Image forming apparatus, image forming method, and program

Abstract

To provide an image forming apparatus, an image forming method, and a program that can reduce downtime and prevent the occurrence of image quality difference.SOLUTION: An image forming apparatus comprises: a receiving unit that receives print data; a collection unit that collects apparatus information that is information on the image forming apparatus; an estimation unit that estimates a cluster to which the apparatus information of the image forming apparatus collected by the collection unit is classified, by using a learning model that is for clustering the apparatus information and that is generated through machine learning using learning data including apparatus information of another image forming apparatus; a generation unit that generates an image processing parameter using correction information for correcting density corresponding to the cluster estimated by the estimation unit; and a print control unit that causes the image forming unit to print the print data by using the image processing parameter generated by the generation unit.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to an image forming apparatus, an image forming method, and a program. [Background technology]

[0002] Conventionally, even when printing the same image, image forming devices have had differences in image quality depending on the printing conditions, timing of printing, etc. The reason for the differences in image quality is that various factors, such as the printing environment (temperature, humidity, air pressure, etc.), the type of paper used for printing, the operating time or durability of the image forming device, etc., intertwine to change the color tone.

[0003] To eliminate such image quality differences, a known method is to measure gradation correction patches printed on recording paper and feed the correction values ​​back to the image generation unit to perform gradation correction and suppress the image quality differences. However, even if the image quality differences are corrected using this method, image quality differences will reoccur by the time of the next adjustment. Furthermore, strict control of image quality differences would increase the number of gradation corrections and increase downtime, so it was necessary to tolerate a certain degree of image quality differences.

[0004] Also, a technology related to gradation correction is known in which, using a learning model trained using density information measured from an adjustment chart in any n number of gradation correction processes, information about the image forming device (such as machine environment information or user usage information), and density information measured from the adjustment chart in a gradation correction process (the n-1th time) performed before the gradation correction process, density estimation is performed based on information about the image forming device when a job is executed, and the density correction table created in the gradation correction process is adjusted based on the estimated result.

[0005] However, this technology has two problems. First, to generate a learning model, adjustment charts must be printed and measured n times. This does not necessarily eliminate downtime for image forming devices. Second, performing the above process n times to generate a learning model for a single image forming device may result in insufficient or inappropriate training data. If outliers are included when performing the process n times to generate a learning model, the training data corresponding to those outliers will also be used. Furthermore, if training data is created at an unbalanced time, it may be inappropriate as training data. For example, if training data is created during a hot and humid season, gradation adjustment may not be performed correctly in the cold and humid winter.

[0006] Furthermore, as a conventional technique, an image formation technique has been disclosed that utilizes data conversion information according to the installation environment of the image forming device in order to realize image formation according to the installation environment of the image forming device (for example, Patent Document 1). Summary of the Invention [Problem to be solved by the invention]

[0007] However, the technology described in Patent Document 1 has a problem in that it is not possible to form images suited to the installation environment of the image forming device. In other words, since the server stores data conversion information suited to environmental conditions, appropriate processing cannot be performed in an environment that is not included in the stored information.

[0008] The present invention has been made in view of the above, and has an object to provide an image forming apparatus, an image forming method, and a program that can reduce downtime and suppress the occurrence of image quality differences. [Means for solving the problem]

[0009] In order to solve the above-mentioned problems and achieve the object, the present invention provides an image forming apparatus comprising: a receiving unit that receives print data; a collecting unit that collects device information, which is information about the image forming apparatus; an estimating unit that estimates a cluster into which the device information of the image forming apparatus collected by the collecting unit is classified, using a learning model for clustering device information generated by machine learning using learning data including device information of other image forming apparatuses; a creating unit that creates image processing parameters using correction information for correcting density corresponding to the cluster estimated by the estimating unit; and a print control unit that causes the image forming unit to print the print data using the image processing parameters created by the creating unit. [Effects of the Invention]

[0010] According to the present invention, downtime can be reduced and the occurrence of image quality differences can be suppressed. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram showing an example of the overall configuration of an image forming system according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of the image forming apparatus according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a hardware configuration of a machine learning server or the like according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of the configuration of functional blocks of the image forming system according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating a gamma correction table. [Figure 6] FIG. 6 is a flowchart illustrating an example of the flow of the machine learning process of the machine learning server according to the embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of the flow of operations of the image forming apparatus according to the embodiment. [Figure 8]FIG. 8 is a flowchart showing an example of the flow of the printing operation of the image forming apparatus according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of an image forming apparatus, an image forming method, and a program according to the present invention will be described in detail with reference to the drawings. Furthermore, the present invention is not limited to the following embodiments, and the components in the following embodiments include those that would be easily conceived by a person skilled in the art, those that are substantially the same, and those that are within the scope of what is called equivalents. Furthermore, various omissions, substitutions, modifications, and combinations of the components can be made without departing from the spirit of the following embodiments.

[0013] (Overall configuration of image forming system) 1 is a diagram showing an example of the overall configuration of an image forming system according to an embodiment of the present invention, and the overall configuration of the image forming system 1 according to the present embodiment will be described with reference to FIG.

[0014] The image forming system 1 shown in Fig. 1 is a system for forming an image by adjusting image quality using machine learning. As shown in Fig. 1, the image forming system 1 includes an image forming apparatus 10, a machine learning server 20, a data server 30, and a user terminal 40. These are capable of mutual data communication via a network N such as a LAN (Local Area Network) or the Internet. Note that the network N may include a wired network or a wireless network.

[0015] The image forming device 10 is a device that performs a printing operation using image processing parameters created using a learning model learned by machine learning in the machine learning server 20. The image forming device 10 is, for example, an MFP (Multifunction Peripheral). Here, an MFP is an image forming device that has at least two of the following functions: a copy function, a printer function, a scanner function, and a fax function.

[0016] The machine learning server 20 is a server that generates learning data based on information from each image forming apparatus including the image forming apparatus 10, performs learning processing by machine learning using the learning data, and generates a learning model.

[0017] The data server 30 is a server that collects information to be used in the learning process in the machine learning server 20 from each image forming apparatus, including the image forming apparatus 10, and provides the information to the machine learning server 20.

[0018] The user terminal 40 is an information terminal that transmits, for example, print data to be printed to the image forming apparatus 10 via the network N.

[0019] (Hardware configuration of image forming device) 2 is a diagram showing an example of the hardware configuration of the image forming apparatus 10 according to the embodiment, and the hardware configuration of the image forming apparatus 10 according to the embodiment will be described with reference to FIG.

[0020] 2, the image forming apparatus 10 includes a CPU (Central Processing Unit) 501, a ROM (Read Only Memory) 502, a RAM (Random Access Memory) 503, a GPU (Graphics Processing Unit) 504, an HDD (Hard Disk Drive) 505, a network I / F 506, an image forming unit 507, a reading unit 508, and sensors 509. These are connected to each other so as to be able to communicate with each other via a bus 510 such as an address bus and a data bus.

[0021] The CPU 501 is a computing device that controls the entire image forming apparatus 10 by reading programs and data from a storage device such as the ROM 502 or the HDD 505 onto the RAM 503 and executing the programs.

[0022] The ROM 502 is a non-volatile storage device that can retain programs and data even when the power is turned off. The ROM 502 stores programs and data such as a basic input / output system (BIOS) that is executed when the image forming apparatus 10 is started up.

[0023] The RAM 503 is a volatile storage device that temporarily stores programs and data.

[0024] The GPU 504 is a computing device that performs efficient calculations by processing data in parallel.

[0025] The HDD 505 is a non-volatile storage device that stores programs and data. The programs stored in the HDD 505 include an OS that controls the entire image forming apparatus 10, and application software that provides various functions by running on the OS. Note that the image forming apparatus 10 may be equipped with an SSD (Solid State Drive) instead of the HDD 504.

[0026] The network I / F 506 is an interface for communicating data with the machine learning server 20, the user terminal 40, etc. via the network N. The network I / F 506 is, for example, a NIC (Network Interface Card) that supports Ethernet (registered trademark) and is capable of wired or wireless communication in accordance with TCP (Transmission Control Protocol) / IP (Internet Protocol), etc.

[0027] The image forming unit 507 is a mechanism for forming an image based on print data received from the user terminal 40 via the I / F 506 .

[0028] The reading unit 508 is a mechanism for reading an image formed on a recording sheet and generating read image data.

[0029] The sensors 509 are sensors that detect, for example, the temperature and humidity of the place where the image forming apparatus 10 is installed.

[0030] The hardware configuration of the image forming apparatus 10 shown in FIG. 2 is an example, and it is not necessary to include all of the components shown in FIG. 2, or other components may be included.

[0031] (Hardware configuration of machine learning servers, etc.) 3 is a diagram showing an example of the hardware configuration of a machine learning server and the like according to the embodiment. The hardware configurations of the machine learning server 20, data server 30, and user terminal 40 according to the embodiment will be described with reference to FIG. 3. Note that the machine learning server 20 will be used as an example.

[0032] As shown in Figure 3, the machine learning server 20 includes a CPU 701, a ROM 702, a RAM 703, an auxiliary storage device 705, a media drive 707, a display 708, a network I / F 709, a keyboard 711, a mouse 712, and a DVD (Digital Versatile Disc) drive 714.

[0033] The CPU 701 is a computing device that controls the overall operation of the machine learning server 20. The ROM 702 is a non-volatile storage device that stores programs for the machine learning server 20. The RAM 703 is a volatile storage device that is used as a work area for the CPU 701.

[0034] The auxiliary storage device 705 is a storage device such as an HDD or SSD that stores various data, programs, and the like.

[0035] The media drive 707 is a device that controls reading and writing of data from and to a recording medium 706 such as a flash memory under the control of the CPU 701 .

[0036] The display 708 is a display device configured with a liquid crystal or organic EL (Electro-Luminescence) display, etc., that displays various information such as a cursor, a menu, a window, characters, or an image.

[0037] The network I / F 709 is an interface for communicating data with external devices such as the image forming apparatus 10 and the data server 30 via a network. The network I / F 709 is, for example, a NIC (Network Interface Card) that is compatible with Ethernet and capable of wired or wireless communication compliant with TCP / IP or the like.

[0038] The keyboard 711 is an input device for selecting letters, numbers, and various instructions, moving the cursor, etc. The mouse 712 is an input device for selecting and executing various instructions, selecting a processing target, moving the cursor, etc.

[0039] The DVD drive 714 is a device that controls reading and writing of data from and to a DVD 713 such as a DVD-ROM or a DVD-R (Digital Versatile Disk Recordable) as an example of a removable storage medium.

[0040] The above-mentioned CPU 701, ROM 702, RAM 703, auxiliary storage device 705, media drive 707, display 708, network I / F 709, keyboard 711, mouse 712 and DVD drive 714 are communicatively connected to each other via a bus 710 such as an address bus and a data bus.

[0041] The hardware configuration of the machine learning server 20 shown in Figure 3 is an example, and does not necessarily include all of the components shown in Figure 3, or may include other components. For example, the machine learning server 20 may include a GPU. Furthermore, the machine learning server 20 is not limited to being configured as a single information processing device as shown in Figure 3, but may be configured as multiple information processing devices.

[0042] The data server 30 and the user terminal 40 also conform to the hardware configuration shown in FIG.

[0043] (Configuration and operation of functional blocks in image forming systems) Fig. 4 is a diagram showing an example of the configuration of functional blocks of an image forming system according to an embodiment. Fig. 5 is a diagram illustrating a gamma correction table. The configuration and operation of the functional blocks of the image forming system 1 according to this embodiment will be described with reference to Figs. 4 and 5.

[0044] As shown in FIG. 4, the image forming device 10 has an apparatus information collection unit 101 (collection unit), an estimation processing unit 102 (estimation unit), an image processing adjustment unit 103 (creation unit), a job control unit 104 (an example of a receiving unit, a print control unit), and a memory unit 105.

[0045] The device information collection unit 101 is a functional unit that collects information about the image forming device 10 (hereinafter, sometimes referred to as device information).

[0046] Here, the device information includes status information and environmental information of the image forming device 10. The status information is information about the status of the image forming device 10, and includes at least one of the total number of pages printed by the image forming unit 507 of the image forming device 10, the color ratio, the average printing rate, and the average number of pages printed continuously. The environmental information is information about the environment of the image forming device 10, and includes at least one of the temperature, humidity, moisture content, and paper type of the location where the image forming device 10 used by the user is installed. The device information collecting unit 101 collects the temperature and humidity detected by the sensors 509. The device information collecting unit 101 collects the paper type from information set in advance by the user.

[0047] Furthermore, when machine learning is performed by the machine learning server 20, the device information collection unit 101 transmits the collected device information to the data server 30 via the network I / F 506.

[0048] The estimation processing unit 102 is a functional unit that uses a learning model stored in the storage unit 105 to estimate a cluster into which the device information of the image forming device 10 collected by the device information collecting unit 101 is classified. As described above, the environmental information included in the device information includes information on paper type. Generally, the image quality of a printed matter is affected not only by the printing environment but also by the paper type used for printing. The estimation process using the learning model by the estimation processing unit 102 takes into account the paper type of the image forming device 10, which can contribute to improving image quality.

[0049] The image processing adjustment unit 103 is a functional unit that creates image processing parameters from a gamma correction table (an example of correction information) for correcting density that corresponds to the cluster of device information estimated by the estimation processing unit 102. For example, in the example shown in Fig. 5 described below, if the estimation processing unit 102 estimates that the device information of the image forming device 10 corresponds to the cluster of point B, the image processing adjustment unit 103 creates image processing parameters from the gamma correction table that corresponds to the image forming device at point B.

[0050] For example, the image forming apparatus 10 may receive in advance from the machine learning server 20 a gamma correction table for each cluster classified by machine learning (clustering) performed by the machine learning server 20, as will be described later, and store the gamma correction table in the storage unit 105. Alternatively, the image processing adjustment unit 103 may notify the machine learning server 20 of the cluster of the device information estimated by the estimation processing unit 102, and receive from the machine learning server 20 a gamma correction table corresponding to the cluster.

[0051] The job control unit 104 is a functional unit that receives a print job via the network I / F 506 and executes processing for the print job. The job control unit 104 has a functional role of executing basic functions of the image forming device 10, such as copying, faxing, and printing, based on user instructions, and is primarily responsible for executing the basic functions. Note that if a print job includes paper type setting information, the device information collection unit 101 may collect the paper type setting information from the print job as paper type information in the device information.

[0052] The storage unit 105 is a functional unit that stores the print data of the print job received by the job control unit 104, the device information collected by the device information collection unit 101, the learning model received from the machine learning server 20, etc. The storage unit 105 is realized by the HDD 505 shown in FIG. 2.

[0053] The device information collection unit 101, estimation processing unit 102, image processing adjustment unit 103, and job control unit 104 are realized by executing a program by the CPU 501 shown in Fig. 2. Note that at least some of the device information collection unit 101, estimation processing unit 102, image processing adjustment unit 103, and job control unit 104 may be realized by a hardware circuit such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). Furthermore, the estimation processing unit 102 may be realized by processing by the GPU 504 shown in Fig. 2, or may be realized by processing by the CPU 501 and the GPU 504.

[0054] As shown in FIG. 4, the machine learning server 20 includes a learning data generation unit 201, a machine learning unit 202, and a storage unit 203.

[0055] The learning data generation unit 201 is a functional unit that receives device information of each image forming device (such as the image forming device 10 and another image forming device) from the data server 30 via the network I / F 709, and processes the device information to generate learning data for use in machine learning by the machine learning unit 202 (for example, into a format for input to generate a learning model). The learning data generation unit 201 stores the generated learning data in the storage unit 203.

[0056] The machine learning unit 202 is a functional unit that reads the learning data generated by the learning data generation unit 201 from the storage unit 203 and generates a learning model for machine learning using the learning data. In this case, the machine learning is assumed to be unsupervised learning, for example, and generates a learning model by grouping the learning data based on device information into several clusters by clustering.

[0057] For example, when device information for image forming devices at three locations, A, B, and C, is acquired, the gamma correction table for converting the input signal of the image forming device at each location into an output signal has the characteristics shown in Fig. 5. Since the input / output relationships at locations A, B, and C are different, as shown in Table 1 below, the learning data for the image forming device 10 at location A is grouped into cluster a, the learning data for the image forming device 10 at location B into cluster b, and the learning data for the image forming device 10 at location C into cluster c through clustering by the machine learning unit 202.

[0058] [Table 1]

[0059] In this case, the learning model generated by the machine learning unit 202 outputs which of the above-mentioned three clusters the image forming device 10 will be classified into when device information of the image forming device 10 is input as input data.

[0060] In the example shown in Figure 5, image forming devices at three locations are grouped into three clusters, but in reality, device information is collected from each image forming device connected to network N and clustering is performed based on that device information, so the number of clusters is not limited to three and the devices may be grouped into any other number of clusters.

[0061] In this way, by adopting unsupervised learning in the machine learning of the machine learning unit 202, it is not necessary to use teacher data as training data as in supervised learning. In other words, the user does not need to attach labels that serve as correct answers for creating training data, which reduces the workload. In addition, device information can be collected from each image forming device connected to the network N and used as training data for machine learning, which makes it possible to timely suppress differences in image quality and improve image quality.

[0062] The machine learning unit 202 stores the generated learning model in the storage unit 203. The machine learning unit 202 also transmits the generated learning model to the image forming apparatus 10 via the network I / F 709. The image forming apparatus 10 stores the received learning model in the storage unit 105.

[0063] The storage unit 203 is a functional unit that stores the learning data generated by the learning data generation unit 201, the learning model generated by the machine learning unit 202, etc. The storage unit 203 is realized by the auxiliary storage device 705 shown in FIG.

[0064] The above-described training data generation unit 201 and machine learning unit 202 are realized by executing a program by CPU 701 shown in Fig. 3. Note that at least a part of the training data generation unit 201 and the machine learning unit 202 may be realized by a hardware circuit such as an FPGA or an ASIC. Furthermore, the machine learning unit 202 may be realized by processing using a GPU as described above, or may be realized by processing using CPU 501 and the GPU.

[0065] As shown in FIG. 4, the data server 30 includes a data collection unit 301 and a storage unit 302.

[0066] The data collection unit 301 is a functional unit that collects device information from the image forming apparatus 10 and other image forming apparatuses via a network I / F 709. The data collection unit 301 stores the collected device information in a storage unit 302. The data collection unit 301 also provides the collected device information to the machine learning server 20 via the network I / F 709. The data collection unit 301 is realized, for example, by a program being executed by the CPU 701 shown in FIG. 3 .

[0067] The storage unit 302 is a functional unit that stores the device information and the like collected by the data collection unit 301. The storage unit 302 is realized by the auxiliary storage device 705 shown in FIG.

[0068] The machine learning server 20 and the data server 30 may be implemented on the same information processing device. The image forming device 10 may have the same functions as the machine learning server 20. In this case, the image forming device 10 may also have the same functions as the data server 30.

[0069] Furthermore, the machine learning server 20 and the data server 30 may each be realized by a single information processing device or by multiple information processing devices. For example, the machine learning server 20 and the data server 30 may be realized by cloud computing technology.

[0070] Furthermore, the functional units of each device in the image forming system 1 shown in FIG. 4 are conceptually illustrated, and are not limited to such a configuration. That is, each functional unit of each device does not need to be configured as a clear software module as shown in FIG. 4, but rather the functions of each functional unit as a whole may be realized by the execution of a program in each device. For example, the multiple functional units illustrated as independent functional units in each device shown in FIG. 4 may be configured as a single functional unit. On the other hand, the function of a single functional unit in each device shown in FIG. 4 may be divided into multiple parts and configured as multiple functional units.

[0071] (Machine learning process flow on the machine learning server) 6 is a flowchart showing an example of the flow of machine learning processing by the machine learning server according to the embodiment. The flow of machine learning processing by the machine learning server 20 according to the embodiment will be described with reference to FIG.

[0072] <Step S11> The learning data generation unit 201 of the machine learning server 20 receives the device information of each image forming device (such as the image forming device 10 and another image forming device) from the data server 30 via the network I / F 709. Then, the process proceeds to step S12.

[0073] <Step S12> The learning data generation unit 201 processes the received learning data (for example, processes it into a format for input to generate a learning model) to generate learning data for use in machine learning by the machine learning unit 202. The learning data generation unit 201 stores the generated learning data in the storage unit 203. Then, the process proceeds to step S13.

[0074] <Step S13> The machine learning unit 202 of the machine learning server 20 reads the learning data generated by the learning data generation unit 201 from the storage unit 203, and generates a learning model for machine learning using the learning data. The machine learning unit 202 stores the generated learning model in the storage unit 203. Then, the process proceeds to step S14.

[0075] <Step S14> The machine learning unit 202 transmits the generated learning model to the image forming apparatus 10 via the network I / F 709. The image forming apparatus 10 stores the received learning model in the storage unit 105.

[0076] (Flow of operation of image forming device) Fig. 7 is a flowchart showing an example of the flow of operation of the image forming apparatus according to the embodiment. Fig. 8 is a flowchart showing an example of the flow of printing operation of the image forming apparatus according to the embodiment. The flow of operation of the image forming apparatus 10 according to the present embodiment will be described with reference to Figs. 7 and 8.

[0077] <Step S21> If the job control unit 104 of the image forming device 10 receives a print job (step S21: Yes), the process proceeds to step S22; if the print job is not received (step S21: No), the operation of the image forming device 10 is terminated.

[0078] <Step S22> The device information collecting unit 101 of the image forming device 10 collects device information from the image forming device 10. The device information collecting unit 101 collects temperature and humidity detected by the sensors 509. The device information collecting unit 101 collects paper type from information set in advance by the user. Note that if the print job includes paper type setting information, the device information collecting unit 101 may collect the paper type setting information from the print job as paper type information in the device information. Then, the process proceeds to step S23.

[0079] <Step S23> The estimation processing unit 102 of the image forming device 10 uses the learning model stored in the storage unit 105 to estimate a cluster into which the device information of the image forming device 10 collected by the device information collecting unit 101 is classified. Then, the process proceeds to step S24.

[0080] <Step S24> The image processing adjustment unit 103 of the image forming apparatus 10 creates image processing parameters from the gamma correction table corresponding to the cluster of apparatus information estimated by the estimation processing unit 102. Then, the process proceeds to step S25.

[0081] <Step S25> The job control unit 104 executes the printing operation for the print data of the received print job by the following steps S251 to S255 using the image processing parameters created by the image processing adjustment unit.

[0082] <<Step S251>> The job control unit 104 performs filter processing to correct the print data, which is RGB image data, so as to improve the sharpness of the print data, and then proceeds to step S252.

[0083] <<Step S252>> The job control unit 104 converts each 8-bit RGB data into CMYK image data so as to correspond to the color space of the image forming unit 507. Then, the process proceeds to step S253.

[0084] <<Step S253>> The job control unit 104 performs a scaling process to convert the size (resolution) of the CMYK image data into the size (resolution) set by the user, and then the process proceeds to step S254.

[0085] <<Step S254>> The job control unit 104 adjusts the image quality by performing table conversion processing for each CMYK and executing gamma correction using the CMYK edge γ table and non-edge γ table previously set for output from the image forming unit 507 and the image processing parameters created by the image processing adjustment unit 103. Then, the process proceeds to step S255.

[0086] <<Step S255>> The job control unit 104 performs gradation processing on the gamma-corrected CMYK image data to convert the number of gradations into a number that conforms to the gradation processing capability of the image forming unit 507. Then, the job control unit 104 causes the image forming unit 507 to form an image based on the gradation-processed CMYK image data.

[0087] As described above, in the image forming apparatus 10 according to this embodiment, the job control unit 104 receives print data, the device information collection unit 101 collects device information relating to the image forming apparatus 10, the estimation processing unit 102 estimates clusters into which the device information of the image forming apparatus 10 collected by the device information collection unit 101 is classified using a learning model for clustering the device information, the learning model being generated by machine learning using learning data including device information of other image forming apparatuses, the image processing adjustment unit 103 creates image processing parameters using a gamma correction table for correcting density that corresponds to the cluster estimated by the estimation processing unit 102, and the job control unit 104 causes the image forming unit 507 to print the print data using the image processing parameters created by the image processing adjustment unit 103. This reduces downtime and suppresses image quality differences.

[0088] Each function of the above-described embodiments can be realized by one or more processing circuits. Here, the term "processing circuit" includes a processor programmed to execute each function by software, such as a processor implemented by an electronic circuit, and devices such as an ASIC, a DSP (Digital Signal Processor), an FPGA, or a conventional circuit module designed to execute each function described above.

[0089] The programs executed by the image forming apparatus 10, machine learning server 20, and data server 30 of the above-described embodiments may be configured to be pre-installed in a ROM or the like and provided. The programs executed by the image forming apparatus 10, machine learning server 20, and data server 30 of the above-described embodiments may be provided as a computer program product by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM (Compact Disc Read Only Memory), a flexible disk (FD), a CD-R (Compact Disk-Recordable), or a DVD (Digital Versatile Disk). The programs executed by the image forming apparatus 10, machine learning server 20, and data server 30 of the above-described embodiments may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. The programs executed by the image forming apparatus 10, machine learning server 20, and data server 30 of the above-described embodiments may be provided or distributed via a network such as the Internet.

[0090] In addition, the programs executed by the image forming device 10, machine learning server 20, and data server 30 in the above-mentioned embodiments have a modular structure including each of the functional units described above, and in terms of actual hardware, the CPU (processor) reads the program from the storage device and executes it, thereby loading each of the functional units described above onto the main storage device, and each functional unit is generated on the main storage device.

[0091] The aspects of the present invention are as follows. <1> An image forming apparatus, a receiving unit that receives print data; a collection unit that collects device information that is information about the image forming device; an estimation unit that estimates a cluster into which the device information of the image forming device collected by the collection unit is classified, using a learning model for clustering device information that is generated by machine learning using learning data including device information of another image forming device; a creating unit that creates image processing parameters using correction information for correcting density corresponding to the cluster estimated by the estimating unit; a print control unit that causes an image forming unit to print the print data using the image processing parameters created by the creation unit; The image forming apparatus is provided with the above. <2> The learning model is generated by unsupervised learning based on clustering of the learning data. <1> 2. The image forming apparatus according to claim 1, wherein: <3> The learning model is generated by a machine learning server using learning data based on device information collected from other image forming devices connected to a network. <1> or <2> 2. The image forming apparatus according to claim 1, wherein: <4> the creation unit creates the image processing parameters using correction information of another image forming apparatus classified into the cluster estimated by the estimation unit. <1> ~ <3> 10. The image forming apparatus according to claim 9, wherein the first and second electrodes are arranged parallel to each other. <5> The device information includes status information regarding the status of the image forming device. <1> ~ <4> 10. The image forming apparatus according to claim 9, wherein the first and second electrodes are arranged parallel to each other. <6> The status information includes at least one of a total number of printed sheets, a color ratio, an average printing rate, and an average number of continuously printed sheets of the image forming apparatus. <5> 2. The image forming apparatus according to claim 1, wherein: <7> The device information includes environmental information relating to an environment of the image forming device. <1> ~ <6> 10. The image forming apparatus according to claim 9, wherein the first and second electrodes are arranged parallel to each other. <8> The environmental information includes at least one of the temperature, humidity, moisture content, and paper type of the place where the image forming apparatus is installed. <7> 2. The image forming apparatus according to claim 1, wherein: <9> An image forming method for an image forming apparatus, comprising: a receiving step of receiving print data; a collection step of collecting device information that is information about the image forming device; an estimation step of estimating a cluster into which the collected device information of the image forming device is classified, using a learning model for clustering device information, the learning model being generated by machine learning using learning data including device information of another image forming device; a creating step of creating image processing parameters using correction information for correcting density corresponding to the estimated cluster; a print control step of causing an image forming unit to print the print data using the created image processing parameters; The image forming method has the following features. <10> The computer of the image forming device a receiving step of receiving print data; a collection step of collecting device information that is information about the image forming device; an estimation step of estimating a cluster into which the collected device information of the image forming device is classified, using a learning model for clustering device information, the learning model being generated by machine learning using learning data including device information of another image forming device; a creating step of creating image processing parameters using correction information for correcting density corresponding to the estimated cluster; a print control step of causing an image forming unit to print the print data using the created image processing parameters; This is a program for executing the above. [Explanation of symbols]

[0092] 1. Image forming system 10 Image forming device 20 Machine Learning Server 30 Data Server 40 User terminals 101 Equipment Information Collection Department 102 Estimation processing unit 103 Image processing adjustment unit 104 Job control section 105 Storage section 201 Learning Data Generation Unit 202 Machine Learning Department 203 Storage section 301 Data Collection Department 302 Storage section 501 CPU 502 ROM 503 RAM 504 GPU 505 HDD 506 Network I / F 507 Image forming unit 508 Reading unit 509 Sensors 510 Bus 701 CPU 702 ROM 703 RAM 705 Auxiliary storage 706 Recording Media 707 Media Drive 708 Display 709 Network I / F 710 Bus 711 keyboard 712 Mouse 713 DVD 714 DVD drive [Prior art documents] [Patent documents]

[0093] [Patent Document 1] Japanese Patent Application Laid-Open No. 2012-201091

Claims

1. An image forming apparatus, a receiving unit that receives print data; a collection unit that collects device information that is information about the image forming device; an estimation unit that estimates a cluster into which the device information of the image forming device collected by the collection unit is classified, using a learning model for clustering device information that is generated by machine learning using learning data including device information of another image forming device; a creating unit that creates image processing parameters using correction information for correcting density corresponding to the cluster estimated by the estimating unit; a print control unit that causes an image forming unit to print the print data using the image processing parameters created by the creation unit; An image forming apparatus comprising:

2. The image forming apparatus according to claim 1 , wherein the learning model is generated by unsupervised learning based on clustering of the learning data.

3. The image forming apparatus according to claim 1 or 2, wherein the learning model is generated by a machine learning server using learning data based on device information collected from another image forming apparatus connected to a network.

4. 3. The image forming apparatus according to claim 1, wherein the creation unit creates the image processing parameters using correction information of another image forming apparatus classified into the cluster estimated by the estimation unit.

5. The image forming apparatus according to claim 1 , wherein the apparatus information includes status information relating to a status of the image forming apparatus.

6. 6. The image forming apparatus according to claim 5, wherein the status information includes at least one of a total number of printed sheets, a color ratio, an average printing rate, and an average number of continuously printed sheets of the image forming apparatus.

7. The image forming apparatus according to claim 1 , wherein the apparatus information includes environmental information relating to an environment of the image forming apparatus.

8. The image forming apparatus according to claim 7 , wherein the environmental information includes at least one of the temperature, humidity, moisture content, and paper type of a location where the image forming apparatus is installed.

9. An image forming method for an image forming apparatus, comprising: a receiving step of receiving print data; a collection step of collecting device information that is information about the image forming device; an estimation step of estimating a cluster into which the collected device information of the image forming device is classified, using a learning model for clustering device information, the learning model being generated by machine learning using learning data including device information of another image forming device; a creating step of creating image processing parameters using correction information for correcting density corresponding to the estimated cluster; a print control step of causing an image forming unit to print the print data using the created image processing parameters; An image forming method comprising the steps of:

10. The computer of the image forming device a receiving step of receiving print data; a collection step of collecting device information that is information about the image forming device; an estimation step of estimating a cluster into which the collected device information of the image forming device is classified, using a learning model for clustering device information, the learning model being generated by machine learning using learning data including device information of another image forming device; a creating step of creating image processing parameters using correction information for correcting density corresponding to the estimated cluster; a print control step of causing an image forming unit to print the print data using the created image processing parameters; A program to execute.

Images