Job content generation device and job content generation program

Abstract

This job content generation device for generating, on the basis of voice data indicating voice received by a smart speaker, job content to be executed by an image formation device corrects at least one of a plurality of setting values in the job content if the plurality of setting values in the job content are a combination such that these setting values cannot be simultaneously set, so that the resulting combination of a plurality of setting values in the job content can be simultaneously set (S73).

Description

Job content generation device and job content generation program

[0001] The present invention relates to a job content generation device and a job content generation program that generate the content of a job to be executed by an image forming device based on voice data representing voice received by a voice receiving device that receives voice input from a user.

[0002] A voice-operated system that operates an image forming apparatus via a smart speaker as a voice reception device has been known (see, for example, Patent Document 1). In the voice-operated system described in Patent Document 1, when job content is generated based on voice data representing voice received by the smart speaker, if the generated job content cannot be executed by the image forming apparatus, the smart speaker notifies an error.

[0003] Japanese Patent Application Laid-Open No. 2021-051416

[0004] However, in the voice-operated system described in Patent Document 1, if the content of a job generated based on voice data indicating the voice received by the smart speaker cannot be executed by the image forming device, the smart speaker always notifies the user of an error, which is a problem as it is not very convenient for the user.

[0005] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a job content generation device and a job content generation program that can improve convenience.

[0006] A job content generation device according to one aspect of the present invention is a job content generation device that generates the content of a job to be executed by an image forming device based on audio data indicating audio received by an audio receiving device, and includes a processor, and a control unit that functions as a job content generation unit that, when multiple setting values ​​in the content are in a predetermined combination that cannot be set simultaneously, corrects at least one of the multiple setting values ​​in the content to a setting value that is in a predetermined combination that can be set simultaneously by executing a job content generation program.

[0007] With this configuration, a job content generation device according to one aspect of the present invention automatically corrects at least one of the multiple setting values ​​in the job content so that, when the combination of multiple setting values ​​in the job content is such that they cannot be set simultaneously, the combination becomes such that the multiple setting values ​​in the job content can be set simultaneously, thereby improving convenience.

[0008] The job content generation device according to one aspect of the present invention may generate the content using a machine learning model based on the voice data.

[0009] With this configuration, a job content generation device according to one aspect of the present invention corrects at least one of the multiple setting values ​​in the job content when the combination of multiple setting values ​​in the job content is such that the multiple setting values ​​in the job content can be set simultaneously, thereby making it possible to correct the job content even if the job content is generated incorrectly in the process of generating the job content using a machine learning model based on voice data.

[0010] A job content generation device according to one aspect of the present invention may correct at least one of the multiple setting values ​​in the content based on the state of the image forming device when the multiple setting values ​​in the content are a combination that cannot be set simultaneously, so that the multiple setting values ​​in the content are a combination that can be set simultaneously.

[0011] With this configuration, a job content generation device according to one aspect of the present invention corrects at least one of a plurality of setting values ​​in the job content based on the state of the image forming device, thereby improving the appropriateness of the corrected job content.

[0012] A job content generation device according to one aspect of the present invention may request the image forming device to send information indicating the status of the image forming device, and then perform the correction using the information sent from the image forming device, determine that the combination is a predetermined combination that cannot be set, and if the combination can be corrected to the appropriate combination even without the information, may not make the request to the image forming device, may not obtain the information from the image forming device, and may perform the correction without using the information.

[0013] With this configuration, the job content generation device according to one aspect of the present invention can omit the process of acquiring information indicating the state of the image forming device from the image forming device, even though the information is not necessary for correcting the job content.

[0014] A job content generation device according to one aspect of the present invention may, when the plurality of setting values ​​in the content include a copy job setting value as the setting value indicating that the job type is copy, and a setting value indicating that the source of the file used for the job is an external storage device attached to the image forming device, correct the copy job setting value to the setting value indicating that the job type is print when the external storage device is actually attached to the image forming device.

[0015] With this configuration, when multiple setting values ​​in the job content include a copy job setting value indicating that the job type is copy and a setting value indicating that the source of the file used for the job is an external storage device attached to the image forming device, if an external storage device is actually attached to the image forming device, the job content generation device corrects the copy job setting value to a setting value indicating that the job type is print, thereby improving the appropriateness of the job content after correction.

[0016] A job content generation device according to one aspect of the present invention may, when the plurality of setting values ​​in the content include a setting value indicating that the job type is a copy, an original size setting value as the setting value indicating the size of the original to be used for the job, and a paper size setting value as the setting value indicating the size of the paper on which an image is to be printed in the job, make a correction to swap the size indicated in the original size setting value and the size indicated in the paper size setting value when the size of the original actually set in the image forming device is not the size indicated in the original size setting value but the size indicated in the paper size setting value.

[0017] With this configuration, a job content generation device according to one aspect of the present invention, when multiple setting values ​​in the job content include a setting value indicating that the job type is a copy, a document size setting value as a setting value indicating the size of the document to be used for the job, and a paper size setting value as a setting value indicating the size of the paper on which an image is to be printed in the job, makes a correction to swap the size indicated in the document size setting value with the size indicated in the paper size setting value when the size of the document actually set in the image forming device is not the size indicated in the document size setting value but the size indicated in the paper size setting value, thereby improving the appropriateness of the job content after correction.

[0018] A job content generation device according to one aspect of the present invention may, when the plurality of setting values ​​in the content include a copy job setting value as the setting value indicating that the job type is copy, and a setting value indicating the file name of a file to be used for the job, correct the copy job setting value to the setting value indicating that the job type is print.

[0019] With this configuration, a job content generation device according to one aspect of the present invention, when multiple setting values ​​in the job content include a copy job setting value indicating that the job type is copy and a setting value indicating the file name of the file to be used for the job, automatically corrects the copy job setting value to a setting value indicating that the job type is print, thereby improving convenience.

[0020] A job content generation device according to one aspect of the present invention may, when the multiple setting values ​​in the content include a setting value indicating that the job type is sending a document, a sending method setting value indicating the type of method for sending the document, and a sending encryption setting value indicating the type of encryption used when sending the document, correct the encryption type indicated in the sending encryption setting value to one that corresponds to the type of sending method indicated in the sending method setting value if the encryption type indicated in the sending encryption setting value does not correspond to the encryption type indicated in the sending method setting value.

[0021] With this configuration, a job content generation device according to one aspect of the present invention, when multiple setting values ​​in the job content include a setting value indicating that the job type is document transmission, a transmission method setting value as a setting value indicating the type of method for transmitting the document, and a transmission encryption setting value as a setting value indicating the type of encryption used when transmitting the document, automatically corrects the encryption type indicated in the transmission encryption setting value to one that corresponds to the type of transmission method indicated in the transmission method setting value when the type of encryption indicated in the transmission encryption setting value does not correspond to the type of transmission method indicated in the transmission method setting value, thereby improving convenience.

[0022] A job content generation program according to one aspect of the present invention causes a computer to function as a job content generation unit that generates the content of a job to be executed by an image forming apparatus based on audio data indicating audio received by an audio reception device that receives audio, and when multiple setting values ​​in the content are in a predetermined combination that cannot be set simultaneously, the job content generation unit corrects at least one of the multiple setting values ​​in the content to a setting value that is in a predetermined combination that can be set simultaneously.

[0023] With this configuration, a computer executing a job content generation program relating to one aspect of the present invention corrects at least one of the multiple setting values ​​in the job content when the combination of multiple setting values ​​in the job content is such that the multiple setting values ​​in the job content can be set simultaneously, thereby improving convenience.

[0024] According to the job content generation device and the job content generation program of the present invention, convenience can be improved.

[0025] 1 is a block diagram of a voice operation system according to an embodiment of the present invention. FIG. 1 is a block diagram of the job content generation device shown in FIG. 1 when the job content generation device is configured by one computer. FIG. 2 is a diagram showing an example of inappropriate job content determination information shown in FIG. 2. FIG. 3 is a block diagram of the job instruction generation device shown in FIG. 1 when the job instruction generation device is configured by one computer. FIG. 4 is a block diagram of the image forming device shown in FIG. 1 when it is an MFP. FIG. 5 is a sequence diagram of the operation of the voice operation system shown in FIG. 1 when the image forming device is operated via a smart speaker. FIG. 6 is a sequence diagram of "job content determination" shown in FIG. 7. FIG. 8 is a sequence diagram of "job execution" shown in FIG.

[0026] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0027] First, the configuration of a voice operation system according to an embodiment of the present invention will be described.

[0028] FIG. 1 is a block diagram of a voice operation system 10 according to the present embodiment.

[0029] 1, the voice operation system 10 includes a job content generation device 30 and a job command generation device 40. A smart speaker 20 is connected to the voice operation system 10 as a voice reception device that receives voice input from a user. The voice operation system 10 may also include at least one other smart speaker in addition to the smart speaker 20 that has a similar configuration to the smart speaker 20.

[0030] The job content generation device 30 generates job content (hereinafter referred to as "job content") to be executed by an image forming device (described later) based on voice data representing the voice received by the smart speaker. The job content generation device 30 may be configured by one computer or multiple computers.

[0031] The job instruction generation device 40 generates job instructions (hereinafter referred to as "job instructions") that can be interpreted by an image forming device (described later) based on the job content generated by the job content generation device 30. The job instruction generation device 40 may be configured with one computer or multiple computers. The voice operation system 10 may also include at least one other job instruction generation device having a configuration similar to that of the job instruction generation device 40, in addition to the job instruction generation device 40.

[0032] An image forming device 50, such as a dedicated printer or an MFP (Multifunction Peripheral), is connected to the voice-operated system 10. In addition to the image forming device 50, at least one other image forming device having a similar configuration to the image forming device 50 may be connected to the voice-operated system 10.

[0033] The smart speaker 20 can communicate with the job content generation device 30 via a network 11 such as the Internet.

[0034] In the voice operation system 10, a job content generating device 30 communicates with a job command generating device 40 via a network 11 such as the Internet.

[0035] The image forming device 50 can communicate with any of the job instruction generating devices within the same network, such as a LAN (Local Area Network). For example, the image forming device 50 can communicate with the job instruction generating device 40 within the same network 12. That is, the job instruction generating device 40 is located within the network 12. On the other hand, the job content generating device 30 is connected to the job instruction generating device 40 via a network 11, such as the Internet, which is different from the network 12, as described above, and is therefore located outside the network 12.

[0036] FIG. 2 is a block diagram of the job content generation device 30 when the job content generation device 30 is configured by one computer.

[0037] As shown in FIG. 2 , the job content generation device 30 includes an operation unit 31, which is an operation device such as a keyboard or a mouse through which various operations are input; a display unit 32, which is a display device such as an LCD (Liquid Crystal Display) that displays various information; a communication unit 33, which is a communication device that communicates with external devices via a network such as a LAN or the Internet, or directly via a wired or wireless connection without using a network; a memory unit 34, which is a non-volatile memory device such as a semiconductor memory or an HDD (Hard Disk Drive) that stores various information; and a control unit 35 that controls the entire job content generation device 30.

[0038] The storage unit 34 stores a job content generation program 34a for generating job content based on voice data. The job content generation program 34a may be installed in the job content generation device 30 during the manufacturing stage of the job content generation device 30, or may be additionally installed in the job content generation device 30 from an external storage medium such as a USB (Universal Serial Bus) memory, or may be additionally installed in the job content generation device 30 from a network.

[0039] The storage unit 34 stores a text data conversion model 34b, which is a machine learning model for converting voice data into text data, and a job content conversion model 34c, which is a machine learning model for converting text data into job content.

[0040] The storage unit 34 stores inappropriate job content determination information 34d as information for determining inappropriate job content.

[0041] FIG. 3 is a diagram showing an example of the inappropriate job content determination information 34d.

[0042] 3, the inappropriate job content determination information 34d indicates, for each inappropriate combination, predetermined combinations of multiple setting values ​​that cannot be set simultaneously in the job content (hereinafter referred to as "inappropriate combinations"), a priority order for determining which inappropriate combination the inappropriate combination corresponds to, and a method for correcting the inappropriate combination. The combination of setting values ​​indicated by the method for correcting the inappropriate combination is an example of a predetermined combination that can be set simultaneously in the job content.

[0043] For example, the inappropriate job content determination information 34d shown in Figure 3 includes an inappropriate combination (hereinafter referred to as "inappropriate combination A") in which multiple setting values ​​in the job content include a setting value indicating that the job type is copy (hereinafter referred to as "copy job setting value") and a setting value indicating that the source of the file used in the job is a USB memory as an external storage device attached to the image forming apparatus (hereinafter referred to as "read source setting value"). In the inappropriate job content determination information 34d shown in Figure 3, the copy job setting value is represented as "job type: copy". In the inappropriate job content determination information 34d shown in Figure 3, the read source setting value is represented as "read source: USB memory".

[0044] Also, for example, the information 34d for determining inappropriate job content shown in Figure 3 includes multiple setting values ​​in the job content, including a copy job setting value, a setting value indicating the size of the document used for the job (hereinafter referred to as the "document size setting value"), and a setting value indicating the size of the paper on which the image is printed in the job (hereinafter referred to as the "paper size setting value"), and includes an inappropriate combination (hereinafter referred to as the "inappropriate combination B") in which the size of the document actually set in the image forming device is not the size indicated by the document size setting value.

[0045] Also, for example, the information 34d for determining inappropriate job content shown in Figure 3 includes an inappropriate combination (hereinafter referred to as "inappropriate combination C") in which multiple setting values ​​in the job content include a copy job setting value and a setting value indicating the file name of a file used in the job (hereinafter referred to as "file name setting value").

[0046] 3, the inappropriate job content determination information 34d includes a plurality of setting values ​​in the job content, including a setting value indicating that the job type is document transmission (hereinafter referred to as the "transmission job setting value"), a setting value indicating the type of document transmission method (hereinafter referred to as the "transmission method setting value"), and a setting value indicating the type of encryption used when transmitting the document (hereinafter referred to as the "transmission encryption setting value"), and includes an inappropriate combination (hereinafter referred to as the "inappropriate combination D") in which the encryption type indicated in the transmission encryption setting value does not correspond to the type of transmission method indicated in the transmission method setting value. In the inappropriate job content determination information 34d shown in FIG. 3, the transmission job setting value is represented as "job type: transmission."

[0047] Regarding priority, for example, since the priority of inappropriate combination C is lower than the priority of inappropriate combination A and inappropriate combination B, it is determined whether or not a combination corresponds to inappropriate combination C only if it does not correspond to either inappropriate combination A or inappropriate combination B.

[0048] In the inappropriate job content determination information 34d shown in Fig. 3, the correction method for inappropriate combination A is to correct the copy job setting value to a setting value indicating that the job type is print (hereinafter referred to as the "print job setting value") when a USB memory is actually attached to the image forming device. In the inappropriate job content determination information 34d shown in Fig. 3, the print job setting value is expressed as "job type: print".

[0049] In the inappropriate job content determination information 34d shown in Figure 3, the correction method for inappropriate combination B is a method of correcting by swapping the size indicated in the original size setting value and the size indicated in the paper size setting value when the size of the original actually set in the image forming device is the size indicated in the paper size setting value.

[0050] In the inappropriate job content determination information 34d shown in FIG. 3, the correction method for the inappropriate combination C is to correct the copy job setting values ​​to the print job setting values.

[0051] In the inappropriate job content judgment information 34d shown in Figure 3, the method of correcting inappropriate combination D is to correct the type of encryption indicated in the encryption setting value at the time of transmission to one that corresponds to the type of transmission method indicated in the transmission method setting value.

[0052] 2 includes, for example, a CPU (Central Processing Unit), a ROM (Read Only Memory) that stores programs and various data, and a RAM (Random Access Memory) that serves as a memory used as a working area for the CPU of the control unit 35. The CPU of the control unit 35 executes programs stored in the storage unit 34 or the ROM of the control unit 35.

[0053] The control unit 35 executes the job content generation program 34a to function as a job content generation unit 35a that generates job content based on the voice data.

[0054] FIG. 4 is a block diagram of the job command generating device 40 when the job command generating device 40 is configured by one computer.

[0055] As shown in FIG. 4, the job command generating device 40 includes an operation unit 41, which is an operation device such as a keyboard or a mouse through which various operations are input; a display unit 42, which is a display device such as an LCD that displays various information; a communication unit 43, which is a communication device that communicates with external devices via a network such as a LAN or the Internet, or directly via a wired or wireless connection without using a network; a memory unit 44, which is a non-volatile memory device such as a semiconductor memory or an HDD that stores various information; and a control unit 45 that controls the entire job command generating device 40.

[0056] The storage unit 44 stores a job instruction generation program 44a for generating job instructions based on job content. The job instruction generation program 44a may be installed in the job instruction generation device 40 during the manufacturing stage of the job instruction generation device 40, or may be additionally installed in the job instruction generation device 40 from an external storage medium such as a USB memory, or may be additionally installed in the job instruction generation device 40 from a network.

[0057] The control unit 45 includes, for example, a CPU, a ROM that stores programs and various data, and a RAM that serves as a memory used as a work area for the CPU of the control unit 45. The CPU of the control unit 45 executes the programs stored in the storage unit 44 or the ROM of the control unit 45.

[0058] The control unit 45 executes the job command generation program 44a to function as a job command generation unit 45a that generates job commands based on the job contents.

[0059] When multiple setting values ​​in the content of a job to be executed by the image forming device 50 are a predetermined combination that cannot be set simultaneously, the job command generation unit 45a performs a process of correcting at least one of the multiple setting values ​​in the content to a setting value that is a predetermined combination that can be set simultaneously.

[0060] FIG. 5 is a block diagram of the image forming apparatus 50 when the image forming apparatus 50 is an MFP.

[0061] As shown in FIG. 5 , the image forming apparatus 50 includes an operation unit 51 which is an operation device such as a button through which various operations are input, a display unit 52 which is a display device such as an LCD that displays various information, a printer 53 which is a printing device that prints images on a recording medium such as paper, a scanner 54 which is a reading device that reads images from a document, a USB port 55, a communication unit 56 which is a communication device that communicates with an external device via a network such as a LAN or the Internet, or directly by wire or wirelessly without using a network, a fax communication unit 57 which is a fax device that communicates with an external facsimile machine (not shown) via a communication line such as a public telephone line, a memory unit 58 which is a non-volatile memory device such as a semiconductor memory or an HDD that stores various information, and a control unit 59 that controls the entire image forming apparatus 50.

[0062] The storage unit 58 stores a job execution program 58a for executing a job. The job execution program 58a may be installed in the image forming apparatus 50 during the manufacturing stage of the image forming apparatus 50, or may be additionally installed in the image forming apparatus 50 from an external storage medium such as a USB memory, or may be additionally installed in the image forming apparatus 50 from a network.

[0063] Control unit 59 includes, for example, a CPU, a ROM that stores programs and various data, and a RAM that serves as a memory used as a work area for the CPU of control unit 59. The CPU of control unit 59 executes programs stored in storage unit 58 or the ROM of control unit 59.

[0064] The control unit 59 executes the job execution program 58a to function as a job execution unit 59a that executes a job.

[0065] Next, the operation of the voice operation system 10 when the image forming apparatus is operated via a smart speaker will be described.

[0066] In the following description, the smart speaker that accepts voice operations for operating the image forming device is assumed to be the smart speaker 20. The image forming device that is the target of the voice operations accepted by the smart speaker 20 is assumed to be the image forming device 50.

[0067] Fig. 6 is a sequence diagram of the operation of the voice operation system 10 when the image forming apparatus 50 is operated via the smart speaker 20. Fig. 7 is a sequence diagram of the "job content determination" shown in Fig. 6. Fig. 8 is a sequence diagram of the "job execution" shown in Fig. 7.

[0068] The user inputs voice into the smart speaker 20 indicating the operation content for the image forming device 50 .

[0069] When voice is input, the smart speaker 20 accepts the voice input to the smart speaker 20 itself, as shown in Figures 6 to 8 (S61).

[0070] When the processing of S61 is completed, the smart speaker 20 transmits voice data indicating the voice received in S61 to the job content generation device 30 (S62).

[0071] For example, if the user inputs the voice "copy on both sides" into the smart speaker 20, the smart speaker 20 transmits voice data indicating the voice "copy on both sides" to the job content generation device 30 (S62).

[0072] When voice data is transmitted from the smart speaker 20 in S62, the job content generation unit 35a of the job content generation device 30 converts the voice data transmitted from the smart speaker 20 in S62 into text data using the text data conversion model 34b (S63).

[0073] When the process of S63 is completed, the job content generating unit 35a converts the text data generated in S63 into job content using the job content conversion model 34c (S64).

[0074] For example, when voice data indicating a voice saying "Copy on both sides" is transmitted from the smart speaker 20 to the job content generation device 30, the job content generation unit 35a of the job content generation device 30 converts the voice data indicating the voice saying "Copy on both sides" into job content including the contents "Job type: Copy" and "Print side: Double-sided" (S63-S64). Here, "Print side: Double-sided" is a setting value indicating that images are printed on both sides of the paper on which they are printed in the job. That is, the job content generation unit 35a converts predetermined keywords (e.g., "copy," "print," "send" for the setting item "Job type," "Print side," "Source," "Original size," "File name," "Transmission method," "Encryption method," "Destination," etc.) that are setting values ​​related to each setting item constituting the job (e.g., "Job type," "Print side," "Source," "Original size," "File name," "Transmission method," "Encryption method," "Destination," etc.) into job content including the contents "Job type," "Print side," "Send," "Double-sided," "Single-sided," etc. for the setting item "Print side," "USB memory," "User hooks," etc. for the setting item "Source," "A4," "A3," "B4," etc. for the setting item "Original size"). For example, for the setting item "file name", it could be "File A", "File B", etc. For the setting item "sending method", it could be "FTP sending", etc. For the setting item "encryption method", it could be "FTP encryption", "E-mail encryption", etc. For the setting item "destination", it could be "Taro", "Jiro", etc.) and it would determine whether the voice data contains the keyword, and if the keyword is included, it would further determine the setting item corresponding to the word indicated by the keyword, thereby converting the voice data into elements that make up the job content, such as "job type: copy" or "print side: double-sided".

[0075] For example, when voice data indicating a voice saying "Print the file in the USB memory" is transmitted from the smart speaker 20 to the job content generation device 30, the job content generation unit 35a of the job content generation device 30 converts the voice data indicating the voice saying "Print the file in the USB memory" into job content including the contents "Job type: Print" and "Source: USB memory" (S63-S64). However, there is also a possibility that the job content generation unit 35a may erroneously convert the voice data into job content including the contents "Job type: Copy" and "Source: USB memory" (S63-S64).

[0076] For example, if voice data indicating a voice saying "Copy from A4 to A3" is transmitted from the smart speaker 20 to the job content generation device 30, the job content generation unit 35a of the job content generation device 30 converts the voice data indicating the voice saying "Copy from A4 to A3" into job content including the contents "Job Type: Copy," "Original Size: A4," and "Paper Size: A3" (S63-S64). However, the job content generation unit 35a may erroneously convert the voice data into job content including the contents "Job Type: Copy," "Original Size: A3," and "Paper Size: A4" (S63-S64). Here, "Original Size: A3" is an original size setting value indicating that the size of the original loaded in the image forming device is A3 size. "Original Size: A4" is an original size setting value indicating that the size of the original loaded in the image forming device is A4 size. "Paper Size: A3" is a paper size setting value indicating that the size of the paper on which the image in the job is printed is A3 size. "Paper size: A4" is a paper size setting value indicating that the size of paper on which an image is printed in a job is A4 size.

[0077] For example, when voice data indicating a voice saying "Copy file A" is transmitted from the smart speaker 20 to the job content generation device 30, the job content generation unit 35a of the job content generation device 30 converts the voice data indicating the voice saying "Copy file A" into job content including the contents "Job type: Copy" and "File name: File A." Here, "File name: File A" is a file name setting value indicating that the file name of the file used for the job is "File A."

[0078] For example, when voice data indicating a voice saying, "Encrypt the image and send the document to Taro via FTP," is transmitted from the smart speaker 20 to the job content generation device 30, the job content generation unit 35a of the job content generation device 30 converts the voice data indicating the voice saying, "Encrypt the image and send the document to Taro via FTP" into job content including the following contents: "Job Type: Send," "Send Method: FTP Send," "Encryption Method: FTP Encryption," and "Destination: Taro" (S64). However, the job content generation unit 35a may erroneously convert the voice data into job content including the following contents: "Job Type: Send," "Send Method: FTP Send," "Encryption Method: Email Encryption," and "Destination: Taro" (S64). Here, "Destination: Taro" is a setting value indicating "Taro" as the destination of the document. "Send Method: FTP Send" is a transmission method setting value indicating FTP transmission as the type of document transmission method. "Encryption method: FTP encryption" is a transmission encryption setting value that indicates "FTP encryption" as the type of encryption used when sending a document. "Encryption method: E-mail encryption" is a transmission encryption setting value that indicates "E-mail encryption" as the type of encryption used when sending a document.

[0079] When the process of S64 is completed, the job content generating unit 35a requests the job command generating device 40 to transmit information indicating the status of the image forming device 50 (S65).

[0080] When the job content generation device 30 requests the job command generation unit 45a of the job command generation device 40 to send information indicating the status of the image forming device 50 in S65, the job command generation unit 45a requests the image forming device 50 to send information indicating the status of the image forming device 50 (S66).

[0081] When the job execution unit 59a of the image forming apparatus 50 is requested by the job instruction generation device 40 to transmit information indicating the status of the image forming apparatus 50 in S66, the job execution unit 59a transmits the information indicating the status of the image forming apparatus 50 to the job instruction generation device 40 (S67). For example, the job execution unit 59a transmits to the job instruction generation device 40, as information indicating the status of the image forming apparatus 50, information indicating whether a USB memory is attached to the USB port 55, information indicating whether a document is set in the scanner 54, and, if a document is set in the scanner 54, information indicating the size of the document set in the scanner 54, as the status of the image forming apparatus 50 (S67).

[0082] For example, when the control unit 59 of the image forming apparatus 50 can communicate with the USB memory via the USB port 55, the control unit 59 determines that a USB memory is attached to the USB port 55. The control unit 59 also determines whether a document is set on the scanner 54 based on a document detection signal received from a sensor that detects whether a document is placed on a document reading table (e.g., a flatbed or a document placement table of an automatic document feeder) provided in the scanner 54. Alternatively, the control unit 59 stores size information indicating the size of recording paper contained in a paper feed cassette received by an operation unit (provided in the image forming apparatus 50) to which the size information is input, and detects the size of recording paper contained in the paper feed cassette to be used for printing based on the stored size information.

[0083] When information indicating the status of the image forming device 50 is sent from the image forming device 50 in S67, the job command generation unit 45a of the job command generation device 40 sends the information indicating the status of the image forming device 50 sent from the image forming device 50 in S67 to the job content generation device 30 (S68).

[0084] When the job content generation unit 35a of the job content generation device 30 receives the information indicating the status of the image forming device 50 sent from the job command generation device 40 in S68, it determines whether the job content generated in S64 is inappropriate based on the job content generated in S64, the received information indicating the status of the image forming device 50, and the inappropriate job content determination information 34d (S69).

[0085] For example, if the job content generation unit 35a generates job content including the content "job type: copy" and "source: USB memory" in S64, the job content generated in S64 falls under the above-mentioned inappropriate combination A, and therefore determines in S69 that the job content generated in S64 is inappropriate.

[0086] Furthermore, for example, if the job content generation unit 35a generates job content including the content "job type: copy," "original size: A3," and "paper size: A4" in S64, when "A4" is sent from the job command generation device 40 in S68 as the size of the original set in the image forming device 50, the job content generated in S64 falls under the above-mentioned inappropriate combination B, and therefore the job content generated in S64 is determined to be inappropriate in S69.

[0087] Furthermore, for example, if the job content generation unit 35a generates job content including the content "job type: copy" and "file name: file A" in S64, the job content generated in S64 falls under the inappropriate combination C described above, and therefore determines in S69 that the job content generated in S64 is inappropriate.

[0088] Furthermore, for example, if the job content generation unit 35a generates job content in S64 that includes the content "job type: send," "send method: FTP send," "encryption method: email encryption," and "destination: Taro," the job content generated in S64 falls under the inappropriate combination D described above, and therefore determines in S69 that the job content generated in S64 is inappropriate.

[0089] If the job content generation unit 35a determines in S69 that the job content generated in S64 is inappropriate, it determines whether the job content generated in S64 can be corrected (S70) based on the job content generated in S64, the information indicating the status of the image forming device 50 received from the job command generation device 40 (S68), and the information for determining inappropriate job content 34d.

[0090] For example, when the job content generation unit 35a generates job content including the content "job type: copy" and "source: USB memory" in S64, and information indicating that a USB memory is not attached to the image forming device 50 is sent from the job command generation device 40 in S68, and when this information is received, the job content generation unit 35a determines in S70 that the job content generated in S64 cannot be corrected based on the inappropriate job content determination information 34d.

[0091] In S70, when the job content generation unit 35a determines that the job content generated in S64 cannot be corrected, the job content generation unit 35a notifies the smart speaker 20 of the error (S71).

[0092] When the smart speaker 20 is notified of an error by the job content generation device 30 in S71, the smart speaker 20 outputs the error notified by the job content generation device 30 in S71 by voice (S72).

[0093] Furthermore, when the job content generation unit 35a determines in S70 that the job content generated in S64 can be corrected, it corrects the job content generated in S64 based on the job content generated in S64, the information indicating the status of the image forming device 50 transmitted from the job command generation device 40 in S68, and the information 34d for determining inappropriate job content (S73).

[0094] For example, if the job content generation unit 35a generates job content including the contents "job type: copy" and "source: USB memory" in S64, when the job command generation device 40 sends information in S68 that a USB memory is attached to the image forming device 50, the job content generation unit 35a corrects the job content including the contents "job type: copy" and "source: USB memory" generated in S64 to job content including the contents "job type: print" and "source: USB memory" based on the "correction method" in the inappropriate job content determination information 34d.

[0095] Also, for example, if the job content generation unit 35a generates job content including the contents "job type: copy," "original size: A3," and "paper size: A4" in S64, when "A4" is transmitted from the job command generation device 40 in S68 as the size of the original set in the image forming device 50, the job content generation unit 35a corrects the job content generated in S64 including the contents "job type: copy," "original size: A3," and "paper size: A4" to job content including the contents "job type: copy," "original size: A4," and "paper size: A3" based on the "correction method" in the inappropriate job content determination information 34d.

[0096] Furthermore, for example, when the job content generation unit 35a generates job content including the content "job type: copy" and "file name: file A" in S64, the job content generation unit 35a corrects the job content including the content "job type: copy" and "file name: file A" generated in S64 to job content including the content "job type: print" and "file name: file A" based on the "correction method" in the inappropriate job content determination information 34d.

[0097] Furthermore, for example, when the job content generation unit 35a generates job content in S64 that includes the contents of "job type: send," "sending method: FTP send," "encryption method: email encryption," and "destination: Taro," the job content generation unit 35a corrects the job content generated in S64 that includes the contents of "job type: send," "sending method: FTP send," "encryption method: email encryption," and "destination: Taro" to the job content that includes the contents of "job type: send," "sending method: FTP send," "encryption method: FTP encryption," and "destination: Taro," based on the "correction method" of the inappropriate job content determination information 34d.

[0098] The job content generation unit 35a determines in S69 that the job content generated in S64 is not inappropriate, or when the processing of S73 is completed, transmits the job content determined in S69 to be not inappropriate or the job content corrected in S73 to the job command generation device 40 (S74).

[0099] The transmission method in S74 may be any method that allows job content to be transmitted from the job content generation device 30 to the job instruction generation device 40. For example, if a publish-subscribe model messaging service is used as the transmission method in S74, the job content generation unit 35a can transmit the job content by publishing a message including the job content. Furthermore, if a publish-subscribe model messaging service is used as the transmission method in S74, the job instruction generation unit 45a of the job instruction generation device 40 can receive the job content by subscribing to the published message.

[0100] When the job content is sent from the job content generation device 30 in S74, the job command generation unit 45a of the job command generation device 40 converts the job content sent from the job content generation device 30 in S74 into a job command that can be interpreted by the image forming device 50, i.e., a job command in a format that can be accepted by the interface provided in the image forming device 50 (S75).

[0101] When the process of S75 is completed, the job command generating unit 45a transmits the job command generated in S75 to the image forming apparatus 50 (S76).

[0102] The transmission method in S76 may be any method that allows a job instruction to be transmitted from the job instruction generation device 40 to the image forming device 50. For example, if a Web service-type interface provided in the image forming device 50 is used as the transmission method in S76, the job instruction generation unit 45a transmits the job instruction by calling this Web service. Also, if a Web service-type interface provided in the image forming device 50 is used as the transmission method in S76, the job execution unit 59a of the image forming device 50 receives the job instruction transmitted by calling this Web service.

[0103] When the job command is transmitted from the job command generating device 40 in S76, the job executing unit 59a of the image forming device 50 executes the job in accordance with the job command transmitted from the job command generating device 40 in S76 (S77).

[0104] As described above, when a combination of multiple setting values ​​in the job content cannot be simultaneously set, the job content generation device 30 corrects at least one of the multiple setting values ​​in the job content so that the combination of multiple setting values ​​in the job content can be simultaneously set (S73), thereby improving convenience. For example, when the multiple setting values ​​in the job content include a copy job setting value and a file name setting value, the job content generation device 30 corrects the copy job setting value to a print job setting value, thereby improving convenience. Also, for example, when the multiple setting values ​​in the job content include a transmission job setting value, a transmission method setting value, and an encryption setting value at transmission, if the encryption type indicated in the encryption setting value at transmission does not correspond to the transmission method type indicated in the transmission method setting value, the job content generation device 30 corrects the encryption type indicated in the encryption setting value to correspond to the transmission method type indicated in the transmission method setting value, thereby improving convenience.

[0105] In particular, the job content generation device 30 corrects at least one of the multiple setting values ​​in the job content based on the state of the image forming device 50, thereby improving the appropriateness of the corrected job content. For example, when the multiple setting values ​​in the job content include a copy job setting value and a read source setting value, the job content generation device 30 corrects the copy job setting value to the print job setting value when a USB memory is actually attached to the image forming device 50, thereby improving the appropriateness of the corrected job content. Also, for example, when the multiple setting values ​​in the job content include a copy job setting value, an original size setting value, and a paper size setting value, when the size of the original actually set in the image forming device is the size indicated by the paper size setting value rather than the size indicated by the original size setting value, the job content generation device 30 performs a correction to swap the size indicated by the original size setting value with the size indicated by the paper size setting value, thereby improving the appropriateness of the corrected job content.

[0106] When the job content has a combination of multiple setting values ​​that cannot be set simultaneously, the job content generation device 30 corrects at least one of the multiple setting values ​​in the job content so that the combination of multiple setting values ​​in the job content can be set simultaneously.Therefore, even if the job content is generated incorrectly in the process of generating the job content using a machine learning model based on voice data, the job content can be automatically corrected.

[0107] The voice-operated system 10 requires that the job content generation device 30, which must have high processing power to generate job content based on voice data representing voice received by the smart speaker 20, is not located within the same network 12 as the image forming device 50, and the job instruction generation device 40, which generates job instructions that can be interpreted by the image forming device 50 based on the job content generated by the job content generation device 30, is located within the same network 12 as the image forming device 50. This reduces the processing power required for the computer that constitutes the job instruction generation device 40, which is located within the same network 12 as the image forming device 50.

[0108] The voice operation system 10 has a job instruction generation device 40 that generates job instructions that can be interpreted by the image forming device 50, located within the same network 12 as the image forming device 50.Therefore, even if the image forming device 50 does not have a mechanism for accepting job instructions that can be interpreted by the image forming device 50 from outside the network 12, the image forming device 50 can be operated via the smart speaker 20.

[0109] The voice operation system 10 requires high processing power to convert voice data representing voice received by the smart speaker 20 into job content using machine learning models called a text data conversion model 34b and a job content conversion model 34c. However, since the job content generation device 30 is not located within the same network 12 as the image forming device 50, the processing power required for a computer located within the same network 12 as the image forming device 50 can be reduced.

[0110] In this embodiment, the job content generation device 30 converts the voice data transmitted from the smart speaker 20 into text data and then converts it into job content. However, the job content generation device 30 may also convert the voice data transmitted from the smart speaker 20 into job content directly using a machine learning model without converting it into text data.

[0111] In this embodiment, the job content generation device 30 acquires the status of the image forming device 50 after processing S64. However, after processing S64, the job content generation device 30 determines that the job content generated in S64 corresponds to an inappropriate combination based on the inappropriate job content determination information 34d. If the job content generation device 30 can correct the combination to an appropriate combination based on the inappropriate job content determination information 34d, the job content generation device 30 may not request the image forming device 50 to transmit information indicating the status of the image forming device 50. In this case, the processes of S65 to S69 are not performed, and after the above determination, the job content generation device 30 performs the process of S70 based on the information indicated by the inappropriate job content determination information 34d. This omits the request to transmit and the reception of information indicating the status of the image forming device 50 that is not necessary for correcting the job content. Note that the job content generation device 30 requests the image forming device 50 to transmit information indicating the status of the image forming device 50 only if the combination cannot be corrected to an appropriate combination based on the information indicated by the inappropriate job content determination information 34d.

[0112] In this embodiment, the voice operation system 10 includes a job instruction generation device 40 in addition to the job content generation device 30. However, the job content generation device 30 may also include the function of the job instruction generation device 40, that is, to generate job instructions that can be interpreted by the image forming device 50. If the job content generation device 30 includes the function of the job instruction generation device 40, it may be located inside the network 12.

[0113] In this embodiment, the voice operation system 10 employs a USB memory as the external storage device attached to the image forming apparatus. However, the external storage device attached to the image forming apparatus may be a storage device other than a USB memory.

Claims

1. A job content generation device that generates content of a job to be executed by an image forming device based on voice data indicating voice received by a voice receiving device, the job content generation device, a control unit that includes a processor, and that functions as a job content generation unit that, when a plurality of setting values ​​in the content are a predetermined combination that cannot be set simultaneously, corrects at least one of the plurality of setting values ​​in the content to a predetermined combination that can be set simultaneously, based on the state of the image forming device, by executing a job content generation program by the processor; The job content generation unit requesting the image forming device to transmit information indicating the status of the image forming device, and making the correction using the information transmitted from the image forming device; If the job content generation device determines that the combination is a predetermined combination that cannot be set and can be corrected to an appropriate combination even without the information, the job content generation device does not make the request to the image forming device, does not obtain the information from the image forming device, and performs the correction without using the information.

2. The job content generation device according to claim 1 , wherein the content is generated using a machine learning model based on the voice data.

3. The job content generation unit When the plurality of setting values ​​in the content are the predetermined combination that cannot be set, including a copy job setting value as the setting value that the job type is a copy, and a setting value that the source of the file used for the job is an external storage device attached to the image forming apparatus, A job content generation device as described in claim 1, wherein when the external storage device is actually attached to the image forming device, the copy job setting value is corrected to the setting value indicating that the job type is printing, thereby correcting multiple setting values ​​in the content to setting values ​​that form a predetermined combination that can be set simultaneously.

4. The job content generation unit When the plurality of setting values ​​in the content are the predetermined combination that cannot be set, including the setting value that the type of the job is copy, an original size setting value as the setting value indicating the size of the original used in the job, and a paper size setting value as the setting value indicating the size of the paper on which an image is printed in the job, A job content generation device as described in claim 1, wherein when the size of the original document actually set in the image forming device is not the size indicated in the original size setting value but the size indicated in the paper size setting value, a correction is made to swap the size indicated in the original size setting value with the size indicated in the paper size setting value, thereby correcting the multiple setting values ​​in the content to setting values ​​that form a predetermined combination that can be set simultaneously.

5. The job content generation unit When the plurality of setting values ​​in the content are the predetermined combination that cannot be set, including a copy job setting value as the setting value that the type of the job is copy, and a setting value that indicates the file name of a file to be used for the job, A job content generation device as described in claim 1, wherein by correcting the copy job setting value to the setting value indicating that the job type is printing, multiple setting values ​​in the content are corrected to setting values ​​that are a predetermined combination that can be set simultaneously.

6. The job content generation unit When the plurality of setting values ​​in the content are the predetermined combination that cannot be set, including the setting value that the type of the job is document transmission, a transmission method setting value as the setting value indicating the type of method for transmitting the document, and a transmission encryption setting value as the setting value indicating the type of encryption when transmitting the document, A job content generation device as described in claim 1, wherein when the type of encryption indicated in the encryption setting value at the time of transmission does not correspond to the type of transmission method indicated in the transmission method setting value, the device corrects the type of encryption indicated in the encryption setting value at the time of transmission to one that corresponds to the type of transmission method indicated in the transmission method setting value, thereby correcting multiple setting values ​​in the content to setting values ​​that form a predetermined combination that can be set simultaneously.

7. Computer, a job content generating unit that generates content of a job to be executed by the image forming apparatus based on voice data indicating voice received by a voice receiving device that receives voice; when a plurality of setting values ​​in the content are a predetermined combination that cannot be set simultaneously, the job content generation unit corrects at least one of the plurality of setting values ​​in the content to a predetermined combination that can be set simultaneously, based on a state of the image forming apparatus; requesting the image forming device to transmit information indicating the status of the image forming device, and making the correction using the information transmitted from the image forming device; A job content generation program that determines that the combination is a predetermined combination that cannot be set, and if the combination can be corrected to an appropriate combination even without the information, does not make the request to the image forming device, does not obtain the information from the image forming device, and performs the correction without using the information.