JPH07121651A - Language recognizing device - Google Patents

Abstract

PURPOSE:To provide a language recognizing device which can decide later what a user supplied when he referred to the input data on a language by storing this input data itself if this data could not be recognized. CONSTITUTION:A language recognizing device consist of a recognizing means 2 which recognizes the input data on a language, a storage means 3 which stores the data corresponding to the input data based on the recognizing result of the means 2, an output means 4 which outputs the data stored in the means 3 or the language accordant with the stored data, and a control means 5 which controls the operations of means 2, 3 and 4 so as to output the data stored in the means 3 through the means 4 when the means 2 didn't recognize the input data and to output the language accordant with the data stored in the means 3 through the means 4 when the means 2 recognized the input data respectively.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a language recognizing device, and more particularly to a language recognizing device capable of outputting input data as it is when the input data regarding the language cannot be recognized. .

[0002]

2. Description of the Related Art A variety of conventional language recognition devices have been implemented, including handwritten character recognition devices and voice recognition devices. There are those that record the mark "I did not exist" and those that repeatedly request input until they can be recognized.

Further, in OCR, there is a system in which an original image is stored and the recognition result and the original image are compared to facilitate the correction of the erroneously recognized character.

[0004]

However, in the first method of the prior art, the data input when it cannot be recognized is lost. Humans can often recognize data that the recognition device could not recognize, so this data should be utilized.

In the second conventional method, the OC is used.
It is necessary to store all the image data read by R, which requires a large storage area.

Further, in the conventional method, it is judged from the user's impression that it is better for the user to recognize the closest character by force rather than repeatedly request the input, or even if the judgment at the time of recognition is bad. In some cases, I was forced to recognize it as a certain character.

The object of the present invention is to save the input data itself when the user cannot recognize the input data relating to the language so that the user can later recognize the input data.
It is to provide a language recognition device capable of discriminating what is input when a user refers to data.

[0008]

The above-mentioned object is to realize a recognition means for recognizing input data relating to a language, and data corresponding to the input data according to the recognition processing result of the recognition means.
Storage means for storing the data, output means for outputting one of the data stored in the storage means and a language corresponding to the data, and the recognition means did not recognize the input data. In this case, the data stored in the storage means is output to the output means, and when the recognition means recognizes the input data, the language corresponding to the data stored in the storage means is output. And a control means for controlling the operation of the recognition means, the storage means and the output means so as to output the means.

[0009]

The recognizing means recognizes the input data relating to the language.

The storage means stores the data corresponding to the input data according to the recognition processing result of the recognition means.

The output means outputs one of the data stored in the storage means and the language corresponding to the data.

The control means outputs the data stored in the storage means to the output means when the recognition means does not recognize the input data, and the recognition means outputs the data. Is recognized, the data stored in the storage means is stored.
The operation of the recognition means, the storage means, and the output means is controlled so that the output means outputs a language corresponding to the data.

[0013]

1 is a block diagram showing an embodiment of a language recognition apparatus according to the present invention.

The language recognition apparatus according to this embodiment has an input means 1 for inputting data to be recognized, a recognition means 2 for recognizing a language, and recognized (coded) data. Alternatively, the storage means 3 for storing the unrecognized data (the input data as it is) and the language corresponding to the recognized data stored in the storage means 3 or the input data as it is is output. Output means 4 for controlling the operation of the apparatus, and control means 5 for controlling the operation of the entire apparatus.
Storage means 3 together with the recognized and coded input data
By storing it in the
When referring to the data, it is possible to determine what was input.

That is, the input data input from the input means 1 is passed to the recognition means 2 by the control means 5.
Here, the input data is also passed to the output means 4 and output as necessary.

The recognition means 2 carries out a recognition process based on the received input data. And if it can be recognized,
The coded data after the recognition is stored in the storage means 3, and if it is not recognized, the unrecognized input data itself is stored in the storage means 3.

At the time of output, if the coded data after recognition is converted into the form at the time of inputting characters, voice, etc. according to the contents of the storage means 3, it is output from the output means 4, but the recognition is performed. In the case of the data that could not be obtained, since the input data itself is stored, it is output from the output means 4 as it is.

FIG. 2 is a block diagram showing a first modification of the embodiment of the language recognition apparatus.

A first modified example of the embodiment of the language recognition device is an input means 11, a handwritten character recognition means 12, and a storage means 13.
The output means 14 and the control means 15 for controlling the operation of the entire apparatus. The control means 15 is located at the center of the device,
It has a microprocessor or a dedicated LSI. The input means 11 is a tablet device equipped with a light pen, an electronic pen using a pressure sensitive sheet, electromagnetic induction, or the like.
The handwriting of the written handwritten character is input to the control means 15.
The output unit 14 is composed of a display such as a CRT or a liquid crystal, and displays the handwriting input from the input unit 11, the characters stored in the storage unit 13 or the unrecognized handwriting.

The handwritten character recognizing means 12 is also provided with a microprocessor or a dedicated LSI (like the control means 15) similarly to the control means 15, and recognizes the handwriting data input from the input means 11.

If the handwritten character recognition means 12 can recognize the input handwriting, the flag indicating that the handwriting has been recognized and its character code are stored in the storage means 1 via the control means 15.
If the input handwriting cannot be recognized, the flag indicating that the handwriting is not recognized and the input data are stored.
The data itself is stored in the storage means 13. That is, the data read from the storage means 13 is provided with a flag indicating whether it is character code or input data itself.

FIG. 3 is a flow chart for explaining the input of characters according to the first modification of FIG.

In FIG. 3, the handwritten character recognizing means 12 recognizes the input handwriting (3-1). If it can be recognized, the flag indicating that it is a character code and the character code of the recognized character are stored in the storage means 13 (3
-2, 3-3). If it cannot be recognized, a flag indicating that it cannot be recognized (this can be said to be a flag indicating that the data is the input data itself) and the input data that cannot be recognized are the storage means 13. (3-2, 3-4).

Next, the processing for outputting the information thus stored will be described.

At this time, the data is read from the storage means 13 and the value of the flag added to the data is checked. If it is a flag representing a character code, the data is regarded as a character code and the character represented by the character code is output to the output means 14. If it is a flag indicating that it cannot be recognized, the data is regarded as the input data itself (that is, the handwriting at the time of input), and the input data itself is output to the output means 14. .

FIG. 4 is a flow chart for explaining the output of characters according to the first modification of FIG.

Data is read from the storage means 13 (4-
1) Check the value of the flag added to the data (4
-2).

If this flag is a flag representing a character code, the read data is regarded as a character code and the character corresponding to the character code is output to the output means 14 (4
-3) On the other hand, if this flag is a flag representing the input data, the data is regarded as the input data itself (that is, the handwriting at the time of input) and output to the output means 14 (4-).
4).

There are various methods of adding a flag to the data, but a simple example will be described below.

(1) When the handwriting at the time of input is stored as graphic data The first bit is used as a flag, and if it is 0, it is a "character code", 1
Then, "input data" will be represented. This flag is 0
If, then the character code itself follows. When this flag is 1, a numerical value indicating the size of the graphic data representing the handwriting follows, and then the graphic data itself representing the handwriting is placed.

FIG. 5 is a diagram for explaining the data structure when the handwriting at the time of input is recognized, and FIG. 6 is a diagram for explaining the data structure when the handwriting at the time of input is not recognized. .

In FIG. 5 (when the handwriting can be recognized),
20 is a storage area for inputting flag 0, 21 is a character code
The reference numeral 22 indicates graphic data representing the character "a", the flag 0 is stored in the storage area 23 of the storage means 13, and the storage area 24 is represented by "a".
The character code (0001) is stored.

In FIG. 6 (when the handwriting cannot be recognized), 25 is a storage area in which the flag 1 is to be input, and 26 is the size of input data (the number of dots in the horizontal direction and the number of dots in the vertical direction). Storage area 27, a storage area 27 into which the input data itself (bit image data) should be input, 2
Reference numeral 8 denotes graphic data representing the character "a". The flag 1 is stored in the storage area 29 of the storage means 13, and the horizontal 1 which is the bit image size in this case is stored in the storage area 30.
The data representing 1 dot and 11 dots in the vertical direction includes 31 bit image data (000, 138, 31) in which each line of the bit image is divided into 4 dots and is expressed by a hexadecimal number of 3 digits. ... 450,000) is stored. In this example, it is desirable that the horizontal dot number of the bit image is a multiple of 4. However, referring to the size data, it is found that the horizontal dot number is 11, and the last 1 bit is obtained. Can be determined to be dummy data, so there is no problem.

(2) When the handwriting at the time of input is stored as stroke data The first bit is used as a flag, and if it is 0, "character code", 1
Represents "input data". When this flag is 1, a numerical value indicating the size (stroke number) of stroke data representing handwriting is followed, and then stroke data itself representing handwriting is placed.

FIG. 7 is a diagram for explaining another data structure when the handwriting at the time of input can be recognized, and FIG. 8 shows another data structure when the handwriting at the time of input is not recognized. FIG.

In FIG. 7 (when the handwriting can be recognized),
Reference numeral 35 is a storage area for inputting flag 0, and 36 is a character code.
A storage area for inputting the code itself, 37 indicates graphic data representing the character "i", a flag 0 is stored in the storage area 38 of the storage means 13, and a "i" is stored in the storage area 39.
The character code (0002) is stored.

In FIG. 8 (when the handwriting cannot be recognized), 40 is a storage area in which the flag 1 is to be input, 41 is a storage area in which the number of strokes of the input data itself is to be input, and 42 is an input. Of the data itself, a storage area for inputting vector data, 43 is graphic data representing the character "i", and the storage area 4 of the storage means 13 is shown.
4 has flag 1 and storage area 45 has 2 strokes.
However, in the storage area 46, the stroke data ((2, 2,
2) (-1, 6, 6) (1, 1, 1) (9, 2, 1) (0,
1, 5)) is stored. In this case, the stroke data is the x coordinate of the starting point, the y coordinate of the starting point, and the number of continuous straight lines followed by the number of continuous straight lines (direction x component, direction y component, length). It is represented as a thing.

FIG. 9 is a block diagram showing a second modification of the embodiment of the language recognition apparatus.

In FIG. 9, reference numeral 51 is input means, 52 is voice recognition means, 53 is storage means, 54 is output means, and 55 is control means for controlling the operation of the entire apparatus.

The control means 55 is arranged at the center of the apparatus and is provided with a microprocessor or a dedicated LSI. The input unit 51 is a voice input device equipped with a microphone or the like, and inputs the sound that has been produced to the control unit 55. The output means 54 is composed of a voice output device including a voice synthesizer and a speaker.

The voice recognition means 52 is also similar to the control means 55.
A microprocessor or a dedicated LSI is provided (may be shared with the control unit 55), and recognizes the voice input from the input unit 51.

If the voice recognizing means 52 can recognize the inputted voice, the voice recognizing means 52 stores the flag indicating that the voice has been recognized and the character code thereof in the storing means 53 via the control means 55. If the recognized voice cannot be recognized, the flag indicating that the voice cannot be recognized and the input data itself are stored in the storage means 53. That is, the storage means 5
A flag is added to the data read from No. 3 to indicate whether it is character code or input data itself.

FIG. 10 is a flow chart for explaining the input of characters according to the second modification shown in FIG.

In FIG. 10, the voice recognition means 52 performs recognition processing of the input voice (10-1).

If the character code is recognized, the flag indicating the character code and the character code are controlled by the control means 55.
It is stored in the storage means 53 via (10-2, 10-
3).

If it cannot be recognized, it is a flag indicating that it cannot be recognized (this can be said to be a flag indicating that the data is the input data itself) and the input data itself that cannot be recognized. Is stored in the storage means 53 (10-2, 10-4).

Next, the processing for outputting the information thus stored will be described.

First, the data is read from the storage means 53 and the value of the flag added to the data is checked.

If the flag is a flag representing a character code, the data is regarded as a character code and the voice of the character represented by the character code is output to the output means 54.

If the flag indicates that it cannot be recognized, the data is regarded as the input data itself (that is, the voice at the time of input), and the input data itself is output means 54. Output to.

FIG. 11 is a flow chart for explaining the output of characters according to the second modification shown in FIG.

Data is read from the storage means 53 (11
-1), the value of the flag added to the data is checked (11-2). If this is a flag representing a character code, the read data is regarded as a character code, and the voice corresponding to the character code is output to the output means 54 (11-
3) If this flag is a flag representing input data, the data is regarded as the input data itself (that is, the voice at the time of input) and is output to the output means 54 (11-
4).

There are various methods for adding a flag to the data, but a simple example will be described below.

The first bit is used as a flag, and 0 indicates "character code" and 1 indicates "input data". When this flag is 0, the character code itself follows.
When this flag is 1, a numerical value indicating the size of PCM data representing voice is followed, and PCM data itself representing voice is placed thereafter.

FIG. 12 is a diagram for explaining the data structure when the voice at the time of input is recognized, and FIG. 13 is a diagram for explaining the data structure when the voice at the time of input is not recognized. is there.

In FIG. 12 (when the voice can be recognized), 60 is a storage area for inputting the flag 0, 61 is a storage area for inputting the character code itself, and 62 is a waveform of the voice "U". Storage area 6 of the storage means 53
3 has a flag 0, and the storage area 64 has a character "U".
Code (0003) is stored.

In FIG. 13 (when voice cannot be recognized), 65 is a storage area in which the flag 1 should be input, and 66 is a storage area in which the size of input data (the number of bytes of input data) should be input. , 67 is the input data itself (PCM data
Storage area 6 of the storage means 53, and 68 indicates the waveform of the input voice "U".
9 indicates the flag 1, the storage area 70 indicates the size (9753) in this case, and the storage area 71 indicates the PCM data (8
0, 25, ... 30, 96) are stored.

In the second modification, a device capable of recognizing and storing a voice and outputting the voice later is taken as an example, but this can be applied to a voice input word processor or the like. For example, when the voice cannot be recognized, a symbol indicating that is displayed on the screen of the word processor, and when the portion is pointed by a cursor key or an electronic pen, the unrecognized voice data itself is output. Such a device may be used.

In this embodiment, the input data itself, which is not recognized by the recognition device, is stored so that the user can input what he / she will refer to later. The recognition process can be performed so that it can be discriminated whether or not it is done.

[0060]

EFFECT OF THE INVENTION Input data that the recognition means cannot recognize.
Even if the recognition means cannot recognize the input data, the user can recognize the input data based on the data output to the output means without re-inputting the language. It is possible to make a distinction, save the storage area of the storage means, and efficiently perform language recognition.

[Brief description of drawings]

FIG. 1 is a block diagram showing an embodiment of a language recognition device of the present invention.

FIG. 2 is a block diagram showing a first modification of the embodiment of the language recognition device.

FIG. 3 is a flowchart illustrating input of characters according to the first modification of FIG.

FIG. 4 is a flowchart for explaining the output of characters according to the first modification of FIG.

FIG. 5 is a diagram illustrating a data structure when a handwriting at the time of input can be recognized.

FIG. 6 is a diagram illustrating a data structure when a handwriting at the time of input cannot be recognized.

FIG. 7 is a diagram illustrating another data structure when a handwriting at the time of input can be recognized.

FIG. 8 is a diagram illustrating another data structure in the case where the handwriting at the time of input cannot be recognized.

FIG. 9 is a block diagram showing a second modification of the embodiment of the language recognition device.

FIG. 10 is a flowchart illustrating input of characters according to the second modified example of FIG. 9.

FIG. 11 is a flowchart illustrating the output of characters according to the second modification of FIG. 9.

FIG. 12 is a diagram illustrating a data structure when a voice at the time of input can be recognized.

FIG. 13 is a diagram showing a case where the voice at the time of input cannot be recognized.
It is a figure explaining the data structure.

[Explanation of symbols]

 1 Input Means 2 Recognition Means 3 Storage Means 4 Output Means 5 Control Means

Claims (1)

[Claims] 1. A recognition means for recognizing input data relating to a language, a storage means for storing data corresponding to the input data according to a recognition processing result of the recognition means, and the storage means. Output means for outputting one of the stored data and a language corresponding to the data; and data stored by the storage means when the recognition means does not recognize the input data. To the output means, and when the recognizing means recognizes the input data, the recognizing means and the storing means output the language corresponding to the data stored in the storage means to the output means. And a control means for controlling the operation of the output means.