing kanji, the recognized character type buffer 2
The information of the corresponding recognized character type in 6 is changed. here,
The recognition character type buffer 26 can separately specify whether or not to recognize each handwritten character type such as hiragana, katakana, kanji, alphanumeric characters, etc., and recognizes each time the corresponding recognition character type icon is pressed.・ The information that is not performed is switched. Specifically, as shown in FIG. 4, for example, these icons are displayed on the display device 3 together with the recognition frame 101 and the conversion candidates 102 for kanji / kanji conversion, and by inputting coordinates in the icon area 100. It is possible to confirm this by activating kana-kana-kana conversion, specifying a plurality of recognized character types, and displaying the icon corresponding to the currently specified character type in reverse video.

The kanji / kana-kanji conversion dictionary 42 is capable of searching for kanji / kanji-mixed words and storing individual frequency information for each input pattern.
The conversion candidate character string is stored in the conversion candidate buffer 26 together with its frequency at this time by converting one or more clauses of the character string stored in the input character buffer 25 into a character string containing Kana-Kanji. After that, the conversion candidate operation unit 14 is activated. The kanji-mixed-kana-kanji conversion dictionary 42 registers, as shown in FIG. 3, for example, all input character string patterns mixed with kanji as readings, and stores frequency information for each input character string pattern.

The conversion candidate operation section 14 rearranges the conversion candidate character strings in the conversion candidate buffer 26 in descending order of frequency with reference to the above frequency information, and then activates the display section 15.
The display unit 15 displays the character recognition frame 10 as shown in FIG.
In addition to displaying 1 and various icons 100 and the like, the character information input from the coordinate input device 1 is displayed as a handwriting pattern, and the characters recognized by the handwritten character recognition unit 12 and the conversion candidate buffer 26 are stored. The plurality of conversion candidate character strings 102 being displayed are displayed.

Next, the operation of each processing of the control device 2 will be described with reference to FIG.
It will be described in more detail with reference to the flowchart shown in FIG. First, in step 501, the initialization work is performed, and the display device 3
The coordinate values of the area of the character recognition frame, the recognized character type icon, and the kana-kanji conversion icon set on the screen of the external storage device 4 are stored in the screen area coordinate buffer 22 of the control device 2.
Read from and other buffers are cleared. Next, in step 502, the input control unit 11 of the control device 1 reads the coordinate value from the coordinate input device 1 and stores it in the coordinate data buffer 21. In step 503, the input coordinate value and the screen area coordinate buffer 22. The position information of the character input frame area on the screen stored in is compared. If the input coordinate value is within the character input frame, the process proceeds to step 504, where this coordinate value is stored in the character coordinate data buffer 23, and then the handwritten character recognition unit 12 is activated. The handwritten character recognition unit 12 recognizes the coordinate value string stored in the character coordinate data buffer 23 as a character in step 505, and the character string obtained as a result of recognition is recognized in step 5
After being stored in the input character buffer 25 at 06, the process returns to step 502 to restart the coordinate input.

On the other hand, when it is determined that the coordinate value input in step 503 is outside the character input frame, the process proceeds to step 507, and the input coordinate value is compared with the position coordinates of various icons. As a result, if the input coordinate value is outside the kana-kanji conversion icon area, the process proceeds to step 512, and if it is within the area, the process proceeds to step 508 to activate the kanji / kana-kanji conversion unit 13. On the other hand, step 512
Then, it is determined whether the input coordinate value is within the character type icon, and if it is within the area of the recognized character type icon, step 5
13, the recognized character type buffer 24 is set here, and then the process returns to step 502. On the other hand, if the coordinate value is outside the character type icon, the process immediately returns to step 502. In step 508, the kanji / kana / kanji conversion unit 13 refers to the kanji / kana / kanji dictionary 42 to convert one or more clauses of the character string stored in the input character buffer 25 into a kana / kanji mixed character string. In step 509, after the character string obtained as a result of the conversion and its frequency are stored in the conversion candidate buffer 26, the conversion candidate operation unit 14 is activated.
In step 510, the conversion candidate operation unit 14 rearranges the candidate character strings in the conversion candidate buffer in descending order of frequency and activates the display unit 15. The display unit 15 displays the conversion candidate character string stored in the conversion candidate buffer 26 on the display device 3 in step 511, and then returns to step 502,
Restart coordinate input.

This situation will be concretely described below with reference to the drawings. Now, as shown in FIG. 6, after the input person inputs “Inyo” into the character input frame 101 of the coordinate input device 1, the kanji mixed kana-kanji conversion icon [Conversion] is pressed with the stylus pen to mix kanji. Fig. 3 shows the conversion of Rikana to Kanji.
As can be seen from the example of the kanji conversion kana-kanji conversion dictionary 42 shown in Fig. 2, "quoting" (frequency 10) and "drinking" (frequency 6) in order of 2
One conversion candidate is displayed on the display device 3. Next, if you enter "Purpose" as shown in Fig. 7, "Drink" (frequency 6)
The conversion candidates are displayed on the display device 3 in the order of “citation” (frequency 3). This is because, as the psychology of the input person, when it is desired to input “quote” as the first candidate, it is presumed that in many cases, “quote” is directly input in Kanji instead of writing “use”. In this way, when determining the priority of conversion candidates for kanji-mixed kana conversion, by using the frequency information that takes into account the pattern of input kanji-mixed character strings, the conversion candidates intended by the inputter are ranked higher. Can be displayed.

According to the present embodiment, the kanji-kana-kana-kanji conversion dictionary 42 has the usage frequency registered for each input character string pattern as shown in FIG. 3, and the input character string pattern is input by handwriting. Since the frequency of use is determined in consideration of the conversion intention of the input person at the time, conversion candidate words obtained from the dictionary 42 when converting the input character string pattern into kanji or kanji are arranged in the order of frequency of use. When displayed on the display device 3, the probability that the first conversion candidate word will be the word desired by the input person is significantly higher than in the past,
It is possible to improve the conversion efficiency of kanji mixed with kanji and facilitate document creation by inputting handwritten characters.

The present invention is not limited to the above embodiment. For example, a method for recognizing characters may be a method other than the above embodiment, and a Kanji conversion dictionary with mixed Kanji is not always the same as this embodiment. It does not have to take such a structure. In short, various modifications can be made without departing from the gist of the present invention.

[0020]

As described above, according to the document creation apparatus of the present invention, the same phoneme in the conversion candidates when the Kanji-mixed kanji character string input by handwriting is converted into the kanji-mixed kanji character is given the optimum priority. The conversion efficiency can be improved by outputting in order.

[Brief description of drawings]

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

2 is a diagram showing an example of an external configuration of the document creating apparatus shown in FIG.

FIG. 3 is a diagram showing an example of the structure of a kanji / kanji conversion dictionary shown in FIG.

FIG. 4 is a diagram showing an example of a screen of the display device shown in FIG.

5 is a flowchart showing an example of a document creation process by the control device shown in FIG.

6 is a diagram showing an input example of a kanji / kana mixed sentence and a display example of conversion candidates thereof in the document creating apparatus shown in FIG.

FIG. 7 is a diagram showing another input example of a kanji / kana mixed sentence and its display example in the document creating apparatus shown in FIG.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Coordinate input device 2 ... Control device 3 ... Display device 4 ... External storage device 11 ... Input control unit 12 ... Handwritten character recognition unit 13 ... Kanji mixed kana / Kanji conversion unit 14 ... Conversion candidate operation unit 15 ... Display unit 21 ... Coordinates Data buffer 22 ... Screen area coordinate buffer 23 ... Character coordinate data buffer 24 ... Recognized character type buffer 25 ... Input character buffer 26 ... Conversion candidate buffer 41 ... Handwritten character recognition dictionary 42 ... Kanji mixed Kanji conversion dictionary

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Kenji Suzuki 70 Yanagimachi, Saiwai-ku, Kawasaki-shi, Kanagawa Toshiba Yanagimachi Factory

Claims (1)

[Claims] 1. A document for creating a document by recognizing a character string mixed with Kanji input by handwriting and converting it into an input character string consisting of a character code, and then converting this input character string with Kanji mixed character. In the creating device, a kanji-kana-kanji conversion dictionary in which a usage frequency and a conversion candidate phrase are registered for each of a plurality of character-string patterns forming the input character string, and the input character string is the kanji-kana kana-kanji conversion dictionary. When kana-kanji conversion is performed, the frequency of use corresponding to the pattern of the input character string is obtained from the kanji-mixed kana-kanji conversion dictionary, and the conversion obtained from the kanji-mixed kana-kanji conversion dictionary in the order of frequency of use. A document creating apparatus comprising: a conversion unit that outputs a candidate phrase.