JP2020030594A - Image forming apparatus, system, control method for image forming apparatus, and program - Google Patents

Abstract

To provide an image forming apparatus that easily recommends more appropriate print settings.SOLUTION: An image forming apparatus 110 is configured: to register the feature amount of printed data and the print setting in association with each other; to acquire the predetermined number of print settings of data similar to the data from the registered print settings based on the feature amount of the data to be printed upon receiving a print instruction; and to present the obtained predetermined number of print settings to the user as recommended print settings for data to be printed.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an image forming apparatus, a system, a control method for an image forming apparatus, and a program.

  In recent years, there is a method of printing electronic data stored in a storage on the Internet from an arbitrary image forming apparatus. Such printing is called pull printing, and the user can print at a desired place at a desired time. In the pull print system, print settings are made on the image forming apparatus. However, print settings on the image forming apparatus may be complicated.

  On the other hand, Patent Literature 1 discloses an information processing apparatus that estimates a print setting recommended for a new print job based on a result learned using print data and print settings of a stored print job. are doing. Patent Literature 1 describes that a recommended print setting is estimated using an identifier using an SVM algorithm.

JP 2018-69684 A

  However, in the method of estimating a recommended print setting using the classifier of Patent Document 1, a large amount of learning data is required for learning of the classifier, and the print setting is recommended until learning of the classifier is completed. Can not do it. In the method of estimating recommended print settings using the classifier of Patent Document 1, recommended print settings are determined for target electronic data for each classification destination by the classifier. For this reason, for example, it is not possible to recommend two or more types of print settings having different purposes for the same electronic data.

  SUMMARY An advantage of some aspects of the invention is to provide an image forming apparatus that simply and more appropriately recommends print settings.

  An image forming apparatus according to an embodiment of the present invention includes a registration unit that associates and registers a feature amount of data on which printing is performed and a print setting, and a feature amount of data on which the printing is performed upon receiving a print instruction. An acquisition unit for acquiring a predetermined number of print settings of data similar to the data from the registered print settings based on the data, and recommending the acquired predetermined number of print settings to the data to be printed. Presentation means for presenting to the user as print settings to be performed.

  According to the image forming apparatus of the present invention, it is possible to simply and easily recommend more appropriate print settings.

FIG. 1 is a diagram illustrating a configuration example of a printing system according to a first embodiment. FIG. 2 is a diagram illustrating a hardware configuration example of an image forming apparatus. FIG. 2 illustrates an example of a software configuration of the image forming apparatus. 9 is a flowchart illustrating an entire flow of a pull print process. 9 is a flowchart illustrating an entire flow of a pull print process. 9 is a flowchart illustrating a process of calculating a feature amount of electronic data. FIG. 6 is a diagram illustrating an example of a table used to determine a feature amount. FIG. 6 is a diagram illustrating an example of a registered print setting. 9 is a flowchart illustrating a process for determining a recommended print setting. It is a figure which shows calculation of the score and the actual example which concern on 1st Embodiment. 9 is an example of a user interface screen in a pull print process. 9 is an example of a user interface screen in a pull print process. 9 is an example of a user interface screen in a pull print process. FIG. 6 is a diagram illustrating a configuration example of a printing system according to a second embodiment. FIG. 3 is a diagram illustrating a hardware configuration example of a learning server. FIG. 3 is a diagram illustrating a software configuration example of an image forming apparatus and a learning server. FIG. 11 is a diagram illustrating processing relating to registration of print settings according to the second embodiment. FIG. 11 is a diagram illustrating an example of a registered print setting according to the second embodiment. It is a figure showing the learning model of the neural network concerning a 2nd embodiment. It is a figure showing the learning model of the neural network concerning a 3rd embodiment.

  Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings.

(1st Embodiment)
FIG. 1 is a diagram illustrating a configuration example of a printing system according to the present embodiment.
In FIG. 1, the image forming apparatus 110 executes a printing process. The information processing device 120 creates electronic data by an application program or holds electronic data received from outside via a network. The information processing device 120 is, for example, a PC (personal computer), a mobile phone, a smartphone, a tablet terminal, or the like.

  The image forming apparatus 110 and the information processing apparatus 120 are connected to the Internet 130 via the local area network 100. The image forming apparatus 110 and the information processing apparatus 120 can communicate with the authentication server 140 and the storage server 150 via the Internet 130. The authentication server 140 manages user information and issues a security token. The storage server 150 transmits, receives, stores, and manages electronic data based on a request from the outside via the Internet 130.

  In the present embodiment, the information processing apparatus 120 stores electronic data in the storage server 150, and the image forming apparatus 110 performs printing processing of the stored electronic data. It is not limited to the information processing device 120. In the present embodiment, the image forming apparatus 110 and the information processing apparatus 120 are connected to different local area networks 100. However, the image forming apparatus 110 and the information processing apparatus 120 are connected to the same local area network. Is also good.

  The storage server 150 provides a general storage service. The storage server 150 manages the electronic data by assigning a URL to each of the stored electronic data. The information processing device 120 and the image forming device 110 communicate with the storage server 150 using a communication protocol such as HTTP or HTTPS. The storage server 150 can also restrict access to electronic data based on the security token (authorization information) issued by the authentication server 140.

  In this case, before accessing the electronic data of the storage server 150, the information processing apparatus 120 and the image forming apparatus 110 communicate with the authentication server 140, perform an authentication process, and issue a security token. One of the specifications regarding the transfer of such authorization information is, for example, OAuth.

[Hardware configuration of image forming apparatus]
FIG. 2 is a diagram illustrating an example of a hardware configuration of the image forming apparatus 110.
Each component of the hardware except the operation unit 206 and the printer engine 209 is connected to the system bus 200. The CPU 201 generally controls each component connected to the system bus 200 based on a program stored in the ROM 202 or the RAM 204.

  The ROM 202 or the HDD 203 stores an operating system (OS), which is a control program of the CPU 201, and a program for performing various processes described below. The HDD 203 also temporarily stores electronic data to be printed, and stores various data used when performing printing. The RAM 204 functions as a main memory, a work area, and the like for the CPU 201.

  The operation unit IF 205 controls input and output from an operation unit 206 having an input device such as a touch panel and hardware keys and a display device such as an LCD. The network IF 207 controls data communication with various information processing devices via a network. The printer engine IF 208 controls input and output of image data and control signals to and from the printer engine 209 that performs heat fixing processing on the transferred image data as a permanent fixed image on a sheet surface.

[Software configuration of image forming apparatus]
FIG. 3 is a diagram illustrating a configuration example of a software module of the image forming apparatus 110.
Each software module shown in FIG. 3 is stored in the HDD 203, loaded into the RAM 204, and executed by the CPU 201.

  The user interface control unit 301 controls a user interface screen displayed on the operation unit 206, and notifies various types of information input from the operation unit 206 to related software modules. The authentication unit 302 receives a login request notified from the user interface control unit 301 based on user information managed by the HDD 203 or an information processing device (not shown) connected to the network. The authentication unit 302 receives an inquiry about various information registered as user information.

  The communication unit 303 controls the network IF 207 to communicate with an information processing device including various servers connected via a network. The pull print control unit 300 controls the entire pull print process performed by the image forming apparatus 110. The pull print control unit 300 controls the user interface control unit 301 to display a user interface screen related to pull print.

  The feature amount calculation unit 304 calculates a feature amount of electronic data that is a print target candidate. The print control unit 305 controls the printer engine 209 to perform print processing based on the specified print settings of the specified electronic data. In the present embodiment, it is assumed that page aggregation, double-sided printing, color mode, and stapling can be set as print settings. However, the present invention is not limited to this. The page aggregation setting is a function of laying out a plurality of images generated by electronic data on one sheet and displaying the images, and can lay out 1, 2, 4, 6, 8, 9, or 16 images on one sheet.

  The double-sided setting is a function for designating whether to perform the printing process on one side of the paper or the printing process on both sides. The color mode setting is a function for designating whether to print an image to be printed on paper in monochrome or color in an image forming apparatus capable of performing color printing. The stapling setting is a function of binding a plurality of output sheets together with a metal staple or the like. , Lower left.

  The print setting registration unit 306 determines whether to use the notified print setting as a recommended setting in the future based on the notified print setting and the feature amount of the electronic data. The print settings determined to be used as the recommended settings are stored in the HDD 203 as registered print settings, and managed by the print setting registration unit 306. The recommended print setting determination unit 307 selects a recommended print setting from the registered print settings managed by the print setting registration unit 306 based on the notified feature amount of the electronic data.

  The electronic data interpretation unit 308 interprets the electronic data, and thereby, the number of image data (the number of pages) formed based on the electronic data, the color information of the image data (color or monochrome), the direction of the image data, and the like. Judge. Of the above software modules, the processing of the print control unit 305 and the operation of the electronic data interpretation unit 308 can be realized by a general method known to those skilled in the art, and a description thereof will be omitted.

[Execution flow of pull print]
FIG. 4 and FIG. 5 are flowcharts showing the overall flow of the pull print processing executed by the image forming apparatus 110.
The flowcharts shown in FIGS. 4 and 5 are executed by each software module described in FIG.

  In step S <b> 401, upon receiving a login request from the user interface control unit 301, the authentication unit 302 performs a login process based on the information passed from the user interface control unit 301. Here, the login process performed by the authentication unit 302 is a process of displaying an authentication screen on the operation unit 206 and inputting a user name and a password, or a process of a card authentication method using close proximity wireless communication such as NFC. is there.

  If the authentication processing is successful, the authentication unit 302 issues a login context to the pull print control unit 300. Here, the login context is information for identifying the user who has performed the login process. The pull print control unit 300 requests the communication unit 303 to obtain a list of electronic data stored in association with the user who has logged in from the storage server 150.

  Before accessing the storage server 150, the communication unit 303 needs to acquire a security token for the user who has logged in to the authentication server 140. In the present embodiment, it is assumed that information for issuing a security token is registered in advance in user information managed by the authentication unit 302. The communication unit 303 obtains information necessary for issuing a security token based on the login context described above, and requests the authentication server 140 to issue a security token.

  Then, the communication unit 303 transmits the issued security token to the storage server 150, acquires a list of electronic data, and passes the list to the pull print control unit 300. Here, the list of electronic data is data in HTML, XML, JSON format or the like including URLs to a plurality of electronic data. The electronic data list may include, for each electronic data, information indicating the date on which the electronic data was created and the name of the user who created the electronic data, in addition to a character string indicating the name of the electronic data.

  In step S402, when the pull print control unit 300 receives the above-described electronic data list, the pull print control unit 300 displays a user interface screen for controlling the electronic data included in the list on the operation unit 206 using the user interface control unit 301. Display on the device. The user interface screen displayed here includes a character string indicating the name of the electronic data described above, and is configured so that the electronic data can be selected based on the name.

  In S403, when detecting that the electronic data is selected, the user interface control unit 301 notifies the pull print control unit 300 of the selected electronic data. In step S404, the pull print control unit 300 determines whether the recommended print settings for the notified electronic data have been calculated. This makes it possible to suppress the calculation of the recommended print settings every time the electronic data is selected.

  For example, information in which the URL of the electronic data on the storage server 150 is associated with the calculated print setting is stored in the RAM 204 or the HDD 203. Then, it may be checked whether the information corresponding to the electronic data selected in S404 is stored in the RAM 204 or the HDD 203. In step S404, if the recommended print setting for the notified electronic data has been calculated, the process proceeds to step S407. If the recommended print setting has not been calculated, the process proceeds to step S405.

  In step S405, the pull print control unit 300 causes the feature amount calculation unit 304 to calculate the feature amount of the selected electronic data. Details of the feature amount will be described later. In step S <b> 406, the pull print control unit 300 uses the recommended print setting determination unit 307 to select a print setting recommended for the selected electronic data from the registered print settings registered by the print setting registration unit 306, One or more print settings suitable for the electronic data are determined.

  The details of the method of determining the recommended print settings will be described later. The print setting determined as the recommended print setting is stored in the RAM 204 or the HDD 203 in association with the electronic data as described above. It is desirable that the stored information be deleted when the print setting registration unit 306 updates the registered print settings. In step S <b> 407, the pull print control unit 300 uses the user interface control unit 301 to display a screen that presents the determined print settings. From this screen, the user can select the print setting or select to set the print setting from the beginning.

  Subsequently, in S408 of FIG. 5, if it is detected that the print setting is selected, the process proceeds to S409, and if it is detected that the print setting is set from the beginning, the process proceeds to S410. In step S409, the user interface control unit 301 notifies the pull print control unit 300 of the selected print setting. When notified of the selected print setting, the pull print control unit 300 sets the print setting in the print control unit 305 to prepare for printing the electronic data selected by the selected print setting.

  In step S410, the user interface control unit 301 determines whether to set print settings from the beginning. If it is selected to set the print settings from the beginning, the process proceeds to S411, and if it is not selected to set the print settings from the beginning, the process returns to S402. In step S411, the user interface control unit 301 notifies the pull print control unit 300 that the user has selected to set print settings from the beginning.

  The notified pull print control unit 300 causes the user interface control unit 301 to display a screen for setting print settings from the beginning. When the completion of the print setting on the screen is detected, the user interface control unit 301 notifies the set print setting to the pull print control unit 300. When notified of the print settings, the pull print control unit 300 sets the print settings in the print control unit 305, thereby preparing to print the electronic data selected by the notified print settings.

  In step S412, the user interface control unit 301 determines whether a print start request has been detected. If a print start request is detected, the process proceeds to step S413. If a print start request is not detected, the process returns to step S402. In step S <b> 413, the pull print control unit 300 starts print processing by notifying the print control unit 305 of the selected electronic data.

  Further, the pull print control unit 300 notifies the print setting registration unit 306 of the feature amount of the electronic data calculated by the feature amount calculation unit 304 and the information on the print setting set in the print control unit 305 in S409 or S411. The print setting registration unit 306 determines whether to register the notified print setting based on the notified feature amount and print setting of the electronic data and the registered print setting that has already been registered. The details of the process for determining whether to register print settings will be described later.

  If it is determined that the print settings are to be registered, the process proceeds to step S414. If it is determined that the print settings are not to be registered, the processes illustrated in FIGS. 4 and 5 end. In step S414, the print setting registration unit 306 stores the notified electronic data feature amount and the print setting in the HDD 203 in association with each other.

[Feature calculation]
FIG. 6 is a flowchart illustrating a process of calculating a feature amount of electronic data.
In step S <b> 501, the feature amount calculation unit 304 passes electronic data for calculating a feature amount to the electronic data interpretation unit 308. The electronic data interpretation unit 308 interprets the received electronic data, calculates the number of image data formed based on the electronic data, the color information of the image data, the direction of the image data, and the like. The feature amount calculation unit 304 is notified.

  In step S502, the feature amount calculation unit 304 converts the feature amount of the electronic data into a vector format based on the notified information. The conversion into the vector format refers to a process of digitizing the notified information into a sequence in a prescribed order based on a table defined in advance for each attribute shown in tables 601 to 603 in FIG. For example, if the notified information has a vertical image direction, one page, and monochrome color information, the generated vector is (0, 0, 0). In the present embodiment, the order of the numerical values of the vectors is defined as the direction of the image, the number of pages, and the order of the color information.

[Register print settings]
Next, registered print settings registered by the print setting registration unit 306 will be described. The print setting registration unit 306 of the present embodiment stores, in the HDD 203, information associating the print data with the feature amount of the electronic data notified from the pull print control unit 300 after printing is performed, as a registered print setting.

  If there is no registered print setting in which the combination of the notified feature amount of the electronic data and the print setting match, the print setting registration unit 306 stores the feature amount and the print setting of the notified electronic data as a new registered print setting. The data is stored in the HDD 203. As described above, since it is determined whether to register the print settings, it is possible to prevent the same print settings from being registered or recommended repeatedly.

FIG. 8 is a diagram illustrating an example of the registered print settings registered by the print setting registration unit 306.
The table 700 shows the registered print settings registered by the print setting registration unit 306. FIG. 8 shows that five registered print settings are registered. Further, the print setting registration unit 306 stores the date and time when the registered print settings are registered in the HDD 203. A table 701 indicates the date and time when the registered print settings stored by the print setting registration unit 306 are registered.

[How to determine recommended print settings]
FIG. 9 is a flowchart illustrating a process of determining a recommended print setting for electronic data.
More specifically, a process in which the recommended print setting determination unit 307 selects a recommended print setting from the registered print settings for the notified electronic data will be described.

  First, in step S801, the recommended print setting determination unit 307 is notified for each registered print setting registered by the print setting registration unit 306 based on the feature amount included in the registered print setting and the notified electronic data feature amount. Calculate the score of the registered print settings for the electronic data. In the present embodiment, the score is a sum of numbers obtained by multiplying the square root of the square (square) of the residual of the same dimension of each feature by a weight for each dimension, that is, a weighted residual square sum. And can be represented by equation 900 shown in FIG. The table 901 in FIG. 10 is a diagram illustrating an example of the weight for each dimension described above.

  In step S802, the recommended print setting determination unit 307 registers and prints the recommended print settings for the notified electronic data based on the calculated score and the date and time when the registered print settings shown in the table 701 in FIG. Obtain a predetermined number from the settings. Specifically, a smaller calculated score value indicates that the corresponding electronic data is more similar to the electronic data that has been previously subjected to the print processing by the print control unit 305. A predetermined number of registered print settings are selected as recommended print settings.

  If the score alone does not allow the user to select a pre-defined number of registered print settings, such as when the scores are equal, the registered date and time are selected based on the date and time when the registered print settings were registered. You can do it. Alternatively, for each registered print setting, the number of times that printing has been performed using the print setting may be stored, and the registered print setting having the greater number of executed times may be preferentially selected.

  A table 902 in FIG. 10 is a diagram illustrating an example of a score calculated for the notified electronic data for each registered print setting. The data of each row of labels 0 to 4 in the table 902 indicates five registered print settings. In the upper right part of the table 902, each feature amount of the five electronic data is shown as the feature amount of the selected data. Each column of the feature amount of the selected data indicates a vector indicating the feature amount of one piece of electronic data.

  According to the table 902, for example, when the feature amount of the notified electronic data is (0, 1, 1), the scores of the registered print settings are 3.0, 1.0, 5.0, 8.0, 9.0. If the recommended number of print settings is specified as three, the recommended print setting determining unit 307 selects the registered print settings with labels 1, 0, and 2 as the recommended print settings.

[User interface screen for pull print processing]
11 to 13 are examples of a user interface screen displayed on the display device of the operation unit 206 by the pull print control unit 300 using the user interface control unit 301.
A screen 1000 in FIG. 11 is an example of a user interface screen for selecting electronic data displayed in S402 in FIG.

  A button 1001 is a button for instructing a screen update. A button 1002 is a button for selecting electronic data to be subjected to pull printing. By detecting the press of these buttons, the user interface control unit 301 detects that the electronic data has been selected. The button 1002 includes a document name, which is the name of the electronic data, the date on which the electronic data was generated, the number of pages of the electronic data, and the name of the user who generated the electronic data.

  These pieces of information are information transmitted from the storage server 150 or information received from the storage server and calculated by the electronic data interpretation unit 308. The check box 1003 is a check box for selecting a plurality of electronic data. When the electronic data is selected by this check box, the electronic data is selected without proceeding to the processing after S404 in FIG. Keep the state.

  The display 1004 displays the number of electronic data items in a selected state (selected state) and a numerical value indicating the total number of electronic data items. A button 1005 is a button for switching a selection state of all electronic data. A button 1006 is a button for instructing deletion of the selected electronic data. A button 1007 is a button for instructing printing of the selected electronic data.

  When detecting a print instruction using the button 1007, the pull print control unit 300 sets a predetermined initial value to the print control unit 305 as a print setting. In this case, it is preferable that the pull print control unit 300 does not notify the print setting registration unit 306 of the print setting. When detecting an instruction to delete electronic data by the button 1006, the pull print control unit 300 deletes information other than the registered print setting of the electronic data for the electronic data to be deleted.

  A dialog 1010 in FIG. 11 is an example of a user interface screen for selecting print settings displayed in S407 in FIG. The dialog 1010 is displayed as a dialog screen as an example, but is not limited thereto. Buttons 1011 to 1013 are buttons for selecting a print setting recommended by the recommended print setting determination unit 307 for the electronic data selected on the screen 1000. Each button displays information on the respective print setting. Is done.

  Although the print setting information is displayed as a character string in the present embodiment, an icon or a thumbnail image indicating a state where the print setting is applied may be displayed. The button 1014 is a button for selecting to set the print settings from the beginning without using the recommended print settings in S410 of FIG. A button 1015 is a button for instructing to cancel printing of the electronic data selected in the dialog 1010.

  A screen 1020 in FIG. 12 is an example of a user interface screen for initially setting the print settings displayed in S411 in FIG. The display 1021 shows information of the electronic data selected on the screen 1000. A text box 1022 is a text box for designating the number of output copies of the electronic data, and the numerical value can be changed by a hardware key of the operation unit 206 or a button 1023 or 1024.

  A button 1025 is a button for performing a color mode setting among the print settings. Upon detecting the press of this button, the pull print control unit 300 displays a dialog 1030 that allows the user to specify a color mode setting using the user interface control unit 301. The drop-down list 1026 is a drop-down button list for performing page aggregation setting.

  A button 1027 is a button for setting staples. When the press of this button is detected, the pull print control unit 300 displays a dialog 1040 that allows the user to specify staple settings using the user interface control unit 301. I do. A button 1028 is a button for instructing to cancel the detailed print settings and return to the screen 1000 or 1010. The button 1029 is a button for instructing printing of the corresponding electronic data according to the print settings set on the screen 1020.

  In a dialog 1030 of FIG. 12, toggle buttons 1031 to 1033 for performing a color mode setting are displayed. Dialog 1030 is displayed as a dialog screen as an example. A button 1034 is a button for instructing to cancel the color mode setting and return to the screen 1020. A button 1035 is a button for confirming the color mode setting.

  A dialog 1040 in FIG. 13 displays a toggle button 1041 or 1042 for setting staples. Buttons 1043 to 1046 are toggle buttons for designating a stapling position. A button 1047 is a button for instructing to cancel the stapling setting and return to the screen 1000. A button 1048 is a button for confirming the stapling setting.

  As described above, according to the present embodiment, an appropriate print setting is selected from the print settings registered based on the feature amount of the electronic data without classifying the electronic data by the classifier constructed with a large amount of learning data. It is possible to do.

(2nd Embodiment)
In the first embodiment, as a score for each registered print setting for electronic data, the square root of the residual square (square) of the same dimension of the electronic data and the feature amount included in the registered print setting is multiplied by a weight for each dimension. Was calculated. However, the method of calculating the score is not limited to this. In the present embodiment, a case where a neural network is used as another score calculation method will be described.

FIG. 14 is a diagram illustrating a configuration example of a printing system according to the present embodiment.
The same components as those in FIG. 1 are denoted by the same reference numerals, and description thereof will be omitted. 14, the image forming apparatus 1100 executes a printing process. The learning server 1101 performs learning based on the characteristic amount of the electronic data transmitted from the image forming apparatus 1100 and the print setting, and recommends the characteristic amount of another electronic data transmitted from the image forming apparatus 1100. The print settings are obtained and transmitted to the image forming apparatus 1100.

  The learning server and the image forming apparatus communicate using a communication protocol such as HTTP or HTTPS. Note that the learning server 1101 may receive a feature amount and / or print setting of electronic data from an image forming apparatus other than the image forming apparatus 1100, and may perform learning.

[Hardware configuration of image forming apparatus]
The hardware configuration of the image forming apparatus 1100 according to the present embodiment is the same as that of the image forming apparatus 110 according to the first embodiment.

[Hardware configuration of learning server]
FIG. 15 is a diagram illustrating an example of a hardware configuration of the learning server 1101.
Each component of the hardware of the learning server 1101 illustrated in FIG. 15 is connected to the system bus 1200. The CPU 1201 comprehensively controls each component connected to the system bus 1200 based on a program stored in the ROM 1202 or the RAM 1204.

  The ROM 1202 or the HDD 1203 stores an OS that is a control program of the CPU 1201 and a program that performs various processes described below. Also, the HDD 1203 temporarily stores electronic data to be processed, and stores various data used when performing various processes. The RAM 1204 functions as a main memory, a work area, and the like for the CPU 1201. The network IF 1205 controls data communication with various information processing apparatuses via a network. The GPU 1206 is originally an image processing unit, but is used as an arithmetic unit for learning a neural network in the present embodiment.

[Software configuration of image forming device and learning server]
FIG. 16 is a diagram illustrating a configuration example of software modules of the image forming apparatus 1100 and the learning server 1101 according to the present embodiment.
The same components as those in FIG. 3 are denoted by the same reference numerals, and description thereof will be omitted. The software modules 1310 to 1313 shown in FIG. 16 are stored in the HDD 1203 of the learning server 1101 and loaded into the RAM 1204, and then executed by the CPU 1201 or the GPU 1206.

  The pull print control unit 1300 according to the present embodiment differs from the pull print control unit 300 according to the first embodiment in the following two points. One is that after the print processing is executed by the print control unit 305, the pull print control unit 300 according to the first embodiment stores in the print setting registration unit 306 the feature amount of the electronic data subject to the print processing. The print setting used for the print processing is notified. On the other hand, the pull print control unit 1300 according to the present embodiment stores the information via the communication units 303 and 1310 in the print setting registration unit of the learning server 1101 after the print processing is executed by the print control unit 305. 1311.

  The other is that the pull print control unit 300 according to the first embodiment inquires of the recommended print setting determination unit 307 about recommended print settings. On the other hand, the pull print control unit 1300 according to the present embodiment queries the recommended print setting determination unit 1313 of the learning server 1101 via the communication units 303 and 1310 for the information.

  The communication unit 1310 communicates with various servers and an information processing apparatus including the image forming apparatus 1100 connected via the network by controlling the network IF 1205. The print setting registration unit 1311 determines whether to use the notified print setting as a recommended setting later based on the print setting notified via the network and the feature amount of the electronic data. The print setting registration unit 1311 stores the notified print settings and the feature amount of the electronic data in the HDD 1203 as learning data.

  The learning unit (identifier) 1312 performs supervised learning of the learning data stored in the HDD 1203 using the registered print setting registered by the print setting registration unit 1311 as a label (correct answer). In the present embodiment, the learning unit 1312 learns using a neural network, but is not limited to this, and any algorithm may be used.

  Further, the learning unit 1312 performs scoring for each registered print setting registered by the print setting registration unit 1311 based on the feature amount of the electronic data notified from the recommended print setting determination unit 1313. Note that in the learning by the learning unit 1312, parallel computation is performed using the GPU 1206 in order to perform a large amount of calculation at high speed.

  The recommended print setting determining unit 1313 notifies the learning unit 1312 of the feature amount of the electronic data notified via the network. Then, the recommended print setting determining unit 1313 selects a recommended print setting from the registered print settings registered by the print setting registration unit 1311 based on the score calculated by the learning unit 1312, and returns the recommended print setting to the image forming apparatus 1100 via the network. I do. Note that the format of the print setting returned at this time is a data format such as HTML, XML, or JSON that can include a plurality of print settings.

Next, a pull print process performed by the image forming apparatus 1100 according to the present embodiment will be described.
The overall flow of the pull print processing according to the present embodiment differs from the overall flow of the pull print processing according to the first embodiment described with reference to FIG. 4 in the following two points. One is a process related to determination of a recommended print setting in S406 of FIG. The other is processing related to registration of print settings in S413 and S414 in FIG. Hereinafter, the two processes described above will be described in detail.

[Register print settings]
In step S <b> 413, when the pull print control unit 1300 starts the print process by notifying the print control unit 305 of the electronic data to be printed, the pull print control unit 1300 performs the following process. The pull print control unit 1300 transmits the feature amount of the electronic data calculated by the feature amount calculation unit 304 and the information on the print setting set in the print control unit 305 in S409 or S411 to the learning server 1101 via the communication units 303 and 1310. The print setting registration unit 1311 is notified.

  FIG. 17 is a flowchart for explaining processing related to registration of print settings, which is executed when the print setting registration unit 1311 of the learning server 1101 receives the above-described information on the feature amount of electronic data and print settings. This process is a process executed in this embodiment instead of the process of S414 in the first embodiment.

  In step S <b> 1401, the print setting registration unit 1311 checks whether the information regarding the print setting, out of the notified information on the feature amount of the electronic data and the print setting, is already stored in the HDD 1203 as the registered print setting. In the first embodiment, as the registered print setting, information in which the notified feature amount of the electronic data is associated with the print setting is stored in the HDD 203 as the registered print setting.

  On the other hand, the registered print settings in the present embodiment are information on print settings stored in an area for storing print settings in which labels of integer values from 1 to k are set. Here, k is equal to the number of units in the output layer of the network model of the neural network of the learning unit 1312. The areas for storing the registered print settings each have a flag indicating whether the print settings are registered (see FIG. 18).

  If the notified print setting has not been saved as the registered print setting, the process advances to step S1402. If the notified print setting has been saved as the registered print setting, the process advances to step S1406. In step S1402, the print setting registration unit 1311 checks whether the notified print setting can be registered as a registered print setting. That is, it is checked whether there is a free space in the area for storing the registered print settings.

  Whether or not there is a vacancy may be confirmed by checking whether there is a flag area indicating that the print setting is not registered in the labels 1 to k described above. If the print setting cannot be registered as the registered print setting, the print setting registration unit 1311 ends the processing for registering the print setting illustrated in FIG. In this case, the notified print settings are not candidates for recommended print settings. On the other hand, if it is possible to register as the registered print setting, the process proceeds to S1403.

  In step S1403, the print setting registration unit 1311 registers the notified print setting as a new registered print setting in an area where the registered print setting is stored. In step S1404, when newly registering the registered print setting, the print setting registration unit 1311 stores information in which the notified feature amount of the electronic data is associated with the print setting information in the HDD 1203 as learning data. In S1405, when the learning data is stored in the HDD 1203, the learning unit 1312 performs learning based on the stored learning data.

  In step S1406, if the notified print setting is already registered as a registered print setting, it is determined whether a combination of the print setting and the notified electronic data feature amount is stored in the HDD 1203. That is, it is determined whether the combination of the notified feature amount of the electronic data and the print setting is registered in the HDD 1203 as the learning data.

  If the combination of the notified feature amount of the electronic data and the print setting is not registered as learning data in the HDD 1203, the process proceeds to S1404, and the corresponding combination is stored as learning data in the HDD 1203 as learning data. If the combination of the notified feature amount of the electronic data and the print setting is already registered in the HDD 1203 as the learning data, the processing illustrated in FIG. 17 ends.

FIG. 19 is a diagram illustrating a neural network model of the learning unit 1312.
The feature of the input layer indicates the feature of the electronic data described above. The number of units in the hidden layer is arbitrary. The number of units in the output layer is the above-described integer value k, which is the number of registered print settings.

  The neural network shown in FIG. 19 uses an error backpropagation method as a learning data using a vector, which is an ONE-HOT expression of a label corresponding to a registered print setting registered by the print setting registration unit 1311 as an output, as a feature amount of electronic data in an input layer. Learn by Note that a softmax function is applied to the activation function of the output layer of the neural network in FIG. For this reason, the output of this neural network for an arbitrary feature can be regarded as the probability of belonging to each label.

[Determine recommended print settings]
As described above, the neural network of the learning unit 1312 can output a probability value for each label for a feature amount of arbitrary electronic data. Therefore, the recommended print setting determining unit 1313 can calculate the score of each registered print setting at a time by inputting the feature amount of the received electronic data to the neural network of the learning unit 1312.

  The recommended print setting deciding unit 1313 extracts print settings corresponding to the scores from the registered print settings registered by the print setting registration unit 1311 in order from the largest score among the scores calculated as described above. To the pull print control unit 1300.

  As described above, according to the present embodiment, it is possible to construct a neural network model that receives a feature amount of electronic data in which a registered print setting is regarded as a label, and learn sequentially. For this reason, even when there is not a large amount of learning data, it is possible to recommend print settings executed in the past for arbitrary electronic data using the feature amount of the data.

  In the present embodiment, the print setting registration unit 1311 performs learning regardless of the number of registered print settings that have been registered. However, if the predetermined number of print settings transmitted by the recommended print setting determination unit 1313 is less than the number of registered print settings that have already been registered, the learning need not be performed. In other words, if the predetermined number is less than the number of registered print settings that have been registered, all registered print settings that have been registered may be transmitted as recommended settings.

(Third embodiment)
In the first embodiment and the second embodiment, the description has been made assuming that the feature amount of the electronic data is obtained by converting the direction, the number of pages, and the color information of the electronic data into a vector format. However, the present invention is not limited to this. The feature amount of the electronic data may be any value as long as it is a numerical expression vector representing the feature of the electronic data.

  For example, an image or the like obtained by rendering the first page of the electronic data can be used as the feature amount of the electronic data. In the present embodiment, a case where a neural network is configured by combining the first page of electronic data with features such as the direction, number of pages, and color information of electronic data as described in the first and second embodiments Will be described.

FIG. 20 is an example of a neural network capable of learning using the first page image and other parameters of the electronic data (the above-described direction, the number of pages, and the like) as feature amounts.
In FIG. 20, CNN stands for Convolutional Neural Network, which is a neural network composed of a convolutional layer and a hidden layer by a pooling layer.

  The neural network according to the present embodiment is configured by superimposing a neural network (NN) that receives an output vector (arbitrary number of dimensions) of the CNN and other electronic data parameters as inputs. In the present embodiment, the feature amount calculation unit 304 of the second embodiment generates a first page image of electronic data as a feature amount of electronic data, and notifies the pull print control unit 1300 of the first page image along with parameters such as the image orientation and the number of pages. I do.

  The print setting registration unit 1311 performs learning by transforming the received image into a form that can be input to the neural network of FIG. As described above, in the present embodiment, since learning can be performed using the feature amount of electronic data that is more suitable for print settings, more preferable print settings can be recommended.

(Other embodiments)
The present invention supplies a program for realizing one or more functions of the above-described embodiments to a system or an apparatus via a network or a storage medium, and one or more processors in a computer of the system or the apparatus read and execute the program. This processing can be realized. Further, it can be realized by a circuit (for example, an ASIC) that realizes one or more functions.

  As described above, the preferred embodiments of the present invention have been described, but the present invention is not limited to these embodiments, and various modifications and changes can be made within the scope of the gist.

110 Image Forming Apparatus 304 Feature Calculation Unit 306, 1311 Print Setting Registration Unit 307, 1313 Recommended Print Setting Determination Unit

Claims (10)

Registering means for registering the feature amount of the printed data and the print setting in association with each other;
When receiving a print instruction, an acquisition unit configured to acquire a predetermined number of print settings of data similar to the data from the registered print settings based on a feature amount of the data to be printed,
An image forming apparatus comprising: a presentation unit configured to present the acquired predetermined number of print settings to a user as recommended print settings of data for performing the printing. Among the recommended print settings and the print settings not using the recommended print settings, further comprising a receiving unit that receives a selection of which print setting to execute,
2. The image forming apparatus according to claim 1, wherein the registration unit registers the selected print setting and a feature amount of data for performing the printing in association with each other.   The acquiring unit may be configured such that the smaller the weighted residual sum of squares of the feature amount of the data to be printed and the feature amount of the registered data is, the smaller the value of the registered data in the data to be printed is. The image forming apparatus according to claim 1, wherein it is determined that the data is similar.   When the weighted residual sum of squares shows the same value for a plurality of registered data feature amounts, a print setting corresponding to the registered data feature amount is used. 4. The system according to claim 3, wherein it is determined that data having a large number of times of use or data having a new date and time of use are more similar to the data for performing the printing.   The registration unit determines whether or not a combination of the feature amount of the printed data and the print setting has already been registered. If the combination has already been registered, the registration unit does not perform the registration. The image forming apparatus according to any one of claims 1 to 4, wherein:   6. The image processing apparatus according to claim 1, wherein the feature amount of the data includes at least one of an orientation of an image formed based on the data, the number of pages, color information, and an image of a first page. Item 10. The image forming apparatus according to item 1. A system including an image forming apparatus and an information processing apparatus,
The image forming apparatus includes:
First transmission means for transmitting the feature amount of the data that has been printed and the print setting;
A second transmission unit configured to transmit a characteristic amount of data to be printed when receiving a print instruction;
An acquisition unit configured to acquire a predetermined number of print settings of the data obtained based on the feature amount of the data to be printed from the information processing apparatus,
Presenting means for presenting the obtained predetermined number of print settings to a user as recommended print settings of data for performing the printing,
The information processing device,
When receiving the feature amount of the data and the print setting from the image forming apparatus, as learning data of the classifier that inputs the feature amount of the data and outputs the print setting, the feature amount of the received data and the print setting are used. Registration means for registering,
Upon receiving the characteristic amount of the data from the image forming apparatus, based on a result output from the discriminator with the data as an input, a determination unit that determines a predetermined number of print settings,
A third transmission unit configured to transmit the determined predetermined number of print settings to the image forming apparatus.   The registering means, when the received print setting is not registered, or when the combination of the feature amount of the received data and the print setting is not registered, the feature amount of the received data and the print setting 8. The system according to claim 7, wherein? Is registered as learning data of the classifier. A registration step of associating and registering the feature amount of the printed data and the print setting,
Upon receiving a print instruction, an acquisition step of acquiring a predetermined number of print settings of data similar to the data from the registered print settings based on the feature amount of the data to be printed,
A method of controlling the image forming apparatus, the method further comprising: presenting the acquired predetermined number of print settings to a user as recommended print settings of the data to be printed.   A program for causing a computer to function as each unit included in the image forming apparatus according to claim 1.

Images