Information processing device, image processing device, setting support method, and setting support program

Abstract

To facilitate the setting work of an image processing device. [Solution] The server 200 includes a model acquisition unit that acquires a learned learning model obtained by machine learning training data including first adjustment parameters that can be set in a first type of first MFP 100-1 to 100-N and first features that indicate the characteristics of first image data that has been image processed by the first MFP 100-1 to 100-N using the first adjustment parameters; a feature acquisition unit that acquires second features that indicate the characteristics of second image data that has been image processed by a second type of second MFP 300; and a prediction unit that predicts third adjustment parameters to be set in a first type of third image processing device from the second features using the learning model.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an image processing device, a setting support method, and a setting support program, and more particularly to an information processing device that supports the setting of an image processing device, the image processing device, a setting support method executed by the information processing device, and a setting support program that causes a computer to execute the setting support method. [Background technology]

[0002] An image processing device, typified by an MFP (Multi Function Peripheral), has the function of processing images. The MFP executes the image processing in accordance with adjustment parameters. Here, assume that an MFP that is already in use is replaced with another new MFP. It is preferable to set adjustment parameters in the new MFP so that the image quality of the image in the image processing executed by the new MFP is the same as the image quality of the image in the image processing executed by the MFP in use. However, the adjustment parameters may differ between the MFP in use and the new MFP, and skill is required to determine the adjustment parameters to be set in the new MFP.

[0003] JP 2020-61018 A describes an image forming system comprising a plurality of image forming devices and a plurality of groups to which the image forming devices can belong, wherein the image forming devices in each group are connected to each other by logical links, and each of the image forming devices comprises a memory unit that stores link information including a destination address and a link weight value that defines the logical link, and image setting information that indicates quantitative setting values ​​related to image formation, a communication unit that performs communication with other image forming devices in accordance with the link information, an image forming unit that performs image formation in accordance with the image setting information, and a setting management unit that changes the image setting information in accordance with instructions from a user, multiplies the changed image setting information by the link weight value, and controls the communication unit to send the changed image setting information to the destination address.

[0004] In the image forming system described in JP 2020-61018 A, image setting information is shared among multiple groups. However, the user must specify the group to which the image forming device belongs. The user must also specify a link weight for each group. This makes the settings complicated. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2020-61018 Summary of the Invention [Problem to be solved by the invention]

[0006] SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and one of the objects of the present invention is to provide an information processing apparatus that makes it easy to set up the image processing apparatus.

[0007] Another object of the present invention is to provide an image processing apparatus that facilitates the setting operation.

[0008] A further object of the present invention is to provide a setting support method that facilitates the setting work of an image processing apparatus.

[0009] It is still another object of the present invention to provide a setting support program that facilitates the setting work of an image processing apparatus. [Means for solving the problem]

[0010] In order to achieve the above-mentioned object, according to one aspect of the present invention, an information processing device includes: a model acquisition unit that acquires a learned learning model obtained by machine learning training data including a first adjustment parameter that can be set in a first image processing device of a first type and a first feature that indicates the characteristics of first image data that has been image processed by the first image processing device using the first adjustment parameter; a feature acquisition unit that acquires a second feature that indicates the characteristics of second image data that has been image processed by a second image processing device of a second type; and a prediction unit that predicts a third adjustment parameter from the second feature using the learning model.

[0011] According to another aspect of the present invention, an image processing device includes the information processing device described above and a setting unit that sets a third adjustment parameter.

[0012] According to another aspect of the present invention, a setting support method causes an information processing device to execute a model acquisition step of acquiring a learned learning model obtained by machine learning training data including a first adjustment parameter that can be set in a first image processing device of a first type and a first feature that indicates the characteristics of first image data that has been image processed by the first image processing device using the first adjustment parameter; a feature acquisition step of acquiring a second feature that indicates the characteristics of second image data that has been image processed by a second image processing device of a second type; and a prediction step of predicting a third adjustment parameter from the second feature using the learning model.

[0013] According to yet another aspect of the present invention, the setting support program causes a computer to execute a model acquisition step of acquiring a learned learning model obtained by machine learning training data including a first adjustment parameter that can be set in a first image processing device of a first type and a first feature that indicates the characteristics of first image data that has been image processed by the first image processing device using the first adjustment parameter; a feature acquisition step of acquiring a second feature that indicates the characteristics of second image data that has been image processed by a second image processing device of a second type; and a prediction step of predicting a third adjustment parameter from the second feature using the learning model. [Brief explanation of the drawings]

[0014] [Figure 1]1 is a diagram showing an example of an overall overview of an image processing system according to a first embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing an example of an outline of the hardware configuration of a server according to the present embodiment. [Figure 3] FIG. 2 is a cross-sectional view schematically illustrating an example of the internal configuration of an MFP. [Figure 4] 1 is a block diagram showing an outline of the hardware configuration of an MFP according to the present embodiment. [Figure 5] FIG. 2 is a block diagram showing an example of functions possessed by a server and a third MFP according to the present embodiment. [Figure 6] 10 is a flowchart illustrating an example of the flow of a model generation process. [Figure 7] 10 is a flowchart illustrating an example of the flow of an adjustment parameter determination process. [Figure 8] 10 is a flowchart illustrating an example of the flow of a setting support process. [Figure 9] 10 is a flowchart illustrating an example of the flow of an additional learning process. [Figure 10] FIG. 10 is a block diagram showing an example of functions possessed by a server and a third MFP of an image processing system in a second modified example. [Figure 11] 10 is a flowchart showing an example of the flow of a setting support process in a second modified example. DETAILED DESCRIPTION OF THE INVENTION

[0015] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description, the same components are denoted by the same reference numerals. The names and functions of these components are also the same. Therefore, detailed description thereof will not be repeated.

[0016] First Embodiment FIG. 1 is a diagram showing an example of an overall overview of an image processing system according to a first embodiment of the present invention. Referring to FIG. 1, image processing system 1 includes server 200, a plurality of first MFPs 100-1 to 100-N (N is a positive integer), a second MFP 300, and a third MFP 100. The plurality of first MFPs 100-1 to 100-N and the third MFP 100 are the same type of image processing device. The second MFP 300 is a different type of image processing device from the first MFPs 100-1 to 100-N and the third MFP 100. The type includes manufacturer, series, and model. Therefore, when the type is defined as manufacturer, two image processing devices that are made by different manufacturers are different types. When the type is defined as series, two image processing devices that are made by the same manufacturer but are in different series are different types. When the type is defined as model, two image processing devices that are made by the same manufacturer but are in different series are different types.

[0017] Server 200 is an example of an information processing device. Server 200 is a general-purpose computer. First MFPs 100-1 to 100-N are each an example of a first image processing device. Second MFP 300 is an example of a second image processing device. Third MFP 100 is an example of a third image processing device.

[0018] The second MFP 300 and the third MFP 100 are connected to a network 3. The network 3 is a local area network (LAN). The network 3 is not limited to a LAN, but may be a wide area network (WAN) or the Internet. The network 3 is connected to the Internet 5 via a gateway (G / W) 7. The server 200 and a plurality of first MFPs 100-1 to 100-N are connected to the Internet 5.

[0019] The second MFP 300 and the third MFP 100 can communicate with each other via the network 3. The server 200 can communicate with the first MFPs 100-1 to 100-N via the Internet 5. The server 200 can communicate with the second MFP 300 and the third MFP 100 via the Internet 5 and the network 3.

[0020] In image processing system 1 of the present embodiment, an example will be described in which a user newly installs third MFP 100. Before installing third MFP 100, first MFPs 100-1 to 100-N and second MFP 300 are assumed to have been installed.

[0021] Fig. 2 is a block diagram showing an example of an outline of the hardware configuration of a server according to the present embodiment. Referring to Fig. 2, server 200 includes a CPU 201 for controlling the entire server 200, a ROM 202, a RAM 203, a hard disk drive (HDD) 204, a communication unit 205, a display unit 206, an operation unit 207, and an external storage device 209.

[0022] The ROM 202 stores programs to be executed by the CPU 201. The RAM 203 is used as a work area for the CPU 201. The HDD 204 is a large-capacity storage device that stores data in a non-volatile manner. A solid-state drive (SSD) may be used instead of the HDD 204. The communication unit 205 connects the CPU 201 to the network 3. The operation unit 207 accepts operations input by the user. The display unit 206 is, but is not limited to, a liquid crystal display device. Note that an organic EL (electroluminescence) display may be used instead of the liquid crystal display device.

[0023] A CD-ROM (Compact Disk Read Only Memory) 209A is attached to the external storage device 209. In this embodiment, an example will be described in which the CPU 201 executes a program stored in the ROM 202. However, the CPU 201 may control the external storage device 209 to read a program to be executed by the CPU 201 from the CD-ROM 209A, store the read program in the RAM 203, and execute the program.

[0024] The recording medium for storing the programs executed by CPU 201 is not limited to CD-ROM 209A, but may be a flexible disk, cassette tape, optical disk, semiconductor memory, etc. Optical disks include MO (Magnetic Optical Disc), MD (Mini Disc), and DVD (Digital Versatile Disc). Semiconductor memory includes IC cards, optical cards, mask ROM, and EPROM (Erasable Programmable ROM).

[0025] Furthermore, CPU 201 may load a program stored in HDD 204 into RAM 203 and execute it by CPU 201. The program stored in HDD 204 includes a program downloaded by CPU 201 from a computer connected to the Internet, or a program written to HDD 204 by a computer connected to the Internet. The program here includes not only a program that can be directly executed by CPU 201, but also a source program, a compressed program, an encrypted program, etc.

[0026] The first MFPs 100-1 to 100-N, the second MFP 300, and the third MFP 100 have in common the scanning function, the image forming function, and the data transmission / reception function, and have the same basic hardware configuration. Therefore, the hardware configuration of the third MFP 100 will be described here as an example. Note that the hardware configurations of the first MFPs 100-1 to 100-N, the second MFP 300, and the third MFP 100 may be the same or different.

[0027] 3 is a cross-sectional view showing an example of the internal configuration of an MFP. Referring to FIG. 3, MFP 100 includes automatic document feeder 120, document reading unit 130 that reads a document, image forming unit 140 that forms an image on paper based on image data, and paper feeding unit 150 that supplies paper to image forming unit 140.

[0028] The automatic document feeder 120 automatically transports multiple documents set on a document tray one by one to a predetermined document reading position set on the platen glass of the document reading unit 130. The automatic document feeder 120 discharges the document, from which the image formed on the document has been read by the document reading unit 130, onto a document output tray.

[0029] The document reading unit 130 exposes the image of a document set on a document glass 11 with an exposure lamp 13 attached to a slider 12 that moves below the document glass 11. Light reflected from the document is guided to a lens 16 by a mirror 14 and two reflecting mirrors 15 and 15A, and forms an image on a CCD (Charge Coupled Devices) sensor 18.

[0030] The reflected light that forms an image on the CCD sensor 18 is converted into image data as an electrical signal within the CCD sensor 18. The image data is converted into printing data in cyan (C), magenta (M), yellow (Y), and black (K) and output to the image forming unit 140.

[0031] The image forming unit 140 includes image forming units 20Y, 20M, 20C, and 20K for yellow, magenta, cyan, and black, respectively. Here, "Y," "M," "C," and "K" represent yellow, magenta, cyan, and black, respectively. An image is formed by driving at least one of the image forming units 20Y, 20M, 20C, and 20K. A full-color image is formed by driving all of the image forming units 20Y, 20M, 20C, and 20K. Printing data for yellow, magenta, cyan, and black are input to the image forming units 20Y, 20M, 20C, and 20K, respectively. The image forming units 20Y, 20M, 20C, and 20K differ only in the color of the toner they use. Therefore, the image forming unit 20Y for forming a yellow image will be described here.

[0032] The image forming unit 20Y includes an exposure device 21Y, a photosensitive drum 23Y, a charging roller 22Y, a developing unit 24Y, and a primary transfer roller 25Y. Around the photosensitive drum 23Y, the charging roller 22Y, the exposure device 21Y, the developing unit 24Y, the primary transfer roller 25Y, and the drum cleaning blade 27Y are arranged in this order along the rotational direction of the photosensitive drum 23Y. Yellow printing data is input to the exposure device 21Y. The photosensitive drum 23Y is an image carrier. The charging roller 22Y uniformly charges the surface of the photosensitive drum 23Y. The primary transfer roller 25Y transfers the toner image formed on the photosensitive drum 23Y onto an intermediate transfer belt 30, which is also an image carrier, by the action of an electric field.

[0033] After being charged by the charging roller 22Y, the photoreceptor drum 23Y is irradiated with laser light emitted by the exposure device 21Y. The exposure device 21Y exposes the image-corresponding portion of the surface of the photoreceptor drum 23Y. This forms an electrostatic latent image on the photoreceptor drum 23Y. Next, the developing device 24Y develops the electrostatic latent image formed on the photoreceptor drum 23Y with charged toner. Specifically, toner is placed on the electrostatic latent image formed on the photoreceptor drum 23Y by the action of electric field force, thereby forming a toner image on the photoreceptor drum 23Y. The toner image formed on the photoreceptor drum 23Y is transferred onto the intermediate transfer belt 30, which is an image carrier, by the action of electric field force using the primary transfer roller 25Y. Any toner remaining on the photoreceptor drum 23Y that has not been transferred is removed from the photoreceptor drum 23Y by the drum cleaning blade 27Y.

[0034] The intermediate transfer belt 30 is suspended tightly by a drive roller 33 and a driven roller 34. When the drive roller 33 rotates counterclockwise in FIG. 2, the intermediate transfer belt 30 rotates counterclockwise in the drawing at a predetermined speed. As the intermediate transfer belt 30 rotates, the driven roller 34 rotates counterclockwise.

[0035] As a result, the image forming units 20Y, 20M, 20C, and 20K sequentially transfer toner images onto the intermediate transfer belt 30. The timing at which each of the image forming units 20Y, 20M, 20C, and 20K transfers a toner image onto the intermediate transfer belt 30 is adjusted based on the detection of the reference marks on the intermediate transfer belt 30. As a result, yellow, magenta, cyan, and black toner images are superimposed on the intermediate transfer belt 30.

[0036] Paper of different sizes is set in paper feed cassettes 35 and 35A, respectively. The paper stored in paper feed cassettes 35 and 35A is supplied to conveyance path 38 by take-out rollers 36 and 36A attached to paper feed cassettes 35 and 35A, respectively, and sent to timing rollers 31 by paper feed roller 37.

[0037] The paper transported by the timing rollers 31 is transported to the nip portion where the intermediate transfer belt 30 and the secondary transfer belt 26 come into contact. The toner image formed on the intermediate transfer belt 30 is transferred to the paper by the action of the electric field force of the secondary transfer belt 26, which is a transfer member. The paper with the transferred toner image is transported to the fixing rollers 32, where it is heated and pressed. This melts the toner and fixes it to the paper. The paper is then transported to the paper output tray 39.

[0038] When forming a full-color image, the MFP 100 drives all of the image forming units 20Y, 20M, 20C, and 20K. When forming a monochrome image, the MFP 100 drives only one of the image forming units 20Y, 20M, 20C, and 20K. It is also possible to form an image by combining two or more of the image forming units 20Y, 20M, 20C, and 20K. Here, we will explain an example in which the MFP 100 employs a tandem system equipped with image forming units 20Y, 20M, 20C, and 20K that form four color toners on paper. However, the MFP 100 may also form images using a four-cycle system in which four color toners are transferred sequentially onto paper using a single photosensitive drum.

[0039] Fig. 4 is a block diagram showing an outline of the hardware configuration of an MFP according to the present embodiment. Referring to Fig. 4, MFP 100 includes a main circuit 110, a document reading unit 130, an automatic document feeder 120, an image forming unit 140, a paper feed unit 150, and an operation panel 160. Operation panel 160 is a user interface.

[0040] Main circuit 110 includes CPU 111, communication interface (I / F) unit 112, ROM 113, RAM 114, HDD 115, facsimile unit 116, and external storage device 117. HDD 115 is a large-capacity storage device. A solid-state drive (SSD) may be used instead of HDD 115. CPU 111 is connected to automatic document feeder 120, document reading unit 130, image forming unit 140, paper feed unit 150, and operation panel 160, and controls MFP 100 overall.

[0041] Facsimile unit 116 is connected to the public switched telephone network (PSTN) and transmits facsimile data to the PSTN. Facsimile unit 116 also receives facsimile data from the PSTN. Facsimile unit 116 stores the received facsimile data in HDD 115, converts it into print data that can be printed by image forming unit 140, and outputs it to image forming unit 140. As a result, image forming unit 140 forms an image on paper based on the facsimile data received by facsimile unit 116. Facsimile unit 116 also converts the data stored in HDD 115 into facsimile data and transmits it to a facsimile device connected to the PSTN.

[0042] The communication I / F unit 112 is an interface for connecting the MFP 100 to the network 3. The communication I / F unit 112 communicates with the PC 200 connected to the network 3 using a communication protocol such as TCP (Transmission Control Protocol) or FTP (File Transfer Protocol).

[0043] ROM 113 stores programs executed by CPU 111 or data required to execute the programs. RAM 114 is used as a work area when CPU 111 executes the programs. RAM 114 also temporarily stores scanned images continuously sent from document scanning unit 130.

[0044] Operation panel 160 is provided on the top surface of MFP 100. Operation panel 160 includes display unit 161 and operation unit 163. Display unit 161 is, for example, a liquid crystal display (LCD), and displays an instruction menu for the user, information related to acquired image data, etc. Note that instead of an LCD, for example, an organic EL display may be used as long as it is a device that displays images.

[0045] The operation unit 163 includes a touch panel 165 and a hard key unit 167. The touch panel 165 is of a capacitance type. Note that the touch panel 165 is not limited to a capacitance type, and other types such as a resistive film type, a surface acoustic wave type, an infrared type, or an electromagnetic induction type can be used. The hard key unit 167 includes a plurality of hard keys. The hard keys are, for example, contact switches.

[0046] CPU 111 executes a print job that communication I / F unit 112 receives from PC 300. The print job includes data to be printed and printing conditions. The data to be printed may be bitmap data or application data. The data to be printed includes data for one or more pages. CPU 111 generates image data (print data) from the data to be printed that is included in the print job in accordance with the printing conditions included in the print job, and outputs the image data to image forming unit 140.

[0047] External storage device 117 is controlled by CPU 111, and has CD-ROM 118 attached thereto. In this embodiment, an example will be described in which CPU 111 executes a program stored in ROM 113. Note that CPU 111 may control external storage device 117 to read a program to be executed by CPU 111 from CD-ROM 118, store the read program in RAM 114, and execute it.

[0048] Fig. 5 is a block diagram showing an example of functions possessed by each of the server and the third MFP in this embodiment. The functions shown in Fig. 5 are realized by CPU 201 provided in server 200 by causing CPU 201 to execute a setting assistance program stored in ROM 202, HDD 204, or CD-ROM 209A. Also, the functions are realized by CPU 111 provided in third MFP 100 by causing CPU 111 to execute a program stored in ROM 113, HDD 115, or CD-ROM 118. Also, the functions shown in Fig. 5 may be realized by hardware provided in each of server 200 and third MFP 100.

[0049] 5, CPU 201 included in server 200 has training data acquisition unit 251, model generation unit 253, feature amount receiving unit 255, prediction unit 257, setting control unit 259, additional data acquisition unit 261, and additional learning unit 263. CPU 111 included in third MFP 100 has second feature amount acquisition unit 51, setting unit 53, switching unit 55, display control unit 57, and additional data generation unit 59.

[0050] Training data acquisition unit 251 acquires training data from multiple first MFPs 100-1 to 100-N. Training data acquisition unit 251 outputs the acquired multiple pieces of training data to model generation unit 253. Here, an example will be described in which training data acquisition unit 251 acquires training data from first MFP 100-1. The training data includes first adjustment parameters set in first MFP 100-1 and first feature amounts indicating characteristics of first image data image-processed by first MFP 100-1 using the first adjustment parameters. The target of image processing is a basic image prepared in advance. The basic image is an image of a predetermined pattern shape formed in a predetermined color. The basic image includes multiple sets of images in which multiple colors and multiple pattern shapes are combined.

[0051] The first feature amount may be the first image data itself. The first feature amount may be a value obtained by performing predetermined statistical processing on the first image data. Each of the plurality of first MFPs 100-1 to 100-N processes a common basic image. Training data including the first feature amount and the first adjustment parameters set for each of the plurality of first MFPs 100-1 to 100-N is acquired.

[0052] The model generation unit 253 uses multiple sets of training data to train the learning model through machine learning. A neural network is used as the learning model. The model generation unit 253 generates a trained learning model by repeating an appropriate number of epochs in which the learning model trains multiple sets of training data through machine learning. The model generation unit 253 outputs the trained learning model to the prediction unit 257 and the additional training unit 263.

[0053] Feature amount receiving unit 255 receives the second feature amount from second MFP 300. The second feature amount is a second feature amount indicating a feature of the second image data subjected to image processing by second MFP 300. Note that when third MFP 100 acquires the second feature amount from second MFP 300, feature amount receiving unit 255 may acquire the second feature amount from third MFP 100.

[0054] The prediction unit 257 predicts the third adjustment parameter from the second feature amount using a trained learning model. The prediction unit 257 provides the second feature amount to the learning model and obtains the output of the learning model as the third adjustment parameter. The prediction unit 257 outputs the third parameter to the setting control unit 259.

[0055] Setting control unit 259 sets the third adjustment parameter input from prediction unit 257 in third MFP 100. For example, setting control unit 259 causes communication unit 205 to transmit a setting command including the third adjustment parameter to third MFP 100. Setting control unit 259 also causes communication unit 205 to transmit a sample image together with the setting command to third MFP 100. The sample image is a first feature included in training data that includes a first adjustment parameter that is identical to or similar to the third adjustment parameter predicted by prediction unit 257 among a plurality of training data. Here, a case will be described as an example in which a first feature included in training data acquired from first MFP 100-1 is transmitted as a sample image.

[0056] Second feature amount acquiring unit 51 included in CPU 111 included in third MFP 100 acquires second feature amounts. The acquired second feature amounts indicate characteristics of the second image data subjected to image processing by second MFP 300. The image subjected to image processing by second MFP 300 is a basic image prepared in advance. This basic image is the same as the basic image subjected to image processing by first MFPs 100-1 to 100-N. Second feature amount acquiring unit 51 transmits the second feature amounts to server 200.

[0057] The setting unit 53 controls the communication I / F unit 112 to receive a setting command from the server 200. The setting unit 53 stores the setting command in the HDD 115.

[0058] Display control unit 57 displays on display unit 161 an image of the third image data obtained by image processing the basic image by second MFP 300. The first feature amount received by setting unit 53 indicates the features of the first image data obtained by image processing the basic image by first MFP 100-1. Since third MFP 100 is the same type as first MFPs 100-1 to 100-N, if the adjustment parameters are the same or similar, the image data obtained by image processing the basic image will be the same or similar. Therefore, display control unit 57 displays on display unit 161 an image corresponding to the first feature amount received by setting unit 53 as an image of the third image data. By comparing the image of the third image data with the basic image, the user can determine whether or not to set the third adjustment parameters.

[0059] Switching unit 55 switches the process to be executed at startup between a process for setting the third adjustment parameter and a process for not setting the third adjustment parameter. Switching unit 55 switches to either process based on a flag stored in HDD 115. The flag is stored in HDD 115 according to an operation input by a user to operation unit 163. For example, the flag is stored in HDD 115 when the user compares an image of the third image data displayed on display unit 161 with a basic image to determine whether or not to set the third adjustment parameter. The flag may also be stored by the manufacturer of third MFP 100.

[0060] At startup, setting unit 53 refers to the flag stored in HDD 115, and if the flag indicates that the third adjustment parameter is to be set, executes the setting command stored in HDD 115. As a result, the third adjustment parameter is set as the value of the setting item corresponding to the image processing. At startup, setting unit 53 refers to the flag stored in HDD 115, and if the flag indicates that the third adjustment parameter is not to be set, does not execute the setting command stored in HDD 115.

[0061] After the third adjustment parameter is set, the value of the setting item corresponding to the image processing may be changed. When the value of the setting item corresponding to the image processing is changed from the third adjustment parameter, the setting unit 53 outputs the changed parameter to the additional data generation unit 59.

[0062] Additional data generation unit 59 generates additional data. The additional data includes change parameters set in third MFP 100 and third feature amounts indicating characteristics of image data processed by third MFP 100 using the change parameters. The image to be subjected to image processing is a basic image prepared in advance, and is the same as the basic image used when the training data is generated. The third feature amount may be the image data itself processed by third MFP 100 using the change parameters. The third feature amount may be a value obtained by performing predetermined statistical processing on the image data processed by third MFP 100 using the change parameters. Additional data generation unit 59 generates additional data including the change parameters and the third feature amount. Additional data generation unit 59 transmits the additional data to server 200.

[0063] Additional data acquisition section 261 included in CPU 201 included in server 200 receives the additional data from third MFP 100. Additional data acquisition section 261 outputs the additional data to additional learning section 263.

[0064] The additional learning unit 263 receives the trained learning model as input from the model generation unit 253 and the additional data as input from the additional data acquisition unit 261. The additional learning unit 263 performs additional learning on the learning model using the additional data. The additional learning unit 263 outputs the trained learning model to the prediction unit 257.

[0065] After the learning model is input from the additional learning unit 263, the prediction unit 257 uses the additionally trained learning model input from the additional learning unit 263 instead of the learning model input from the model generation unit 253.

[0066] Next, we will explain the learning models for each image processing. Image processing includes scanning, which optically reads an original and outputs image data, printing, which forms an image of the image data on a recording medium, and copying, which forms an image of the image data output by scanning on a recording medium.

[0067] <Learning model for scanning processing> Regarding the training data used by the model generation unit 253 to generate a learning model corresponding to scan processing, a case where the training data acquisition unit 251 acquires the training data from the first MFP 100-1 will be described as an example. The training data includes first adjustment parameters and first feature amounts. The first adjustment parameters include parameters for scan processing. The parameters for scan processing are values ​​set for setting items corresponding to the scan processing executed by the first MFP 100-1. Therefore, the first adjustment parameters do not include values ​​set for setting items used by the first MFP 100-1 to execute print processing other than scan processing. The first feature amounts are values ​​indicating the features of image data that the first MFP 100-1 reads and outputs a basic image using the first adjustment parameters. Here, the first feature amounts are assumed to be bitmap data obtained by converting image data to a predetermined resolution.

[0068] The model generation unit 253 performs machine learning on the learning model using the first feature amount of the training data as an explanatory variable and the first adjustment parameter as a target variable.

[0069] Second feature amount acquiring unit 51 included in CPU 111 provided in third MFP 100 acquires a second feature amount. The second feature amount is a value indicating a feature of image data that second MFP 300 reads and outputs a basic image. Second feature amount acquiring unit 51 acquires the second feature amount from second MFP 300 and transmits the second feature amount to server 200. The image that second MFP 300 targets for scan processing is a basic image that has been prepared in advance. This basic image is the same as the basic image that first MFPs 100-1 to 100-N target for image processing.

[0070] Prediction unit 257 predicts the third adjustment parameter from the second feature amount using a trained learning model. Prediction unit 257 provides the second feature amount to the learning model and acquires the output of the learning model as the third adjustment parameter. Here, the second feature amount is bitmap data obtained by converting image data to a predetermined resolution. The third adjustment parameter is a parameter for scan processing, and corresponds to a value set in a setting item corresponding to the scan processing executed by third MFP 100.

[0071] <Learning model for print processing> Regarding the training data used by the model generation unit 253 to generate a learning model corresponding to print processing, a case where the training data acquisition unit 251 acquires the training data from the first MFP 100-1 will be described as an example. The training data includes first adjustment parameters and first feature amounts. The first adjustment parameters include parameters for scan processing. The parameters for scan processing are values ​​set in setting items corresponding to the scan processing executed by the first MFP 100-1. The first feature amounts are values ​​indicating the features of image data that the first MFP 100-1 reads and outputs using the parameters for scan processing, after forming a basic image on a recording medium using the parameters for print processing. Here, the first feature amounts are assumed to be bitmap data obtained by converting the image data to a predetermined resolution.

[0072] The model generation unit 253 performs machine learning on the learning model using the first feature amount of the training data and the scan processing parameters among the first adjustment parameters as explanatory variables and the print processing parameters among the first adjustment parameters as objective variables.

[0073] Second feature amount acquisition unit 51 included in CPU 111 provided in third MFP 100 acquires a second feature amount. The second feature amount is a value indicating a feature of image data that is output by having second MFP 300 form a basic image on a recording medium and then having third MFP 100 read and output the image formed on the recording medium. Second feature amount acquisition unit 51 acquires the second feature amount based on image data obtained by second MFP 300 reading the recording medium on which the basic image has been formed. Second feature amount acquisition unit 51 transmits the second feature amount to server 200. The basic image formed by second MFP 300 is the same as the basic image that was the target of image processing by first MFPs 100-1 to 100-N.

[0074] The prediction unit 257 predicts the third adjustment parameter from the second feature amount using a trained learning model. The prediction unit 257 provides the learning model with the second feature amount and the scan processing parameters set in the third MFP 100, and acquires the output of the learning model as the third adjustment parameter. Before the prediction unit 257 predicts the third adjustment parameter, it is preferable that the scan processing parameters in the third MFP 100 are set to values ​​predicted by the learning model corresponding to the above scan processing. The second feature amount is a value indicating the characteristics of image data that is read and output by the third MFP 100 after the second MFP 300 forms a basic image on a recording medium. Here, the second feature amount is assumed to be bitmap data obtained by converting image data to a predetermined resolution. The third adjustment parameter is a print processing parameter and corresponds to a value set in a setting item corresponding to the print processing executed by the third MFP 100.

[0075] 6 is a flowchart showing an example of the flow of model generation processing. The model generation processing is performed by CPU 201 of server 200 by causing CPU 201 to execute a model generation program stored in ROM 202, HDD 204, or CD-ROM 209A. The model generation program is a part of the setting assistance program.

[0076] 6, CPU 201 included in server 200 acquires training data from first MFPs 100-1 to 100-N (step S01), and proceeds to step S02. First MFPs 100-1 to 100-N are of the same type as third MFP 100. The training data includes first features and first adjustment parameters. In step S02, a learning model is trained by machine learning, and the process proceeds to step S03. In step S03, the trained learning model is stored in HDD 204, and the process ends.

[0077] When the CPU 201 generates a learning model corresponding to the scan processing, the first adjustment parameters include parameters for the scan processing. When the CPU 201 generates a learning model corresponding to the scan processing, the CPU 201 performs machine learning on the learning model using the first feature amount of the training data as an explanatory variable and the parameters for the scan processing as an objective variable.

[0078] When the CPU 201 generates a learning model corresponding to print processing, the first adjustment parameters include parameters for scan processing and parameters for print processing. The CPU 201 performs machine learning on the learning model using the first feature amount of the training data and the parameters for scan processing as explanatory variables and the parameters for print processing as objective variables.

[0079] 7 is a flowchart showing an example of the flow of adjustment parameter determination processing. The adjustment parameter determination processing is executed by CPU 201 provided in server 200 by causing CPU 201 to execute an adjustment parameter determination program stored in ROM 202, HDD 204, or CD-ROM 209A. The adjustment parameter determination program is part of the setting assistance program.

[0080] 7, CPU 201 acquires the second feature amount from second MFP 300 (step S11), and proceeds to step S12. In step S12, CPU 201 predicts the third adjustment parameter from the second feature amount using the learning model, and proceeds to step S13. In step S13, CPU 201 sets the third adjustment parameter in third MFP 100, and ends the process.

[0081] When CPU 201 determines the third adjustment parameters corresponding to the scan processing, CPU 201 uses a trained learning model generated for the scan processing. In this case, the second feature amount is a value indicating the features of image data that second MFP 300 reads and outputs a basic image. In step S12, CPU 201 provides the second feature amount to the learning model and determines the adjustment parameters output by the learning model as the third adjustment parameters. The third adjustment parameters output by the learning model correspond to the scan processing parameters of third MFP 100.

[0082] When CPU 201 determines the third adjustment parameters corresponding to print processing, CPU 201 uses a trained learning model generated for print processing. In this case, the second feature amount is a value indicating the features of image data that third MFP 100 reads and outputs from an image formed by second MFP 300 of a reference image on a recording medium. In step S12, CPU 201 provides the second feature amount and the scan processing parameters set in third MFP 100 to the learning model, and determines the adjustment parameters output by the learning model as the third adjustment parameters. The third adjustment parameters output by the learning model correspond to the print processing parameters of third MFP 100.

[0083] 8 is a flowchart showing an example of the flow of the setting support process. The setting support process is performed by CPU 111 included in third MFP 100 by causing CPU 111 to execute a setting support program stored in ROM 113, HDD 115, or CD-ROM 118.

[0084] 8, CPU 111 included in third MFP 100 acquires second feature amounts (step S51) and proceeds to step S52. When adjustment parameters corresponding to scan processing are set, CPU 111 acquires image data that second MFP 300 reads and outputs a basic image. CPU 111 controls communication I / F unit 112 to communicate with second MFP 300 to acquire the image data. CPU 111 generates second feature amounts indicating characteristics of the image data acquired from second MFP 300. When adjustment parameters corresponding to print processing are set, CPU 111 acquires image data obtained by second MFP 300 reading an image formed by the basic image on a recording medium. The user causes second MFP 300 to form a basic image on a recording medium and then causes third MFP 100 to read the recording medium.

[0085] In the next step S52, CPU 111 requests server 200 to make a prediction. CPU 111 controls communication I / F unit 112 to send a prediction request command to server 200. When setting adjustment parameters corresponding to scan processing, the prediction request command includes the second feature amount. When setting adjustment parameters corresponding to print processing, the prediction request command includes the second feature amount and parameters for scan processing set in third MFP 100. The parameters for scan processing are values ​​set in setting items corresponding to scan processing.

[0086] In step S53, CPU 111 determines whether a setting command has been received. CPU 111 remains in a standby state until a setting command is received (NO in step S53), and if a setting command is received (YES in step S53), the process proceeds to step S54. The setting command includes a third adjustment parameter and a first feature amount. The third adjustment parameter includes a value to be set for a setting item corresponding to the scan process. The first feature amount is a value that is paired with a first adjustment parameter that is the same as or similar to the third adjustment parameter in the training data.

[0087] In step S54, CPU 111 branches the process depending on the flag. CPU 111 reads the flag stored in HDD 115 and selects a process. If the flag indicates the setting mode, CPU 111 proceeds to step S55, and if the flag indicates the non-setting mode, CPU 111 proceeds to step S59. The setting mode is an operating mode indicating that the third adjustment parameter is set to the setting item. The non-setting mode is an operating mode indicating that the third adjustment parameter is not set to the setting item.

[0088] In step S55, a sample image is displayed, and the process proceeds to step S56. A sample image is generated based on the first feature amount included in the setting command received from server 200 in step S53, and displayed on display unit 161. The sample image is generated from the first feature amount, of the training data, that is paired with a first adjustment parameter that is identical or similar to the third adjustment parameter. Therefore, when setting parameters corresponding to a scan process, the sample image is an image that is similar to image data obtained by reading a basic image when the third adjustment parameters are set in third MFP 100. Furthermore, when setting parameters corresponding to a print process, the sample image is an image that is similar to an image formed by forming a basic image on a recording medium when the third adjustment parameters are set in third MFP 100. Therefore, the user can determine whether or not to set the third adjustment parameter by, for example, comparing the sample image with the basic image.

[0089] In step S56, CPU 111 determines whether permission has been granted by the user. If operation unit 163 receives an instruction operation indicating permission, CPU 111 determines that permission has been granted by the user, and if operation unit 163 receives an instruction operation indicating denial of permission, CPU 111 determines that permission has not been granted by the user. If permission has been granted by the user, the process proceeds to step S57; otherwise, the process proceeds to step S58. In step S57, the third adjustment parameter is set, and the process ends.

[0090] In step S58, the third adjustment parameter is changed, and the process proceeds to step S61. The changed third adjustment parameter is set.

[0091] In step S59, a setting value is accepted, and the process proceeds to step S60. A setting value to be set for a setting item corresponding to image processing is accepted. In step S60, the accepted setting value is set for the setting item, and the process proceeds to step S61.

[0092] If the process proceeds to step S61, values ​​at least partially different from the third adjustment parameters are set for the setting items corresponding to the image processing. In step S61, additional data is generated, and the process proceeds to step S62. The additional data corresponding to the scan processing includes a third feature amount indicating the characteristics of image data output by reading the basic image with document reading unit 130, and parameters for the scan processing. The additional data corresponding to the print processing includes a third feature amount indicating the characteristics of image data output by reading the image formed by the basic image on a recording medium with document reading unit 130, parameters for the scan processing, and parameters for the print processing. In step S62, the additional data is sent to server 200, and the process ends.

[0093] 9 is a flowchart showing an example of the flow of the additional learning process. The additional learning process is executed by CPU 201 of server 200 by causing CPU 201 to execute an additional learning program stored in ROM 202, HDD 204, or CD-ROM 209A. The additional learning program is part of the setting assistance program.

[0094] 9, CPU 201 included in server 200 acquires additional data from third MFP 100 (step S21), and proceeds to step S22. The additional data includes third features and change parameters. In step S22, the learning model is additionally trained, and the process proceeds to step S23. In step S23, the additionally trained learning model is stored in HDD 204, and the process ends.

[0095] When CPU 201 additionally trains a learning model corresponding to scan processing, the change parameters include the scan processing parameters set in third MFP 100. When CPU 201 additionally trains a learning model corresponding to scan processing, CPU 201 additionally trains the learning model using the third feature amount of the additional data as an explanatory variable and the scan processing parameters as an objective variable. The fourth feature amount is a value indicating the features of image data that third MFP 100 reads and outputs by document reading unit 130 a basic image.

[0096] When the CPU 201 generates a learning model corresponding to the print process, the change parameters include the scan process parameters and the print process parameters. The CPU 201 performs additional learning on the learning model using the third feature amount of the additional data and the scan process parameters as explanatory variables and the print process parameters as objective variables.

[0097] <First Modification> Image processing system 1 in the above-described embodiment determines parameters for scan processing and parameters for print processing to be set in third MFP 100. In the first modified example, image processing system 1 determines parameters for scan processing and parameters for print processing to be set in third MFP 100 using a learning model corresponding to copy processing.

[0098] Regarding the training data used by the model generation unit 253 to generate a learning model corresponding to the copy process, a case where the training data acquisition unit 251 acquires the training data from the first MFP 100-1 will be described as an example. The training data includes first adjustment parameters and first feature amounts. The first adjustment parameters include parameters for scan processing and parameters for print processing. The parameters for scan processing are values ​​set for setting items corresponding to the scan processing executed by the first MFP 100-1. The parameters for print processing are values ​​set for setting items corresponding to the print processing executed by the first MFP 100-1. The first feature amounts are values ​​indicating the features of image data that the first MFP 100-1 reads and outputs using the parameters for scan processing, after forming a basic image on a recording medium using the parameters for print processing. Here, the first feature amounts are assumed to be bitmap data obtained by converting the image data to a predetermined resolution.

[0099] The model generation unit 253 performs machine learning on the learning model using the first feature amount of the training data as an explanatory variable and the scan processing parameter and the print processing parameter of the first adjustment parameter as an objective variable.

[0100] Second feature amount acquisition unit 51 included in CPU 111 provided in third MFP 100 acquires a second feature amount. The second feature amount is a value indicating a feature of image data that is output by having second MFP 300 form a basic image on a recording medium and then having third MFP 100 read and output the image formed on the recording medium. Second feature amount acquisition unit 51 acquires the second feature amount based on image data obtained by second MFP 300 reading the recording medium on which the basic image has been formed. Second feature amount acquisition unit 51 transmits the second feature amount to server 200. The basic image formed by second MFP 300 is the same as the basic image that was the target of image processing by first MFPs 100-1 to 100-N.

[0101] The prediction unit 257 predicts the third adjustment parameters from the second feature amounts using a trained learning model. The prediction unit 257 provides the second feature amounts to the learning model and acquires the output of the learning model as the third adjustment parameters. The second feature amounts are values ​​indicating the features of image data that are output by the third MFP 100 after the second MFP 300 has performed a copy process on a basic image and the image formed on a recording medium has been read. The copy process includes a scan process for reading the basic image and a print process for forming an image of the image data obtained by the scan process on a recording medium. Here, the second feature amounts are assumed to be bitmap data obtained by converting the image data to a predetermined resolution. The third adjustment parameters include parameters for the scan process and parameters for the print process. The parameters for the scan process included in the third adjustment parameters correspond to values ​​set in setting items corresponding to the scan process executed by the third MFP 100. The parameters for the print process included in the third adjustment parameters correspond to values ​​set in setting items corresponding to the print process executed by the third MFP 100.

[0102] <Second Modification> In image processing system 1 in the above-described embodiment, server 200 generates a learning model and predicts the third adjustment parameter using the learning model. In image processing system 1 in the second modified example, server 200 generates a learning model and second MFP 300 predicts the third adjustment parameter using the learning model. Below, differences from image processing system 1 described above will be mainly described.

[0103] Fig. 10 is a block diagram showing an example of functions possessed by each of a server and a third MFP in an image processing system according to a second modified example. Referring to Fig. 10, the functions possessed by CPU 201 included in server 200 according to the second modified example differ from the functions shown in Fig. 5 in that CPU 201 does not include feature amount receiving unit 255, prediction unit 257, and setting control unit 259, and that model transmission unit 265 is added. Furthermore, the functions possessed by CPU 111 included in third MFP 100 according to the second modified example differ from the functions shown in Fig. 5 in that model acquisition unit 61 and device-side prediction unit 63 are added, and display control unit 57 is changed to display control unit 57A. The other functions are the same as those shown in Fig. 5, and therefore description thereof will not be repeated here.

[0104] Referring to FIG. 10, model transmission unit 265 included in CPU 201 included in server 200 transmits the trained learning model generated by model generation unit 253 and the training data to third MFP 100.

[0105] Model acquisition unit 61 included in CPU 111 included in third MFP 100 acquires a learning model and training data. When communication I / F unit 112 receives the learning model and training data from server 200, model acquisition unit 61 acquires the learning model and training data. Model acquisition unit 61 outputs the learning model to device-side prediction unit 63 and outputs the training data to display control unit 57.

[0106] The device-side prediction unit 63 has the same function as the prediction unit 257. The device-side prediction unit 63 receives the second feature from the second feature acquisition unit 51. The device-side prediction unit 63 predicts the third adjustment parameter from the second feature using the learning model received from the model acquisition unit 61. The device-side prediction unit 63 provides the second feature to the learning model and acquires the output of the learning model as the third adjustment parameter. The device-side prediction unit 63 outputs the third parameter to the setting unit 53.

[0107] The display control unit 57A displays on the display unit 161 an image of the third image data obtained by image processing the basic image by the second MFP 300. The display control unit 57A receives the third adjustment parameters from the setting unit 53 and the training data from the model acquisition unit 61. The display control unit 57A extracts training data including first adjustment parameters identical or similar to the third adjustment parameters from the training data. The display control unit 57A generates a sample image based on a first feature amount included in the extracted training data. The first feature amount indicates a feature of the first image data obtained by image processing the basic image by the first MFP 100-1. Since the third MFP 100 is the same type as the first MFP 100-1, if the adjustment parameters are identical or similar, the image data obtained by image processing the basic image will be identical or similar. Therefore, the display control unit 57A displays the sample image as an image of the third image data on the display unit 161. The user can determine whether or not to set the third adjustment parameters by comparing the image of the third image data with the basic image.

[0108] Fig. 11 is a flowchart showing an example of the flow of the setting support process in the second modified example. The setting support process in the modified example differs from the setting support process shown in Fig. 8 in that step S71 is added before step S51. Another difference is that steps S72 and S73 are added after step S51. Another difference is that steps S52 and S53 are deleted. The other steps are the same as the setting support process shown in Fig. 8, so description thereof will not be repeated here.

[0109] In step S71, the learning model and training data are acquired, and the process proceeds to step S51. CPU 111 controls communication I / F unit 112 to acquire the learning model and training data from server 200.

[0110] In step S51, the second feature amount is acquired, and the process proceeds to step S72. When setting adjustment parameters corresponding to scan processing, CPU 111 acquires image data that second MFP 300 reads and outputs a basic image, and generates second feature amounts. When setting adjustment parameters corresponding to print processing, CPU 111 acquires image data that second MFP 300 obtains by reading an image formed by forming the basic image on a recording medium, and generates second feature amounts.

[0111] In step S72, CPU 111 predicts the third adjustment parameter from the second feature amount using the learning model acquired in step S71, and the process proceeds to step S73. In step S73, CPU 111 acquires a sample image, and the process proceeds to step S54. When step S55 is executed, the sample image generated in step S73 is displayed.

[0112] <Third Modification> In the above-described embodiment, the first MFPs 100-1 to 100-N, the second MFP 300, and the third MFP 100 are described as examples of image processing devices, but the image processing devices of the present invention are not limited to these. The image processing device may be a scanner device that can perform scanning processing but cannot perform image formation processing. Furthermore, although the image formation processing is described as an example of a method of forming an image using toner, a method of forming an image on a recording medium using ink may also be adopted.

[0113] <Summary of implementation form> (Item 1) A model acquisition unit acquires a trained learning model obtained by machine learning training data including first adjustment parameters that can be set in a first type of first image processing device and first feature amounts that indicate characteristics of first image data that has been image processed by the first image processing device using the first adjustment parameters; a feature amount acquiring unit that acquires a second feature amount indicating a feature of the second image data that has been image processed by a second image processing device of a second type; a prediction unit that predicts a third adjustment parameter from the second feature amount using the learning model.

[0114] According to this aspect, a model acquisition unit acquires a trained learning model that is machine-learned using a first adjustment parameter that can be set in a first image processing device of a first type as a response variable and a first feature amount that indicates a feature of first image data that has been image-processed by the first image processing device using the first adjustment parameter as an explanatory variable; a feature amount acquiring unit that acquires a second feature amount indicating a feature of the second image data that has been image processed by a second image processing device of a second type; and a prediction unit that predicts a third adjustment parameter to be set in the third image processing device of the first type from the second feature amount using the learning model.

[0115] According to this aspect, a trained learning model is acquired by machine learning training data including a first adjustment parameter settable in a first image processing device of a first type and a first feature amount indicating a feature of first image data image processed by the first image processing device using the first adjustment parameter. A third adjustment parameter to be set in a third image processing device of the first type is predicted using the learning model from a second feature amount indicating a feature of second image data image processed by a second image processing device of a second type. Therefore, a third adjustment parameter is determined for causing the third image processing device to perform image processing that results in an image of similar image quality to the image processed by the second image processing device. Therefore, it is possible to determine an adjustment parameter for causing one of different types of image processing devices to perform image processing similar to image processing performed by the other. As a result, an information processing device that facilitates the configuration of the image processing devices can be provided.

[0116] (Item 2) The information processing device according to item 1, further comprising a setting control unit that sets the third adjustment parameter in the third image processing device.

[0117] According to this aspect, the third adjustment parameter is set in the third image processing device, so that the third image processing device can be made to perform image processing similar to the image processing performed by the second image processing device.

[0118] (Item 3) an additional data acquisition unit that acquires additional data including a changed parameter obtained by changing the third adjustment parameter in the third image processing device and a third feature amount that indicates a feature of third image data that has been image-processed by the third image processing device using the changed parameter when the third adjustment parameter is changed after the third adjustment parameter is set in the third image processing device; Item 3. The information processing device according to item 2, further comprising an additional learning unit that additionally learns the additional data to the already-learned learning model.

[0119] According to this aspect, the already trained learning model is additionally trained using additional data including a changed parameter obtained by changing the third adjustment parameter and a third feature amount indicating a feature of the third image data image processed by the third image processing device using the changed parameter, thereby improving the prediction accuracy of the learning model.

[0120] (Item 4) A training data acquisition unit that collects the training data; 4. The information processing device according to any one of items 1 to 3, further comprising: a model generation unit that performs machine learning of the training data on the learning model.

[0121] According to this aspect, training data is collected and the learning model is trained by machine learning using the training data, so that the relationship between the adjustment parameters and the image quality in the first image processing device can be modeled.

[0122] (Item 5) The first image data is data obtained by the first image processing device performing the image processing on a predetermined pattern image, 5. The information processing device according to any one of items 1 to 4, wherein the second image data is data obtained by the second image processing device performing the image processing on the pattern image.

[0123] According to this aspect, the same pattern image is image-processed by the first image processing device and the second image processing device, and therefore, regardless of the adjustment parameters set in the second type of image processing device, it is possible to predict the third adjustment parameters for causing the first type of image processing device to perform the same image processing as the image processing performed by the second type of image processing device.

[0124] (Item 6) The information processing device according to any one of items 1 to 5, wherein the image processing includes a reading process executed by a document reading device that optically reads an image formed on a recording medium in accordance with the first adjustment parameters.

[0125] According to this aspect, the image processing includes a reading process executed in accordance with the first adjustment parameter, and therefore it is possible to predict a third adjustment parameter for causing the first type of image processing device to execute a reading process similar to the reading process executed by the second type of image processing device.

[0126] (Item 7) The information processing device according to any one of items 1 to 6, wherein the image processing includes image forming processing that is executed by an image processing device that forms an image on a recording medium based on image data, in accordance with a first adjustment parameter.

[0127] According to this aspect, the image processing includes image formation performed in accordance with the first adjustment parameter, and therefore it is possible to predict a third adjustment parameter for causing the first type of image processing device to perform an image formation process similar to the image formation process performed by the second type of image processing device.

[0128] (Item 8) An information processing device according to any one of items 1 to 7, and a setting unit that sets the third adjustment parameter.

[0129] According to this aspect, it is possible to provide an image processing device that facilitates the setting work.

[0130] (Item 9) The image processing device according to item 8, further comprising a switching unit that switches the processing to be executed at startup between processing for setting the third adjustment parameter and processing for not setting the third adjustment parameter at startup.

[0131] According to this aspect, a process is executed to either set the third adjustment parameter or not set the third adjustment parameter at startup, so that it is possible to set whether or not the third adjustment parameter is set automatically.

[0132] (Item 10) The image processing device according to item 8 or 9, further comprising a display control unit that displays an image of the third image data that has been subjected to the image processing using the third adjustment parameter.

[0133] According to this aspect, an image of the third image data that has been image-processed using the third adjustment parameter is displayed, allowing the user to check whether the third adjustment parameter has been set correctly.

[0134] (Item 11) A model acquisition step of acquiring a trained learning model by machine learning training data including a first adjustment parameter that can be set in a first image processing device of a first type and a first feature amount that indicates a feature of first image data that has been image processed by the first image processing device using the first adjustment parameter; a feature amount acquiring step of acquiring second feature amounts indicating features of the second image data processed by a second image processing device of a second type; A setting support method that causes an information processing device to execute a prediction step of predicting a third adjustment parameter to be set in the third image processing device of the first type from the second feature using the learning model.

[0135] According to this aspect, it is possible to provide a setting support method that makes it easy to set up an image processing device.

[0136] (Item 12) A model acquisition step of acquiring a trained learning model obtained by machine learning training data including first adjustment parameters that can be set in a first image processing device of a first type and first feature amounts that indicate features of first image data that has been image processed by the first image processing device using the first adjustment parameters; a feature amount acquiring step of acquiring second feature amounts indicating features of the second image data processed by a second image processing device of a second type; A setting support program that causes a computer to execute a prediction step of predicting a third adjustment parameter to be set in the third image processing device of the first type from the second feature using the learning model.

[0137] According to this aspect, it is possible to provide a setting support program that facilitates the setting work of an image processing device.

[0138] The embodiments disclosed herein should be considered to be illustrative in all respects and not restrictive. The scope of the present invention is defined by the claims, not by the above description, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0139] 1 image processing system, 100 third MFP, 100-1 to 100-N first MFP, 200 server, 300 second MFP, 3 network, 5 Internet, 51 second feature acquisition unit, 53 setting unit, 55 switching unit, 57, 57A display control unit, 59 additional data generation unit, 61 model acquisition unit, 63 device side prediction unit, 251 training data acquisition unit, 253 model generation unit, 255 feature reception unit, 257 prediction unit, 259 setting control unit, 261 additional data acquisition unit, 263 additional learning unit, 265 model transmission unit, 110 main circuit, 111 CPU, 112 communication I / F unit, 113 ROM, 114 RAM, 115 HDD, 116 facsimile unit, 117 external storage device, 118 CD-ROM, 120 automatic document feeder, 130 Document reading unit, 140 image forming unit, 150 paper feeding unit, 160 operation panel, 161 display unit, 163 operation unit, 201 CPU, 202 ROM, 203 RAM, 204 HDD, 205 communication unit, 206 display unit, 207 operation unit, 209 external storage device, 209A CD-ROM.

Claims

1. a model acquisition unit that acquires a trained learning model that is machine-learned using training data including first adjustment parameters that can be set in a first type of first image processing device and first feature amounts that indicate features of first image data that has been image-processed by the first image processing device using the first adjustment parameters; a feature amount acquiring unit that acquires a second feature amount indicating a feature of the second image data processed by a second image processing device of a second type; a prediction unit that predicts a third adjustment parameter to be set in the third image processing device of the first type from the second feature amount using the learning model.

2. The information processing apparatus according to claim 1 , further comprising a setting control unit that sets the third adjustment parameter in the third image processing apparatus.

3. an additional data acquisition unit that, when the third adjustment parameter is changed after the third adjustment parameter is set in the third image processing device, acquires additional data including a changed parameter obtained by changing the third adjustment parameter and a third feature amount that indicates a feature of the image data that has been image-processed by the third image processing device using the changed parameter; The information processing device according to claim 2 , further comprising an additional learning unit that additionally learns the additional data to the already-learned learning model.

4. a training data acquisition unit that collects the training data; The information processing device according to claim 1 , further comprising: a model generation unit that performs machine learning on the training data to the learning model.

5. the first image data is data obtained by the first image processing device performing the image processing on a predetermined pattern image, The information processing apparatus according to claim 1 , wherein the second image data is data obtained by the second image processing apparatus performing the image processing on the pattern image.

6. The information processing apparatus according to claim 1 , wherein the image processing includes a reading process executed by a document reading device that optically reads an image formed on a recording medium in accordance with the first adjustment parameters.

7. The information processing apparatus according to claim 1 , wherein the image processing includes image forming processing that is executed in accordance with the first adjustment parameters by an image processing apparatus that forms an image on a recording medium based on image data.

8. An information processing device according to any one of claims 1 to 5; a setting unit that sets the third adjustment parameter.

9. The image processing device according to claim 8 , further comprising a switching unit that switches, as a process to be executed at startup, between a process for setting the third adjustment parameter and a process for not setting the third adjustment parameter at startup.

10. The image processing device according to claim 8 , further comprising a display control unit that displays an image of the third image data that has been subjected to the image processing using the third adjustment parameter.

11. a model acquisition step of acquiring a trained learning model by machine learning training data including first adjustment parameters that can be set in a first type of first image processing device and first feature amounts that indicate features of first image data that has been image processed by the first image processing device using the first adjustment parameters; a feature amount acquiring step of acquiring a second feature amount indicating a feature of the second image data processed by a second image processing device of a second type; A setting support method that causes an information processing device to execute a prediction step of predicting a third adjustment parameter to be set in the third image processing device of the first type from the second feature using the learning model.

12. a model acquisition step of acquiring a trained learning model by machine learning training data including first adjustment parameters that can be set in a first type of first image processing device and first feature amounts that indicate features of first image data that has been image processed by the first image processing device using the first adjustment parameters; a feature amount acquiring step of acquiring a second feature amount indicating a feature of the second image data processed by a second image processing device of a second type; A setting support program that causes a computer to execute a prediction step of predicting a third adjustment parameter to be set in the third image processing device of the first type from the second feature using the learning model.

Images