FR3067851A1 - SYSTEM AND METHOD FOR VOICE CONTROL OF IMAGE PROCESSING DEVICE - Google Patents

Abstract

- System and method for voice control of an image processing device. The system (1) for voice control of an image processing device (2) comprises a voice recognition module (3) comprising a reception element (4) of a user-generated voice message and a unit processing device (5) for transcribing a received voice message into a text message, a database (6) comprising predetermined processing commands of the image processing device (2), an analysis unit (7) for comparing each text message with the predetermined processing orders and, in case of conformity of the text message with one of the processing commands, selecting this processing command, a transmission unit (8) for transmitting a command command, representative of the selected processing order, and a control unit (9) for receiving a control command transmitted by the transmission unit (8) and for controlling an action of the image processing device (2), representative of that order of comm ande received.

Description

TECHNICAL AREA

The present invention relates to a system and method for voice control of an image processing device.

STATE OF THE ART

Conventional image processing devices have a multitude of functions, such as photocopying, printing, scanning, faxing, etc. Usually, a user of such an image processing device wishing to access one of these functionalities must select, from the main menu of a touch screen if the image processing device has it or via keys, the general function he wishes to activate. Then, the user refines his choice by selecting one or more options offered in the different submenus. Once the desired function is fully defined and confirmed by the user, the image processing device performs the corresponding action.

In addition, certain image processing devices are also provided with an alert function which allows them to emit sound messages, corresponding to more or less long and repeated beeps. The purpose of these coded sound messages is to inform the user, generally in addition to a text message on the touch screen, about one or more problems encountered by the device and which prevent him from performing the action corresponding to the user-defined function.

Despite these arrangements, the use of an image processing device remains dependent on the use of the touch screen or keys. If the latter is damaged, preventing for example access to the submenus, the functionalities which a user can access will be reduced or even unavailable. In addition, people with visual impairments who wish to use a function of the device are penalized by a touch-sensitive interface alone, since they cannot be certain that the action performed by the device corresponds well to the functionality they wish to use.

In addition, although certain functions, considered as standard, can be activated via a dedicated key on the touch screen, access to the other functions requires the sometimes laborious selection of several options in the submenus of the device. image processing, which can be time consuming and a source of error.

STATEMENT OF THE INVENTION

The object of the present invention is to remedy these drawbacks. It relates to a voice control system of an image processing device.

According to the invention, the voice control system of an image processing device comprises:

- a voice recognition module comprising at least one element for receiving a voice message generated by a user and a processing unit for transcribing a received voice message into a text message;

- at least one database comprising predetermined processing orders of the image processing device;

- an analysis unit configured to compare each text message with said predetermined processing orders recorded in the database and for, in case of conformity of the text message with one of said processing orders, select this processing order;

- a transmission unit configured to transmit a control order, representative of the selected processing order;

- a control unit arranged on the image processing device and configured to receive a control order transmitted by the transmission unit and to control an action of the image processing device, representative of this received control order.

Thus, thanks to the invention, any person wishing to use one of the functionalities of the image processing device directly addresses a precise order by voice to the voice control system of said image processing device. This order, consisting of a sentence specifying all the desired options, saves time and minimizes the risk of error in the menus and submenus for selecting functions.

Although not exclusively, the present invention adapts perfectly to the needs of users with visual impairment by allowing voice access to the functions of the image processing device.

In a preferred embodiment, the voice control system comprises a control module configured to:

- check the possibility, for the image processing device, of executing a command order transmitted by the transmission unit to the control unit;

- decide, depending on this possibility or not respectively, either to confirm the order order or to cancel the order order, the action representative of said order order being only carried out by the control unit in the event of confirmation of the order.

Thus, the control module converts a processing order received from the user into a control order sent to the image processing device only if it is possible for the latter to perform the action, for example if it is not already performing an action.

In addition, said voice control system advantageously includes an information module, which comprises:

- the transmission unit which is configured to transmit information on a decision to confirm or cancel a command order transmitted to the control unit;

- the analysis unit which is configured to transcribe said information into a textual information message;

- the voice recognition module, which is configured to transcribe the text information message into a voice information message and transmit said voice information message.

Advantageously, the information module communicates to the user the progress of the order ordered.

In addition, said voice control system preferably includes a validation module comprising:

- an element for generating a question relating to a selected processing order;

- the voice recognition module, which is configured to transcribe said question into an auxiliary voice message and transmit said auxiliary voice message, the voice recognition module also being configured to receive a voice response message, generated by a user, in response to said auxiliary voice message and for transcribing this received voice response message into a text response message;

- the analysis unit which is configured to compare this text response message to validation orders and to, if the text message complies with one of said validation orders, validate the processing order.

Thus, the validation module allows the user to confirm his order or easily cancel it in the event of an error. In addition, the validation module informs the user in case of non-compliance of his request with the possible functionality of the image processing device.

Furthermore, in a preferred embodiment, the actions that can be performed by the image processing device include at least some of the following actions:

- a hard copy;

- stapling of copied sheets;

- scanning to a portable data storage device or an electronic mailbox;

- a fax.

In addition, at least one of said elements for receiving and transmitting a voice message is preferably integrated with one of the following elements:

- the image processing device;

- the voice recognition module.

Preferably, at least one of said elements for receiving and transmitting a voice message, if it is integrated into the voice recognition module, is linked to the processing unit by a wired link or by a link. wireless.

In addition, the transmission unit is linked to the control unit via a wireless link or via a wired link.

Furthermore, in a first embodiment, at least the processing unit, the analysis unit and the database are integrated into a single central processing unit.

In addition, in a second embodiment, the processing unit and the analysis unit are integrated into different central processing units.

The present invention also relates to a method of voice control of an image processing device.

According to the invention, said method comprises:

a voice recognition step, implemented by a voice recognition module, and comprising a sub-step for receiving a voice message generated by a user and a processing sub-step for transcribing the received voice message into a message textual;

an analysis step, implemented by an analysis unit, and consisting in comparing each text message with said predetermined processing orders recorded in a database comprising predetermined processing orders of the image processing device and for , in case of conformity of the text message with one of said processing orders, select this processing order;

- a transmission step, implemented by a transmission unit, and consisting in transmitting a control order, representative of the selected processing order;

- an ordering step, implemented by a control unit, and consisting of receiving a command order sent and commanding an action of the image processing device, representative of this command command received.

In a preferred embodiment, the method comprises a control step, implemented by a control module, and comprising:

- a verification sub-step consisting in verifying the possibility, for the image processing device, of executing a control order transmitted by the transmission unit to the control unit;

a decision-making sub-step consisting in deciding, according to this possibility or not respectively, either to confirm the order order or to cancel the order order, the action representative of said order order being only performed by the control unit in the event of confirmation of the order.

Preferably, said method comprises an information step, implemented by an information module, and comprising:

- a transmission sub-step, implemented by a transmission unit, and consisting in transmitting information on a decision to confirm or cancel an order ordered to the image processing device;

- an analysis sub-step, implemented by an analysis unit, and consisting of transcribing said information into a textual information message;

- a processing sub-step, implemented by the voice recognition module, and consisting in transcribing the text information message into a voice information message;

- a transmission sub-step, implemented by a transmission element, and consisting in transmitting a voice information message intended for a user.

Advantageously, the method includes a validation step comprising:

- a substep for generating a question relating to a selected processing order;

- an analysis sub-step, implemented by an analysis unit, and consisting of transcribing said information into a textual information message;

a first processing sub-step, implemented by a voice recognition module, and consisting in transcribing said question into an auxiliary voice message and transmitting said auxiliary voice message;

a second processing sub-step, also implemented by the voice recognition module and consisting in receiving a voice response message, generated by a user, in response to said auxiliary voice message and in transcribing this received voice response message into a text response message;

- an analysis sub-step, implemented by the analysis unit, and consisting in comparing this text response message with validation orders and for, in case of conformity of the text message with one of said orders validation, validate the processing order.

The present invention also relates to an image processing assembly which comprises at least one image processing device and at least one voice control system of the image processing device, such as that described above.

DESCRIPTION OF THE FIGURES

The appended figures will make it clear how the invention can be implemented. In these figures, identical references designate similar elements.

Figure 1 is the block diagram of a particular embodiment of a voice control system according to the invention.

FIG. 2 schematically illustrates a particular embodiment of a method for voice control of an image processing device.

FIG. 3 is a block diagram of steps of the voice control method in a particular embodiment.

DETAILED DESCRIPTION

The control system 1, shown diagrammatically in FIG. 1, is intended to allow the use, by voice command, of at least certain functionalities of an image processing device 2 (hereinafter “device 2”) by a user O (FIG. 2), in particular a person with a visual impairment.

Device 2, for example a multifunction photocopier, has many functions such as copying, photocopying, scanning, faxing, etc. The user O of the control system 1 accesses these functionalities using an interface which communicates his choice, sent in the form of a voice message (hereinafter "voice instruction") to a so-called internal computer server 9 (hereinafter after "internal server 9"). This internal server 9 commands the device 2 with which it is generally integrated, to execute the action corresponding to the voice instruction of the user O. The interface which allows communication between the user O and the device 2 is the voice control system 1, a preferred embodiment of which is illustrated in FIG. 1 and detailed below.

In this embodiment, the control system 1 comprises a voice recognition module 3 comprising a voice message receiving element 4, for example a microphone 4, or a computer peripheral comprising a microphone 4, arranged so as to optimize reception of the user's voice instruction O and a processing unit 5. A wired link connects the microphone 4 to the processing unit 5.

According to a first variant, the microphone 4 is an independent element linked to the processing unit 5 by a wireless link.

In a particular embodiment, the microphone 4 is directly integrated into the device 2 and a wireless link ensures the connection with the processing unit 5.

The processing unit 5, integrated in a first central unit, translates the voice instruction of the user O concerning an action to be executed by the device 2 into a text message (hereinafter "text"), which can also be a word rather than a sentence (or part of a sentence). The processing unit 5 transmits this text to an analysis unit 7. It should be noted that the processing unit 5 and the analysis unit 7 operate according to a so-called client / server architecture, that is to say say that the processing unit 5 (client) sends requests, in this case a text to be analyzed, to the analysis unit 7 (server) which responds thereto. The exchanges between the client and the server are done using an http / https protocol.

A second central unit, independent of the first central unit, comprises, in a particular embodiment, a database 6 and the analysis unit 7, which receives or transmits texts representing respectively either a voice instruction from the user O is information from device 2, for example if it cannot perform an action due to lack of paper. The analysis unit 7 is able to compare texts with one or more lists of processing orders, validation orders or information specific to the device 2 and contained in the database 6. In the event of compliance between the text and an element of a list, the analysis unit 7 selects it.

In a variant of this embodiment, the database 6 is integrated into a central unit different from that of the analysis unit 7.

The control unit 9 is the internal server 9 of the device 2. It receives the processing orders from the analysis unit 7 in the form of URLs which correspond to the address of the computer programs hosted by the internal server 9 Each processing order corresponds to the execution of a computer program which controls the execution of an action by the device 2. The analysis units 7 and control units 9 communicate with each other by means of a unit. 8 which transmits SOAP messages via WebAPI transactions. The transmission unit 8 provides a wireless link configured in access point mode, that is to say without the information passing through the Internet, for security reasons. In an alternative embodiment, the transmission unit 8 is an Ethernet cable connecting the analysis 7 and control 9 units.

In addition, the control unit 9 forms part, with the transmission unit 8, of a control module 10 (automatic) capable of verifying whether or not the transmitted processing order can be carried out by the device 2.

In addition, the processing unit 5, the analysis unit 7, the database 6 and the transmission unit 8 form, with a voice message transmission element 12, for example speakers 12 generally integrated into the device 2, an information module 11 (automatic). By means of this information module 11, the user O is informed whether his voice instruction concerning the functionality of the device 2 chosen (hereinafter “initial voice instruction”) will be executed or not. A wireless link allows the connection between the processing unit 5 and the speakers 12.

In a particular embodiment, the speakers 12 are independent elements of the device 2 and are connected to the voice recognition module 3 by a wired link.

Furthermore, the processing unit 5, the analysis unit 7, the database 6, the microphone 4 and the speakers 12 are part of a validation module 13 (automatic) which requests the user O whether or not to validate the processing order to be transmitted to the internal server 9.

The system 1, as described above, implements, automatically, the general steps of the method represented in FIG. 2:

a voice recognition step ERC, during which a user O utters an initial voice instruction to the voice recognition module 3 (URC in FIG. 2), which by means of the microphone 4 and then of the processing unit 5 is translated into a text sent to the analysis unit 7 (UA in FIG. 2) via an http / https protocol. This is followed by a step of analyzing the text received by the analysis unit 7 which consists in comparing the text of the initial voice instruction to a list of processing orders contained in a database 6. As for example, if the initial voice instruction of user O is “scan a page”, the analysis unit 7 compares the text of the initial voice instruction of user O with the elements of the list of the database 6. If a digitization order appears there, then this processing order will be selected by the analysis unit 7;

an EV validation step, implemented by the validation module 13 which includes the voice recognition modules 3 and the analysis unit 7, this EV validation step consists, once the processing order has been selected, of ask a question about this processing order. By a voice response, user O must confirm that the action that will be executed by device 2 is in accordance with his initial voice instruction or, on the contrary, cancel any action. In the latter case, no order is sent to the internal server 9 of the device 2;

an execution step EE, during which the control module 10, and more specifically the internal server 9, receives a request from the analysis unit 7 which is a SOAP message. The internal server 9 checks whether it is possible for the device 2 (DTI in FIG. 2) to execute an action, in which case, the action will be executed and the system informs the user O thereof via the module information 11.

These general steps are presented here in more detail, with reference to FIG. 3.

The voice recognition step ERC comprises a first step E11 of receiving the initial voice instruction from the user O via the microphone 4, then of transmission of this initial voice instruction to the processing unit 5 which translates it into a text and sends it to the analysis unit 7.

During the following analysis step E21, the text is compared with a list of processing orders executable by the device 2, which is contained in a database 6. If the text corresponds to one of the processing orders (predetermined) for the device 2, the latter is selected and a text question relating to this processing order is automatically sent to the processing unit 5.

This is followed by a step EV of validation of the processing order by the user O which first of all includes a step of voice recognition E12. The textual question relating to the processing order is translated by the processing unit 5 into an auxiliary voice message, emitted by the speakers 12. The user O has the choice between confirming that the processing order sent to the device 2 corresponds to his initial voice instruction or cancel said processing order. In the event that user O wishes to cancel the processing order, he emits a voice response specifying the cancellation, for example "action canceled".

During a voice recognition step E13, the cancellation voice response is translated into a cancellation response text by the processing unit 5, then this cancellation response text is sent to the unit d analysis 7. During the next analysis step E23, the analysis unit 7 compares the cancellation response text received with a list of validation orders contained in the database 6. In the event of correspondence, the previously selected processing order is canceled.

On the other hand, if the user O confirms that he wishes to execute the action, the confirmation voice response is received, then translated by the processing unit 5 during a voice recognition step E14 into a text. Confirmation response confirming the initial voice instruction. This confirmation response text is then sent to the analysis unit 7 which, during an analysis step E24, compares the confirmation response text with the list of validation orders from the database 6 In the event of a correspondence between the confirmation of the user O and a confirmation element of the list of validation orders, the previously selected processing order is sent, in the form of a URL request to the internal server 9 of the device 2, via the transmission unit 8.

During the execution step EE, the request received by the internal server 9 is interpreted as a command order which corresponds to a computer program capable of commanding the execution of the action relating to the transmitted processing order. . Before executing the computer program, a control step E34, implemented by the control module 10, is carried out. During this step E34, the internal server 9 checks the possibility, for the device 2, of executing the command order. According to this possibility, the control module 10 decides to confirm or cancel the order in question. For example, if the order order corresponds to copying a document but device 2 is already performing an action or there is no more sheet of paper in device 2, the control module 10 cancels the order. On the other hand, if the device 2 is ready to execute the commanded action, the control module 10 confirms the command order. During the command step E44, the internal server 9 executes the computer program corresponding to the command order, which controls the execution of the action by the device 2.

Whether the order is confirmed or canceled, the decision taken during the control step E34 by the control module 10 is communicated to the user O during the information steps E15, E25 and E16, E26, by through the information module 11. In fact, when the command order is canceled, the internal server 9 transmits the cancellation information to the analysis unit 7 which, during step d analysis E25, compares the cancellation information with a list of information contained in the database 6 and, in the event of a match, converts the cancellation information into a cancellation information text. Then, in the voice recognition step E15, the processing unit 5 which receives this cancellation information text translates it into an auxiliary voice message, for example “machine not available”, which is then transmitted by the top - speakers 12.

When the command order is confirmed and the action will be executed by the device 2, the internal server 9 sends confirmation information to the analysis unit 7 which, during the analysis step E26, compares it to the list of information in database 6 and then selects, in the event of conformity, the corresponding confirmation information text. Finally, during the voice recognition step E16, the processing unit 5 receives the confirmation information text, translates it into an auxiliary voice message, for example “the instruction is sent”, which is emitted by the top Speakers

12.

The voice control system 1 as well as the implementation of the voice control method make it possible to dispense with the use of usual control means, for example touch screens. The following advantages are thus obtained in particular:

- a faster and easier selection of the functionalities of the image processing device 2 without going through menus or submenus which can be a source of errors between the initial choice and the result of the action;

- use of image processing devices 2 possible for people with visual impairment.

Claims (15)

1. Voice control system of an image processing device, characterized in that it comprises: - a voice recognition module (3, URC) comprising at least one element for receiving (4) a voice message generated by a user (O) and a processing unit (5) for transcribing a received voice message into a message textual; - at least one database (6) comprising predetermined processing orders of the image processing device (2); an analysis unit (7, UA) configured to compare each text message with said predetermined processing orders recorded in the database (6) and for, in case of conformity of the text message with one of said processing orders, select this processing order; - a transmission unit (8) configured to transmit a control order, representative of the selected processing order; - a control unit (9) arranged on the image processing device (2) and configured to receive a control command transmitted by the transmission unit (8) and to control an action of the image processing device (2), representative of this order received. 2. System according to claim 1, characterized in that it comprises a control module (10) configured for: - check the possibility, for the image processing device (2), of executing a control order transmitted by the transmission unit (8) to the control unit (9); - decide, depending on this possibility or not respectively, either to confirm the order order or to cancel the order order, the action representative of said order order being only carried out by the control unit (9) in case of confirmation of the order. 3. System according to one of the preceding claims, characterized in that it comprises an information module (11), comprising: - the transmission unit (8) which is configured to transmit information on a decision to confirm or cancel a control order transmitted to the control unit (9); - the analysis unit (7, UA) which is configured to transcribe said information into a textual information message; - the voice recognition module (3, URC), which is configured to transcribe the text information message into a voice information message and transmit said voice information message. 4. System according to any one of the preceding claims, characterized in that it comprises a validation module (13) comprising: - an element for generating a question relating to a selected processing order; - the voice recognition module (3, URC), which is configured to transcribe said question into an auxiliary voice message and transmit said auxiliary voice message, the voice recognition module (3, URC) also being configured to receive a response message voice, generated by a user (O), in response to said auxiliary voice message and for transcribing this received voice response message into a text response message; - the analysis unit (7, UA) which is configured to compare this text response message with validation orders and for, if the text message complies with one of said validation orders, validate the order treatment. 5. System according to any one of the preceding claims, characterized in that the actions capable of being carried out by the image processing device (2) comprise at least some of the following actions: - a hard copy; - stapling of copied sheets; - scanning to a portable data storage device or an electronic mailbox; - a fax. 6. System according to any one of the preceding claims, 5 characterized in that at least the receiving element (4) of a voice message and / or a transmitting element (12) of a voice message are integrated into one of the following elements: - the image processing device (2); - the voice recognition module (3, URC). 10 7. System according to claim 6, characterized in that at least one of said elements for receiving (4) and transmitting (12) a voice message, if it is integrated into the voice recognition module (3 , URC), is linked to the processing unit (5) by a wired link or by a wireless link. 15 8. System according to any one of the preceding claims, characterized in that the transmission unit (8) is linked to the control unit (9) via a wireless link or via a wired link. 9. System according to any one of claims 1 to 8, characterized in that at least the processing unit (5), the analysis unit (7, 20 UA) and the database (6) are integrated into a single central processing unit. 10. System according to any one of claims 1 to 8, characterized in that the processing unit (5) and the analysis unit (7, UA) are integrated in different central processing units. 25 11. Method for voice control of an image processing device, characterized in that it comprises: - a voice recognition step (E11), implemented by a voice recognition module (3, URC), and comprising a substep of Reception of a voice message generated by a user (O) and a processing sub-step for transcribing the received voice message into a text message; - an analysis step (E21), implemented by an analysis unit (7, UA), and consisting in comparing each text message with said predetermined processing orders recorded in a database (6) comprising orders predetermined processing of the image processing device (2) and for, in case of conformity of the text message with one of said processing orders, select this processing order; - a transmission step, implemented by a transmission unit (8), and consisting in transmitting a control order, representative of the selected processing order; - a control step (E44), implemented by a control unit (9), and consisting in receiving a control command issued and in controlling an action of the image processing device (2), representative of this order received. 12. Method according to claim 11, characterized in that it comprises a control step (E34), implemented by a control module (10), and comprising: - a verification sub-step consisting in verifying the possibility, for the image processing device (2), of executing a control order transmitted by the transmission unit (8) to the control unit (9 ); a decision-making sub-step consisting in deciding, according to this possibility or not respectively, either to confirm the order order or to cancel the order order, the action representative of said order order being only performed by the control unit (9) in the event of confirmation of the order. 13. Method according to any one of claims 11 and 12, characterized in that it comprises an information step, implemented by an information module (11), and comprising: - a transmission sub-step, implemented by a transmission unit (8), and consisting in transmitting information on a decision to carry out or cancel a command ordered to the image processing device (2); - an analysis sub-step (E25, E26), implemented by an analysis unit (7, UA), and consisting in transcribing said information into a textual information message; - a processing sub-step (E15, E16), implemented by the voice recognition module (3, URC), and consisting in transcribing the text information message into a voice information message; - a transmission substep, implemented by a transmission element (12), and consisting in transmitting a voice information message intended for a user (O). 14. Method according to any one of claims 11 to 13, characterized in that it includes a validation step (EV) comprising: - a substep for generating a question relating to a selected processing order; - a first processing sub-step (E12), implemented by a voice recognition module (3, URC), and consisting in transcribing said question into an auxiliary voice message and transmitting said auxiliary voice message; - a second processing sub-step (E13, E14), also implemented by the voice recognition module (3, URC) and consisting in receiving a voice response message, generated by a user (O), in response to said auxiliary voice message and transcribing this received voice response message into a text response message; - an analysis sub-step (E23, E24), implemented by the analysis unit (7, UA), and consisting in comparing this textual response message with validation orders and for, in the event of conformity of the text message with one of said validation orders, validate the processing order. 15. An image processing assembly, characterized in that it comprises at least one image processing device (2) and at least one voice control system (1) of the image processing device (2), as specified under any of claims 1 to 10.