JP2018069684A - Information processing device, information processing system, and information processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enhance accuracy for recommending setting desired by a user.SOLUTION: An information processing device includes: a reception part for receiving a print job together with user information corresponding to a user; a machine learning part for learning print data of the print job received by the reception part and print setting, and estimating recommended print setting to a new print job received by the reception part on the basis of a learning result; an output part for outputting the setting information estimated by the machine learning part; and an acquisition part for acquiring application propriety information showing whether the user refuses the application of the setting information outputted by the output part. When the acquisition part acquires the application propriety information, the machine learning part further learns the print data of the print job received by the reception part and the print setting on the basis of the application propriety information, and estimates recommended print setting to a new print job received by the reception part.SELECTED DRAWING: Figure 4

Description

  The present invention relates to an information processing apparatus, an information processing system, and an information processing method.

  There are some known techniques for recommending print settings to a user in an MFP (Multifunction Peripheral) that prints an image with a function as an information processing apparatus.

  Japanese Patent Application Laid-Open No. 2004-228561 stores a set of print settings and print mode information used in an executed print job as history information, and based on the stored history information and new print job information. An information processing apparatus that presents a print setting screen configured by arranging a set of recommended print settings for each print mode to a new print job is disclosed.

  However, conventionally, even if print settings are recommended for the user, it has not been known whether the recommended print settings are actually effective. In addition, since it is not known whether the recommended print setting is actually applied, there is a problem that even if the user rejects the recommended print setting, the same print setting is recommended again.

  The present invention has been made in view of the above, and provides an information processing device, an information processing system, and an information processing method capable of avoiding repeated recommendation of a setting not desired by a user. Objective.

  In order to solve the above-described problems and achieve the object, the present invention learns a receiving unit that receives a print job together with user information corresponding to the user, and print data and print settings of the print job received by the receiving unit. Then, based on the learning result, a machine learning unit that estimates a recommended print setting for a print job newly received by the receiving unit, and an output that outputs setting information indicating the print setting estimated by the machine learning unit And an acquisition unit that acquires applicability information indicating whether or not the user has refused to apply the setting information output by the output unit, and the machine learning unit uses the applicability information. Is acquired, the print data and print settings of the print job received by the receiving unit are further learned based on the applicability information, and the recommended print for the print job newly received by the receiving unit is obtained. To estimate the set.

  According to the present invention, there is an effect that it is possible to avoid repeatedly recommending a setting that is not desired by the user.

FIG. 1 is a diagram illustrating a configuration of an information processing system according to the embodiment. FIG. 2 is a diagram illustrating a hardware configuration of the server. FIG. 3 is a diagram illustrating a hardware configuration of the image forming apparatus. FIG. 4 is a functional block diagram illustrating an overview of the functions of the operation unit. FIG. 5 is a flowchart illustrating an operation example of the operation unit when recommending print settings to the user. FIG. 6 is a diagram showing a specific example of information stored in the storage unit for use in the process (calculation of recommended settings) shown in FIG. FIG. 7 is a diagram illustrating a print job of the user A. FIG. 8 is a diagram illustrating recommended settings calculated by the machine learning unit. FIG. 9 is a diagram illustrating recommended settings calculated by the machine learning unit for the user A and stored in the storage unit. FIG. 10 is a diagram illustrating a print setting change dialog displayed on the display unit. FIG. 11 is a diagram illustrating a print setting change dialog when there are a plurality of recommended setting items. FIG. 12 is a diagram illustrating a first modification of the information stored in the storage unit. FIG. 13 is a diagram illustrating a second modification of the information stored in the storage unit. FIG. 14 is a diagram illustrating a third modification of the information stored in the storage unit. FIG. 15 is a diagram illustrating a fourth modification of the information stored in the storage unit. FIG. 16 is a diagram illustrating a fifth modification of the information stored in the storage unit. FIG. 17 is a diagram illustrating a sixth modification of the information stored in the storage unit. FIG. 18 is a diagram illustrating a seventh modification of the information stored in the storage unit. FIG. 19 is a functional block diagram illustrating functions of the operation unit and the server in order to avoid setting recommendation that the user does not want. FIG. 20 is a sequence diagram illustrating an operation of a modified example of the information processing system in a case where print settings are recommended to the user.

  Hereinafter, an information processing system according to an embodiment will be described in detail with reference to the accompanying drawings.

[System configuration]
FIG. 1 is a diagram illustrating a configuration of an information processing system 100 according to the embodiment. As shown in FIG. 1, the information processing system 100 is configured by connecting, for example, a personal computer (PC) 150, a server 200, and an image forming apparatus 300 to each other via a network 600 such as the Internet.

  The PC 150 is used, for example, when the user transmits a print job to the image forming apparatus 300 together with user information for identifying the user. In addition, the PC 150 may be used when the device administrator performs settings for the information processing system 100. The server 200 stores information related to the information processing system 100 such as settings for the image forming apparatus 300, for example.

  The image forming apparatus 300 is, for example, an MFP, and performs printing according to user information and a print job transmitted from the PC 150 or the like. Here, the image forming apparatus 300 performs printing according to print settings.

[Hardware configuration]
Next, a hardware configuration of each unit constituting the information processing system 100 will be described. FIG. 2 is a diagram illustrating a hardware configuration of the server 200. As shown in FIG. 2, the server 200 includes a central processing unit (CPU) 201, a read only memory (ROM) 202, a random access memory (RAM) 203, a hard disk drive (HDD) 204, and a communication interface (I / F). 205, a keyboard (mouse) 206, and a display 207. Note that the PC 150 also has substantially the same hardware configuration as that of the server 200, and thus the description thereof is omitted.

  The CPU 201 executes a program and controls each unit constituting the server 200. The ROM 202 is a read-only nonvolatile storage medium and stores a program such as firmware. The RAM 203 is a volatile storage medium capable of reading and writing information at high speed, and is used as a work area when the CPU 201 processes information. The HDD 204 is a nonvolatile storage medium that can read and write information, and stores an OS (Operating System), various control programs, application programs, and the like. The CPU 201 controls the overall operation of the server 200 by executing a program stored in the ROM 202 or the HDD 204 with the RAM 203 as a work area (work area). The PC 150 and the server 200 each exhibit a characteristic function by executing different programs stored in the ROM 202 or the HDD 204.

  The communication I / F 205 is an interface for connecting to other devices via the network 600. The keyboard 206 is a user interface for a user to input information to the server 200, and constitutes an input device together with a mouse or the like. The display 207 is a visual user interface for the user to check the state of the server 200.

  FIG. 3 is a diagram illustrating a hardware configuration of the image forming apparatus 300. The image forming apparatus 300 includes a main body 400 capable of realizing various functions such as a copy function, a scanner function, a fax function, and a printer function, and an operation unit 500 that receives a user operation input. Note that accepting a user operation is a concept including accepting information (including a signal indicating a coordinate value of a screen) input according to the user operation. The main body 400 and the operation unit 500 are connected via a dedicated communication path 302 so that they can communicate with each other. The communication path 302 may be, for example, a USB (Universal Serial Bus) standard, but may be of any standard regardless of whether it is wired or wireless.

  The main body 400 can perform an operation corresponding to the operation received by the operation unit 500. The main body 400 can also communicate with an external device such as the PC 150 and can perform an operation in accordance with an instruction received from the external device.

  First, the hardware configuration of the main body 400 will be described. As shown in FIG. 3, the main body 400 includes a CPU 401, a ROM 402, a RAM 403, an HDD 404, a communication interface (I / F) 405, a connection interface (I / F) 406, and an engine unit 407. These are connected to each other via a system bus 408.

  The CPU 401 comprehensively controls the operation of the main body 400. The ROM 402 is a read-only nonvolatile storage medium and stores a program such as firmware. The RAM 403 is a volatile storage medium capable of reading and writing information at high speed, and is used as a work area when the CPU 401 processes information. The HDD 404 is a nonvolatile storage medium that can read and write information, and stores an OS, various control programs, application programs, and the like. The CPU 401 uses the RAM 403 as a work area (work area) and executes a program stored in the ROM 402 or the HDD 404 to control the overall operation of the main body 400, and the above-described copy function, scanner function, fax function, printer function, and the like. Implement various functions.

  The communication I / F 405 is an interface for connecting to the network 600. The connection I / F 406 is an interface for communicating with the operation unit 500 via the communication path 302.

  The engine unit 407 is hardware that performs processing other than general-purpose information processing and communication for realizing a copy function, a scanner function, a fax function, and a printer function. For example, a scanner (image reading unit) that scans and reads an image of a document, a plotter (image forming unit) that performs printing on a sheet material such as paper, and a fax unit that performs fax communication are provided. Furthermore, options such as a finisher for sorting printed sheet materials and an ADF (automatic document feeder) for automatically feeding a document can be provided.

  Next, the hardware configuration of the operation unit 500 will be described. As illustrated in FIG. 3, the operation unit 500 includes a CPU 501, a ROM 502, a RAM 503, a flash memory 504, a communication interface (I / F) 505, a connection interface (I / F) 506, and an operation panel 507. And an external connection interface (I / F) 508, which are connected to each other via a system bus 509.

  The CPU 501 comprehensively controls the operation of the operation unit 500. The ROM 502 is a read-only nonvolatile storage medium and stores a program such as firmware. The RAM 503 is a volatile storage medium capable of reading and writing information at high speed, and is used as a work area when the CPU 501 processes information. The flash memory 504 is a nonvolatile storage medium that can read and write information, and stores an OS, various control programs, application programs, and the like. The CPU 501 controls the overall operation of the operation unit 500 by executing a program stored in the ROM 502 or the flash memory 504 using the RAM 503 as a work area (work area), and receives information (images) according to the input received from the user. Various functions described later such as display of) are realized. The flash memory 504 stores, for example, various settings for the image forming apparatus 300, user information and device information described later, and the like.

  The communication I / F 505 is an interface for connecting to the network 600. The connection I / F 506 is an interface for communicating with the main body 400 via the communication path 302.

  The operation panel 507 accepts various inputs in accordance with user operations and various types of information (for example, information in accordance with accepted operations, information indicating the operation status of the image forming apparatus 300, information indicating setting status, and the like). Is a user interface for displaying In this example, the operation panel 507 is configured by a liquid crystal display device (LCD) having a touch panel function, but is not limited thereto. For example, an organic EL display device equipped with a touch panel function may be used. The external connection I / F 508 is an interface for connecting peripheral devices, for example.

  Next, functions of the operation unit 500 will be described. FIG. 4 is a functional block diagram illustrating an overview of functions that the operation unit 500 has. As illustrated in FIG. 4, the CPU 501 of the operation unit 500 executes a program stored in the ROM 502 or the flash memory 504 using the RAM 503 as a work area (work area), for example, the input unit 50, the display unit 51, and the reception The unit 52, the transmission unit 53, the storage unit 56, and the machine learning unit 57 are realized.

  The input unit 50 receives various inputs according to user operations via the operation panel 507. For example, the input unit 50 acquires applicability information indicating whether or not the user has refused to apply setting information (described later) displayed by the display unit 51.

  The display unit 51 outputs the setting information indicating the print setting estimated by the machine learning unit 57 described later on the operation panel 507. For example, the display unit 51 performs an output to display a print setting change dialog that allows the user to select whether or not to change a print setting recommended by a machine learning unit 57 described later.

  The receiving unit 52 receives information transmitted from the PC 150 or the server 200. For example, the receiving unit 52 receives a print job together with user information corresponding to the user via the communication I / F 505 (or the communication path 302). The transmission unit 53 transmits information to the PC 150 or the server 200 via the communication I / F 505 (or the communication path 302).

  Note that the input unit 50 and the reception unit 52 constitute an acquisition unit 54 that acquires information from outside the operation unit 500. In addition, the display unit 51 and the transmission unit 53 constitute an output unit 55 that outputs information from the operation unit 500 to the outside.

  The storage unit 56 stores, for example, user information received via the receiving unit 52 (or the communication path 302), print data of a print job, print settings, and the like in the flash memory 504. In addition, the storage unit 56 indicates whether or not the user has actually applied the print settings recommended by the machine learning unit 57 described later to the flash memory 504 to the print job (see FIG. 9). Remember. For example, the storage unit 56 stores the applicability information acquired by the acquisition unit 54 described above in the flash memory 504. Here, information indicating the contents of the rejection history is used as applicability information. Note that the print settings recommended by the machine learning unit 57 are hereinafter referred to as recommended settings. In addition, information indicating the content of recommended settings is described as setting information.

  The machine learning unit 57 learns a method (model) for estimating a recommended print setting (calculating a recommended setting) for a new print job based on the print data and print settings of the print job received by the receiving unit 52. To do. Then, the machine learning unit 57 estimates a print setting recommended for the print job newly received by the receiving unit 52 (calculates a recommended setting). The machine learning performed by the machine learning unit 57 is realized using a known technique (method) such as support vector machine (SVM), clustering, neural network, or decision tree learning. For example, the machine learning unit 57 extracts an analysis target from the print data and the print setting, performs an analysis including calculation of a feature amount of the analysis target, and estimates a recommended print setting by using a classifier using an SVM algorithm. To do.

  The machine learning unit 57 may estimate print settings for each of a plurality of items, or may estimate a plurality of contents (set values) for each item. For example, the machine learning unit 57 may be configured to estimate the print settings for each of a plurality of items such as color settings, print surface, and aggregate settings, or 2 in 1 for one item such as the aggregate settings. A plurality of contents (set values) such as 4in1 may be estimated. When estimating a plurality of items or a plurality of set values, the machine learning unit 57 extracts, for example, an analysis target based on applicability information that indicates whether the user individually rejects each of the items stored in the flash memory 504. And perform analysis. Further, when estimating a plurality of items or a plurality of set values, the machine learning unit 57 ranks each estimation. In addition, the machine learning unit 57 may be partially or entirely configured by hardware including an ASIC, FPGA, and circuit elements.

  Next, an operation example of the operation unit 500 will be described. FIG. 5 is a flowchart illustrating an operation example of the operation unit 500 when the print setting is recommended to the user. As shown in FIG. 5, in the operation unit 500, when the receiving unit 52 receives a print job (S100), the storage unit 56 stores the print settings and print data included in the print job in the flash memory 504 (S102).

  Next, the machine learning unit 57 sets recommended print settings for the new print job based on the learning result using the print data and print settings of the print job stored in the flash memory 504 by the storage unit 56. Estimation (calculation of recommended settings) is performed (S104).

  Then, the machine learning unit 57 determines whether or not the user has rejected the calculated recommended setting (recommended print setting) based on the applicability information stored in the flash memory 504 by the storage unit 56. (S106). When the machine learning unit 57 determines that the recommended setting has been rejected by the user at the extraction stage of the analysis target (S106: Yes), the operation unit 500 ends the process. If the machine learning unit 57 determines that the user has not rejected the recommended setting (S106: No), the operation unit 500 proceeds to the process of S108.

  The display unit 51 displays a print setting change dialog based on setting information indicating the print setting estimated by the machine learning unit 57 on the operation panel 507 (S108). The print setting change dialog may be displayed by the PC 150. Thereafter, the storage unit 56 stores the print setting (selection result) selected by the user with reference to the print setting change dialog in the flash memory 504 (S110).

  Next, specific processing in the operation example of the operation unit 500 illustrated in FIG. 5 will be described. FIG. 6 is a diagram showing a specific example of information stored in the flash memory 504 by the storage unit 56 for use in the process of S104 (calculation of recommended settings) shown in FIG. For example, the information illustrated in FIG. 6 is information stored in the flash memory 504 regarding jobs from all users in the information processing system 100.

  Here, it is assumed that user A first transmits a print job as shown in FIG. The machine learning unit 57 uses the information stored in the flash memory 504 by the storage unit 56 to calculate a recommended setting. FIG. 8 is a diagram illustrating recommended settings calculated by the machine learning unit 57. The machine learning unit 57 determines whether or not the combination of the calculated recommended setting and the print setting / print data has been rejected by the user A based on the applicability information stored in the flash memory 504. Then, the machine learning unit 57 estimates a recommended print setting based on the applicability information.

  FIG. 9 is a diagram illustrating recommended settings calculated by the machine learning unit 57 for the user A and stored in the flash memory 504 by the storage unit 56. When the machine learning unit 57 determines that the user A has not rejected the recommended setting of FIG. 8 using the example of the rejection history shown in FIG. 9, the display unit 51 displays the recommended setting estimated by the machine learning unit 57. A print setting change dialog corresponding to the accepted and accepted recommended settings is generated and displayed on the operation panel 507.

  FIG. 10 is a diagram illustrating a print setting change dialog displayed on the display unit 51. After viewing the print setting change dialog displayed on the operation panel 507 by the display unit 51, the user A selects print settings using the input unit 50 via the operation panel 507. The storage unit 56 stores the print setting selected by the user A in the flash memory 504 for each user. For example, when the user A selects “No” in the print setting change dialog, the machine learning unit 57 changes the refusal history to “Yes” as the applicability information for the user A. In this case, the operation unit 500 does not recommend to the user A the recommended setting in which the rejection history for the user A is changed to “Yes”. That is, since the storage unit 56 stores applicability information for each user in the flash memory 504, the machine learning unit 57 does not recommend the recommended setting rejected by the user A to the user A, but recommends it to the user B. . However, the machine learning unit 57 may be configured to arbitrarily switch the application range of the refusal history data used for a specific user.

  FIG. 11 is a diagram illustrating a print setting change dialog when there are a plurality of recommended setting items. As shown in FIG. 11, when there are a plurality of recommended setting items, the machine learning unit 57 selects the item that the user wants to set according to the result selected by the input unit 50 via the operation panel 507. Change only the print settings at once. For example, when there are a plurality of recommended setting items, the display unit 51 performs a display that is not rejected by the user and recommended from the higher priority order.

  Further, the machine learning unit 57 switches whether to learn only a specific user's history or all user's history with a predetermined threshold. For example, the machine learning unit 57 learns from the history of all users if the history of a specific user is less than a certain number, and learns only from the history of a specific user if the history of a specific user is greater than a certain number Calculate the recommended setting based on the result.

  Next, another example of the operation learned by the machine learning unit 57 will be described. FIG. 12 is a diagram illustrating a first modification of information (data) learned by the machine learning unit 57 and stored in the flash memory 504 by the storage unit 56. As shown in FIG. 12, when the machine learning unit 57 learns the number of pages and the presence / absence of stapling, the storage unit 56 stores a setting history on whether or not to staple according to the number of pages in the flash memory 504 for each job. To do. The machine learning unit 57 learns from the setting history stored in the flash memory 504 by the storage unit 56 and estimates a recommended setting.

  FIG. 13 is a diagram illustrating a second modification of information (data) learned by the machine learning unit 57 and stored in the flash memory 504 by the storage unit 56. As shown in FIG. 13, when the machine learning unit 57 learns the number of pages and the aggregation setting, the storage unit 56 stores a setting history indicating how to aggregate according to the number of pages in the flash memory 504 for each job. Remember. The machine learning unit 57 learns from the setting history stored in the flash memory 504 by the storage unit 56 and estimates a recommended setting.

  FIG. 14 is a diagram showing a third modification of information (data) learned by the machine learning unit 57 and stored in the flash memory 504 by the storage unit 56. As shown in FIG. 14, when the machine learning unit 57 learns the setting of the number of pages and the printing surface, the storage unit 56 stores a setting history indicating how the printing surface is set according to the number of pages for each job. Stored in the flash memory 504. The machine learning unit 57 learns from the setting history stored in the flash memory 504 by the storage unit 56 and estimates a recommended setting.

  FIG. 15 is a diagram illustrating a fourth modification of information (data) learned by the machine learning unit 57 and stored in the flash memory 504 by the storage unit 56. As shown in FIG. 15, when the machine learning unit 57 learns the average character size and aggregation setting of the printed material, the storage unit 56 stores a setting history indicating how the aggregation is performed according to the average character size for each job. Store in the flash memory 504. The machine learning unit 57 learns from the setting history stored in the flash memory 504 by the storage unit 56 and estimates a recommended setting.

  FIG. 16 is a diagram illustrating a fifth modification of information (data) learned by the machine learning unit 57 and stored in the flash memory 504 by the storage unit 56. As shown in FIG. 16, when the machine learning unit 57 learns the average character size and the print surface of the printed material, the storage unit 56 stores a setting history indicating how the print surface is set according to the average character size. Each job is stored in the flash memory 504. The machine learning unit 57 learns from the setting history stored in the flash memory 504 by the storage unit 56 and estimates a recommended setting.

  FIG. 17 is a diagram illustrating a sixth modification of information (data) learned by the machine learning unit 57 and stored in the flash memory 504 by the storage unit 56. As shown in FIG. 17, when the machine learning unit 57 learns the number of pages, the user's age, and the aggregation setting, the storage unit 56 shows how to aggregate according to the number of pages and the user's age. Are stored in the flash memory 504 for each job. The machine learning unit 57 learns from the setting history stored in the flash memory 504 by the storage unit 56 and estimates a recommended setting.

  FIG. 18 is a diagram illustrating a seventh modification of information (data) learned by the machine learning unit 57 and stored in the flash memory 504 by the storage unit 56. As shown in FIG. 18, when the machine learning unit 57 learns the color ratio of print data (the ratio of black-and-white images and color images) and color setting, how the storage unit 56 performs color setting according to the color ratio. A setting history indicating whether or not the data is stored in the flash memory 504 for each job. The machine learning unit 57 learns from the setting history stored in the flash memory 504 by the storage unit 56 and estimates a recommended setting.

  Note that when the device administrator acquires applicability information indicating that the recommended setting is rejected, the operation unit 500 sets the rejection history to “Yes” for all users. That is, when the acquisition unit 54 acquires applicability information indicating that a predetermined user has refused to apply the setting information displayed on the operation panel 507 by the display unit 51, the machine learning unit 57 receives the applicability information. Is considered to indicate that all users have refused to apply the setting information. Therefore, when there is a recommended setting that the device administrator does not want to use for general users, it is possible to set the recommended setting that is not desired to be used in a lump.

  As described above, when the acquisition unit 54 acquires the applicability information, the information processing system 100 further learns and receives the print data and print settings of the print job received by the reception unit 52 based on the applicability information. Since the print setting recommended by the unit 52 for the newly received print job is estimated, the accuracy of recommending the setting desired by the user can be improved.

[Modification]
Next, a modification of the information processing system 100 configured so that the server 200 performs machine learning will be described. Here, a configuration in which the server 200 is configured to perform machine learning will be described as a modified example. FIG. 19 shows a modification of the information processing system 100 configured so that the server 200 performs machine learning. The operation unit 500 and the server 200 perform recommendations for print settings that avoid setting recommendations that the user does not want. It is a functional block diagram which illustrates the function which has.

  As shown in FIG. 19, in a modification of the information processing system 100, the CPU 501 of the operation unit 500 executes a program stored in the ROM 502 or the flash memory 504 with the RAM 503 as a work area (work area). For example, the input unit 50, the display unit 51, the reception unit 52, the transmission unit 53, and the storage unit 56 are realized. Note that among the modifications of the information processing system 100 illustrated in FIG. 19, components that are substantially the same as the components of the information processing system 100 illustrated in FIG. 4 are denoted by the same reference numerals and description thereof is omitted.

  Note that the input unit 50 and the reception unit 52 constitute an acquisition unit 54 that acquires information from outside the operation unit 500. In addition, the display unit 51 and the transmission unit 53 constitute an output unit 55 that outputs information from the operation unit 500 to the outside.

  In the modification of the information processing system 100, the CPU 201 of the server 200 executes a program stored in the ROM 202 or the HDD 204 with the RAM 203 as a work area (working area), so that the control unit 21, the storage unit 22, The 2nd receiving part 23, the 2nd transmission part 24, and the machine learning part 25 are implement | achieved. The control unit 21 controls each unit constituting the server 200.

  The second receiving unit 23 receives user information, print data of the print job, print settings, applicability information, and the like transmitted by the operation unit 500 via the communication I / F 205. The storage unit 22 stores print data, print settings, and the like of the print job in the HDD 204.

  In addition, the storage unit 22 associates with the user information applicability information indicating whether or not the user has actually applied the print settings recommended by the machine learning unit 25 described later to the print job (see FIG. 9). Remember. Such applicability information is acquired via the acquisition unit 54 of the operation unit 500 and transmitted to the server 200 via the output unit 55 of the operation unit 500.

  The second transmission unit 24 transmits the result estimated by the machine learning unit 25 (described later) to the operation unit 500 via the communication I / F 205.

  The machine learning unit 25 recommends print settings (a plurality of items or a plurality of setting values) for a new print job based on the print data, print settings, and applicability information already stored in the HDD 204. In the learning, for example, based on applicability information indicating whether or not the user has rejected the recommendation of a plurality of items or a plurality of setting values, extraction of an analysis target is performed. And perform analysis. Then, the machine learning unit 25 uses a method (model) that is a learning result to recommend a print setting that avoids a setting that is not desired by the user. That is, the machine learning unit 25 has substantially the same function as the machine learning unit 57 described above.

  Next, the operation of a modified example of the information processing system 100 will be described. FIG. 20 is a sequence diagram illustrating an operation of a modified example of the information processing system 100 in a case where print settings are recommended to the user.

  First, when a print job is input and registered by the user in the operation unit 500 (S200), the transmission unit 53 of the operation unit 500 transmits user information, print settings included in the print job, and print data to the server 200. (S202, S204).

  The server 200 operates the machine learning unit 25 to estimate print settings (a plurality of items or a plurality of setting values) recommended for a new print job based on the print settings and the print data, and the recommended The setting (recommended print setting) is recommended by operating the second transmission unit 24 on the condition that the setting has never been rejected by the user based on the applicability information stored in the HDD 204 (S206). The setting (recommended print setting) is transmitted to the operation unit 500 as an estimation result (S208).

  The display unit 51 of the operation unit 500 receives the setting information indicating the print setting estimated by the machine learning unit 25 of the server 200 by the receiving unit 52 and displays a print setting change dialog based on the print setting on the operation panel 507 ( S210).

  As described above, a method (model) for estimating print settings (a plurality of items or a plurality of setting values) recommended for the print job based on the print data and print settings of the new print job is learned, and the During learning, an analysis target is extracted and analyzed based on applicability information indicating whether or not the user has rejected the recommendation of a plurality of items or a plurality of set values. Accordingly, it is possible to recommend print settings that avoid setting recommendations that the user does not want using a method (model) that is a learning result.

  The program executed in the information processing system 100 of the above-described embodiment is a file in an installable format or an executable format, and is a CD-ROM, a flexible disk (FD), a CD-R, a DVD (Digital Versatile Disk). It may be configured to be recorded and provided on a computer-readable recording medium such as USB (Universal Serial Bus), or may be configured to be provided or distributed via a network such as the Internet. Further, various programs may be provided by being incorporated in advance in a nonvolatile recording medium such as a ROM.

DESCRIPTION OF SYMBOLS 50 Input part 51 Display part 52 Reception part 53 Transmission part 54 Acquisition part 55 Output part 56 Storage part 57 Machine learning part 100 Information processing system 150 PC
200 Server 300 Image Forming Apparatus 400 Main Body 500 Operation Unit 600 Network

Japanese Patent Laying-Open No. 2015-150707

Claims (10)

A receiving unit for receiving a print job together with user information corresponding to the user;
A machine learning unit that learns print data and print settings of a print job received by the receiving unit, and that estimates a recommended print setting for a print job newly received by the receiving unit based on a learning result;
An output unit that outputs setting information indicating print settings estimated by the machine learning unit;
An acquisition unit for acquiring applicability information indicating whether the user has refused to apply the setting information output by the output unit;
Have
The machine learning unit
When the acquisition unit acquires applicability information, the print data and print settings of the print job received by the receiving unit are further learned based on the applicability information, and the newly received print job is received by the receiving unit. An information processing apparatus characterized by estimating a recommended print setting. The output unit is
Output by sending or displaying the setting information,
The acquisition unit
The information processing apparatus according to claim 1, wherein the applicability information is received or acquired by an input from a user. The machine learning unit
The information processing apparatus according to claim 1, wherein a print setting including at least one of a plurality of setting items and a plurality of setting values for the setting items is learned. 4. The storage device according to claim 1, further comprising: a storage unit that stores print data and print settings of a print job received by the reception unit, and applicability information acquired by the acquisition unit. 5. Information processing device. The storage unit
Storing print data and print settings of a print job received by the receiving unit, and applicability information acquired by the acquiring unit for each user;
The machine learning unit
When the number of print data, print settings, and applicability information stored in the storage unit for each user is smaller than a predetermined number, based on the print data, print settings, and applicability information for all users Estimating recommended print settings for a print job newly received by the receiving unit, and the number of print data, print settings, and applicability information stored in the storage unit for each user is greater than a predetermined number In this case, the reception unit estimates a recommended print setting for a newly received print job based on print data, print setting, and applicability information for each user. 5. The information processing apparatus according to 4. The machine learning unit
A combination of the number of pages of the print job received by the receiving unit and at least one of the stapling presence / absence setting, the aggregation setting, and the printing surface setting, or the average character size of the print job received by the receiving unit, and the aggregation setting The information processing apparatus according to claim 1, wherein a combination with at least one of printing surface setting and printing surface setting is learned. The machine learning unit
The ratio of black and white images and color images included in the print data of the print job received by the receiving unit is learned, and the recommended print setting for the newly received print job is estimated based on the learning result The information processing apparatus according to claim 1, wherein the information processing apparatus is an information processing apparatus. The machine learning unit
When the acquisition unit acquires applicability information indicating that a predetermined user has rejected application of the setting information output from the output unit, the applicability information indicates that all users have rejected application of the setting information. The information processing apparatus according to any one of claims 1 to 7, wherein the information processing apparatus is regarded as indicating. An information processing system in which an information processing apparatus that receives a print job together with user information corresponding to a user and a server can transmit and receive information to and from each other,
A machine learning unit that learns the print data and print settings of the received print job and estimates a recommended print setting for the newly received print job based on the learning result;
An output unit that outputs setting information indicating print settings estimated by the machine learning unit;
An acquisition unit for acquiring applicability information indicating whether the user has refused to apply the setting information output by the output unit;
Have
The machine learning unit
When the acquisition unit acquires applicability information, it further learns print data and print settings of the received print job based on the applicability information, and estimates a recommended print setting for the newly received print job An information processing system characterized by Receiving a print job together with user information corresponding to the user;
Learning print data and print settings of the received print job, and estimating recommended print settings for the newly received print job based on the learning result;
Outputting setting information indicating the estimated print setting;
Obtaining applicability information indicating whether the user has refused to apply the output setting information; and
Further learning the print data and print settings of the received print job based on the acquired applicability information, and estimating a recommended print setting for the newly received print job;
An information processing method including:

Images