Information processing apparatus, image processing apparatus, setting support method, and program product

Abstract

The invention relates to an information processing apparatus, an image processing apparatus, a setting assistance method, and a setting assistance computer program product. The server (200) is provided with: a model acquisition unit that acquires a learned learning model after machine learning of training data, the training data includes a first adjustment parameter that can be set for a first MFP (100-1 to 100-N) of a first type, and a first feature quantity that represents a feature of first image data obtained by image processing of the first MFP (100-1 to 100-N) using the first adjustment parameter; a feature amount acquisition unit that acquires a second feature amount indicating a feature of second image data obtained by image processing by a second MFP (300) of a second type; and a prediction unit that predicts a third adjustment parameter for setting a third image processing device of the first type on the basis of the second feature amount using the learning model.

Description

Technical Field

[0001] This invention relates to an information processing apparatus, an image processing apparatus, a setting assistance method, and a setting assistance computer program product, and particularly to an information processing apparatus that assists in setting up an image processing apparatus, the image processing apparatus, the setting assistance method executed by the information processing apparatus, and a setting assistance computer program product that causes a computer to execute the setting assistance method. Background Technology

[0002] Image processing devices, such as MFPs (Multi-Function Peripheral), have the function of processing images. The MFP performs image processing according to adjusted parameters. Here, we assume the case where an existing MFP is replaced with a new one. Preferably, the adjusted parameters for the new MFP are set so that the image quality of the image processed by the new MFP is the same as the image quality of the image processed by the existing MFP. However, there are cases where the adjusted parameters differ between the existing and new MFPs, and determining the adjusted parameters used to set the new MFP requires a certain level of skill.

[0003] Japanese Patent Application Publication No. 2020-61018 discloses an image forming system comprising multiple image forming apparatuses and multiple groups to which the image forming apparatuses belong. The system is characterized in that the image forming apparatuses within each group are interconnected via logical links. Each image forming apparatus comprises: a storage unit storing link information including a destination address and a link weight value defining the logical link, and image setting information representing quantitative setting values ​​related to image forming; a communication unit performing communication with other image forming apparatuses based on the link information; an image forming unit performing image forming based on the image setting information; and a setting management unit modifying the image setting information according to instructions from a user, multiplying the modified image setting information by the link weight value, and controlling the communication unit to send the multiplied image setting information to the destination address.

[0004] The image forming system described in Japanese Patent Application Publication No. 2020-61018 sets up shared image information for each of multiple groups. However, the user must specify the group to which the image forming apparatus belongs. Furthermore, the user must specify the link weight for each group. Therefore, the setup becomes cumbersome.

[0005] Patent Document 1: Japanese Patent Application Publication No. 2020-61018 Summary of the Invention

[0006] The present invention was made to solve the above-mentioned problems. One of the objectives of the present invention is to provide an information processing apparatus that makes the setting up of an image processing apparatus easier.

[0007] Another object of the present invention is to provide an image processing apparatus that simplifies setup procedures.

[0008] Another object of the present invention is to provide a setting assistance method that makes setting up an image processing device easier.

[0009] Another object of the present invention is to provide a setup assistance program that makes setting up an image processing device easier.

[0010] To achieve the above objectives, according to a certain technical solution of the present invention, an information processing apparatus includes: a model acquisition unit that acquires a learning model after machine learning of training data, the training data including a first adjustment parameter that can be set for a first image processing apparatus of a first type and a first feature quantity representing features of first image data obtained by the first image processing apparatus using the first adjustment parameter; a feature quantity acquisition unit that acquires a second feature quantity representing features of second image data obtained by the second image processing apparatus of a second type; and a prediction unit that uses the learning model to predict a third adjustment parameter based on the second feature quantity.

[0011] According to another technical solution of the present invention, the image processing apparatus includes: the information processing apparatus described above; and a setting unit for setting a third adjustment parameter.

[0012] According to another technical solution of the present invention, an auxiliary method is set to enable an information processing device to perform the following steps: a model acquisition step, acquiring a learning model after machine learning of training data, the training data including a first adjustment parameter that can be set for a first image processing device of a first type and a first feature quantity representing the features of a first image data obtained by the first image processing device using the first adjustment parameter; a feature quantity acquisition step, acquiring a second feature quantity representing the features of a second image data obtained by a second image processing device of a second type; and a prediction step, using the learning model to predict a third adjustment parameter based on the second feature quantity.

[0013] According to another technical solution of the present invention, an auxiliary computer program product is configured to enable a computer to perform the following steps: a model acquisition step, acquiring a learning model after machine learning of training data, wherein the training data includes a first adjustment parameter that can be set for a first image processing device of a first type and a first feature quantity representing the features of the first image data obtained by the first image processing device using the first adjustment parameter; a feature quantity acquisition step, acquiring a second feature quantity representing the features of the second image data obtained by the second image processing device of a second type; and a prediction step, using the learning model to predict a third adjustment parameter based on the second feature quantity. Attached Figure Description

[0014] Figure 1 This is a diagram illustrating an example of the overall outline of the image processing system according to the first embodiment of the present invention.

[0015] Figure 2 This is a block diagram illustrating an example of the hardware structure of the server in this embodiment.

[0016] Figure 3 This is a cross-sectional view schematically representing an example of the internal structure of an MFP.

[0017] Figure 4 This is a block diagram illustrating the general hardware structure of the MFP in this embodiment.

[0018] Figure 5 This is a block diagram illustrating an example of the functions of the server and the third MFP in this embodiment.

[0019] Figure 6 This is a flowchart illustrating an example of the model generation process.

[0020] Figure 7 This is a flowchart illustrating an example of how adjusting parameters determines the processing flow.

[0021] Figure 8 This is a flowchart illustrating an example of setting up auxiliary processing procedures.

[0022] Figure 9 This is a flowchart illustrating an example of an append-learning process.

[0023] Figure 10 This is a block diagram illustrating an example of the functions of the server and the third MFP in the image processing system of the second variation.

[0024] Figure 11 This is a flowchart illustrating an example of the process for setting up auxiliary processing in the second variation. Detailed Implementation

[0025] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the following description, the same reference numerals are used to denote the same parts. The names and functions of these parts are also the same. Therefore, detailed descriptions of these parts will not be repeated.

[0026] <First Implementation>

[0027] Figure 1 This is a diagram illustrating an example of the overall outline of the image processing system according to the first embodiment of the present invention. (Refer to...) Figure 1 The image processing system 1 includes a server 200, multiple first MFP100-1 to 100-N (N being a positive integer), a second MFP300, and a third MFP100. The multiple first MFP100-1 to 100-N and the third MFP100 are image processing devices of the same type. The second MFP300 is an image processing device of a different type from the first MFP100-1 to 100-N and the third MFP100. The type includes manufacturer, series, and model. Therefore, when the type is set to manufacturer, two image processing devices with different manufacturers are of different types. When the type is set to series, even if the manufacturers are the same, two image processing devices with different series are of different types. When the type is set to model, even if the manufacturers and series are the same, two image processing devices with different models are of different types.

[0028] Server 200 is an example of an information processing device. Server 200 is a general-purpose computer. The first MFP100-1 to 100-N are examples of a first image processing device. The second MFP300 is an example of a second image processing device. The third MFP100 is an example of a third image processing device.

[0029] The second MFP300 and the third MFP100 are connected to network 3. Network 3 is a local area network (LAN). Network 3 is not limited to a LAN; it can also be a WAN (Wide Area Network) or the Internet. Network 3 is connected to the Internet 5 via gateway (G / W) 7. Server 200 and multiple first MFP100-1 to 100-N are connected to the Internet 5.

[0030] The second MFP300 and the third MFP100 can communicate with each other via network 3. The server 200 can communicate with the first MFP100-1 to 100-N via the Internet 5. The server 200 can communicate with the second MFP300 and the third MFP100 via the Internet 5 and network 3.

[0031] In the image processing system 1 of this embodiment, the example of the user setting the third MFP100 is described. It is assumed that before setting the third MFP100, the first MFP100-1 to 100-N and the second MFP300 have been set.

[0032] Figure 2 This is a block diagram illustrating an example of the hardware structure of the server in this embodiment. (Refer to...) Figure 2 The server 200 includes a CPU 201, ROM 202, RAM 203, hard disk drive (HDD) 204, communication unit 205, display unit 206, operation unit 207, and external storage device 209 for controlling the server 200 as a whole.

[0033] ROM 202 stores the program executed by CPU 201. RAM 203 is used as the working area of ​​CPU 201. HDD 204 is a high-capacity storage device that non-volatilely stores data. A solid-state drive (SSD) can also be used instead of HDD 204. Communication unit 205 connects CPU 201 to network 3. Operation unit 207 accepts operations input by the user. Display unit 206 is not a limiting component, but it is a liquid crystal display device. Alternatively, an organic EL (electroluminescence) display can be used instead of a liquid crystal display device.

[0034] External storage device 209 is equipped with CD-ROM (Compact Disk Read Only Memory) 209A. In this embodiment, an example of CPU 201 executing a program stored in ROM 202 will be described. However, CPU 201 may also control external storage device 209 to read a program for CPU 201 to execute from CD-ROM 209A, store the read program in RAM 203, and execute it.

[0035] Furthermore, the recording medium for storing programs executed by the CPU 201 is not limited to the CD-ROM 209A; it can also be a floppy disk, magnetic tape, optical disc, semiconductor memory, or other media. Optical discs include MO (Magnetic Optical Disc), MD (Mini Disc), and DVD (Digital Versatile Disc). Semiconductor memory includes IC cards, optical cards, mask ROMs, and EPROMs (Electrically Erasable Programmable ROMs).

[0036] Furthermore, CPU 201 can also load programs stored in HDD 204 into RAM 203 and execute them. Programs stored in HDD 204 include programs downloaded by CPU 201 from a computer connected to the Internet, or programs written to HDD 204 by a computer connected to the Internet. The term "program" here includes not only programs that can be directly executed by CPU 201, but also source code, compressed programs, encrypted programs, etc.

[0037] The first MFP100-1 to 100-N, the second MFP300, and the third MFP100 all share the functionality of scanning, image forming, and data transmission / reception, and their basic hardware structures are identical. Therefore, the hardware structure of the third MFP100 will be described here as an example. Furthermore, the hardware structures of the first MFP100-1 to 100-N, the second MFP300, and the third MFP100 exhibit both similarities and differences.

[0038] Figure 3 This is a cross-sectional view schematically illustrating an example of the internal structure of an MFP. (See reference...) Figure 3 The third MFP100 includes an automatic original document transport device 120, an original document reading unit 130 for reading original documents, an image forming unit 140 for forming an image on paper based on image data, and a paper feeding unit 150 for supplying paper to the image forming unit 140.

[0039] The automatic document transport device 120 automatically transports multiple originals placed on the original document tray one by one to the designated original document reading position set on the document table glass of the original document reading unit 130. The automatic document transport device 120 then discharges the original document, after the image formed on the original document has been read by the original document reading unit 130, to the original document output tray.

[0040] The original document reading unit 130 exposes the image of the original document placed on the original document glass 11 by an exposure lamp 13 mounted on a slider 12 that moves below it. The reflected light from the original document is guided by mirror 14 and two mirrors 15, 15A to lens 16, and imaged by CCD (Charge Coupled Device) sensor 18.

[0041] The reflected light imaged by the CCD sensor 18 is converted into image data as an electrical signal within the CCD sensor 18. The image data is converted into cyan (C), magenta (M), yellow (Y), and black (K) printing data and output to the image forming unit 140.

[0042] 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. When all image forming units 20Y, 20M, 20C, and 20K are driven, a full-color image is formed. Printing data for yellow, magenta, cyan, and black is 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 process; therefore, the image forming unit 20Y used to form a yellow image will be described here.

[0043] The image forming unit 20Y includes an exposure device 21Y, a photosensitive drum 23Y, a charged roller 22Y, a developer 24Y, and a primary transfer roller 25Y. Around the photosensitive drum 23Y, the charged roller 22Y, the exposure device 21Y, the developer 24Y, the primary transfer roller 25Y, and the drum cleaning blade 27Y are arranged sequentially along the rotation direction of the photosensitive drum 23Y. Yellow printed text is input to the exposure device 21Y using data. The photosensitive drum 23Y serves as the image carrier. The charged roller 22Y uniformly charges the surface of the photosensitive drum 23Y. The primary transfer roller 25Y, under the action of an electric field, transfers the toner image formed on the photosensitive drum 23Y onto the intermediate transfer belt 30, which serves as the image carrier.

[0044] After being charged by the charged roller 22Y, the photosensitive drum 23Y is irradiated by a laser emitted by the exposure device 21Y. The exposure device 21Y exposes the image-corresponding area on the surface of the photosensitive drum 23Y. This forms an electrostatic latent image on the photosensitive drum 23Y. Next, the developer 24Y develops the electrostatic latent image formed on the photosensitive drum 23Y using charged toner. Specifically, toner is loaded onto the electrostatic latent image formed on the photosensitive drum 23Y by the action of an electric field, thereby forming a toner image on the photosensitive drum 23Y. The toner image formed on the photosensitive drum 23Y is transferred by the primary transfer roller 25Y to the intermediate transfer belt 30, which serves as the image carrier, under the action of an electric field. Any toner left on the photosensitive drum 23Y that is not transferred is removed from the photosensitive drum 23Y by the drum cleaning blade 27Y.

[0045] The intermediate transfer belt 30 is suspended without loosening by the drive roller 33 and the driven roller 34. When the drive roller 33 moves along... Figure 2 When the intermediate transfer belt 30 rotates counterclockwise, it rotates at a specified speed in the counterclockwise direction shown in the figure. Accompanying the rotation of the intermediate transfer belt 30, the driven roller 34 rotates counterclockwise.

[0046] Therefore, image forming units 20Y, 20M, 20C, and 20K sequentially transfer toner images onto the intermediate transfer belt 30. The timing of each image forming unit 20Y, 20M, 20C, and 20K transferring its toner image onto the intermediate transfer belt 30 is adjusted based on the detection of reference marks attached to the intermediate transfer belt 30. Thus, yellow, magenta, cyan, and black toner images are superimposed on the intermediate transfer belt 30.

[0047] Paper of different sizes is placed in paper feed cassettes 35 and 35A respectively. The paper stored in paper feed cassettes 35 and 35A is fed to the conveying path 38 by take-out rollers 36 and 36A respectively installed in paper feed cassettes 35 and 35A, and then sent to the timing roller 31 by paper feed roller 37.

[0048] The paper, conveyed by the timing roller 31, is fed to the nip section where the intermediate transfer belt 30 and the secondary transfer belt 26 meet. The toner image formed on the intermediate transfer belt 30 is transferred to the paper by the secondary transfer belt 26, which serves as a transfer component, under the action of an electric field. The paper with the toner image transferred is then conveyed to the fixing roller 32, where it is heated and pressurized. As a result, the toner melts and is fixed onto the paper. Afterward, the paper is conveyed to the output tray 39.

[0049] When forming a full-color image, the third MFP100 drives all image forming units 20Y, 20M, 20C, and 20K; however, when forming a monochrome image, it drives any one of the image forming units 20Y, 20M, 20C, and 20K. Alternatively, it can combine two or more of the image forming units 20Y, 20M, 20C, and 20K to form an image. Furthermore, an example of the third MFP100 using image forming units 20Y, 20M, 20C, and 20K connected in series to form toner images of four colors on paper will be described here. However, the third MFP100 can also form an image in a four-cycle manner, sequentially transferring the four toner images onto the paper using a single photosensitive drum.

[0050] Figure 4 This is a block diagram illustrating the general hardware structure of the MFP in this embodiment. (Refer to...) Figure 4 The MFP100 includes a main circuit 110, a document reader 130, an automatic document feeder 120, an image forming unit 140, a paper feeder 150, and an operation panel 160. The operation panel 160 is the user interface.

[0051] The main circuit 110 includes a CPU 111, a communication interface (I / F) unit 112, a ROM 113, a RAM 114, an HDD 115, a fax unit 116, and an external storage device 117. The HDD 115 is a high-capacity storage device. A solid-state drive (SSD) can also be used instead of the HDD 115. The CPU 111 is connected to the automatic document feeder 120, the document reader 130, the image forming unit 140, the paper feeder 150, and the operation panel 160, and controls the entire MFP 100.

[0052] Fax unit 116 is connected to the Public Switched Telephone Network (PSTN) and sends fax data to the PSTN. It also receives fax data from the PSTN. Fax unit 116 stores the received fax data in HDD 115 and converts it into printable data that can be printed by image forming unit 140, then outputs this printable data to image forming unit 140. Thus, image forming unit 140 forms an image on paper using the fax data received by fax unit 116. Additionally, fax unit 116 converts the data stored in HDD 115 into fax data and sends this fax data to a fax device connected to the PSTN.

[0053] The communication I / F unit 112 is an interface for connecting the MFP100 to the network 3. The communication I / F unit 112 communicates with the server 200 connected to the network 3 using communication protocols such as TCP (Transmission Control Protocol) or FTP (File Transfer Protocol).

[0054] ROM 113 stores the program executed by CPU 111, or the data required to execute the program. RAM 114 is used as the working area when CPU 111 executes the program. In addition, RAM 114 temporarily stores read images continuously sent from the original document reading unit 130.

[0055] An operation panel 160 is disposed on the upper surface of the MFP100. The operation panel 160 includes a display unit 161 and an operation unit 163. The display unit 161 is, for example, a liquid crystal display (LCD) device, which displays user-defined menus, information related to acquired image data, etc. Alternatively, an organic EL display may be used instead of an LCD device to display images.

[0056] The operation unit 163 includes a touch panel 165 and a hard key unit 167. The touch panel 165 is capacitive. However, the touch panel 165 is not limited to capacitive technology; for example, it can use resistive film, surface acoustic wave, infrared, electromagnetic induction, or other methods. The hard key unit 167 includes multiple hard keys. These hard keys are, for example, contact switches.

[0057] CPU 111 executes the print job received from PC 300 by communication I / F unit 112. The print job includes data to be printed and print conditions. The data to be printed can be either bitmap data or application data. The data to be printed includes data for each page or more. CPU 111 generates image data (printing data) based on the print conditions included in the print job and the data to be printed included in the print job, and outputs the image data to image forming unit 140.

[0058] External storage device 117 is controlled by CPU 111 and contains CD-ROM 118. In this embodiment, an example of CPU 111 executing a program stored in ROM 113 will be described. Alternatively, CPU 111 may control external storage device 117 to read a program for CPU 111 execution from CD-ROM 118, store the read program in RAM 114, and execute it.

[0059] Figure 5 This is a block diagram illustrating an example of the functions of the server and the third MFP in this embodiment. The CPU 201 of the server 200 executes a setup assistance program stored in ROM 202, HDD 204, or CD-ROM 209A, thereby enabling the CPU 201 to perform the setup. Figure 5 The functions shown are as follows. Furthermore, by having the CPU 111 of the third MFP100 execute the program stored in ROM 113, HDD 115, or CD-ROM 118, the CPU 111 achieves the following: Figure 5 The functions shown are as described. Alternatively, they can be achieved using the hardware inherent in both the server 200 and the third MFP100. Figure 5 The functions shown.

[0060] Reference Figure 5 The CPU 201 of the server 200 includes a training data acquisition unit 251, a model generation unit 253, a feature quantity receiving unit 255, a prediction unit 257, a setting control unit 259, an additional data acquisition unit 261, and an additional learning unit 263. The CPU 111 of the third MFP 100 includes a second feature quantity acquisition unit 51, a setting unit 53, a switching unit 55, a display control unit 57, and an additional data generation unit 59.

[0061] The training data acquisition unit 251 acquires training data from multiple first MFPs 100-1 to 100-N. The training data acquisition unit 251 outputs the acquired training data to the model generation unit 253. Here, the example of the training data acquisition unit 251 acquiring training data from the first MFP 100-1 will be described. The training data includes a first adjustment parameter set for the first MFP 100-1 and a first feature quantity representing the characteristics of the first image data obtained by image processing using the first adjustment parameter. The object of image processing is a pre-prepared basic image. The basic image is an image with a pre-determined pattern shape formed by pre-determined colors. The basic image includes multiple sets of images composed of multiple colors and multiple pattern shapes.

[0062] The first feature can also be the first image data itself. Alternatively, the first feature can be a value obtained by performing prescribed statistical processing on the first image data. Multiple first MFPs 100-1 to 100-N process a common basic image. Training data is acquired, including first adjustment parameters and first feature values ​​set for each of the multiple first MFPs 100-1 to 100-N.

[0063] The model generation unit 253 uses multiple training data to enable the learning model to perform machine learning. The learning model uses a neural network. The model generation unit 253 generates a fully learned learning model by repeating the process of enabling the learning model to learn from combinations of multiple training data an appropriate number of times. The model generation unit 253 outputs the fully learned learning model to the prediction unit 257 and the supplementary learning unit 263.

[0064] The feature receiving unit 255 receives a second feature from the second MFP 300. The second feature is a feature representing the characteristics of the second image data obtained by the second MFP 300 through image processing. Furthermore, if the third MFP 100 obtains the second feature from the second MFP 300, the feature receiving unit 255 may also obtain the second feature from the third MFP 100.

[0065] The prediction unit 257 uses the learned model to predict the third adjustment parameter based on the second feature value. The prediction unit 257 assigns the second feature value to the learned model and obtains the output of the learned model as the third adjustment parameter. The prediction unit 257 outputs the third adjustment parameter to the setting control unit 259.

[0066] The setting control unit 259 sets the third adjustment parameter input from the prediction unit 257 to the third MFP 100. For example, the setting control unit 259 causes the communication unit 205 to send a setting command including the third adjustment parameter to the third MFP 100. Additionally, the setting control unit 259 causes the communication unit 205 to send a sample image along with the setting command to the third MFP 100. The sample image is a first feature included in the training data from multiple training data sets, which includes a first adjustment parameter that is the same as or approximately the third adjustment parameter predicted by the prediction unit 257. Here, the example of sending a sample image is taken as the case where the first feature included in the training data obtained from the first MFP 100-1 is used as the example.

[0067] The CPU 111 of the third MFP 100 acquires a second feature value via a second feature value acquisition unit 51. The second feature value represents the characteristics of the second image data obtained by the second MFP 300 through image processing. The image that the second MFP 300 is designated as the object of image processing is a pre-prepared basic image. This basic image is identical to the basic images that the first MFPs 100-1 to 100-N are designated as the objects of image processing. The second feature value acquisition unit 51 sends the second feature value to the server 200.

[0068] The setting unit 53 controls the communication I / F unit 112 to receive setting commands from the server 200. The setting unit 53 stores the setting commands in the HDD 115.

[0069] The display control unit 57 displays the image of the third image data obtained by the second MFP 300 through image processing of the basic image on the display unit 161. The first feature value received by the setting unit 53 represents the characteristics of the first image data obtained by the first MFP 100-1 through image processing of the basic image. The types of the third MFP 100 are the same as those of the first MFP 100-1 to 100-N. Therefore, if the adjustment parameters are the same or similar, the image data obtained by image processing of the basic image will be the same or similar. Therefore, the display control unit 57 displays the image corresponding to the first feature value received by the setting unit 53 as the image of the third image data on the display unit 161. The user can determine whether the third adjustment parameter should be set by comparing the image of the third image data with the basic image.

[0070] The switching unit 55 switches between two processes: setting the third adjustment parameter and not setting the third adjustment parameter, as the process executed at startup. The switching unit 55 switches to either process based on a flag stored in the HDD 115. The flag is stored in the HDD 115 according to the user's input to the operation unit 163. For example, when the user compares the image of the third image data formed on the display unit 161 with the basic image to determine whether to set the third adjustment parameter, the flag is stored in the HDD 115. Alternatively, the flag may also be stored by the manufacturer of the third MFP 100.

[0071] Upon startup, the setting unit 53 refers to a flag stored in the HDD 115, and if the flag indicates that a third adjustment parameter is to be set, it executes a setting command stored in the HDD 115. Thus, the third adjustment parameter is set to a value corresponding to a setting item for image processing. Upon startup, the setting unit 53 refers to a flag stored in the HDD 115, and if the flag indicates that the third adjustment parameter is not to be set, it does not execute a setting command stored in the HDD 115.

[0072] After the third adjustment parameter is set, there may be a situation where the value of the setting item corresponding to image processing is changed. When the value of the setting item corresponding to image processing is changed from the third adjustment parameter, the setting unit 53 outputs the changed parameter to the additional data generation unit 59.

[0073] The supplementary data generation unit 59 generates supplementary data. The supplementary data includes modified parameters set for the third MFP 100 and a third feature quantity representing the characteristics of the image data obtained by image processing using the modified parameters on the third MFP 100. The image to be processed is a pre-prepared base image, the same as the base image used when generating training data. The third feature quantity can also be the image data obtained by image processing using the modified parameters on the third MFP 100 itself. Alternatively, the third feature quantity can be a value obtained by performing prescribed statistical processing on the image data obtained by image processing using the modified parameters on the third MFP 100. The supplementary data generation unit 59 generates supplementary data including the modified parameters and the third feature quantity. The supplementary data generation unit 59 sends the supplementary data to the server 200.

[0074] The CPU 201 of the server 200 has an additional data acquisition unit 261 that receives additional data from the third MFP 100. The additional data acquisition unit 261 outputs the additional data to the additional learning unit 263.

[0075] The supplementary learning unit 263 receives the learned model from the model generation unit 253 and receives supplementary data from the supplementary data acquisition unit 261. The supplementary learning unit 263 uses the supplementary data to perform supplementary learning on the learned model. The supplementary learning unit 263 outputs the learned model after supplementary learning to the prediction unit 257.

[0076] After receiving the learning model from the additional learning unit 263, the prediction unit 257 uses the learning model that has been additionally learned from the additional learning unit 263 instead of the learning model received from the model generation unit 253.

[0077] Next, the learning models for each image processing step will be explained. Image processing includes scanning processing, which optically reads the original and outputs image data; printing processing, which forms an image of the image data on a recording medium; and photocopying processing, which forms an image of the image data output from the scanning processing on a recording medium.

[0078] <Learning model corresponding to scanning processing>

[0079] The following description will take the case where the model generation unit 253 generates training data for a learning model corresponding to the scanning process, and the training data acquisition unit 251 acquires training data from the first MFP 100-1 as an example. The training data includes a first adjustment parameter and a first feature quantity. The first adjustment parameter includes scanning processing parameters. These scanning processing parameters are values ​​set for settings corresponding to the scanning process performed on the first MFP 100-1. Therefore, the first adjustment parameter does not include values ​​set for settings used for printing processes other than scanning processes performed on the first MFP 100-1. The first feature quantity is a value representing a characteristic of the image data that the first MFP 100-1 reads from the base image and outputs using the first adjustment parameter. Here, the first feature quantity is set to bitmap data after converting the image data to a predetermined resolution.

[0080] The model generation unit 253 uses the first feature of the training data as the explanatory variable and the first adjustment parameter as the target variable to enable the learning model to perform machine learning.

[0081] The CPU 111 of the third MFP 100 acquires a second feature value via a second feature acquisition unit 51. The second feature value is a value representing a characteristic of the image data read and output by the second MFP 300 from the base image. The second feature acquisition unit 51 acquires the second feature value from the second MFP 300 and sends it to the server 200. The image that the second MFP 300 is set to scan is a pre-prepared base image. This base image is the same as the base image that the first MFPs 100-1 to 100-N are set to image process.

[0082] The prediction unit 257 uses the learned model to predict the third adjustment parameter based on the second feature value. The prediction unit 257 assigns the second feature value to the learned model and obtains the output of the learned model as the third adjustment parameter. Here, the second feature value is set to convert the image data into bitmap data at a predetermined resolution. The third adjustment parameter is a parameter for the scanning process, corresponding to the value set for the setting item corresponding to the scanning process performed on the third MFP100.

[0083] <Learning Model Corresponding to Printing Process>

[0084] The following description will take the case where the model generation unit 253 generates training data for a learning model corresponding to printing processing, and the training data acquisition unit 251 acquires training data from the first MFP 100-1 as an example. The training data includes a first adjustment parameter and a first feature quantity. The first adjustment parameter includes scanning processing parameters. The scanning processing parameters are values ​​set for settings corresponding to the scanning processing performed on the first MFP 100-1. The first feature quantity represents the value of a characteristic of the image data read and output by the first MFP 100-1 using the scanning processing parameters, after the basic image is formed on the recording medium using the printing processing parameters. Here, the first feature quantity is set to bitmap data converted to a predetermined resolution.

[0085] The model generation unit 253 uses the first feature quantity of the training data and the scanning processing parameter in the first adjustment parameter as explanatory variables, and the printing processing parameter in the first adjustment parameter as the target variable, to enable the learning model to perform machine learning.

[0086] The CPU 111 of the third MFP 100 acquires a second feature value via a second feature value acquisition unit 51. The second feature value represents the value of a feature of image data that causes the second MFP 300 to form a basic image on a recording medium, and which is then read and output by the third MFP 100 from the image formed on the recording medium. The second feature value acquisition unit 51 acquires the second feature value based on image data obtained by reading the recording medium from which the second MFP 300 forms the basic image. The second feature value acquisition unit 51 sends the second feature value to the server 200. The basic image formed by the second MFP 300 is the same as the basic image that the first MFPs 100-1 to 100-N are designated as objects for image processing.

[0087] The prediction unit 257 uses the learned model to predict the third adjustment parameter based on the second feature value. The prediction unit 257 assigns the second feature value and the scanning processing parameters set for the third MFP100 to the learned model, and obtains the output of the learned model as the third adjustment parameter. Preferably, before the prediction unit 257 predicts the third adjustment parameter, the third MFP100 is set with the value obtained by predicting the scanning processing parameters using the learning model corresponding to the aforementioned scanning processing. The second feature value represents the value of the image data that causes the second MFP300 to form a basic image on the recording medium, and the third MFP100 to read and output the image formed on the recording medium. Here, the second feature value is set to bitmap data after converting the image data to a predetermined resolution. The third adjustment parameter is a printing processing parameter, corresponding to the value set for the setting item corresponding to the printing processing performed by the third MFP100.

[0088] Figure 6 This is a flowchart illustrating an example of the model generation process. The model generation process is performed by the CPU 201 of the server 200, which executes a model generation program stored in ROM 202, HDD 204, or CD-ROM 209A. The model generation program is part of the setup auxiliary program.

[0089] Reference Figure 6 The CPU 201 of server 200 acquires training data from the first MFP100-1 to 100-N (step S01), and the processing proceeds to step S02. The types of the first MFP100-1 to 100-N are the same as those of the third MFP100. The training data includes a first feature and a first adjustment parameter. In step S02, the learning model performs machine learning, and the processing proceeds to step S03. In step S03, the learned model is stored in HDD 204, and the processing ends.

[0090] When the CPU201 generates a learning model corresponding to the scan processing, the first adjustment parameter includes the parameters used for the scan processing. When generating a learning model corresponding to the scan processing, the CPU201 uses the first feature of the training data as the explanatory variable and the parameters used for the scan processing as the target variable to enable the learning model to perform machine learning.

[0091] When the CPU201 generates a learning model corresponding to the printing process, the first adjustment parameters include parameters for scanning and parameters for printing. The CPU201 uses the first feature of the training data and the parameters for scanning as explanatory variables, and the parameters for printing as the target variable, to enable the learning model to perform machine learning.

[0092] Figure 7This is a flowchart illustrating an example of the parameter adjustment decision process. The parameter adjustment decision process is performed by the CPU 201 of the server 200, which executes an adjustment parameter decision program stored in ROM 202, HDD 204, or CD-ROM 209A. The adjustment parameter decision program is part of the setting auxiliary program.

[0093] Reference Figure 7 CPU 201 obtains the second feature value from the second MFP 300 (step S11), causing the processing to proceed to step S12. In step S12, CPU 201 uses the learning model to predict the third adjustment parameter based on the second feature value, causing the processing to proceed to step S13. In step S13, CPU 201 sets the third adjustment parameter for the third MFP 100, and the processing ends.

[0094] When CPU 201 determines the third adjustment parameter corresponding to the scanning process, CPU 201 uses the learned model generated for the scanning process. In this case, the second feature value represents the value of the feature of the image data read and output by the second MFP 300 from the basic image. In step S12, CPU 201 assigns the second feature value to the learning model and determines the adjustment parameter output by the learning model as the third adjustment parameter. The third adjustment parameter output by the learning model is equivalent to the scanning processing parameter of the third MFP 100.

[0095] When CPU 201 determines the third adjustment parameter corresponding to the printing process, CPU 201 uses the learned model generated for the printing process. In this case, the second feature value represents the value of the image data output by the third MFP 100 after the second MFP 300 has formed the reference image on the recording medium. In step S12, CPU 201 assigns the second feature value and the scanning processing parameters set for the third MFP 100 to the learning model, and determines the adjustment parameter output by the learning model as the third adjustment parameter. The third adjustment parameter output by the learning model is equivalent to the printing processing parameters of the third MFP 100.

[0096] Figure 8 This is a flowchart illustrating an example of the setup assistance process. The setup assistance process is performed by the CPU 111 of the third MFP100 executing the setup assistance program stored in ROM 113, HDD 115, or CD-ROM 118.

[0097] Reference Figure 8The CPU 111 of the third MFP 100 acquires the second feature value (step S51), and the process proceeds to step S52. When adjustment parameters corresponding to the scanning process are set, the CPU 111 acquires image data output by the second MFP 300 reading the basic image. The CPU 111 acquires image data by communicating with the second MFP 300 via the control communication I / F unit 112. The CPU 111 generates a second feature value representing the characteristics of the image data acquired from the second MFP 300. When adjustment parameters corresponding to the printing process are set, the CPU 111 acquires image data obtained by reading the image after the second MFP 300 forms the basic image on the recording medium. After the user causes the second MFP 300 to form the basic image on the recording medium, the third MFP 100 reads the basic image formed on that recording medium.

[0098] In the next step S52, the CPU 111 requests prediction from the server 200. The CPU 111 controls the communication I / F unit 112 to send a prediction request instruction to the server 200. When adjustment parameters corresponding to the scanning process are set, the prediction request instruction includes a second feature value. When adjustment parameters corresponding to the printing process are set, the prediction request instruction includes the second feature value and scanning processing parameters set for the third MFP 100. The scanning processing parameters are values ​​set for settings corresponding to the scanning process.

[0099] In step S53, CPU 111 determines whether a setting instruction has been received. CPU 111 remains in standby mode until a setting instruction is received ("No" in step S53). If a setting instruction is received ("Yes" in step S53), the process proceeds to step S54. The setting instruction includes a third adjustment parameter and a first feature value. The third adjustment parameter includes a value set for the setting item corresponding to the scanning process. The first feature value is a value in the training data that is grouped with the first adjustment parameter, which is the same as or similar to the third adjustment parameter.

[0100] In step S54, CPU 111 branches the processing based on a flag. CPU 111 reads the flag stored in HDD 115 and selects a processing step. If the flag indicates a setting mode, CPU 111 proceeds to step S55; if the flag indicates a non-setting mode, CPU 111 proceeds to step S59. The setting mode indicates an operation mode that sets a third adjustment parameter for a setting item. The non-setting mode indicates an operation mode that does not set a third adjustment parameter for a setting item.

[0101] 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 value included in the setting instruction received from the server 200 in step S53, and the sample image is displayed on the display unit 161. The sample image is generated based on the first feature value grouped with the same or similar first adjustment parameter in the training data. Therefore, when the parameters corresponding to the scanning process are set, the sample image is an image that closely resembles the image data obtained by reading the base image when the third adjustment parameter is set on the third MFP100. Furthermore, when the parameters corresponding to the printing process are set, the sample image is an image that closely resembles the image formed on the recording medium when the third adjustment parameter is set on the third MFP100. Therefore, the user can compare the sample image with the base image to determine whether the third adjustment parameter should be set.

[0102] In step S56, CPU 111 determines whether the user has granted permission. If the operation unit 163 receives an instruction indicating permission, it is determined that the user has granted permission; if the operation unit 163 receives an instruction indicating disallowment, it is determined that the user has not granted permission. If the user has granted permission, 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.

[0103] In step S58, the third adjustment parameter is changed, and the process proceeds to step S61. The changed third adjustment parameter is set.

[0104] In step S59, the setting value is accepted, and the process proceeds to step S60. The setting value for the 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.

[0105] If the process proceeds to step S61, values ​​are set for the settings corresponding to image processing that are at least partially different from the third adjustment parameter. In step S61, additional data is generated, and the process proceeds to step S62. The additional data corresponding to scanning processing includes a third feature quantity representing the characteristics of image data that is read from the basic image by the document reading unit 130 and output, and scanning processing parameters. The additional data corresponding to printing processing includes a third feature quantity representing the characteristics of image data that is read from the image formed on the recording medium by the document reading unit 130 and output, and scanning processing parameters and printing processing parameters. In step S62, the additional data is sent to the server 200, and the process ends.

[0106] Figure 9This is a flowchart illustrating an example of the append-learning process. The append-learning process is performed by the CPU 201 of the server 200, which executes an append-learning program stored in ROM 202, HDD 204, or CD-ROM 209A. The append-learning program is part of the setup auxiliary program.

[0107] Reference Figure 9 The CPU 201 of server 200 obtains additional data from the third MFP 100 (step S21), causing the processing to proceed to step S22. The additional data includes the third feature quantity and the modified parameters. In step S22, the learning model performs additional learning, and the processing proceeds to step S23. In step S23, the learning model after the additional learning is completed is stored in HDD 204, and the processing ends.

[0108] When the CPU 201 performs additional learning on the learning model corresponding to the scanning process, the changed parameters include the scanning processing parameters set for the third MFP 100. When the CPU 201 performs additional learning on the learning model corresponding to the scanning process, it uses the third feature of the additional data as the explanatory variable and the scanning processing parameters as the target variable to perform additional learning on the learning model. The fourth feature is a value representing the characteristics of the image data that the third MFP 100 reads from the basic image and outputs through the original document reading unit 130.

[0109] When the CPU201 generates a learning model corresponding to the printing process, the changed parameters include the scanning processing parameters and the printing processing parameters. The CPU201 uses the third feature of the appended data and the scanning processing parameters as explanatory variables, and the printing processing parameters as the target variable, to enable the learning model to perform append learning.

[0110] <First Variation>

[0111] In the above embodiments, the image processing system 1 determines the scanning processing parameters and the printing processing parameters for setting the third MFP 100. In a first variation, the image processing system 1 uses a learning model corresponding to the copying process to determine the scanning processing parameters and the printing processing parameters for setting the third MFP 100.

[0112] The following explanation will focus on the case where the model generation unit 253 generates training data for a learning model corresponding to the copying process, and the training data acquisition unit 251 acquires training data from the first MFP 100-1. The training data includes a first adjustment parameter and a first feature quantity. The first adjustment parameter includes scanning processing parameters and printing processing parameters. The scanning processing parameters are values ​​set for settings corresponding to the scanning process performed by the first MFP 100-1. The printing processing parameters are values ​​set for settings corresponding to the printing process performed by the first MFP 100-1. The first feature quantity represents the value of a characteristic of the image data read and output by the first MFP 100-1 using the scanning processing parameters after the basic image is formed on the recording medium using the printing processing parameters. Here, the first feature quantity is set to bitmap data converted to a predetermined resolution.

[0113] The model generation unit 253 uses the first feature of the training data as the explanatory variable and the scanning processing parameter and printing processing parameter of the first adjustment parameter as the target variable, and enables the learning model to perform machine learning.

[0114] The CPU 111 of the third MFP 100 acquires a second feature value via a second feature value acquisition unit 51. The second feature value represents the value of a feature of image data generated by the second MFP 300 forming a basic image on a recording medium, and then read and output by the third MFP 100 from the image formed on the recording medium. The second feature value acquisition unit 51 acquires the second feature value based on image data obtained by reading an image of the basic image formed by the second MFP 300 on the recording medium. The second feature value acquisition unit 51 sends the second feature value to the server 200. The basic image formed by the second MFP 300 is the same as the basic image that the first MFPs 100-1 to 100-N are designated as objects for image processing.

[0115] The prediction unit 257 uses the learned model to predict the third adjustment parameter based on the second feature value. The prediction unit 257 assigns the second feature value to the learned model and obtains the output of the learned model as the third adjustment parameter. The second feature value represents the value of the image data that causes the second MFP 300 to perform copying processing on the basic image, and the third MFP 100 to read the image formed on the recording medium and output it. The copying processing includes scanning processing to read the basic image and printing processing to form the image data obtained through the scanning processing on the recording medium. Here, the second feature value is set to convert the image data into bitmap data at a predetermined resolution. The third adjustment parameter includes scanning processing parameters and printing processing parameters. The scanning processing parameters included in the third adjustment parameter correspond to the values ​​set for the settings corresponding to the scanning processing performed by the third MFP 100. The printing processing parameters included in the third adjustment parameter correspond to the values ​​set for the settings corresponding to the printing processing performed by the third MFP 100.

[0116] <Second Variation>

[0117] In the image processing system 1 described in the above embodiment, the server 200 generates a learning model and uses the learning model to predict the third adjustment parameter. In the image processing system 1 of the second variation, the server 200 generates a learning model, and the second MFP 300 uses the learning model to predict the third adjustment parameter. Hereinafter, the differences from the image processing system 1 described above will be the main focus of the explanation.

[0118] Figure 10 This is a block diagram illustrating an example of the functions of the server and the third MFP in the image processing system of the second variation. (See reference...) Figure 10 The functions of the CPU 201 in the server 200 in the second variation are the same as those in the second variation. Figure 5 The difference in functionality shown is that CPU 201 lacks the feature quantity receiving unit 255, prediction unit 257, and setting control unit 259, and adds a model transmitting unit 265. Furthermore, the CPU 111 in the third MFP 100 of the second variant has the same functionality as... Figure 5 The difference in functionality shown is the addition of a model acquisition unit 61 and a device-side prediction unit 63, and the change of the display control unit 57 to a display control unit 57A. Other functions are the same. Figure 5 The functions shown are the same, so they will not be explained again here.

[0119] Reference Figure 10 The model sending unit 265 of the CPU 201 of the server 200 sends the learned learning model and training data generated by the model generation unit 253 to the third MFP 100.

[0120] The model acquisition unit 61 of the CPU 111 in the third MFP100 acquires the learning model and training data. When the communication I / F unit 112 receives the learning model and training data from the server 200, the model acquisition unit 61 acquires the learning model and training data. The model acquisition unit 61 outputs the learning model to the device-side prediction unit 63 and outputs the training data to the display control unit 57A.

[0121] The device-side prediction unit 63 has the same function as the prediction unit 257. The device-side prediction unit 63 receives a second feature quantity from the second feature quantity acquisition unit 51. Using the learning model input from the model acquisition unit 61, the device-side prediction unit 63 predicts a third adjustment parameter based on the second feature quantity. The device-side prediction unit 63 assigns the second feature quantity 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 adjustment parameter to the setting unit 53.

[0122] The display control unit 57A displays the image of the third image data obtained by the second MFP 300 through image processing of the base image on the display unit 161. The display control unit 57A inputs a third adjustment parameter from the setting unit 53 and training data from the model acquisition unit 61. The display control unit 57A extracts training data from the training data that includes a first adjustment parameter that is the same as or similar to the third adjustment parameter. The display control unit 57A generates a sample image based on a first feature quantity included in the extracted training data. The first feature quantity represents the characteristics of the first image data obtained by the first MFP 100-1 through image processing of the base image. The third MFP 100 is of the same type as the first MFP 100-1; therefore, if the adjustment parameters are the same or similar, the image data obtained by image processing of the base image is the same or similar. Therefore, the display control unit 57A displays the sample image as the image of the third image data on the display unit 161. The user can determine whether the third adjustment parameter should be set by comparing the image of the third image data with the base image.

[0123] Figure 11 This is a flowchart illustrating an example of the setup auxiliary processing in the second variation. The setup auxiliary processing in the variation is... Figure 8 One difference in the setup auxiliary process shown is the addition of step S71 before step S51. Another difference is the addition of steps S72 and S73 after step S51. Yet another difference is the deletion of steps S52 and S53. Other processes are the same as... Figure 8 The auxiliary processing settings shown are the same, so they will not be repeated here.

[0124] In step S71, the learning model and training data are acquired, and the process proceeds to step S51. The CPU 111 controls the communication I / F unit 112 to acquire the learning model and training data from the server 200.

[0125] In step S51, the second feature value is acquired, and the process proceeds to step S72. With adjustment parameters corresponding to the scanning process set, CPU 111 acquires image data output by the second MFP300 reading the basic image and generates the second feature value. With adjustment parameters corresponding to the printing process set, CPU 111 acquires image data obtained by reading the image after the second MFP300 forms the basic image on the recording medium and generates the second feature value.

[0126] In step S72, CPU 111 uses the learning model obtained in step S71 to predict the third adjustment parameter based on the second feature value, causing the processing to proceed to step S73. In step S73, CPU 111 acquires a sample image, causing the processing to proceed to step S54. If step S55 is executed, the sample image generated in step S73 is displayed.

[0127] <Third Variation>

[0128] In the above embodiments, the first MFP100-1 to 100-N, the second MFP300, and the third MFP100 were described as examples of image processing apparatuses, but the image processing apparatus in this invention is not limited to these. The image processing apparatus may also be a scanner apparatus capable of performing scanning processing but not image forming processing. Furthermore, the image forming process was illustrated using toner to form an image, but it may also be used to form an image on a recording medium using ink.

[0129] <Overview of Implementation Methods>

[0130] (Item 1) An information processing apparatus, comprising:

[0131] The model acquisition unit acquires a learning model that has been learned after machine learning is performed on the training data. The training data includes a first adjustment parameter that can be set for the first image processing device of the first type and a first feature quantity that represents the features of the first image data obtained by the first image processing device using the first adjustment parameter for image processing.

[0132] The feature acquisition unit acquires a second feature quantity representing the features of the second image data obtained by the second image processing apparatus of the second type performing the aforementioned image processing; and

[0133] The prediction unit uses the learning model described above to predict the third adjustment parameter based on the second feature quantity.

[0134] According to this technical solution, it is an information processing device, comprising:

[0135] The model acquisition unit acquires a learning model that has been learned by machine learning, with a first adjustment parameter that can be set for the first type of first image processing device as the target variable and a first feature quantity that represents the features of the first image data obtained by the first image processing device using the first adjustment parameter as the explanatory variable.

[0136] The feature acquisition unit acquires a second feature quantity representing the features of the second image data obtained by the second image processing apparatus of the second type performing the aforementioned image processing; and

[0137] The prediction unit uses the learning model described above to predict the third adjustment parameter set for the third image processing device of the first type based on the second feature quantity described above.

[0138] According to this technical solution, a learning model is obtained after machine learning is performed on training data. The training data includes first adjustment parameters that can be set for a first image processing device of a first type, and a first feature quantity representing the features of first image data obtained by the first image processing device using the first adjustment parameters. Based on the second feature quantity representing the features of second image data obtained by a second image processing device of a second type, the learning model predicts a third adjustment parameter for setting a third image processing device of the first type. Therefore, a third adjustment parameter is determined for causing the third image processing device to perform image processing that produces an image with the same image quality as the image obtained by the second image processing device. Therefore, it is possible to determine adjustment parameters for causing the same image processing performed by one of the image processing devices of a different type to be performed by the other. As a result, an information processing apparatus that simplifies the setting of image processing devices can be provided.

[0139] (Item 2) The information processing apparatus according to Item 1, wherein,

[0140] It also includes a setting control unit, which sets the third adjustment parameter for the third image processing device.

[0141] According to this technical solution, a third adjustment parameter is set for the third image processing device. Therefore, the third image processing device can perform the same image processing as that performed by the second image processing device.

[0142] (Item 3) The information processing apparatus according to item 2, further comprising:

[0143] The additional data acquisition unit acquires additional data when the third adjustment parameter is changed after it has been set in the third image processing apparatus. The additional data includes a changed parameter resulting from the change in the third adjustment parameter and a third feature quantity representing the characteristics of the third image data obtained by the third image processing apparatus using the changed parameter for image processing.

[0144] An additional learning unit is added, enabling the learned model to learn further from the additional data.

[0145] According to this technical solution, the learned model undergoes further learning using supplementary data, including modified parameters obtained by changing the third adjustment parameters and supplementary data representing the features of the third image data obtained by the third image processing device using the modified parameters for image processing. Therefore, the prediction accuracy of the learned model can be improved.

[0146] (Item 4) The information processing apparatus according to any one of items 1 to 3, further comprising:

[0147] The training data acquisition department collects the aforementioned training data; and

[0148] The model generation unit enables the learning model to perform machine learning on the training data.

[0149] According to this technical solution, by collecting training data and using the training data to enable the learning model to perform machine learning, the relationship between the adjustment parameters and image quality in the first image processing device can be modeled.

[0150] (Item 5) The information processing apparatus according to any one of items 1 to 4, wherein,

[0151] The aforementioned first image data is obtained by performing the aforementioned image processing on a predetermined pattern image using the aforementioned first image processing device.

[0152] The second image data is obtained by performing the image processing on the pattern image using the second image processing device.

[0153] According to this technical solution, the same pattern image is processed in both the first image processing apparatus and the second image processing apparatus. Therefore, it is possible to predict a third adjustment parameter for causing the first image processing apparatus to perform the same image processing as that performed by the second image processing apparatus, regardless of the adjustment parameters set for the second type of image processing apparatus.

[0154] (Item 6) The information processing apparatus according to any one of items 1 to 5, wherein,

[0155] The image processing described above includes reading processing performed by an original document reading device that optically reads an image formed on a recording medium, according to the first adjustment parameter described above.

[0156] According to this technical solution, image processing includes readout processing performed according to a first adjustment parameter. Therefore, a third adjustment parameter can be predicted to cause the first type of image processing device to perform the same readout processing as that performed by the second type of image processing device.

[0157] (Item 7) The information processing apparatus according to any one of items 1 to 6, wherein,

[0158] The image processing described above includes image forming processing performed by an image processing apparatus that forms an image on a recording medium based on image data, according to a first adjustment parameter.

[0159] According to this technical solution, image processing includes image formation performed according to a first adjustment parameter. Therefore, a third adjustment parameter can be predicted to enable the first type of image processing device to perform the same image formation process as that performed by the second type of image processing device.

[0160] (Item 8) An image processing apparatus, comprising:

[0161] The information processing device described in any one of items 1 to 7; and

[0162] The setting unit sets the aforementioned third adjustment parameter.

[0163] According to this technical solution, an image processing device can be provided that makes the setup process easier.

[0164] (Item 9) The image processing apparatus according to Item 8, wherein,

[0165] It also includes a switching unit that switches to either the process of setting the third adjustment parameter or the process of not setting the third adjustment parameter at startup, as the process to be executed at startup.

[0166] According to this technical solution, at startup, either setting the third adjustment parameter or not setting the third adjustment parameter can be performed. Therefore, it is possible to set whether the third adjustment parameter is set automatically.

[0167] (Item 10) The image processing apparatus according to item 8 or 9, wherein,

[0168] It also includes a display control unit that displays an image of the third image data obtained by performing the image processing using the third adjustment parameters.

[0169] According to this technical solution, an image of third image data obtained by image processing using third adjustment parameters is displayed. The user can confirm whether the third adjustment parameters have been set correctly.

[0170] (Item 11) A setting assistance method that causes an information processing device to perform the following steps:

[0171] The model acquisition step involves acquiring a learning model that has been learned after machine learning on the training data. The training data includes a first adjustment parameter that can be set for the first image processing device of the first type and a first feature quantity that represents the features of the first image data obtained by the first image processing device using the first adjustment parameter for image processing.

[0172] The feature acquisition step involves acquiring a second feature quantity representing the features of the second image data obtained by the second image processing apparatus of the second type after performing the aforementioned image processing; and

[0173] The prediction step uses the learning model described above to predict the third adjustment parameter set for the third image processing device of the first type based on the second feature quantity described above.

[0174] According to this technical solution, a setting assistance method can be provided to make setting up an image processing device easier.

[0175] (Item 12) A setup assistance program that causes a computer to perform the following steps:

[0176] The model acquisition step involves acquiring a learning model that has been learned after machine learning on the training data. The training data includes a first adjustment parameter that can be set for the first image processing device of the first type and a first feature quantity that represents the features of the first image data obtained by the first image processing device using the first adjustment parameter for image processing.

[0177] The feature acquisition step involves acquiring a second feature quantity representing the features of the second image data obtained by the second image processing apparatus of the second type after performing the aforementioned image processing; and

[0178] The prediction step uses the learning model described above to predict the third adjustment parameter set for the third image processing device of the first type based on the second feature quantity described above.

[0179] According to this technical solution, a setup assistance program can be provided to make setting up the image processing device easier.

[0180] It should be considered that the embodiments disclosed herein are illustrative and not restrictive in all respects. The scope of the invention is not shown by the foregoing description, but by the claims, including all modifications within the meaning and scope of the claims.

Claims

1. An information processing device, wherein, have: The model acquisition unit acquires a learning model after machine learning is performed on the training data. The training data includes a first adjustment parameter that can be set for the first image processing device of the first type and a first feature quantity that represents the features of the first image data obtained by the first image processing device using the first adjustment parameter to perform image processing. The feature acquisition unit acquires a second feature quantity representing the features of the second image data obtained by the second image processing apparatus of the second type performing the image processing; and The prediction unit uses the learning model to predict a third adjustment parameter for setting the third image processing device for the first type based on the second feature quantity.

2. The information processing apparatus according to claim 1, wherein, It also includes a setting control unit, which sets the third adjustment parameter for the third image processing device.

3. The information processing apparatus according to claim 2, wherein, It also has: The additional data acquisition unit acquires additional data when the third adjustment parameter is changed after it has been set in the third image processing apparatus. The additional data includes a changed parameter obtained by changing the third adjustment parameter and a third feature quantity representing the characteristics of the image data obtained by the third image processing apparatus using the changed parameter to perform image processing. as well as An additional learning unit is added, enabling the learned model to perform additional learning on the additional data after it has completed its initial learning.

4. The information processing apparatus according to claim 1, wherein, It also has: The training data acquisition unit collects the training data; and The model generation unit enables the learning model to perform machine learning on the training data.

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

6. The information processing apparatus according to claim 1, wherein, The image processing includes reading processing performed by an original document reading device that optically reads an image formed on a recording medium, based on the first adjustment parameter.

7. The information processing apparatus according to claim 1, wherein, The image processing includes image forming processing performed by an image processing apparatus that forms an image on a recording medium based on image data, according to the first adjustment parameter.

8. An image processing apparatus, wherein, have: The information processing apparatus according to any one of claims 1 to 5; and The setting unit sets the third adjustment parameter.

9. The image processing apparatus according to claim 8, wherein, It also includes a switching unit that switches to either the process of setting the third adjustment parameter or the process of not setting the third adjustment parameter at startup, as the process to be executed at startup.

10. The image processing apparatus according to claim 8, wherein, It also includes a display control unit that displays an image of the third image data obtained by performing the image processing using the third adjustment parameter.

11. A method for setting up assistance, wherein, The information processing device performs the following steps: The model acquisition step involves acquiring a learning model that has been learned after machine learning on the training data. The training data includes a first adjustment parameter that can be set for a first image processing device of a first type and a first feature quantity that represents the features of the first image data obtained by the first image processing device using the first adjustment parameter to perform image processing. The feature acquisition step involves acquiring a second feature quantity that represents the features of the second image data obtained by the second image processing device of the second type performing the image processing. as well as The prediction step involves using the learning model to predict a third adjustment parameter for setting the third image processing device for the first type based on the second feature quantity.

12. A setting-aided computer program product, wherein, Have the computer perform the following steps: The model acquisition step involves acquiring a learning model that has been learned after machine learning on the training data. The training data includes a first adjustment parameter that can be set for a first image processing device of a first type and a first feature quantity that represents the features of the first image data obtained by the first image processing device using the first adjustment parameter to perform image processing. The feature acquisition step involves acquiring a second feature quantity that represents the features of the second image data obtained by the second image processing device of the second type performing the image processing. as well as The prediction step involves using the learning model to predict a third adjustment parameter for setting the third image processing device for the first type based on the second feature quantity.

Images