JPH032960A - Kana/kanji converting device - Google Patents

Abstract

(57) [Summary] This bulletin contains application data before electronic filing, so abstract data is not recorded.

Description

DETAILED DESCRIPTION OF THE INVENTION Field of Application to Industry The present invention relates to a kana-kanji conversion device that converts input kana data into a kana-kanji mixed string.

2. Description of the Related Art In recent years, kana-kanji conversion devices have been widely used in various Japanese language processing devices as devices for inputting Japanese characters. The kana-kanji conversion device can convert an input kana string into a kana-kanji mixed string. For example, the next kana column today's reading should be swollen.

If you enter The weather is sunny today.

You can perform the conversion with In addition, some recent kana I] character conversion devices are capable of increasing the efficiency of selecting homophones by referring to data on semantic connections between independent words. For example, the next kana column this year measures the success and success of the year.

Suppose we input and perform the conversion. The expressions for ``kojiyo'' include ``factory,''``improvement,'' and ``courtesy,'' but dictionaries have registered that ``productivity'' and ``improvement'' are connected as semantic conjunction data between independent words. We will refer to it and aim to improve productivity this year.

You can perform the conversion with

Problems to be Solved by the Invention However, when inputting a kana string, the conventional kana-kanji conversion device described above does not convert between independent words unless complex phrases containing semantically connected independent words are treated as one conversion unit. There was a problem that semantically connected data could not be used. In other words, in the conventional kana-kanji conversion device, no matter what the most recently input and finalized conversion sentence is, the concatenation between independent words is referred to only in units of conversion. For example, the text used in explaining conventional technology aims to improve productivity this year.

When trying to enter This year is special By converting, we get the following kanji string.

This year is all about productivity. next, Measure your health.

Assume that we input and perform conversion on this string.

Conventional kana-kanji conversion devices do not refer to the independent words ``this year'' and ``productivity'' that were the units of previous conversion, so there is no data to support semantic conjunctions.

Therefore, the priority order of candidates for "Kojiyo" is the order in which they are registered in the dictionary or the order in which they are ranked through learning. Therefore, the conventional kana-kanji conversion device produces the following conversion result, for example.

Plan the factory.

Combined with the previous conversion unit, ``This year is the year of productivity,'' the overall goal is to become a productive factory this year.

This will result in incorrect conversion results.

Means for Solving the Problem In order to solve this problem, the present invention includes an independent word storage means for storing an independent word determined immediately before, and stores the independent word determined immediately before by referring to an independent word continuity table. , now converts newly input Kana data.

Effect: With the above configuration, an input kana string is converted into a sentence containing kanji and kana while referring to the independent words of the previous conversion result.

Embodiment Hereinafter, a kana-kanji conversion device according to an embodiment of the present invention will be described with reference to the drawings.

FIG. 1 is a functional block diagram of a kana-kanji conversion device according to an embodiment of the present invention, in which 1 is an input means having a means for inputting a baka string and a means for instructing conversion from a kana string to a kanji-kana mixed string; 2 is an input means; 1 is an input kana string storage unit that stores the kana strings created manually; 3 is a word dictionary that stores word pronunciations, kanji notation, and part-of-speech information in pairs; 4 is a grammar between words with each part-of-speech attribute. 5 is an independent word conjunctive table that records the degree of semantic connection between independent words, and 6 is a memorized independent word information for the most recently converted Kanji-kana mixed string. last-minute conversion information storage unit, 7
searches for the word term 'a3 while referring to the independent words stored in the part-of-speech indirection table 4, the independent word concatenation table 5, and the conversion information storage section 6, and converts the kana string stored in the input kana string storage section 2 into kanji. The kana-kanji conversion control unit converts the kana-mixed string into a kana-mixed string, stores the independent word information of the conversion result in the previous conversion information storage unit 6, and outputs the notation of the conversion result. An output character string storage unit 9 stores the strings, and 9 is a display means for displaying the kanji-kana mixed strings stored in the output character string storage unit 8.

FIG. 2 is a circuit block diagram of the kana-kanji conversion device of this embodiment, where 10 is a keyboard, 11 is a central processing unit (hereinafter abbreviated as CP'U), and 12 is a cathode ray tube display (hereinafter referred to as CRT display). ), 13 is a read-only memory (hereinafter abbreviated as ROM),
14 is a random access memory (hereinafter abbreviated as RAM).

The input means 1 shown in FIG. The independent word conjunction table 5 is stored in the ROM 13, and the kana-kanji conversion control unit 7 is stored in the CPU II in the ROM 13.
and RO while exchanging data with RAM14.
By executing the program stored in M13,
The display means 9 is realized by a CRT display 12. The ROM 13 also stores a control program according to the flowchart shown in FIG.

FIG. 4 is a diagram showing the data structure of the word dictionary 3. The word dictionary 3 stores readings expressed in kana data, corresponding notations as kanji data, and parts of speech of each notation.

FIG. 5 is a diagram showing the data structure of the independent word continuation table 5. For example, since the independent word "steel manufacturing" is often followed by the independent word "factory", these two independent words are paired,
It also remembers multiple pairs of independent words that have a high probability of being consecutive.

The operation of the kana-kanji conversion apparatus of this embodiment configured as described above will be explained below based on the flowchart shown in FIG.

Assume that as the last conversion, ``This year is the year of the year'' was input, and the result of the conversion was ``This year's productivity'' was obtained. In this case, the immediately preceding conversion information storage unit 6 stores, as shown in FIG.
It is stored that the independent word of the last clause was "productivity."

First, when a clear sequence is input to the input means 1 in step (a), its contents are stored in the input non-column storage section 2.

For example, the following column Measure your health.

When inputted through the input means 1, the human input is stored in the string storage section 2. When the conversion key of the input means 1 is further operated, the process proceeds to step (B), where the Gana-Kanji conversion control section 7 searches the word dictionary 3 and the part-of-speech connection table 4 to determine the next clause break. FIG. 4 is a diagram showing the contents of the word dictionary 3 of one embodiment. In the example sentence, "Kojiyowo"
up to becomes the next clause. Generally, even when the division of a bunsetsu is decided, there are multiple lengths of independent words that make up the clause, and even independent words of the same length have different spellings. In this example, ``Kojiyo'' is the only reading of the independent word in the bunsetsu, and the independent words in this reading include ``factory,''``improvement,''``courtesy,'' and ``kujo.'' It is not possible to decide at this point which reading to adopt. Figure 7 shows candidates for independent words in the extracted bunsetsu.

Next, in step (c), the kana-kanji conversion control section 7 retrieves the independent words stored in the immediately preceding conversion information storage section 6. Next, in step (d), while referring to the independent word concatenation table 5, the dekana kanji conversion control unit 7 searches for a conjunctive meaning between the independent word in the clause before ia and the independent word selected as a candidate, and Select a word. In the example case, "productivity" and "improvement"
is searched for to be concatenated, and "improvement" is selected as the independent word.

At this time, the independent word "improvement" adopted in the current clause is stored in the immediately preceding conversion information storage unit 6. Next, in step (e),
Check whether all input sentences have been converted, and if so, proceed to step (to).

If not completed, perform the operation from step (b).

FIG. 8 shows the contents of the previous conversion information storage section 6 after the current conversion is completed. The information stored in the previous conversion information storage section 6 is referenced at the time of the next conversion. The conversion result is stored in the output character string storage section 8. Next, the process proceeds to step (to), and the conversion result is displayed on the display means 9 as shown in FIG.

As described in detail, the present invention performs kana-kanji conversion while referring to the conjunctive information of the independent words of the conversion result that was just converted and confirmed, thereby performing semantic processing across input units and correcting the errors. You can convert columns to kanji/kana mixed columns, allowing you to input sentences efficiently.

[Brief explanation of drawings]

FIG. 1 is a functional block diagram of a kana-kanji conversion device according to an embodiment of the present invention, FIG. 2 is a circuit block diagram of the device, and FIG.
The figure is a flowchart of the process, Figure 4 is a schematic diagram showing the contents of the word dictionary, Figure 5 is a schematic diagram showing the contents of the independent word concatenation table, and Figures 6 and 8 are the contents of the previous conversion information storage section. 7 is a diagram showing the word candidates raised during processing, and FIG. 9 is a diagram showing an example of a display of a string of kanji and kana mixed as a result of conversion. l...Input means 2...Input kana string storage unit 3...Word dictionary 4...Part-of-speech connection table 5...Independent word Concatenation table 6... Last-minute conversion information storage section 7... Kana-Kanji conversion control section 8... Output character string storage section 9... Display means 0... ... Keyboard ■ ... CPU 2 ... CRT display 3 ... ROM 4 ... RAM

Claims (1)

[Scope of Claims] A storage means for storing input kana data, an independent word continuous table storing a plurality of independent word pairs with a high connection frequency, an independent word storage means for storing an independent word determined immediately before, Kana-kanji converting means for converting newly input kana data stored in the storage means into kanji-kana mixed data by referring to the independent word continuation table for the continuity with the independent words stored in the independent word storage means; A kana-kanji conversion device characterized by having the following.