JP2003169171A - Image forming device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image forming device in which operability can be improved by eliminating the erroneous decision of audio recognition by recognizing a large number of commands corresponding to a mode or language set in an image forming device. <P>SOLUTION: The image forming device is composed of an operation processing means 1000 comprising a key input means 1100, a plurality of audio recognition databases 1810 and 1820, audio recognition database selecting means 1800, command discriminating means 1200, picture display means 1700, picture database means 1500 and display control means 1600 or the like and an image control means 2000 comprising an input means 2100, output means 2200 and operation control means 2300. <P>COPYRIGHT: (C)2003,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image forming apparatus having an operation unit for recognizing a voice operation instruction by a voice recognition means.

[0002]

2. Description of the Related Art Conventionally, as an input means of an image forming apparatus, an input is made by a key on an operation panel.

Further, even if the voice recognition is performed, there is only one voice recognition database.

It has been difficult to make many voices recognized by a single voice recognition database, and the recognition rate has become low.

Recent image forming apparatuses have been highly functionalized, and many mode settings have been required.

[0006]

The recognition rate cannot be made high enough to recognize all the many modes and setting methods of recent image forming apparatuses by voice recognition.

A large number of commands are recognized according to the mode, language, etc. being set to eliminate erroneous determination of voice recognition and improve operability.

[0008]

Therefore, in the present invention, the above-mentioned goal is achieved by providing an image forming apparatus shown in any one of the following items (1) to (3). Is.

(1) In the image forming apparatus, a key input means, a plurality of voice recognition databases, a voice recognition database selection means for selecting the plurality of voice recognition databases, a voice input means, and the voice recognition database selection means. Using the voice recognition database selected in step 1, the voice recognition means for recognizing the voice data of the voice input means and whether the data from the key input means or the data from the voice recognition means are valid as a command are determined. Command determining means, screen display means, screen database means in which a combination of screen data displayed on the screen display means and valid commands on the screen is accumulated, and screen data of the screen database means. The screen is displayed on the screen by controlling according to the command from the command determining means. The operation processing means having a display control means for controlling the output means, an input means, an output means, and an operation control means for controlling and operating the output means based on information from the input means. And an image control unit that starts operation in response to an instruction from the image forming apparatus.

(2) The image forming apparatus as described in (1) above, wherein the voice recognition database selecting means makes a selection corresponding to the currently displayed screen mode.

(3) The image forming apparatus according to (1), wherein the voice recognition database selecting means makes a selection corresponding to a language input from the voice inputting means.

[0012]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described in detail below with reference to the drawings.

(Embodiment) FIG. 1 is a block diagram showing the present invention.

In FIG. 1, 1000 is an operation processing means,
2000 is an image control means.

The operation processing means 1000 is a key input means 1
100, command determination means 1200, voice input means 13
00, voice recognition means 1400, screen database 150
0, display control means 1600, display means 1700, voice recognition database selection means 1800, voice recognition database 1 (1810), voice recognition database 2 (182).
0), consists of.

The key input means 1100 inputs information from a hard key on the operation unit or a soft key on the touch panel.

The voice input means 1300 converts voice input from a microphone into an electric signal.

The voice recognition database 1 (1810) and the voice recognition database 2 (1820) store spectrum patterns to be recognized as voice as data.

The voice recognition means 1400 removes noise using a voice recognition algorithm, analyzes the spectrum of the frequency, and uses the voice recognition database selected by the voice recognition database selection means to select only the voice. Determine whether

The command determination means 1200 receives data from the key input means 1100 or the voice recognition means 1400 and determines whether the data is a valid command.

The screen database 1500 is a database that stores screen data to be displayed.

The display control means 1600 acquires screen data from the screen database and displays it on the display means 1700. The display control means 1600 is the command determination means 1200.
Based on the command determination data sent from the display unit 170
It controls to change the display data displayed by 0. In addition, the command determination data sent from the command determination unit 1200 is used to instruct the image control unit to operate as necessary.

The image control means 2000 has an input means 210.
0, output means 2200, and operation control means 2300.

The input means 2100 performs input processing such as a sensor necessary for image formation. The output unit 2200 controls loads such as a motor and an actuator required for image formation.

FIG. 2 is a sectional view showing a concrete example of the image forming apparatus according to the present invention.

In FIG. 2, reference numeral 100 denotes a copying apparatus main body, 1
Reference numeral 80 denotes a circulating automatic document feeder (RDF).

Reference numeral 101 is a platen glass as a document placing table, 102 is a scanner, which is composed of a document illumination lamp 103, a scanning mirror 104 and the like. The scanner is reciprocally scanned in a predetermined direction by a motor (not shown), and the reflected light of the original is transmitted through the lens 108 through the scanning mirrors 104 to 106 to form an image on the CCD sensor 109.

A laser beam 129 converted into an electric signal by the image sensor unit 109 in the exposure control unit 120 composed of a laser, a polygon scanner, etc., and modulated based on the image signal subjected to the predetermined image processing described later. Is irradiated onto the photosensitive drum 110.

Around the photosensitive drum 110, a primary charger 112, a developing device 121, a transfer charger 118, a separation charger 119, a cleaning device 116, and a pre-exposure lamp 11.
4 is equipped. In the image forming unit 126, the photoconductor drum 110 is rotated in the direction of the arrow shown in the figure by a motor (not shown), and after being charged to a desired potential by the primary charger 112, the laser from the exposure controller 120 is emitted. Light 1
29 is irradiated and an electrostatic latent image is formed. The electrostatic latent image formed on the photosensitive drum 110 is developed by the developing device 121 and visualized as a toner image. On the other hand, the transfer paper fed by the pickup rollers 133 and 134 from the upper cassette 131 or the lower cassette 132 is sent to the main body by the paper feed rollers 135 and 136, and is fed to the transfer belt by the registration rollers 137 to be visualized. The formed toner image is transferred to the transfer paper by the transfer charger 118. The photoconductor drum after the transfer is cleaned by the cleaner device 1.
The residual toner is cleaned by 16 and the pre-exposure lamp 114
This erases the residual charge.

The transfer paper after the transfer is separated from the drum by the separation charging device 119, sent to the fixing device 141 by the conveyor belt 130, fixed by pressing and heating, and discharged to the outside of the main body 100 by the discharging roller 123. .

The main body 100 is equipped with a deck 150 capable of accommodating, for example, 4000 sheets of transfer paper. The lifter 151 of the deck 150 rises according to the amount of transfer paper so that the transfer paper always contacts the paper feed roller 152. Also, a multi-manual feed 15 capable of accommodating 100 sheets of transfer paper
Equipped with 3.

Further, in FIG. 2, the paper discharge roller 123
The transfer paper sent out from is switched to the double-sided recording side or the multiplex recording side by the paper discharge flapper 154. Also,
A lower conveyance path 158 guides the transfer paper fed from the paper discharge roller 123 to the re-feed tray 156 by reversing the transfer paper via the reversing path 155. Further, reference numeral 157 denotes a multiple flapper for switching a double-sided recording path and a multiplex recording path,
By tilting this to the left, the transfer paper
It directly leads to the lower transport path 158 without going through 5. A sheet re-feeding roller 159 feeds the transfer sheet to the photoconductor drum 126 side through the path 160. 161 is a paper ejection flapper 154
Is a discharge roller which is disposed in the vicinity of and discharges the transfer sheet switched to the discharge side by the discharge flapper 154 to the outside of the machine. During double-sided recording (double-sided copying) or multiplex recording (multiplex copying), the discharge flapper 154 is raised and the copied transfer sheet is stored in the re-feed tray 156 in a state of being turned upside down via the conveying paths 155 and 158. To do. At this time, during double-sided recording, the multiple flapper 157 is tilted to the right, and during multiple recording, the transfer sheets stored in the re-feed tray 156 are fed one by one from the bottom by the sheet feed roller 159 via the path 160. It is guided to the registration roller 137 of the main body.

When the transfer paper is reversed and discharged from the main body 100, the paper discharge flapper 154 is moved upward to raise the flapper 1.
Tilt 57 to the right to transfer the copied transfer paper to the transport path 15.
5 and the trailing edge of the transfer paper is the first feed roller 162.
After passing through the sheet, the reversing roller 163 conveys it to the second feed roller side, and the discharge roller 161 reverses the transfer paper and discharges it outside the machine.

FIG. 3 is a view showing a concrete operation panel of this embodiment.

The operation panel 200 includes a liquid crystal screen 210, a reset key 211, a guide key 212, a user mode key 213, an interrupt key 214, a secret key 215, a ten key 216, a clear key 217, a start key 218, a stop key 219, a microphone 230, Microphone jack 24
It consists of zero.

The liquid crystal screen 210 is a screen for displaying setting contents and machine status. The reset key 211 is a key for setting the setting contents to the initial mode. The guide key is a key for displaying a screen on which an explanation of the operation method is written on the liquid crystal screen. The user mode key 213 is a key for entering a mode for making various settings of the machine. The interrupt key is a key for temporarily stopping the operating machine on the way and performing another job operation. The secret code key 215 is a key to be entered after the secret code is inserted in the secret code mode in which the machine cannot be used unless the secret code is inserted. The ten-key pad 216 is a key for inputting the number of copies and a value during various settings. The clear key 217 is a key for clearing the input value. The start key 218 is a key for starting an image forming operation. The stop key 219 is a key for stopping the image forming operation. The microphone 230 is for inputting voice. The microphone jack 240 is a cord plug of a microphone (not shown) so that the microphone can be used at any position.

FIG. 4 shows a concrete example of the screen database 1500.

The screen database 1500 includes an index 1510, a screen type 1520, a screen data storage location 1
530, valid voice command 1540, valid key 1550
Is a group of items, and is composed of multiple items.

The index 1510 is a number for distinguishing each item. The screen type 1520 is a content for explaining the outline of screen items displayed on the display unit 1700. The screen data storage location 1530 contains the address where the data to be actually displayed on the display means 1700 is stored. The valid voice command 1540 stores a command which becomes valid as a voice command while the screen is displayed. The valid key 1550 stores the type of key that is valid as a key input while the screen is displayed.

FIG. 5 is an explanatory diagram of the voice input means, the voice recognition means, and the voice recognition database selection means.

The voice input means 1300 is a voice input microphone 1.
It consists of 310 and an acoustic analysis unit 1320.

In the voice recognition means 1400, the collation unit 14 for collating the voice from the voice input means and the voice recognition database.
It consists of 10.

The voice input microphone 1310 converts voice into an electric signal. At this time, a plurality of voice waveforms are used at the same time to reduce noise.

The acoustic analysis unit 1320 removes noise and compares the spectral patterns.

The voice recognition database 1810 stores spectrum patterns to be recognized as voice as data.

Speech recognition database selection means 1800
Is for selecting which data group to use from a plurality of speech recognition databases.

For example, if the currently displayed mode is the copy mode, the voice recognition database regarding the copy mode setting command is selected to increase the recognition rate. In the case of the service mode, the voice recognition database regarding the service mode setting command is selected to increase the recognition rate.

The collation unit 1410 retrieves the spectrum pattern from the voice input unit from the selected reference pattern in the voice recognition database, and recognizes it as a voice if they match.

FIG. 6 is a flowchart showing a specific operation procedure.

The process starts from step 700 in FIG.

At step 710, the key input means 1100
Check to see if the key was entered. If there is a key input, the process proceeds to step 720. If there is no key input, the process proceeds to step 711.

In step 711, the voice input means 1300
Check if there is voice input. If there is no voice input, the process returns to step 710, the key input is checked again, and the process is repeated until any input is made.

If there is voice input, step 750.
Proceed to.

In step 750, the voice recognition database selection means selects the optimum voice recognition database according to the currently displayed screen.

Subsequently, in step 712, the voice recognition means 1400 checks whether the voice input is a valid voice. Here, if the operation of the machine is on or noise in the external environment, it is determined to be invalid, and the process returns to step 710. If it is determined to be valid, the process proceeds to step 713.

In step 713, the screen database 15
00 is searched. Explaining with reference to FIG. 4, if the screen currently displayed is the standard screen, the index type is checked in order, and the item of the standard screen for the screen type 1520 is checked.
If found, the contents of that item will be used in the checks from the next step.

At step 714, it is checked whether the command is valid on the current screen. This checks whether the inputted voice command matches the valid voice command of the item in the screen database. In the case of the standard screen, voice commands such as "copy start" and "reset" are valid.
In the case of the motor operation instruction display screen, the voice commands such as "motor start", "stop", and "reset" are valid.

If the command is not registered as a command, it is not a command for the machine but a conversation with the surroundings or an erroneous instruction. Therefore, the processing is not performed and the process returns to step 710. If it is a valid command,
Go to step 715.

In step 715, it is checked whether the valid command is a command for changing the screen.

For example, in the case of the standard screen, if "reset" is a command for changing the screen, the process proceeds to step 716 to process the screen as the initial screen, and then returns to step 710 again.

Also, for example, in the case of the display screen of the motor operation instruction, if it is "reset", since it is a command to change the screen, the process proceeds to step 716, the process of making the screen the initial screen, and again to step 710. Return.

If the command does not change the screen, the process proceeds to step 717. In step 717, it is determined whether the command is to be operated.

For example, in the case of a standard screen, if "copy start" is a command to start the operation,
In step 718, the operation control unit 2300 is instructed to start copying. If it is not a command to operate, the process returns to step 710.

Further, for example, in the case of the display screen of the motor operation instruction, if "motor start", it is a command to start the operation of the motor, so the processing proceeds to step 718.
The operation control means 2300 is instructed to start the rotation operation of the motor. If it is not a command to operate, step 7
Return to 10.

On the other hand, if it is determined in step 720 that the key is valid, the process proceeds to step 721.

In step 721, the screen database 15
00 is searched.

Explaining with reference to FIG. 4, if the currently displayed standard screen is the standard screen, the index order is checked, and the screen type 1520 checks the item of the standard screen. If found, the contents of that item will be used in the checks from the next step.

At step 722, it is checked whether the command is valid on the current screen. This checks whether the entered key matches the valid key of the item in the screen database.

In the case of the standard screen, "start key", "numeric keypad", "reset key", etc. are valid for key input.

If it is not registered as a command, it is an erroneous instruction such as a pressing error.
The subsequent processing is not performed and the process returns to step 710. If the key is valid, the process proceeds to step 723.

In step 723, it is checked whether a valid command is a key for changing the screen. For example, in the case of the standard screen, if the key is a "reset key", which is a key for changing the screen, the process proceeds to step 724, the process of making the screen the initial screen is performed, and the process returns to step 710 again.

If the command does not change the screen, the process proceeds to step 725. In step 725, it is determined whether or not the key input is to be operated. For example, in the case of the standard screen, if the key is a “start key”, the key input is to start the operation, so the process proceeds to step 726, and the operation control means 2300 is instructed to start copying. If it is not a command to operate, the process returns to step 710.

[0073]

In the image forming apparatus according to the present invention, the key input means, the plurality of voice recognition databases, the voice recognition database selection means for selecting the plurality of voice recognition databases, the voice input means, and the voice recognition. Using the voice recognition database selected by the database selection means, voice recognition means for recognizing voice data of the voice input means, and data from the key input means or data from the voice recognition means are valid as commands. Of the screen database means for storing the combination of the screen data displayed on the screen display means and the effective command on the screen, and the screen database means. The screen display means is controlled by controlling screen data according to a command from the command determination means. The operation processing comprises: an operation processing means having a display control means for displaying, an input means, an output means, and an operation control means for controlling and operating the output means based on information from the input means. By configuring the image control means for starting operation in response to an instruction from the means, it is possible to increase the recognition rate so that a large number of modes and setting methods can be recognized by voice recognition.

Further, many commands can be recognized according to the mode, language, etc. being set, erroneous determination of voice recognition can be eliminated, and operability can be improved.

[Brief description of drawings]

FIG. 1 is an overall block diagram of the present invention.

FIG. 2 is a sectional view of the image forming apparatus of the present invention.

FIG. 3 is a schematic view of an operation panel according to an embodiment of the present invention.

FIG. 4 is a detailed diagram of a screen database 1500 of the present invention.

FIG. 5 is an explanatory diagram of voice input means, voice recognition means, and voice recognition database selection means of the present invention.

FIG. 6 is an operation flowchart of the present invention.

[Explanation of symbols]

100 Copying machine body 180 Circular Automatic Document Feeder (RDF) 200 Operation panel 210 LCD screen 211 Reset key 212 Guide key 213 User mode key 214 Interrupt key 215 PIN code 216 numeric keypad 217 clear key 218 Start key 219 stop key 230 microphone 240 microphone jack 1000 operation processing means 1100 Key input means 1200 command determination means 1300 voice input means 1310 voice input microphone 1320 Acoustic Analysis Department 1400 Speech recognition means 1410 collation unit 1500 screen database 1510 Index 1520 screen type 1530 Screen data storage location 1540 valid voice commands 1550 Valid key 1600 Display control means 1700 display means 1800 Speech recognition database selection means 1810 Speech recognition database 1 1820 Speech recognition database 2 2000 image control means 2100 input means, 2200 output means, 2300 Motion control means

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁷ Identification code FI theme code (reference) G03G 21/00 386 G06F 3/00 601 5D015 G06F 3/00 601 3/12 C 5E501 3/12 3/16 320B 3/16 320 320D G06T 11/60 200 G06T 11/60 200 B41J 29/00 T G10L 15/06 G10L 3/00 521V F Term (reference) 2C061 AP04 AQ06 BB10 CQ01 CQ05 CQ24 CQ34 2H027 EF06EE08EE09EE08EE09EE08EE09EE08EE06EE08EE FA08 FA25 FA35 GA19 GA23 GA30 GA32 GA33 GA35 GA37 GA48 GA52 GA56 GB14 GB19 ZA07 5B021 AA19 BB01 CC05 QQ01 5B050 AA10 CA07 CA09 FA10 FA19 5C062 AA05 AB17 AB20 AB23 AC21 FA21 CA15 FA23 CB11 FA21 CA15 523

Claims (3)

[Claims] 1. An image forming apparatus comprising: a key input means, a plurality of voice recognition databases, a voice recognition database selection means for selecting the plurality of voice recognition databases, a voice input means, and the voice recognition database selection means. Voice recognition means for recognizing voice data of the voice input means by using the selected voice recognition database;
A command determination means for determining whether the data from the key input means or the data from the voice recognition means is a valid command, a screen display means, screen data displayed on the screen display means, and a screen Screen database means in which a combination of valid commands is stored, and display control means for controlling the screen data of the screen database means according to the command from the command determination means and displaying the screen data on the screen display means. The operation processing means has an operation processing means, an input means, an output means, and an operation control means for controlling and operating the output means based on the information from the input means. The operation is started by an instruction from the operation processing means. And an image control unit for controlling the image forming apparatus. 2. The voice recognition database selecting means,
The image forming apparatus according to claim 1, wherein the image forming apparatus is selected in accordance with a currently displayed screen mode. 3. The voice recognition database selection means,
The image forming apparatus according to claim 1, wherein the selection is made according to a language input from the voice input unit.