JP2001060149A - Document preparing device, and recording medium recorded with document preparation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a document preparing device and a recording medium in which a document preparing processing program is recorded, capable of applying a recognizing processing to arbitrary speech data and displaying the data as character information in a prescribed area, and excellent in operability. SOLUTION: At the time of drag 1 drop to a patient name input area 23 of a medical certificate preparation window 102 by operating a mouse and selecting an audio data file 'file 1' in which 'patient name' is recorded (S4), the date/time of consultation or name of doctor recorded in the header area of the audio data file 'file 1' is read out and displayed in correspondent display areas 21 and 22 of the relevant window 102 and further, the recognized result is displayed in a patient name input area 23 by applying voice recognizing processing to the audio data of the audio data file 'file 1'. The progress from the symptoms of a disease to the first consultation, remarks and passage are similarly processed as well.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to a document creation apparatus, and more particularly, to a document creation apparatus that performs speech recognition processing on voice data to create a document, and a recording medium storing a document creation processing program.

[0002]

2. Description of the Related Art Conventionally, when a fixed form such as a medical certificate of a doctor is prepared using, for example, a word processor or the like, a format including a predetermined fixed form is prepared in advance to facilitate the preparation. A method of setting a text input area in an arbitrary text format at a predetermined location is widely known.

[0003] In recent years, there is also known a voice recognition system that captures voice data with a personal computer or the like and performs voice recognition using voice recognition software. Further, there is also known a technical means for automatically converting a voice input from a microphone into a text in a text format by using such a voice recognition system and displaying the text on a monitor screen. Various techniques have been proposed for utilizing such a text creation technique using a speech recognition technique for inputting a text text in the above-described fixed text format.

In the text text input technology using such a voice recognition technology, it is common that a user inputs a voice after moving a cursor to a predetermined text text input area by using a keyboard, a mouse, or the like. .

On the other hand, in recent years, there have been proposed various so-called digital voice recording apparatuses for converting a sound source such as voice into a digital signal and recording the digital signal.
Japanese Patent Application Publication No. 0180 proposes an audio data processing control device that enables audio data once recorded by such a digital audio recording device to be handled by a simple operation on a personal computer.

[0006] Further, the present applicant has previously disclosed in Japanese Patent Application Laid-Open No. 10-34.
No. 0179 proposes a dictation system in which voice data is passed from the voice data processing control device to a voice recognition device to perform voice processing and display the text on a screen.

According to such a dictation system, without directly inputting a voice to a personal computer or the like, the voice is temporarily recorded in a voice recording device, and then the recorded voice data is transferred to a personal computer or the like. It is possible to perform voice recognition, text creation, and the like.

For example, when a doctor prepares a medical certificate while looking at an X-ray image, it is troublesome to operate an input device such as a keyboard each time. Then, the recorded voice data is transferred to a personal computer or the like which functions as a voice recognition system later to perform voice recognition and text creation.

[0009]

Although the processing control apparatus and dictation system for voice data by the present applicant described above are very useful, in these techniques, the recording data specified by a window dedicated to voice recognition is used. All of the text was once converted into a text by speech recognition, and then a desired arbitrary portion was designated in the text using a keyboard, a mouse, or the like, and was copied (cut) and pasted to a predetermined area in a fixed text format. Therefore, it was not always easy to use.

[0010] That is, in the above-mentioned conventional technique, first, a desired range of the recording data transferred from the voice recording device is specified, and then a predetermined area in a fixed text format is selected, and the recording specified in the area is selected. The data could not be subjected to speech recognition processing and converted into text.

SUMMARY OF THE INVENTION The present invention has been made in view of the above circumstances, and provides an easy-to-use document creation apparatus and a document creation processing program which can perform speech recognition processing on arbitrary voice data and display it as character information in a predetermined area. It is an object of the present invention to provide a recorded recording medium.

[0012]

In order to achieve the above object, a first document creating apparatus of the present invention is a document creating apparatus for performing a document creating process by a programmed computer, and includes at least a predetermined text input. A document editing window display for displaying a document editing window including a set of regions; an audio data file display window displaying for displaying an audio data file display window including an icon related to the audio data file; By the pointing device for selection, any icon among the icons related to the audio data file displayed in the audio data file display window is selected and dragged and dropped to an arbitrary text input area displayed in the document editing window. When operated Voice recognition processing means for performing voice recognition processing on voice data relating to the voice data file corresponding to the selected icon, and voice recognition result display means for displaying the text converted by the voice recognition processing means in the text input area And characterized in that:

[0013] To achieve the above object, a second aspect of the present invention is provided.
The document creation device is a document creation device that performs a document creation process by a programmed computer, document display window display means for displaying a document edit window including at least a predetermined set of text input area,
An audio data waveform window displaying means for displaying an audio data waveform window for displaying a time axis waveform of audio recorded as an audio data file, and at least a pointing device for selecting an audio data file to display in the audio data waveform window. When an arbitrary waveform area in the time axis waveform of the selected audio is selected and dragged and dropped on an arbitrary text input area displayed in the document editing window, audio data corresponding to the selected waveform area And voice recognition result display means for displaying the text converted by the voice recognition processing means in the text input area.

[0014] To achieve the above object, a third aspect of the present invention is provided.
The document creation device is a document creation device that performs a document creation process by a programmed computer, document display window display means for displaying a document edit window including at least a predetermined set of text input area,
The audio data file display window displaying means for displaying the audio data file display window including the index information assigned to the audio data file and the pointing device for selecting at least the audio data file are displayed in the audio data file display window. When an arbitrary audio data area is selected based on the index information and drag-and-drop operation is performed on an arbitrary text input area displayed in the document editing window, an audio data corresponding to the selected audio data area is output. It is characterized by comprising speech recognition processing means for performing recognition processing, and speech recognition result display means for displaying the text converted by the speech recognition processing means in the text input area.

[0015] To achieve the above object, the first aspect of the present invention is as follows.
Is a recording medium on which a program for performing a document creation process by a computer is recorded, and a document editing window for displaying a document editing window including at least a predetermined set of text input areas. Window display function for displaying an audio data file display window including an icon relating to the audio data file, and a pointing device for selecting at least the audio data file. When an arbitrary icon is selected from the icons related to the audio data file displayed in and is dragged and dropped to an arbitrary text input area displayed in the document editing window, the icon corresponding to the selected icon is selected. A program for realizing a voice recognition processing function of performing voice recognition processing on voice data related to a voice data file, and a voice recognition result display function of displaying text converted by the voice recognition processing function in the text input area. Record

In order to achieve the above object, the second aspect of the present invention
Is a recording medium on which a program for performing a document creation process by a computer is recorded, and a document editing window for displaying a document editing window including at least a predetermined set of text input areas. Window display function for displaying a time axis waveform of a voice recorded as a voice data file, a voice data waveform window display function for displaying a voice data waveform window, and a pointing device for selecting at least a voice data file. When an arbitrary waveform area is selected from the time axis waveform of the audio displayed in the audio data waveform window and dragged and dropped to an arbitrary text input area displayed in the document editing window, the selected waveform is displayed. Audio to audio data corresponding to the area And voice recognition processing function of performing the identification process,
A program for realizing a speech recognition result display function for displaying the text converted by the speech recognition processing function in the text input area is recorded.

In order to achieve the above object, the third aspect of the present invention
Is a recording medium on which a program for performing a document creation process by a computer is recorded, and a document editing window for displaying a document editing window including at least a predetermined set of text input areas. Window display function for displaying an audio data file display window including index information assigned to the audio data file, and a pointing device for selecting at least the audio data file. When an arbitrary audio data area is selected based on the index information displayed on the display window and dragged and dropped on an arbitrary text input area displayed on the document editing window, the selected audio data area is displayed. A program for realizing a voice recognition processing function of performing voice recognition processing on voice data corresponding to a region, and a voice recognition result display function of displaying text converted by the voice recognition processing function in the text input area. Record.

[0018]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is an explanatory diagram showing a conceptual overall configuration of a document creating apparatus according to a first embodiment of the present invention.

This document creation device, as shown in FIG.
A digital recorder 1 for converting a sound into an electric signal and converting it into sound data; a miniature card 2 which is detachably mounted on the digital recorder 1 and used as a recording medium for recording the sound data; A PC card adapter 3 for inserting the card 2 into a PC card slot (not shown) to enable connection; a display 5 for displaying text and the like; a keyboard 6; a mouse 7; And a personal computer 4 as a voice processing device for performing processing by the control program 8, the voice recognition program 9 or the text creation program 10 on the voice data obtained from the computer 2.

The digital recorder 1 is used as a recording means, and converts a sound inputted by a microphone (not shown) into a digital signal and records it as a sound data file on a recording medium. As this recording medium, for example, a flash memory card called a miniature card which is detachable from the digital recorder 1 is used. When the miniature card 2 is inserted into the personal computer 4 via, for example, the PC card adapter 3, the audio data file recorded on the miniature card 2 is transferred to a hard disk (not shown) in the personal computer 4. It has become.

The personal computer 4 is constituted by connecting a main body keyboard 6, a so-called pointing device (input device) such as a mouse 7, and a display 5 which is a display device for displaying text and the like. The hard disk (not shown) of the personal computer 4 has a control program 8 for displaying information on the transferred audio data file and reproducing the audio data file, and automatically outputs the selected audio data file to the audio data file. Speech recognition program 9 capable of displaying text on display 5 after recognition
And a document creation program 10 in which a text input area is set at a predetermined position in the standard document format. The control program 8, the speech recognition program 9, and the text creation program 10 constitute a document creation processing program.

These document creation processing programs do not need to be stored in the hard disk HDD (in this case, a hard disk built in the personal computer 4 in advance) when the personal computer 4 is shipped and sold. That is, an external recording medium connectable to the personal computer 4, for example, a CD-
The control program 8, the voice recognition program 9, and the text creation program 10 may be recorded in a ROM, MO, FD, or the like, and may be appropriately installed on the hard disk of the personal computer 4.

Further, the control program 8, the voice recognition program 9, and the text creation program 10 are provided in the CD-ROM.
Not only can the data be transferred from a recording medium such as a ROM to the hard disk of the personal computer 4, but also can be taken into the personal computer 4 from an external recording device or the like via a communication line (wired or wireless).

That is, a medium (including a communication line) on which the control program 8, the voice recognition program 9, and the text creation program 10 are recorded can be put on a distribution / sales channel separately from the personal computer 4 itself. The document is created by being transferred to the personal computer 4 and executed.

In the first embodiment, the audio data file recorded on the removable flash memory card (miniature card 2) is transferred via the PC card adapter 3. The audio data file may be transferred by directly connecting to the personal computer 4, or may be transferred by wireless data communication.

As a pointing device,
In addition to the mouse 7, input devices such as a trackball, a tablet, a joystick, and a light pen are assumed.
Further, the keys themselves on the keyboard 6 can also serve the same role as these input devices.

Next, a description will be given of an example in which the document creating apparatus according to the first embodiment is used as an apparatus for creating a medical certificate. In this example, a medical certificate creation program is used as the speech recognition program 9 and the document creation program 10.

FIG. 2 is an explanatory diagram showing one display example of the display 5 when the control program 8 and the diagnostic certificate creation program (the speech recognition program 9 and the sentence creation program 10) are activated.

As shown in FIG. 2, at this time, the display 5 displays a control window 101 as a voice data file display window and a medical certificate creation window 102 as a document editing window.

The control window 101 includes:
It has a so-called menu bar 11, a toolbar 12, a file list display section 13, a reproduction display section 14, a reproduction control section 15, and the like. The file list display section 13 is a section for displaying a plurality of types of audio data files as a list, and an icon 13 corresponding to each audio data file.
a is correlated and displayed.

In the first embodiment, the voice data files to be handled, such as "patient name", "disease name", "the progress from onset to the first consultation", "findings and progress", are stored in advance in a voice recording device or the like. Assume a recorded audio data file. These audio data are file1, file, respectively.
The file X is recorded as e2, file3, and file4. As shown in FIG. 2, each fileX is associated with a predetermined icon 13a indicating a file related to audio data.

On the other hand, the medical certificate creation window 102
"Diagnosis date and time", "physician name", "patient name", "disease name", "elapsed time from onset to first consultation", "findings and progress" character string display, and the above "diagnosis date and time", "doctor name"
The diagnosis date / time display area 21 and the doctor name display area 22 corresponding to the character string display, and the “patient name”, “disease name”,
A patient name input area 23, a disease name input area 24, and a progress input area 25 from disease onset to first consultation, which are text character input areas respectively corresponding to the character string display of "process from onset to first consultation" and "findings and progress". , Findings and progress input area 26 are set.

The text character input area is
The patient name input area 23, the disease name input area 24, the progress input area 25 from the onset of the disease to the first consultation, and the findings and progress input area 26 are designated by using a pointing device such as the mouse 7 and then text is input from the keyboard 6. It is possible to input characters and display the result of voice recognition processing as described later.

Next, in the medical certificate creating apparatus,
A method of actually creating a medical certificate will be described with reference to a flowchart shown in FIG. It should be noted that in the figure, each step shown as a processing flow on the left side (steps S1 to S7)
Indicates the operation of the user, and the respective processes on the right side, which are connected to these steps by bold lines, are performed in steps S1 to S
7 corresponding to the personal computer 4 (internal CP
U, etc.). Hereinafter, the operation of the personal computer 4 is referred to as the CP.
The operation of U is shown.

First, the user records the input items of the medical certificate creation program in the digital recorder 1 in the form of files. In other words, the "patient name" as the voice data file file1, the "disease name" as the file2, and the f
ile3 "The progress from onset to first consultation", same file
"Findings and progress" are recorded as e4 (step S1).

FIG. 4 is an explanatory diagram showing a recording area of the audio memory of each file. As shown in the figure, the recording area of the audio memory is a header area 3 such as index information.
1 and an audio data area 32.

In the present embodiment, the user information, the recording start date and time, the recording end date and time, and the index mark (I mark) address (No. 1 to No. 15 in this embodiment) are recorded in the header area 31. It has become so. That is, in the header area 31, the diagnosis date and time (recording start date and time, recording end date and time) and the doctor's name are recorded for each file.

Returning to FIG. 3, after finishing recording on the digital recorder 1, the user then inserts the miniature card 2 into the personal computer 4 via the PC card adapter 3.
(Step S2). Thereby, the recorded voice data file is transferred to the personal computer 4 (step S21).

Next, the user operates the personal computer 4.
To operate the control program 8 and the medical certificate creation program (the speech recognition program 9 and the sentence creation program 1)
0) (Step S3), the display 5
Displays a control window 101 and a medical certificate creation window 102 (step S31).

Next, the user operates the mouse 7 to select the icon 13a corresponding to the voice data file file1 in which the "patient name" is recorded as shown in FIG. Drag and drop to the input area 23 (step S4). This allows the CPU (internal to the personal computer 4) to first
Diagnosis date and time (recording start date and time, recording end date and time) recorded in the header area of the audio data file file1
Alternatively, the information of the doctor's name is read, and each information is displayed in the diagnosis date / time display area 21 and the doctor's name display area 22 of the medical certificate creation window 102 (step S41).

Subsequently, the CPU sets the audio data file fi
The voice recognition processing is performed on the voice data of le1, and the recognition result is displayed in the patient name input area 23 of the medical certificate creation window 102 (step S42).

Next, the user operates the mouse 7 to select the voice data file file2 in which the "disease name" is recorded as shown in FIG. Drag and drop (step S5). As a result, the CPU performs voice recognition processing on the voice data of the voice data file file2, and displays the recognition result in the disease name input area 24 of the medical certificate creation window 102 (step S51).

Next, the user operates the mouse 7 to select the voice data file file3 in which the contents of "the progress from the onset of the disease to the first consultation" are recorded as shown in FIG. Is dragged and dropped into the progress input area 25 from the onset of the disease to the first consultation (step S6). As a result, the CPU performs voice recognition processing on the voice data of the voice data file file3, and displays the recognition result in the progress input area 25 from the onset to the first consultation in the medical certificate creation window 102 (step S61).

Next, the user operates the mouse 7 to select the file 4 in which the contents of "findings and progress" are recorded as shown in FIG.
2 and drag and drop to the finding and progress input area 26
Drop (step S7). This allows the CPU
performs voice recognition processing on the voice data of file4,
The recognition result is displayed in the finding and progress input area 26 of the medical certificate creation window 102 (step S71).

As described above, in the document creating apparatus according to the first embodiment, first, a desired file is selected from the audio data files transferred from the audio recording apparatus, and the file is reproduced as a text document in a fixed text format. When the above-mentioned predetermined area is selected, the voice data relating to the selected voice data file is subjected to voice recognition processing and can be converted into text as text character information, thereby providing a very easy-to-use document creation device. be able to.

In the first embodiment, file1
The recording start date and time (diagnosis date and time information) and the user information (doctor name information) recorded in the header area 31 are read out and displayed in the diagnosis date and time display area 21 and the doctor name display area 22 of the medical certificate creation window 102, respectively. However, this is not limited to file 1 and may be read from another audio data file.

Further, the order of the processes in steps S4 to S7 (see FIG. 3) is not limited to the order described above, and the same effect can be obtained even if the user freely changes the order and operates. Needless to say.

Next, a document creation device according to a second embodiment of the present invention will be described. The configuration of the document creation device of the second embodiment is the same as that of the first embodiment as shown in FIG. Further, in the document creation device of the first embodiment, the fifteen related to the “patient name” is used as the voice data file.
le1, file2 relating to "disease name", file3 relating to "the progress from the onset to the first consultation", and file4 relating to "findings and progress", and performing voice recognition in an arbitrary text input area for each of these voice data files. In the second embodiment, an arbitrary section in each voice data file is selected, and only the selected section is subjected to voice recognition in the text input area. To make text sentences. Other configurations and operations are the same as those in the first embodiment.

FIG. 9 shows a display example of the display 5 when the control program 8 and the diagnostic certificate creation program (the speech recognition program 9 and the sentence creation program 10) are activated in the document creation device of the second embodiment. FIG.

As shown in FIG. 9, in the second embodiment, a waveform display button 16 is newly provided on the so-called toolbar 12 in the control window 101 also displayed in the first embodiment. When the waveform display button 16 is clicked, an audio data waveform window 103 is opened separately from the control window 101, and the audio data file fi selected in the file list display section 13 is opened.
The time axis waveform of the audio data related to leX is displayed.

Further, the audio data waveform window 1
An arbitrary section can be selected from the time axis audio data waveform displayed at 03 by using a pointing device such as the mouse 7.

Here, the significance of selecting an arbitrary section from the time axis audio data waveform will be briefly described. In the document creation apparatus according to the present embodiment, it is assumed that the audio data to be reproduced is often recorded by the user himself, and the audio data recorded in each audio data file is relatively Considering that it is assumed to be a short time, it is not very difficult for the user to read the section of the audio data desired to be reproduced only by watching the state of the time axis audio data waveform. Rather, it is considered that desired audio data can be found relatively easily by appealing visually as waveform information.

As described above, in the present embodiment, a section desired to be reproduced can be selected and reproduced only by looking at the waveform information, instead of selecting and reproducing all the recorded audio data files. .

The user selects a desired section using the pointing device such as the mouse 7 as described above, and drags the selected section to an arbitrary text input area, for example, a finding and progress input area 26. Drop. Thereby, the CPU of the personal computer 4
Performs voice recognition processing on the voice data of the selected section, and displays a corresponding text sentence.

The other configuration and operation are the same as those of the first embodiment, and the detailed description is omitted here.

As described above, in the document creating apparatus according to the second embodiment, in addition to the effects of the first embodiment, a section desired to be reproduced in the selected audio data file is selected while looking at the audio data waveform. It is possible to obtain more accurate text sentences.

Next, a document creating apparatus according to a third embodiment of the present invention will be described. The configuration of the document creation apparatus of the third embodiment is the same as that of the first embodiment as shown in FIG. Further, in the document creation device of the first embodiment, the fifteen related to the “patient name” is used as the voice data file.
le1, file2 relating to "disease name", file3 relating to "the progress from the onset to the first consultation", and file4 relating to "findings and progress", and performing voice recognition in an arbitrary text input area for each of these voice data files. However, in the third embodiment, a predetermined section is made to be speech-recognized in the text input area based on the index information given in each audio data file. It is characterized in that Other configurations and operations are the same as those in the first embodiment.

By the way, a technique for recording index information in audio data in order to enhance the searchability of audio data is well known. The third embodiment has been made in view of such technology.

FIG. 10 shows a display example of the display 5 when the control program 8 and the diagnostic certificate creation program (the speech recognition program 9 and the text creation program 10) are activated in the document creation device of the third embodiment. FIG.

The digital recorder 1 used in the document creating apparatus according to the third embodiment is provided with an index mark button (not shown). When the index mark button is pressed during recording or playback, the address at that time is read. The value is recorded in the index area of the header area. It is assumed that a specific value (for example, FFFFH) is recorded as an initial value of each index area,
If the value is the specific value, it can be determined that the index mark is not recorded.

As shown in FIG. 10, in the third embodiment, the index mark display 17 is displayed on the reproduction display section 14 in the control window 101 also displayed in the first embodiment. Has become.

The addition and deletion of index marks can be performed on the screen of the control window 101. FIG. 11 is an explanatory diagram showing an example of a case where the “edit” menu on the menu bar 13 is selected and “add index mark” is selected in the document creating apparatus according to the third embodiment. When the “addition of index mark” is executed, an address indicating the reproduction position at that time is recorded in the index area as an index mark address.

FIGS. 12 to 14 are diagrams for explaining a method of setting a speech recognition target section in the document creation apparatus according to the present embodiment.

Now, in one voice data file, “patient name”, “disease name”, “elapsed time from onset to first consultation”,
It is assumed that a message about "findings and progress" is recorded, and index marks A, B, and C are recorded between the contents. At this time, the reproduction display section is displayed as shown in FIG.

Here, for example, when it is desired to perform the speech recognition processing of the content of “the progress from the onset of the disease to the first consultation”,
By operating a pointing device such as the mouse 7, the mouse pointer 18 is set to a section sandwiched between index marks B and C with a message about “the progress from the onset to the first consultation”. And this mouse pointer 1
When the mouse 7 is clicked while the mouse 8 is aligned, FIG.
As shown in the figure, the section is selectively displayed. The selection display may be reversed on the reproduction display unit 14 or may be displayed in another color. FIG.
Is an example in which a section having a message about “findings and progress” is selected.

When the target section for speech recognition is selected and dragged and dropped into the corresponding input area of the medical certificate creation window 102, the speech recognition processing is performed on the selected section. The text is displayed.

The other configuration and operation are the same as those of the first embodiment, so that the detailed description is omitted here.

As described above, in the document creating apparatus according to the third embodiment, in addition to the effects of the first embodiment, a section desired to be reproduced can be selected from the selected audio data file based on the index information. , You can get more accurate text sentences.

In each of the above-described embodiments, audio data recorded in advance using a digital recorder has been described as an example of audio data to be displayed as text.
The present invention is not limited to this, and sound data recorded by directly connecting a microphone to a personal computer may be used.

As described above, according to each of the above-described embodiments, it is possible to designate any voice data or any section thereof, perform voice recognition in any text input area in the standard document format, and convert it to text. Thus, an easy-to-use document creation device can be provided.

[Appendix] According to the embodiment of the present invention as described in detail above, the following configuration can be obtained. That is, (1) a first display screen (a medical certificate creation window 10) for displaying a predetermined format defining a plurality of document input areas.
2) and a second display screen (control window 101) for displaying identifiers of a plurality of audio files in which audio data is recorded.
Operating means (mouse 7) for selecting one of the audio files displayed on the second display screen and inputting the selected information to one of the document input areas displayed on the first display screen;
Performing voice recognition processing for converting voice data recorded in the voice file selected by the operation means into characters, and displaying the voice-recognized characters in a predetermined document input area of the first display screen. A document creation apparatus characterized by performing the following.

(2) A first display screen (diagnostic report creation window 102) for displaying a predetermined format defining a plurality of document input areas, and a second display screen (audio data waveform) for displaying a time axis waveform of audio data. Window 103)
Operating means (mouse 7) for selecting a predetermined area of the time axis waveform of the audio data displayed on the second display screen and inputting this selection information to one of the document input areas displayed on the first display screen And performs voice recognition processing for converting voice data recorded in a predetermined area selected by the operation means into characters, and converts the voice-recognized characters into a predetermined document input area on the first display screen. A document creation apparatus characterized by displaying on a document.

(3) A first display screen (diagnostic report creation window 102) for displaying a predetermined format defining a plurality of document input areas, and a second display for displaying index information added to a voice file in which voice data is recorded. A predetermined area of the audio data is selected based on the display screen (control window 101) and the index information displayed on the second display screen, and the selected information is selected from the document input area displayed on the first display screen. Operating means (mouse 7) for inputting the voice data, performing voice recognition processing for converting voice data recorded in the predetermined area selected by the operating means into characters, and converting the voice-recognized characters to the above-mentioned characters. A document creation device for displaying in a predetermined document input area of a first display screen.

(4) A first display screen (diagnostic report creation window 102) for displaying a predetermined format defining a plurality of document input areas, and a second display screen (control window 101, Based on the audio data waveform window 103) and the division information displayed on the second display screen, a predetermined area of the audio data is selected, and this selected information is selected as one of the document input areas displayed on the first display screen. And a voice recognition process for converting voice data recorded in a predetermined area selected by the operation means into characters.
A document creation apparatus, wherein a character subjected to voice recognition processing is displayed in a predetermined document input area of the first display screen.

[0076]

As described above, according to the present invention, it is possible to perform a voice recognition process on arbitrary voice data and display it as character information in a predetermined area, and to record a user-friendly document preparation device and a document preparation processing program. Recording medium can be provided.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram showing a conceptual overall configuration of a document creation device according to a first embodiment of the present invention.

FIG. 2 is a diagram illustrating the document creation apparatus according to the first embodiment;
FIG. 4 is an explanatory diagram showing a display example of a display when a control program and a medical certificate creating program (a voice recognition program and a sentence creating program) are activated.

FIG. 3 is a diagram illustrating the document creating apparatus according to the first embodiment;
5 is a flowchart illustrating a method for creating a medical certificate.

FIG. 4 is a diagram illustrating the document creating apparatus according to the first embodiment;
FIG. 3 is an explanatory diagram showing a recording area of an audio memory of each audio data file.

FIG. 5 is a diagram illustrating the document creating apparatus according to the first embodiment.
FIG. 11 is an explanatory diagram showing a state in which an audio data file in which a “patient name” is recorded is dragged and dropped into a patient name input area.

FIG. 6 is a diagram illustrating the document creation apparatus according to the first embodiment;
FIG. 11 is an explanatory diagram showing a state where a voice data file in which a “disease name” is recorded is dragged and dropped into a patient name input area.

FIG. 7 is a diagram illustrating the document creation apparatus according to the first embodiment;
FIG. 11 is an explanatory diagram showing a state in which a voice data file in which “the progress from the onset of disease to the first consultation” is recorded is dragged and dropped into a patient name input area.

FIG. 8 is a diagram illustrating the document creation apparatus according to the first embodiment;
FIG. 11 is an explanatory diagram showing a state in which a voice data file in which “findings and progress” are recorded is dragged and dropped into a patient name input area.

FIG. 9 is an explanatory diagram showing a display example of a display when a control program and a medical certificate creation program (a speech recognition program and a text creation program) are activated in the document creation device according to the second embodiment of the present invention. is there.

FIG. 10 is an explanatory diagram showing one display example of a display when a control program and a diagnostic certificate creation program (a speech recognition program and a text creation program) are activated in the document creation device according to the third embodiment of the present invention. is there.

FIG. 11 is an explanatory diagram showing a state when adding or deleting an index mark on a control window in the document creating apparatus according to the third embodiment.

FIG. 12 is a diagram illustrating a method for setting a speech recognition target section in the document creation device according to the third embodiment.

FIG. 13 is a diagram illustrating a method for setting a speech recognition target section in the document creation device according to the third embodiment.

FIG. 14 is a diagram illustrating a method for setting a speech recognition target section in the document creation device according to the third embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Digital recorder 2 ... Miniature card 3 ... PC card adapter 4 ... Personal computer 5 ... Display 6 ... Keyboard 7 ... Mouse 8 ... Control program 9 ... Speech recognition program 10 ... Sentence creation program 13 ... File list display section 13a ... Icon 101 Control window 102: Medical certificate creation window 103: Voice data waveform window

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G10L 15/28 G10L 3/00 551P 571K

Claims (6)

[Claims] 1. A document creation apparatus for performing document creation processing by a programmed computer, comprising: a document editing window display means for displaying a document editing window including at least a set of predetermined text input areas; and an audio data file. A voice data file display window displaying means for displaying a voice data file display window including the icon according to the above, and at least a pointing device for selecting a voice data file, the voice data file displayed in the voice data file display window When any of the icons is selected and dragged and dropped to any text input area displayed in the document editing window, the audio data associated with the audio data file corresponding to the selected icon is displayed. Document creating apparatus characterized by comprising: a voice recognition processing means for performing voice recognition processing, a voice recognition result display means for the converted text by the speech recognition processing means for displaying on the text input region. 2. A recording medium storing a program for performing a document creation process by a computer, wherein a document editing window display function for displaying a document editing window including at least a set of predetermined text input areas, An audio data file display window display function for displaying an audio data file display window including an icon relating to a data file; and a voice data file displayed in the audio data file display window by at least a pointing device for selecting an audio data file. When an arbitrary icon is selected from among the icons according to and the drag-and-drop operation is performed on an arbitrary text input area displayed in the document editing window, the audio data relating to the audio data file corresponding to the selected icon is displayed. A voice recognition processing function for performing speech recognition processing on the data, a recording medium the converted text by the speech recognition processing function recording a program for realizing the voice recognition result display function of displaying on the text entry area. 3. A document creation apparatus for performing document creation processing by a programmed computer, comprising: a document editing window display means for displaying a document editing window including at least a set of predetermined text input areas; Audio data waveform window display means for displaying an audio data waveform window for displaying a time axis waveform of audio recorded as audio data, and a voice device displayed in the audio data waveform window by at least a pointing device for selecting an audio data file. When an arbitrary waveform area is selected from the time axis waveforms and drag-and-drop operation is performed on an arbitrary text input area displayed in the document editing window, voice recognition corresponding to the selected waveform area is performed. Voice recognition processing means for performing processing; A speech recognition result display unit for displaying the text converted by the speech recognition processing unit in the text input area. 4. A recording medium on which a program for performing a document creation process by a computer is recorded, wherein a document editing window display function for displaying a document editing window including at least a predetermined set of text input areas; An audio data waveform window display function for displaying an audio data waveform window for displaying a time axis waveform of audio recorded as a data file, and a pointing device for selecting at least an audio data file, are displayed in the audio data waveform window. When an arbitrary waveform area is selected from the time axis waveform of the audio and dragged and dropped to an arbitrary text input area displayed in the document editing window, audio data corresponding to the selected waveform area is generated. Voice recognition processing function to perform voice recognition processing and Recording medium for recording a program for realizing the voice recognition result display function of displaying on the text input area the converted text by the speech recognition processing function. 5. A document creation apparatus for performing document creation processing by a programmed computer, comprising: a document editing window display means for displaying a document editing window including at least a predetermined set of text input areas; and an audio data file. A voice data file display window displaying means for displaying a voice data file display window including the index information given to the voice data file, and at least a pointing device for selecting a voice data file. When an arbitrary voice data area is selected based on the selected voice data area and a drag and drop operation is performed on an arbitrary text input area displayed in the document editing window, voice recognition processing is performed on the voice data corresponding to the selected voice data area. Document creation device, wherein the speech recognition processing unit, and the speech recognition result display means for the converted text by the speech recognition processing means for displaying on the text entry area, further comprising a performing. 6. A recording medium on which a program for performing a document creation process by a computer is recorded, wherein a document editing window display function for displaying a document editing window including at least a predetermined set of text input areas, An audio data file display window display function for displaying an audio data file display window including index information assigned to the data file, and an index displayed in the audio data file display window by at least a pointing device for selecting an audio data file. When an arbitrary voice data area is selected based on the information and a drag-and-drop operation is performed on an arbitrary text input area displayed in the document editing window, voice recognition is performed on the voice data corresponding to the selected voice data area. A voice recognition processing function for performing processing, a recording medium that the converted text by the speech recognition processing function recording a program for realizing the voice recognition result display function of displaying on the text entry area.