JP2019077116A - Information processing device, information processing method, and program - Google Patents

Abstract

To set appropriate print setting values for an electronic document to be newly printed on the basis of print setting values for an electronic document that was printed in the past.SOLUTION: An information processing device according an embodiment of this invention includes: print setting value group identification means for identifying a print setting value group corresponding to print setting values for a printed document for each of a plurality of printed documents from print setting value groups formed according to combination of print setting values; a print setting value group determination means for determining a print setting value group for a new print document from a feature amount of a printed document of the identified print setting value group and a feature amount of the new print document; and setting means for setting the print setting values of the print setting value group of the new print document for the new print document.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an information processing apparatus capable of executing print processing, an information processing method, and a program.

  Conventionally, when printing an electronic document with a printer or a multifunction peripheral, there are cases where an operation rule is applied that applies and prints a specific print setting to a specific type of electronic document. For example, operating rules such as “A certain application must be printed on both sides of A4 size paper” and “A certain specification must be printed on both sides of A4 size paper and N-up” are defined by company regulations. May be N-up is a type of allocation printing, and is a print setting in which N pages in an electronic document are laid out and printed on one side of a printing sheet.

  However, if the print setting is defined only as the operation rule, for example, the user who executes printing does not recognize the operation rule or forgets the operation rule itself, the print setting Printing may occur without being applied. In such a case, it is necessary to apply the correct print settings and print again, which causes problems such as a delay in a workflow using printed matter and waste of paper.

  On the other hand, there is a method of setting a print setting value having high correlation to the feature amount of the electronic document to be newly printed based on the print setting value of the electronic document printed in the past. For example, in the technology described in Patent Document 1, first, cluster classification is performed based on the similarity of the feature amounts of the electronic document printed in the past, and the print setting value most frequently used in the electronic document of each cluster is determined . Then, a cluster to which the electronic document to be newly printed belongs is obtained, and the print setting value of the cluster is set for the new electronic document to be printed.

JP, 2015-202667, A

  In the patent document 1, an electronic document having a high degree of similarity of feature amounts is classified into the same cluster, and the print setting value most frequently used in the electronic document classified into the cluster is adopted as the print setting value of the cluster. Be done. Therefore, for example, an electronic document similar in format is likely to be classified into the same cluster as an electronic document having a high degree of similarity of feature amounts, and a single print setting value is adopted as a print setting value of the cluster. . However, even an electronic document having a similar format may have to be printed with different print settings, and in the technique described in Patent Document 1, in such a case, the electronic document to be newly printed may be printed. In some cases, it was not possible to set appropriate print settings.

  The present invention has been made in view of such problems, and the purpose of the present invention is more appropriate for an electronic document to be newly printed based on print setting values of the electronic document printed in the past. In setting print setting values.

  The information processing apparatus according to an embodiment of the present invention specifies a print setting value group corresponding to the print setting value of the printed document for each of the plurality of printed documents from the print setting value group by the combination of the print setting values. Print setting in which the print setting value group of the new print document is determined by the print setting value group specifying unit, the feature amount of the printed document of the specified print setting value group, and the feature amount of the new print document The information processing apparatus is characterized by comprising value group determination means, and setting means for setting a print setting value of a print setting value group of the new print document to the new print document.

  According to the present invention, it is possible to set more appropriate print setting values for the newly printed electronic document based on the print setting values of the electronic document printed in the past.

It is a figure which shows the hardware constitutions of the information processing apparatus in one Embodiment of this invention. It is a figure which shows the functional block of the information processing apparatus in one Embodiment of this invention. It is a flow chart of group classification rule generation processing in one embodiment of the present invention. FIG. 6 is a diagram showing an example of a print setting value group in the embodiment of the present invention. It is a figure which shows the example of the printing setting value group classification | category result in one Embodiment of this invention. FIG. 7 is a diagram showing an example of a drawing command included in PDL data according to an embodiment of the present invention. FIG. 8 is a diagram showing an example of drawing identifiers in all printed documents and the number of drawing identifiers and the appearance probability in a specific print setting value group in one embodiment of the present invention. 5 is a flowchart of print setting processing according to an embodiment of the present invention. It is a flow chart of group classification rule generation processing in one embodiment of the present invention.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The following embodiments do not limit the invention according to the claims. Further, not all combinations of features described in the following embodiments are necessarily essential to the present invention.

First Embodiment
(Hardware configuration)
FIG. 1 is a diagram illustrating an example of a hardware configuration of an information processing apparatus in the present embodiment.

  A printer 100 shown in FIG. 1 is an information processing apparatus in the present embodiment. The present embodiment is also applicable to devices other than the printer 100. Also, the present embodiment can be applied to any print data classification device that classifies print data (i.e., electronic documents).

  In the printer 100, the controller unit 120 controls input and output of image signals and device information. The CPU 101 centrally controls the devices connected to the system bus 105 in the controller unit 120. Specifically, the CPU 101 reads the control program stored in the ROM 103 or the HDD 104 into the RAM 102 and executes it.

  A RAM 102 is a main memory of the CPU 101, and is used as a work area when the CPU 101 executes a control program. The ROM 103 stores in advance a boot program to be executed when the printer 100 is powered on. The HDD 104 stores an operating system and a control program main body in advance. The HDD 104 is also used to temporarily or long-term hold large-capacity data such as bitmap images and print data.

  A network I / F 106 is connected to a network 113 such as a local area network to input and output print data and device information.

  The operation unit I / F 107 is an interface unit with the operation unit 114, and outputs bit map data displayed on the operation unit 114 to the operation unit 114. The operation unit I / F 107 also transmits information input by the user from the operation unit 114 to the CPU 101. The operation unit 114 includes a display such as a liquid crystal panel as an output device and a sound source, and includes a touch panel or a hard key as an input device.

  The controller unit 120 is connected to the printer engine 115 via the device I / F 108. The device I / F 108 sends an image signal, instructs a device operation, receives device information, and the like based on an instruction from the CPU 101.

  The printer engine 115 is an output device that outputs an image signal from the controller unit 120 onto a medium such as paper. The printer engine 115 can output an image signal by any method such as an electrophotographic method or an inkjet method.

  A RIP (Raster Image Processor) 109 is dedicated hardware for expanding a display list (DL) into a bitmap image. The DL is an intermediate data generated by interpreting print data, and is generated on the RAM 102 by the CPU 101. The RIP 109 processes the DL generated on the RAM 102 at high speed and in parallel with the execution of the CPU 101.

  The printer image processing unit 110 performs image correction, halftoning and the like on image data to be printed. The image rotation unit 112 rotates image data. The image compression and expansion unit 111 performs compression and expansion processing of image data. The image compression / decompression unit 111 performs JPEG compression / decompression processing on multi-level image data, and performs compression / decompression processing such as JBIG, MMR, or MH on binary image data.

(Functional configuration)
FIG. 2 is a diagram showing functional blocks of the information processing apparatus in the present embodiment.

  A printer 100, which is an information processing apparatus, includes a data receiving unit 201, a PDL interpreter 202, a renderer 203, a user interface 204, a job control unit 205, and a print driver 206. The printer 100 further includes a feature extraction unit 207, a group determination unit 208, a group classification processing unit 209, a job data storage unit 210, a group classification rule storage unit 211, and a group definition unit 212.

  A program for realizing the above-described processing units included in the printer 100 is stored in advance in the HDD 104, loaded into the RAM 102, and then executed by the CPU 101. More specifically, this program is loaded into the RAM 102 by the OS (Operating System) executed by the CPU 101, is given an execution right in units of threads, and is executed.

  The data receiving unit 201 receives print data transmitted from a host computer, a server, or a client device such as a PC (all not shown). In the present embodiment, print data is PDL data described in page description language (PDL). The received print data is held by the job data storage unit 210 via the job control unit 205. At this time, print setting values of print data are also stored in association with each other. The job control unit 205 is responsible for overall job control from data reception to printing.

  The PDL interpreter 202 interprets the PDL data to generate a DL, which is intermediate data. The generated DL is held by the job data storage unit 210 via the job control unit 205. The renderer 203 generates a bitmap image from the DL. A lot of processing by the renderer 203 is executed by the RIP 109 which is dedicated hardware. The generated bitmap image is stored in the job data storage unit 210 via the job control unit 205.

  The print driver 206 sends a print instruction and a bitmap image to the printer engine 115 via the device I / F 108. At this time, the print driver 206 also performs image correction by the printer image processing unit 110.

  The user interface 204 controls the operation unit 114 via the operation unit I / F 107. The user interface 204 generates data to be displayed on the display (for example, a liquid crystal panel) of the operation unit 114, and updates the display on the display in accordance with an input from a touch panel or a hard key. Further, when the input from the operation unit 114 is any job execution instruction, the user interface 204 transmits the job execution instruction to the job control unit 205.

  The feature amount extraction unit 207 analyzes PDL data to extract a feature amount. The extracted feature amount is stored in the job data storage unit 210 via the job control unit 205.

  The group determination unit 208 determines the print setting value group of the PDL data according to the feature amount of the PDL data and the group classification rule stored in the group classification rule storage unit 211 according to the instruction of the job control unit 205. Furthermore, the print setting values defined in the determined print setting value group are acquired from the group definition unit 212, and are passed to the job control unit 205. Details of the process will be described later.

  The group classification processing unit 209 determines a rule for determining a print setting value group to which the PDL data belongs based on the feature amount of the PDL data stored in the job data storage unit 210 and the print setting value stored in association therewith. Generate This rule is called a group classification rule. That is, the group classification rule by the feature amount is generated such that the PDL data is classified into the print setting value group having the same print setting value defined by the group definition unit 212. The group classification rule generated by the group classification processing unit 209 is stored in the group classification rule storage unit 211. Details of the process will be described later.

  The job data storage unit 210 temporarily or long-term holds each of the print data (PDL data), the print setting value, the DL, the bit map image, and the feature amount. That is, the job data storage unit 210 holds data related to the print job.

  The group classification rule storage unit 211 stores the group classification rule generated by the group classification processing unit 209.

  The group definition unit 212 stores print setting value group definition information. The definition information of the print setting value group is information determined by a combination of a plurality of print setting values. The definition information of the print setting value group may be extracted from the print setting values associated with the PDL data stored in the job data storage unit 210 by the group classification processing unit 209, or may be defined in advance by the user. It is also good. Further, the definition information of the print setting value group stored in the group definition unit 212 may be changed by the user.

  In the present embodiment, the group classification processing unit 209 classifies each printed document for each print setting value group based on the print setting values of the printed electronic document (hereinafter, also referred to as a printed document). Further, the group classification processing unit 209 generates a group classification rule for each print setting value group based on the feature amount of the printed document classified into the same print setting value group. This means that the difference between feature quantities of an electronic document printed with the same print setting value and an electronic document printed with another print setting value is obtained. Furthermore, when the group determination unit 208 receives an electronic document to be newly printed (hereinafter, also referred to as a print document), the print document is determined from the feature amount of the print document based on the generated group classification rule. Determine whether it belongs to the print setting value group. After determining the print setting value group to which the received print document belongs, the group determination unit 208 acquires a combination of print setting values defined in the print setting value group, and passes the combination to the job control unit 205. The job control unit 205 sets the combination of the received print setting values as the print setting for the print document.

  As described above, the information processing apparatus according to the present embodiment uses the group classification rule for classifying the newly received print document into the print setting value group from the feature amounts of the printed document grouped into each print setting value. I ask for it. By doing this, the information processing apparatus according to the present embodiment can determine which print setting value group the print document belongs to, using the newly received feature quantity of the print document, and the past printing It is possible to set print setting values in line with the example of the completed document.

  The processing by the information processing apparatus according to the present embodiment includes group classification rule generation processing for generating a classification rule of a print setting value group, and print setting processing for performing print setting by applying the group classification rule to the received print document. And two processes. Each process will be described in order below.

(Group classification rule generation process)
FIG. 3 shows a flowchart of group classification rule generation processing in the present embodiment. Each step in the flowchart is implemented by the CPU 101 executing a program stored in the HDD 104.

  First, in step S301, the group classification processing unit 209 determines whether the definition of the print setting value group is stored in the group definition unit 212. The print setting value group is a combination of print setting values such as double-sided printing setting, color mode setting, N-up setting, etc., as one group. If it is determined that the definition of the print setting value group is saved, the process proceeds to step S304. On the other hand, if it is determined that the definition of the print setting value group is not saved, the process proceeds to step S302.

  In step S302, the group classification processing unit 209 defines a print setting value group. Specifically, the group classification processing unit 209 extracts a print setting value different for each document from the print setting values in the past printed document stored in the job data storage unit 210, and is a combination of the print setting values. Define print setting groups. That is, the group classification processing unit 209 functions as print setting value group definition means. The print setting value group may be previously defined by the user based on a combination of print setting values.

  FIG. 4 shows an example of a print setting value group in the present embodiment. Group IDs 001 to 012 represent IDs for identifying each print setting value group. Each print setting value group defines a combination of three types of print setting values: duplex printing setting, color mode setting, and N-up setting. For example, the print setting value group identified by the group ID 001 is defined as a group indicating a combination of print setting values in which the duplex setting is On, the color mode setting is monochrome, and the N-up setting is 1 in 1. The print setting value group may be defined as a combination including other types of print setting values, or may be defined as a combination of fewer types of print setting values. Here, in order to simplify the description, the duplex setting is binary of On and Off, the color mode setting is monochrome, binary of color, and the N-up setting is a combination of three values of 1in1, 2in1, and 4in1. A total of 12 print setting value groups are defined. Each print setting may include other settings, in which case it may be added to the print settings group definition.

  In step S303, the group classification processing unit 209 stores the defined print setting value group in the group definition unit 212.

  Next, in step S304, the group classification processing unit 209 determines whether the job data storage unit 210 has a predetermined number or more of printed documents. This is to learn a feature amount of the document for each print setting based on what print setting the past printed document has been printed to generate a group classification rule. When the number of printed documents is small, it depends largely on noise and feature amounts having an accidental deviation, and it is not possible to correctly generate a group classification rule. Therefore, if it is determined that there are no more than a predetermined number of printed documents, the process ends. On the other hand, if it is determined that a predetermined number or more of printed documents exist, the process proceeds to step S305.

  In step S305, the group classification processing unit 209 specifies, for all printed documents, print setting value groups corresponding to combinations of print setting values of the printed documents. Specifically, the group classification processing unit 209 takes out the print setting value of the printed document stored in the job data storage unit 210, and compares it with the print setting value group stored in the group definition unit 212. The group classification processing unit 209 determines, from the print setting values of the printed document and the definition of the print setting value group, to which print setting value group each of the plurality of printed documents belongs. In the case of the print setting value group definition shown in FIG. 4, assuming that the duplex setting is On, the color mode is monochrome, and the N-up setting is 1 in 1 in the print settings of a certain printed document, the printed document has group ID 001. It is determined to belong to the print setting value group of Thus, the group classification processing unit 209 specifies the print setting value group for all printed documents. That is, the group classification processing unit 209 functions as a print setting value group specifying unit.

  FIG. 5 shows an example of the result of specifying print setting value groups for all printed documents. This result indicates the number of printed documents classified for each print setting value group. In this example, there are a total of 100 printed documents. Among them, the number of printed documents classified into the print setting value group of group ID 001, that is, the number of documents printed with duplex setting On, color mode monochrome, and N-up setting 1 in 1, is ten. Similarly, the number of printed documents classified into the print setting value group of the group ID 002 is four, and the number of printed documents classified into the print setting value group of the group ID 003 is six. Here, in order to simplify the description, it is assumed that all printed documents are classified into any print setting value group. The group classification processing unit 209 also stores in which print setting value group each printed document is classified.

  Next, in step S306, the group classification processing unit 209 generates a group classification rule from the features of the printed document included in each print setting value group. That is, the group classification processing unit 209 functions as a group classification rule generation unit. The group classification processing unit 209 performs the group classification rule based on the feature amount of the printed document in each print setting value group so that the newly received print document is correctly classified into any of the print setting value groups. Generate This can be thought of as supervised group classification learning using printed documents of each print setting value group. Generally, supervised group classification methods include learning methods such as simple Bayes, decision trees, random forests, support vector machines, and neural networks. Although the present embodiment is described as performing group classification based on a simple Bayesian probability model that has relatively high classification accuracy and can be calculated at high speed, any learning method may be used.

  In classification learning based on a simple Bayesian probability model, when a document D is given, a group classification rule is generated by obtaining, from learning data, parameters of a calculation formula for obtaining a probability that the document D belongs to a specific group G. The probability P (G | D) that the document D belongs to a specific group G can be expressed as the following equation (1).

  In fact, although the equation (1) includes the product of a constant on the right side, the description is omitted because it can be ignored in comparing the magnitude relation of probability.

  Here, the appearance probability P (G) of the group G is obtained by the ratio of the document whose print setting of the printed document to be learned corresponds to the group G. Here, the appearance probability P (Mi | G) of the feature variable in the group G is assumed to be the appearance probability of the drawing identifier Mi of the PDL command in the printed document included in the group G. The appearance probability of the drawing identifier Mi is obtained by (number of drawing identifiers Mi in group G) / (number of all drawing identifiers in group G). In addition, the appearance probability of the drawing identifier Mi is actually calculated using Laplace smoothing, as shown in the equation (2) described later. Further, as described later, the drawing identifier Mi is a combination of the type of drawing command (drawing command) included in the PDL data, position information (approximate coordinates), and the number of point sequences, and the document according to the present embodiment It is treated as a feature of

  As described above, it is possible to obtain the probability that the document D belongs to a specific group G by treating the document D as a drawing identifier group in the PDL command and calculating the product of the probabilities of obtaining each drawing identifier.

  FIG. 6 shows an example of a drawing command (drawing command) included in PDL data. In the illustrated example, the drawing commands include DrawPath, DrawFillPath, DrawText, and DrawImage. DrawPath is a command for drawing a line segment connecting point sequences composed of coordinate arrays, and the color and line width of the line are specified as additional parameters. As coordinates, a pixel coordinate system whose origin is the upper left corner is used. DrawFillPath is a command for filling an area surrounded by a point sequence constituted by a coordinate array, and the color of the fill is specified as an additional parameter. DrawPath and DrawFillPath can also draw a curve by connecting line segments by point sequences finely. DrawText is a command for drawing a character string in a specified font, and (character) size, color, and drawing position are specified as additional parameters. DrawImage is a command for drawing a pixel data string in bitmap format, and the size (width, height) and the drawing position are specified as additional parameters.

  FIG. 7 shows an example of drawing identifiers in all printed documents, and the number and appearance probability of each drawing identifier included in a printed document belonging to a specific print setting value group. In the illustrated example, the number of drawing identifiers Mi included in the printed document belonging to the print setting value group (hereinafter also referred to as a print setting value group G001) having the group ID 001 described above and the appearance probability of each drawing identifier Mi P (Mi | G001) is shown. The feature amount of the printed document is expressed as multidimensional data, in which one drawing identifier is one dimension and the number of drawing identifiers is a value of that dimension. In the illustrated example, the drawing identifier “DrawPath — 100 — 80 — 2” having a drawing identifier ID of 1 indicates that there are two-point line drawing in the approximate coordinates (100, 80) by the DrawPath command. Further, it is shown that two drawing identifiers exist in the printed document belonging to the print setting value group G001. The drawing identifier “DrawText — 230 — 250 — 8” having a drawing identifier ID of 4 indicates that there is a text drawing of the character string length 8 at the approximate coordinates (230, 250) by the DrawText command. Also, it is shown that four drawing identifiers exist in the printed document belonging to the print setting value group G001. The drawing identifier "DrawImage_850_1200_2400_1200" having a drawing identifier ID of 5 indicates that there is an image drawing having a width: 2400 and a height: 1200 at the approximate position (850, 1200) by the DrawImage command. Further, it is shown that one drawing identifier exists in the print setting value group G001.

  In the example shown in FIG. 7, there are 724 types of drawing identifiers in all printed documents. Further, the number of drawing identifiers included in the printed document belonging to the print setting value group G001 is 285.

  In the extraction of the drawing identifier as described above, things which are not appropriate as information which clearly characterizes the document, such as noise, are removed in advance. For example, temporary comments or meaningless writing. In addition, since it is considered that a drawing identifier that appears with almost the same probability in all the documents is not necessary for the determination of the print setting group, such data is deleted. For example, when the page display is included in all the documents in approximately the same position with the same size, the drawing identifier of the PDL command for the page display is removed.

  The appearance probability P (Mi | G001) of the drawing identifier Mi in the print setting value group G001 can be calculated using the following equation (2).

  Here, the appearance probability P (Mi | G001) is calculated using Laplace smoothing so that the probability does not become zero even if the number of drawing identifiers Mi is zero. The total number of drawing identifiers in the print setting value group G001 is 285, and the number of drawing identifiers in all the printed documents is 724.

  Further, the appearance probability P (G 001) of the print setting value group G 001 is the total number of printed documents included in the print setting value group G 001 shown in FIG. It is obtained by dividing by the number of completed documents.

  In this way, it is possible to calculate all the parameters for obtaining the probability that the document D belongs to the print setting value group G001, as shown in the above equation (1). In the present embodiment, the calculated parameter is a group classification rule. That is, the determination of to which print setting value group the newly received print document belongs is performed using the above-mentioned parameters, as described later.

  Next, in step S307, the group classification processing unit 209 determines whether group classification rules have been generated for all print setting value groups. That is, the group classification processing unit 209 determines whether the appearance probability P (G) of the print setting value group G and the appearance probability P (Mi | G) of all the drawing identifiers Mi have been calculated for each print setting value group. Do. Although the example of the print setting value group G001 has been described with reference to FIG. 7, the appearance probability P (G) of the print setting value group and the appearance probability P of each drawing identifier in each group are similarly applied to other print setting value groups. Calculate (Mi | G). If the above parameters have not been calculated for all print setting value groups, the process of step S306 is repeated for print setting value groups that have not been calculated. On the other hand, if it is determined that the above parameters have been calculated for all print setting value groups, the process proceeds to step S308.

  In step S308, the group classification processing unit 209 stores the above-described parameters calculated for all print setting value groups in the group classification rule storage unit 211 as a group classification rule.

  As described above, in the present embodiment, the newly received print document is classified into the print setting value group based on the feature amount of the printed document (that is, the drawing identifier and the number thereof included in the printed document). Generate group classification rules.

  In this embodiment, the drawing identifier of the drawing command included in the PDL data is used as the feature amount of the document, but the text extracted from the PDL data is decomposed into word units by morphological analysis or the like, and the appearance frequency is divided into feature amounts It may be calculated as Further, as the feature amount of the document, not only the feature amount included in the document data but also the identifier of the user who has executed the printing of the document or the identifier indicating the time zone in which the printing of the document has been executed may be used. Furthermore, data not included in the document data itself but associated with the printing operation of the document may also be used, such as an identifier representing a device such as a host computer or server or a device such as a PC that has submitted the document to a printer.

  Further, the group classification rule generation process according to the flowchart shown in FIG. 3 may be periodically and repeatedly executed at predetermined time intervals, or may be executed each time one print process is completed.

(Print setting process)
FIG. 8 shows a flowchart of print setting processing in the present embodiment. The print setting process is performed on a print document newly submitted to the printer 100. Each step in the flowchart is implemented by the CPU 101 executing a program stored in the HDD 104.

  First, in step S801, the job control unit 205 receives a retention print document from a host computer, a server, or a client device such as a PC (all not shown). The retention print document is a print document to be subjected to retention print. The reservation printing is a function in which the printer 100 temporarily holds the print document received via the network in a storage medium, and executes printing in accordance with a print execution instruction from the operation unit by the user. The print execution instruction is transmitted to the job control unit 205 after the user interface 204 receives it. In the present embodiment, the data of the print document includes a job ticket storing PDL data and print settings.

  Next, in step S802, the job control unit 205 determines whether the group classification rule is stored in the group classification rule storage unit 211. If it is determined that the group classification rule has not been saved, the process ends. On the other hand, if it is determined that the group classification rule is stored, the process proceeds to step S803.

  In step S 803, the feature amount extraction unit 207 extracts the feature amount of the received print document (hereinafter, also referred to as a received document). In the present embodiment, the type and number of drawing identifiers based on the drawing command included in the PDL data are used as the feature quantities of the received document. Therefore, the feature quantity extraction unit 207 extracts the feature quantity of the received document in the same manner as the process in step S306 of the flowchart shown in FIG. More specifically, it counts how many drawing identifiers of drawing identifiers ID1 to 724 shown in FIG. 7 are included in the received document.

  Next, in step S804, the group determination unit 208 classifies the received document into which print setting value group based on the feature amount extracted from the received document and the group classification rule stored in the group classification rule storage unit 211. Determine if it will be. That is, the group determination unit 208 functions as a print setting value group determination unit that determines a print setting value group of a new print document. The group determination unit 208 uses the appearance probability P (Mi | G) of the drawing identifier Mi in each print setting value group as shown in FIG. 7. Although FIG. 7 shows only the print setting value group G001 as an example, the same applies to other print setting value groups. The group determination unit 208 applies, for each print setting value group, the appearance probability P (Mi | G) for the drawing identifier Mi included in the received document to the above equation (1), and the received document belongs to the print setting value group. Calculate the probability. Furthermore, the group determination unit 208 determines that the print setting value group for which the highest probability among the calculated probabilities is calculated is the print setting value group to which the received document belongs. Since the appearance probability P (Mi | G) is a number after the decimal point, normally, in calculating the product, the logarithm of each appearance probability is taken to convert the integration into a sum. The above equation (1) is not a problem in comparing the magnitudes of the probabilities because the magnitude relationship does not change even if the logarithm of both sides is used.

  Next, in step S805, the group determination unit 208 determines whether the highest probability among the probabilities calculated to determine the print setting value group of the received document is equal to or greater than a predetermined value. This takes into account the possibility that the features of the received document are not included in any print setting value group, and the received document does not belong to any group if the highest probability among the calculated probabilities is not greater than or equal to a predetermined value. It is to judge that. Therefore, when it is determined that the highest probability among the calculated probabilities is not equal to or more than the predetermined value, the processing is ended. On the other hand, if it is determined that the highest probability among the calculated probabilities is equal to or greater than the predetermined value, the process proceeds to step S806.

  In step S806, the group determination unit 208 acquires, from the group definition unit 212, the print setting value of the print setting value group determined to which the received document belongs, and passes the print setting value to the job control unit 205.

  Next, in step S807, the job control unit 205 sets the print setting value acquired in step S806 for the received document. That is, the job control unit 205 functions as a print setting value setting unit. The received document is printed using the print setting value set by the job control unit 205.

  Although the above-described print setting process has been described for the retention print document, the present invention is not limited to this, and the start time of printing is designated even for a normal print document that the printer 100 sequentially performs print processing It may be a reserved print document.

  As described above, the information processing apparatus according to the present embodiment determines which print setting value group the document should be classified and which print setting value should be based on the received feature amount of the print document. Do. The rule for determining the print setting value group to which the received print document belongs is generated by the feature value extracted from the document having the same print setting value among the documents printed in the past. That is, the feature of the document having a specific print setting value is obtained for each print setting value group from the past print result, and the received print document is applied to the print setting value group having the most similar feature amount. As a result, it is possible to easily obtain the print setting value to be set for the document having the specific feature amount from the print setting value of the document printed in the past.

  In addition, when it is desired to set a specific print setting value to a document having a specific feature value as an operation rule, only documents printed according to the specific print setting value among past print documents are subjected to classification learning target data You can give as. By doing so, it is possible to save the trouble of setting the print setting value for the document having the specific feature amount and to improve the convenience.

Second Embodiment
In the second embodiment of the present invention, in the group classification rule generation process described above, the process of improving the accuracy of the group classification rule by the document feature amount by dynamically redefining the definition of the print setting value group will be described. . In the following description, differences from the above-described first embodiment will be described.

  In addition, the hardware configuration and the functional configuration of the information processing apparatus in the present embodiment are the same as those in the first embodiment described above, and thus the description thereof will be omitted.

(Group classification rule generation process)
FIG. 9 shows a flowchart of group classification rule generation processing in the present embodiment. The process from step S901 to step S905 is the same as the process from step S301 to step S305 in FIG. Further, the processing from step S910 to step S912 is the same as the processing from step S306 to step S308 in FIG. Therefore, the description of the process in each of these steps is omitted, and in the following, the process from step S906 to step S909 will be described.

  In the group classification rule generation process in the present embodiment, after the group classification processing unit 209 specifies the print setting value groups of all the printed documents in step S905, the process proceeds to step S906.

  In step S 906, the group classification processing unit 209 calculates, for all printed documents, the degree of similarity between the documents. For example, the group classification processing unit 209 sets each of the drawing identifiers as shown in FIG. 7 as one dimension, and considers the number of each drawing identifier as a value in each dimension, and sets the Euclidean distance in the multidimensional space to each document. The degree of similarity is calculated by Note that the method of calculating the degree of similarity is not limited to this method, and other methods may be used.

  Next, in step S 907, the group classification processing unit 209 determines that the ratio in which the documents having the degree of similarity equal to or more than a predetermined value (that is, the documents having high degrees of similarity) belong to different print setting value groups is equal to or more than a predetermined value Determine if it is. If it is determined that the ratio is not the predetermined value or more, the process proceeds to step S910. On the other hand, if it is determined that the ratio is equal to or greater than the predetermined value, the process proceeds to step S908.

  In step S 908, the group classification processing unit 209 redefines the print setting value group. This avoids the case where the same document or an extremely similar document is given to the learning data as a different group when classifying each document as supervised learning, and a rule for classifying the same is not correctly generated. In order to Usually, these are often excluded from teacher data for learning. However, since the groups in the present embodiment are combinations of print setting values, there is a possibility that they can be used as correct teacher data by changing the definition of the print setting value groups. Specifically, in the definition of the print setting value group as shown in FIG. 4, the group classification processing unit 209 removes any one of the duplex setting, the color mode, and the N-up print setting value from the group definition. , Redefine print setting group. By reducing the print setting values included in the print setting value group in this manner, the possibility that documents having the same feature amount belong to the same print setting value group is increased.

  Next, in step S 909, the group classification processing unit 209 stores the redefined print setting value group in the group classification rule storage unit 211. Thereafter, the process returns to step S 905 to repeat the process.

  The processing from step S 910 to step S 912 is the same as the processing from step S 306 to step S 308 in FIG. 3 as described above, and thus the description thereof is omitted.

  The user may redefine the print setting value group. That is, when the ratio in which documents having high similarity belong to different print setting value groups is equal to or more than a predetermined value, the group classification processing unit 209 notifies the user via the user interface 204 to that effect. Then, in response to the notification, the user may edit the print setting value group via the user interface 204 and redefine it.

  As described above, according to the present embodiment, a document having extremely similar feature quantities is classified into different groups, and generation of more appropriate group classification rules is performed so as not to prevent group classification rule generation. Can. As a result, a more accurate document determination rule can be generated, and convenience in print setting of a newly received print document can be improved.

(Other embodiments)
The present invention supplies a program that implements one or more functions of the above-described embodiments to a system or apparatus via a network or storage medium, and one or more processors in a computer of the system or apparatus read and execute the program. Processing is also feasible. It can also be implemented by a circuit (eg, an ASIC) that implements one or more functions.

Claims (10)

Print setting value group specifying means for specifying a print setting value group corresponding to the print setting value of the printed document from each of the plurality of printed documents from the print setting value group by the combination of the print setting values;
Print setting value group determining means for determining a print setting value group of the new print document based on the feature amount of the printed document of the specified print setting value group and the feature amount of the new print document;
Setting means for setting print setting values of the print setting value group of the new print document in the new print document;
An information processing apparatus comprising:   2. The information processing apparatus according to claim 1, further comprising print setting value group definition means for extracting print setting values of the plurality of printed documents and defining the plurality of print setting value groups.   The information processing apparatus according to claim 1, wherein the plurality of print setting value groups are defined by a user. The apparatus further comprises group classification rule generation means for generating a group classification rule for determining a print setting value group of the new print document from the feature amount of the printed document of the specified print setting value group,
4. The print setting value group determining unit determines a print setting value group of the new print document according to the group classification rule and the feature amount of the new print document. The information processing apparatus according to any one of the items.   When the group classification rule generation unit generates the group classification rule, the group classification rule generation unit determines that a ratio in which a plurality of printed documents having similarities of a predetermined value or more belong to different print setting value groups is a predetermined value or more. In this case, the print setting value group is redefined by reducing the number of print setting values included in the print setting value group, and the group classification rule is generated based on the redefined print setting value group. The information processing apparatus according to claim 4, wherein:   The information processing apparatus according to any one of claims 1 to 5, wherein the feature amount includes a type of drawing command and position information included in a document.   The information processing apparatus according to any one of claims 1 to 6, wherein the feature amount includes the number of appearances of a word constituting a text included in a document.   The feature amount may further include at least one of an identifier of a user who has executed printing of a document, a time zone in which printing of a document has been executed, and an identifier of a device that has submitted a document. The information processing apparatus according to 6 or 7.   A program for causing a computer to function as the information processing apparatus according to any one of claims 1 to 8. Identifying a corresponding print setting value group from the print setting values of the printed document for each of the plurality of printed documents from the print setting value group based on the combination of the print setting values;
Determining a print setting value group of the new print document based on the feature amount of the printed document of the specified print setting value group and the feature amount of the new print document;
Setting a print setting value of a print setting value group of the new print document to the new print document.

Images