JP2004185048A - Printing time prediction device, printing time prediction method, program and storage medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To predict a printing time considering the time up to the end of the preceding printing processing even in the existence of a document under printing by enabling the calculation of the actual necessary time for printing after the instruction of printing by a user. <P>SOLUTION: A printing monitoring program 102 registers, when printing processing is executed from an application 106, printing record data including printing information for each document to be printed and a first printing time showing the necessary time from the start of the application 106 or a printer driver 107 to the end of the printing by a printer 2000 in a printing record database 104, and a learning data generation program forms learning data on the basis of each registered printing record data, and a predicted printing time display program predicts, on the basis of the printing information for each document to be printed and the formed learning data, the first printing time of printing processing for the document concerned. <P>COPYRIGHT: (C)2004,JPO&NCIPI

Description

ユニットへ入力されたＸは、ユニットの応答特性ｆ（Ｘ）に従って変形されるが、応答関数としてよく用いられるものが、図１２に示すシグモイド関数である。
【００８６】
図１２は、シグモイド関数を示す図である。
【００８７】
図１３は、階層型ニューラルネットの一例を示す図である。
【００８８】
図１３に示すように、階層型ニューラルネットでは、各ユニットＵ（図中の「○」印）を入力層Ｌａ、１層または複数層により構成される中間層Ｌｂ及び出力層Ｌｃに階層化している。
【００８９】
ユニットＵ間の接続は、各層Ｌａ，Ｌｂ，Ｌｃ間での接続であって、同一層内での接続はなく、また、信号は入力から出力へ一方向にしか伝わらない。
【００９０】
通常、入力層ＬａのユニットＵはシグモイド特性や閾値をもたず、入力値がそのまま出力に表れる。ニューラルネットの出力値は次に示す（数２）のように非常に簡単な形で表される。
【００９１】
【数２】

前記階層型ニューラルネットワークの学習アルゴリズム（学習エンジン）としては、教師信号と出力信号の２乗誤差が最小となるように、最急降下法を用いて中間層Ｌｂと出力層Ｌｃとの間の結合荷重及び閾値、入力層Ｌａと中間層Ｌｂとの間の結合荷重及び閾値を順次変化させていく誤差逆伝播学習則（バックプロパゲーション）がよく用いられており、本実施形態でもこれを用いることができる。
【００９２】
図１４は、本発明の印刷時間予測装置の予測エンジンに使用可能なニューラルネットの一例を示す図である。
【００９３】
以下、図１４を用いて、図５に示した予測印刷時間表示プログラムを説明する。
【００９４】
図５のステップＳ１０２，Ｓ１０３に示した全印刷所要時間の予測工程では、それぞれ図６（ａ），（ｂ）に示した印刷情報を入力層Ｌａの入力信号とし、全印刷所要時間学習データ１０５ａをニューラルネットの結合荷重Ｗ_ｉｊ，Ｖ_ｊとして、全印刷所要時間を予測する。
【００９５】
また、図５のステップＳ１０４に示したプリンタの印刷時間の予測工程では、図６（ｃ）に示した印刷情報を入力層Ｌａの入力信号とし、プリンタの印刷時間学習データをニューラルネットの結合荷重Ｗ_ｉｊ，Ｖ_ｊとして、プリンタの印刷時間を予測する。
【００９６】
次に、図１４を用いて、図９に示した学習データ作成プログラムを説明する。
【００９７】
図９のステップＳ３０２に示した学習工程では、まず、印刷記録データベース１０４から読み出した印刷情報（図１０（ａ））を入力層Ｌａの入力信号として全印刷所要時間を予測（出力層Ｌｃの出力信号）し、印刷記録データベース１０４から読み出した印刷時間（図１０（ａ））を教師信号とし、この教師信号と前記ニューラルネットの出力信号との２乗誤差が最小となるように、最急降下法を用いて中間層Ｌｂと出力層Ｌｃとの間の結合荷重Ｖ_ｊ及び閾値、入力層Ｌａと中間層Ｌｂとの間の結合荷重Ｗ_ｉｊ及び閾値を順次変化させ、結合荷重Ｗ_ｉｊ，Ｖ_ｊ（全印刷所要時間学習データ１０５ａ）を作成する（誤差逆伝播学習アルゴリズム）。
【００９８】
また、印刷記録データベースから読み出した印刷情報（図１０（ｂ））を入力層Ｌａの入力信号としてプリンタの印刷時間を予測（出力層Ｌｃの出力信号）し、印刷記録データベース１０４から読み出した印刷時間（図１０（ｂ））を教師信号とし、この教師信号と前記ニューラルネットの出力信号との２乗誤差が最小となるように、最急降下法を用いて中間層Ｌｂと出力層Ｌｃとの間の結合荷重Ｖ_ｊ及び閾値、入力層Ｌａと中間層Ｌｂとの間の結合荷重Ｗ_ｉｊ及び閾値を順次変化させ、結合荷重Ｗ_ｉｊ，Ｖ_ｊ（プリンタの印刷時間学習データ１０５ｂ）を作成する（誤差逆伝播学習アルゴリズム）。
【００９９】
最後に、図９のステップＳ３０３で、全印刷所要時間学習データ１０５ａ，プリンタの印刷時間学習データ１０５ｂをそれぞれ保存し、学習データ作成プログラムを終了する。
【０１００】
以上示したように、ユーザがアプリケーションから印刷を指示してから（使用者が印刷ボタンを押してから）プリンタが印刷終了するまでの実際の印刷所要時間（プリンタの動作時間だけではない）を算出し、ユーザに通知することができる。
【０１０１】
また、印刷中の文書が先に（既に）ある場合でも、その印刷が終わるまでの時間も考慮した印刷所要時間を算出することができる。
【０１０２】
さらに、印刷時には、印刷監視プログラムが常に、印刷情報や印刷所要時間の収集を行い、そのデータを使って学習し、予測するので、精度の高い予測を行うことができる。
【０１０３】
また、印刷開始時でも、予測した印刷終了予測時間を画面に表示することができ、さらに、印刷途中、印刷の進行状態が変わった時点で再予測して、より精度の高い印刷時間を表示することができる。
【０１０４】
また、印刷情報を予測印刷時間表示プログラムに通知する機能に対応していない一般のアプリケーションからの印刷でも、印刷データがプリンタドライバに来た時点で、プリンタドライバが印刷情報を予測印刷時間表示プログラムに通知することで、プリンタドライバが印刷データを受信した時点を入力印刷開始と判断し、印刷所要時間を予測することができる。なお、この場合、ユーザが印刷指示した時間ではなく、プリンタドライバが印刷データを受信した時点をからプリンタでの印刷が終了するまでを印刷所要時間とする。
【０１０５】
さらに、予測エンジンにニューラルネットワークを使用する場合、印刷所要時間は上記（数２）に示したように非常に簡単な数式で表せるため、印刷所要時間の推測に、複雑な計算や検索等を行う必要がない。よって、装置に負荷をかけないため、予測処理によりプリント処理に影響を与えてしまうこともなく、学習処理によりプリンタの経年変化をも考慮しながら印刷時間を最適に予測することができる。
【０１０６】
また、予測するためのデータが少ない場合でも、ある程度近い値を求めることもできる。
【０１０７】
従って、ユーザは、印刷の終了時間がわかるため、印刷が終了しているかプリンタを確認する必要がなくなる。
【０１０８】
また、複数のプリンタがある場合、どのプリンタが一番早く印刷終了するかがわかる。
【０１０９】
さらに、印刷時間が少ないプリンタを選択することが多くなるため、プリンタを効率よく使用することができる。
【０１１０】
また、本発明の印刷時間予測装置は、プリントサーバ上等で動作させることも可能であり、全てのユーザで使用することができる。
【０１１１】
さらに、アプリケーションやプリンタドライバから、印刷予測／表示のみを行う（実際に印刷は行わない）ことも可能に構成してもよく、印刷していない時でも、印刷時間の予測が可能であるので、ユーザからの一つの指示により、その時点で、使用可能な全てのプリンタに対する印刷時間の予測，表示を実行するように構成し、印刷前に最適なプリンタを選択して印刷可能に構成してもよい。
【０１１２】
また、本発明の印刷時間予測装置を総合印刷システム（印刷管理ソフト全体）へ組み込むようにしてもよい。
【０１１３】
さらに、本発明の印刷時間予測装置は、出力センタ（プリンタなど出力に関係する企業内の部門や会社に対応し、高速プリンタを何台も使用して大量印刷を業務としている部門や会社等）等の大量データの印刷での終了時間予測が可能であり、効率のよいプリンタで印刷させることができる。
【０１１４】
また、上記各実施形態（応用例）とを組み合わせた構成も本発明に含まれるものである。
【０１１５】
以下、図１５に示すメモリマップを参照して本発明に係る情報処理装置（印刷時間予測装置）で読み出し可能なデータ処理プログラムの構成について説明する。
【０１１６】
図１５は、本発明に係る情報処理装置（印刷時間予測装置）で読み出し可能な各種データ処理プログラムを格納する記録媒体のメモリマップを説明する図である。
【０１１７】
なお、特に図示しないが、記録媒体に記憶されるプログラム群を管理する情報、例えばバージョン情報，作成者等も記憶され、かつ、プログラム読み出し側のＯＳ等に依存する情報、例えばプログラムを識別表示するアイコン等も記憶される場合もある。
【０１１８】
さらに、各種プログラムに従属するデータも上記ディレクトリに管理されている。また、インストールするプログラムやデータが圧縮されている場合に、解凍するプログラム等も記憶される場合もある。
【０１１９】
本実施形態における図５，図７，図９に示す機能が外部からインストールされるプログラムによって、ホストコンピュータにより遂行されていてもよい。そして、その場合、ＣＤ−ＲＯＭやフラッシュメモリやＦＤ等の記録媒体により、あるいはネットワークを介して外部の記録媒体から、プログラムを含む情報群を出力装置に供給される場合でも本発明は適用されるものである。
【０１２０】
以上のように、前述した実施形態の機能を実現するソフトウエアのプログラムコードを記録した記録媒体を、システムあるいは装置に供給し、そのシステムあるいは装置のコンピュータ（またはＣＰＵやＭＰＵ）が記録媒体に格納されたプログラムコードを読出し実行することによっても、本発明の目的が達成されることは言うまでもない。
【０１２１】
この場合、記録媒体から読み出されたプログラムコード自体が本発明の新規な機能を実現することになり、そのプログラムコードを記憶した記録媒体は本発明を構成することになる。
【０１２２】
プログラムコードを供給するための記録媒体としては、例えば、フレキシブルディスク，ハードディスク，光ディスク，光磁気ディスク，ＣＤ−ＲＯＭ，ＣＤ−Ｒ，ＤＶＤ−ＲＯＭ，磁気テープ，不揮発性のメモリカード，ＲＯＭ，ＥＥＰＲＯＭ，シリコンディスク等を用いることができる。
【０１２３】
また、コンピュータが読み出したプログラムコードを実行することにより、前述した実施形態の機能が実現されるだけでなく、そのプログラムコードの指示に基づき、コンピュータ上で稼働しているＯＳ（オペレーティングシステム）等が実際の処理の一部または全部を行い、その処理によって前述した実施形態の機能が実現される場合も含まれることは言うまでもない。
【０１２４】
さらに、記録媒体から読み出されたプログラムコードが、コンピュータに挿入された機能拡張ボードやコンピュータに接続された機能拡張ユニットに備わるメモリに書き込まれた後、そのプログラムコードの指示に基づき、その機能拡張ボードや機能拡張ユニットに備わるＣＰＵ等が実際の処理の一部または全部を行い、その処理によって前述した実施形態の機能が実現される場合も含まれることは言うまでもない。
【０１２５】
また、本発明は、複数の機器から構成されるシステムに適用しても、１つの機器からなる装置に適用してもよい。また、本発明は、システムあるいは装置にプログラムを供給することによって達成される場合にも適応できることは言うまでもない。この場合、本発明を達成するためのソフトウエアによって表されるプログラムを格納した記録媒体を該システムあるいは装置に読み出すことによって、そのシステムあるいは装置が、本発明の効果を享受することが可能となる。
【０１２６】
さらに、本発明を達成するためのソフトウエアによって表されるプログラムをネットワーク上のデータベースから通信プログラムによりダウンロードして読み出すことによって、そのシステムあるいは装置が、本発明の効果を享受することが可能となる。
【０１２７】
【発明の効果】
以上説明したように、本発明によれば、アプリケーションプログラムから印刷処理を実行した際に、該印刷処理される文書の各印刷情報と該文書の印刷処理を前記アプリケーションプログラム又はプリンタドライバが開始してからプリンタが印刷終了するまでの所要時間を示す第１の印刷時間とを含む印刷記録データを登録し、該登録された各印刷記録データに基づいて学習データを作成しておき、印刷処理する文書の各印刷情報と前記作成された学習データとに基づいて、前記文書に対する印刷処理の第１の印刷時間を予測することにより、使用者が印刷指示してからの実際の印刷所要時間を算出することができ、印刷中の文書が既にある場合でも、該先行の印刷処理が終わるまでの時間やプリンタの経年変化をも考慮した印刷時間を予測することができる等の効果を奏する。
【図面の簡単な説明】
【図１】本発明の一実施形態を示す印刷時間予測装置を適用可能な情報処理装置の構成を示すブロック図である。
【図２】本発明の一実施形態を示す印刷時間予測装置の構成を示すブロック図である。
【図３】図２に示した印刷記録データベースの一例を示す図である。
【図４】図２に示した印刷時間予測装置，アプリケーション，プリンタドライバ，プリンタにおけるシーケンスを示す図である。
【図５】本発明の印刷時間予測装置における第１の制御処理手順の一例を示すフローチャートである。
【図６】図５に示す予測印刷時間表示プログラムの入力信号と出力信号を示す図である。
【図７】本発明の印刷時間予測装置における第２の制御処理手順の一例を示すフローチャートである。
【図８】図７に示す印刷監視プログラムが印刷記憶データベースに設定（登録）するデータを示す図である。
【図９】本発明の印刷時間予測装置における第３の制御処理手順の一例を示すフローチャートである。
【図１０】図９に示す学習データ作成プログラムの入力信号と教師信号を示す図である。
【図１１】ニューラルネットのニューロンモデル（ユニット）の構成を示す図である。
【図１２】シグモイド関数を示す図である。
【図１３】階層型ニューラルネットの一例を示す図である。
【図１４】本発明の印刷時間予測装置の予測エンジンに使用可能なニューラルネットの一例を示す図である。
【図１５】本発明に係る情報処理装置（印刷時間予測装置）で読み出し可能な各種データ処理プログラムを格納する記憶媒体のメモリマップを説明する図である。
【図１６】従来の印刷時間予測の範囲を示す図である。
【符号の説明】
１００ 印刷時間予測装置
１０１ 予測印刷時間表示プログラム
１０２ 印刷監視プログラム
１０３ 学習プログラム
１０４ 印刷記録データベース
１０５ａ，１０５ｂ 学習データ
１０６ アプリケーション
１０７ プリンタドライバ
１０８ スプーラ
２０００ プリンタ[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a print time estimating apparatus, a print time estimating method, a program, and a recording medium for estimating a required printing time of a document to be subjected to print processing from an application program.
[0002]
[Prior art]
Conventional methods for estimating print time include a method for estimating a completion time based on only the amount of print data, a method for analyzing print data and estimating a required time for each command, and an actual print time for one page. Was measured and the measurement result was multiplied by the number of pages to calculate the total required printing time.
[0003]
[Problems to be solved by the invention]
FIG. 16 is a diagram showing a conventional print time estimation range.
[0004]
As shown in the figure, all of the above conventional methods for estimating the printing time correspond to the “printing (operation) time of the printer” 1604, and the “printing time in the application” 1601, and the “previous print document exists” The “waiting time” 1602, “printer transfer time” 1603, and the like have been ignored.
[0005]
However, the printing time felt by the user usually corresponds to the time from the start of printing by the application to the end of printing by the printer, as indicated by 1600 in the figure. There is a problem that there is a difference between the printing time and the printing time, which is not practical.
[0006]
SUMMARY OF THE INVENTION The present invention has been made to solve the above-described problems, and an object of the present invention is to provide a method for performing printing processing from an application program so that each print information of the document to be printed and printing of the document are performed. A first print time indicating a required time from when the application program or the printer driver starts the processing until the printer finishes printing is registered. Print record data including the first print time is registered based on each of the registered print record data. The learning data is created, and based on each print information of the document to be printed and the created learning data, a first printing time of the printing process for the document is predicted, so that the user can issue a print instruction. The actual required printing time after the printing can be calculated, and even if the document being printed already exists, the time until the preceding printing process is completed or the printer To provide a printing time predicting apparatus and a printing time prediction method and a program and recording medium can be predicted printing time considering also the annual cycle.
[0007]
[Means for Solving the Problems]
According to a first aspect of the present invention, when print processing is executed from an application program (the application 106 shown in FIG. 2), each print information (print information 201 to 212 shown in FIG. 3) of a document to be printed is executed. And a first print time (a print time shown in FIG. 3) indicating a time required from when the application program or the printer driver (the printer driver 107 shown in FIG. 2) starts the printing process of the document to when the printer finishes printing. 301), and a learning unit (FIG. 2) for creating learning data based on each print record data stored in the storage unit. 2, a learning data creation program 103), print information of a document to be printed, and the learning information created by the learning means. Based on the data, characterized by having a prediction means for predicting a first print time of the print processing for the document (predicted printing time display program 101 shown in FIG. 2).
[0008]
In a second invention according to the present invention, when the progress of the printing process changes (at the time of starting the application printing and at the time of ending the printer driver printing), the predicting unit is configured to execute the processing based on the print information that can be acquired at the time. , For re-estimating the first printing time, and providing a notifying means (a predicted printing time display program 101 shown in FIG. 1) for notifying the first printing time predicted by the predicting means for each prediction. It is characterized by the following.
[0009]
According to a third aspect of the present invention, the print record data stored in the storage means includes a second print time (see FIG. 3) indicating a time required from the time when the printer starts the printing process of the document until the end of the printing. And the prediction unit predicts the second print time based on each print information that can be acquired at the time when the printer starts the print processing. Wherein the notifying unit also notifies the second printing time predicted by the predicting unit.
[0010]
In a fourth aspect according to the present invention, the learning unit includes a prediction result of the prediction unit based on each print information in each print record data stored in the storage unit, and a print result stored in the storage unit. The learning data is created based on a first printing time and a second printing time in the recording data.
[0011]
According to a fifth aspect of the present invention, when a print process is executed from an application program, each print information of the document to be printed and the print process of the document are started after the application program or the printer driver starts the print process. Registration step (steps S201 to S205 in FIG. 7) for registering print record data including a first print time indicating a time required until printing is completed, and learning data based on the registered print record data. (Steps S301 to S303 in FIG. 9), and a first print time of a print process for the document is predicted based on each print information of the document to be printed and the created learning data. And a prediction step (steps S101 to S103 in FIG. 5).
[0012]
A sixth invention according to the present invention is a program for executing the print time estimating method according to claim 5.
[0013]
A seventh invention according to the present invention is characterized in that a program for executing the printing time prediction method according to the fifth invention is stored in a recording medium in a computer-readable manner.
[0014]
BEST MODE FOR CARRYING OUT THE INVENTION
First, the configuration of an information processing apparatus to which the print time prediction device of the present invention can be applied will be described.
[0015]
FIG. 1 is a block diagram illustrating a configuration of an information processing apparatus to which a print time prediction apparatus according to an embodiment of the present invention can be applied.
[0016]
In the figure, reference numeral 1000 denotes an information processing apparatus to which the print time prediction device of the present invention can be applied. In the information processing apparatus 1000, reference numeral 1 denotes a CPU, which controls each device connected to the system bus 4 based on a program stored in a program ROM of the ROM 3, and totally controls the entire information processing apparatus 1000.
[0017]
The font ROM of the ROM 3 stores font data and the like, and the data ROM of the ROM 3 stores various data. Reference numeral 2 denotes a RAM, which functions as a main memory, a work area, and the like of the CPU 1.
[0018]
A keyboard controller (KBC) 5 controls input from a keyboard (KB) 9 or a pointing device (not shown) such as a mouse. Reference numeral 6 denotes a display controller (DC) which controls the display on the display 10. The display may be a CRT or another type of display device such as an LCD.
[0019]
A memory controller (MC) 7 controls access to a hard disk (HD) 11, a flexible disk (FD) (not shown), a CD-ROM, and the like. Reference numeral 8 denotes a network interface (NWI / F), which controls communication with the printer 2000 via the network 3000.
[0020]
FIG. 2 is a block diagram illustrating a configuration of a printing time prediction apparatus according to an embodiment of the present invention.
[0021]
In the figure, reference numeral 100 denotes a printing time prediction device, which comprises a predicted printing time display program 101, a print monitoring program 102, a learning data creation program 103, a print storage database 104, a memory for storing learning data 105 (105a, 105b), and the like. You.
[0022]
The printer driver 107 has a function of notifying the print monitoring program 102 of printing start and printing end, and a function of requesting the printer 2000 to issue a printing start and end notification.
[0023]
Note that the print data normally flows from the application 106 to the printer 2000 through the printer driver 107 and the spooler 108.
[0024]
The predicted printing time display program 101, print monitoring program 102, learning data creation program 103, application 106, printer driver 107, and spooler 108 are based on the programs stored in the HD 11 in the information processing apparatus 101 shown in FIG. And executed by the CPU 1.
[0025]
The predicted printing time display program 101 includes a prediction engine described later, and the learning data creation program 103 includes a learning engine described later.
[0026]
Further, the print record database 104 is realized on the HD 11 in the information processing apparatus 1000 shown in FIG.
[0027]
Further, 105a is “total printing required time learning data” described later, and 105b is “printer printing time learning data” described later, and is stored in the HD 11 or the RAM 2 in the information processing apparatus 1000 shown in FIG. Shall be stored.
[0028]
FIG. 3 is a diagram showing an example of the print record database 104 shown in FIG.
[0029]
As shown in the figure, the print record database 104 includes a print information group 200 and a print time information group 300.
[0030]
In the print information group 200, reference numeral 201 denotes print information indicating a print application name for performing print processing, reference numeral 202 denotes print information indicating a printer driver name for performing print processing, and reference numeral 203 denotes print indicating a print port for performing print processing. Information.
[0031]
Reference numeral 204 denotes print information indicating the CPU usage rate when performing the print processing, 205 denotes print information indicating the number of jobs waiting to be printed when performing the print processing, and 206 denotes whether the print processing is single-sided printing or double-sided printing. Print information to be displayed.
[0032]
Reference numeral 207 denotes print information indicating the size of print data to be subjected to print processing, reference numeral 208 denotes print information indicating the name of a printer to be subjected to print processing, and reference numeral 209 denotes print information indicating the number of pages of a document to be subjected to print processing.
[0033]
Reference numeral 210 denotes print information indicating a print start time in an application or a printer driver, reference numeral 211 denotes print information indicating an end time of print processing in the printer driver, and reference numeral 212 denotes print information indicating a start time of print processing in the printer. is there.
[0034]
The print information 200 is configured to include, in addition to the print information 201 to 212, other information such as page layout information, information indicating whether color printing or monochrome printing, and information indicating the warm-up time of the printer. You may.
[0035]
Further, in the print time group 300, reference numeral 301 denotes information indicating “total print required time” including waiting for spool printing, and a print time indicating a time from when printing is started by the application to when the end page is printed by the printer. It is.
[0036]
Further, reference numeral 302 denotes information indicating "printing time of the printer", which is the printing time indicating the time from when the printer starts receiving the print data to when the printer finishes printing the last page.
[0037]
FIG. 4 is a diagram showing a sequence in the print time prediction device 100, the application 106, the printer driver 107, and the printer 2000 shown in FIG. Note that (1) to (12) show each sequence.
[0038]
First, as shown in (1) in the figure, the application 106 receives a print instruction from the user, print application name, printer driver name, print port, CPU usage rate, number of jobs waiting to be printed, one-sided / two-sided, The print information 201 to 206, 208, and 209 that can be acquired, such as the printer name and the number of pages, are notified to the estimated print time display program 101 and the print monitoring program 102.
[0039]
In the case of printing from an application that does not support the function of notifying print information as described above, the printer driver 107 converts the print information 201 to 206, 208, and 209 into the estimated print time display program 101 and prints the print information. The monitoring program 102 is notified.
[0040]
Then, as shown in (2), the predicted printing time display program 101 executes a prediction engine, which will be described later, based on the print information 201 to 206, 208, 209 received in (1) and the total required printing time learning data 105a. Then, the total required printing time is calculated (estimated) and displayed on the screen (display 10).
[0041]
Further, as shown in (3), the print monitoring program 102 prints the print information 201 to 206, 208, 209 received from the application 106 or the printer driver 107 and the current time as a print start time (print information 210). It is stored in the database 104.
[0042]
Next, as shown in (4), when printing is completed, the printer driver 107 prints the estimated print time display program 101 and the print monitoring program 102 with the print data, such as the print data size 207, which could not be acquired by the application 106. Of the size (print information 207).
[0043]
Then, as shown in (5), the estimated print time display program 101 uses the print engine 201 to 209 and the total print time learning data 105a received in (4) to generate a total print time The time is calculated (estimated) again and displayed on the screen (display 10).
[0044]
Next, as shown in (6), the print monitoring program 102 stores the print information 207 and the current time received in (4) in the print record database 104 as the driver end time (print information 211).
[0045]
Next, upon receiving the print data, the printer 2000 notifies the estimated print time display program 101 and the print monitoring program 102 as shown in (7).
[0046]
Then, as shown in (8), the estimated print time display program 101 is based on the print information 201 to 204 and 206 to 209 (information notified from the application 106 and the printer driver 107) and the print time learning data 105b of the printer. Then, the printing time of the printer is calculated (estimated) using a prediction engine described later, and displayed on the screen (display 10).
[0047]
Further, as shown in (9), the print monitoring program 102 stores the current time in the print record database 104 as the printer start time (print information 212).
[0048]
Then, as shown in (10), the printer 2000 notifies the print monitoring program 102 when printing is completed.
[0049]
In response to this notification, as shown in (11), the print monitoring program 102 calculates the actual “total print required time” and “printer print time” based on the print information 210 and 211 and the current time. Then, the print time is stored in the print record database 104 as the print time 301 or 302.
[0050]
Further, as shown in (12), the learning data creation program 103 periodically refers to the print record database 104 to perform a learning process to be described later, and obtains the total printing required time learning data 105a and the printing time learning data of the printer. 105b is created and stored. In this learning process, the printing information 200 is used as an input signal, and the printing process 300 actually used is used as a teacher signal to perform the learning process.
[0051]
Hereinafter, the operation of the predicted printing time display program 101 shown in FIG. 2 will be described with reference to FIGS.
[0052]
FIG. 5 is a flowchart showing an example of a first control processing procedure in the printing time prediction apparatus of the present invention, and corresponds to the operation of the predicted printing time display program 101 shown in FIG. It is assumed that the processing of this flowchart is executed by the CPU 1 based on a program stored in the HD 11 or another recording medium shown in FIG. The processing in this flowchart is executed at the start of application printing, at the end of printer driver printing, at the start of printer printing, and the like (note that the more information is collected, the higher the accuracy of prediction is.) Furthermore, S101 to S105 indicate each step.
[0053]
FIG. 6 is a diagram showing input signals and output signals of the predicted printing time display program 101 shown in FIG.
[0054]
6A corresponds to the input signal and the output signal of the prediction engine when the type is notified of the start of the application printing, and FIG. 6B is the input signal and the output of the prediction engine when the notification of the printing end of the printer driver is notified. FIG. 6C corresponds to the input signal and the output signal of the prediction engine at the time of notification of the start of printer printing.
[0055]
Hereinafter, the operation of the predicted printing time display program 101 will be described with reference to FIG.
[0056]
First, if there is any notification to the estimated printing time display program 101, the type of notification is determined in step S101, and if it is determined that the type of notification is notification of the start of application printing, in step S102, The print application name, printer driver name, print port, CPU usage rate, number of jobs waiting to be printed, single-sided / double-sided, printer name, page number notified from the application 106 (print information 201 to 206, 208 shown in FIG. , 209 etc.), and using the received print information as an input signal to a prediction engine described later, predicts the total required printing time (print time 301 shown in FIG. 6A) (output signal of the prediction engine), and Proceed to S105.
[0057]
If it is determined in step S101 that the type of notification is a printer driver print end notification, in step S103, the size of the print data notified from the printer driver 107 is received, and the size of the received print data is received. And the print information received at the start of application printing (print information 201 to 209 shown in FIG. 6B) as an input signal of a prediction engine to be described later, and the entire printing required time (print time 301 shown in FIG. 6B). Prediction (output signal of the prediction engine), and the process proceeds to step S105.
[0058]
If it is determined in step S101 that the type of notification is a notification of the start of printer printing, in step S104, the print information received at the start of application printing and at the end of the printer driver (the printing information shown in FIG. Using the information 201 to 204 and 206 to 209) as input signals to a prediction engine described later, the printer print time (print time 302 shown in FIG. 6C) is predicted (output signal of the prediction engine), and the process proceeds to step S105. .
[0059]
In step S105, the predicted print time (or the remaining print time calculated from the predicted time may be displayed) is displayed on the display 10 shown in FIG. 1, and the process ends.
[0060]
Hereinafter, the operation of the print monitoring program 102 shown in FIG. 2 will be described with reference to FIGS.
[0061]
FIG. 7 is a flowchart illustrating an example of a second control processing procedure in the printing time prediction apparatus according to the present invention, and corresponds to the operation of the print monitoring program 102 illustrated in FIG. It is assumed that the processing of this flowchart is executed by the CPU 1 based on a program stored in the HD 11 or another recording medium shown in FIG. It is assumed that the processing of this flowchart is executed when application printing starts, when printer driver printing ends, when printer printing starts, and when printer printing ends. Furthermore, S201 to S205 indicate each step.
[0062]
FIG. 8 is a diagram showing data set (registered) in the print storage database 104 by the print monitoring program 102 shown in FIG.
[0063]
8A corresponds to the data set when the notification of the start of the application printing is set, FIG. 8B corresponds to the data set when the notification of the printing end of the printer driver is set, and FIG. FIG. 8D corresponds to data set at the end of printer printing when notification of printing start is made.
[0064]
Hereinafter, the operation of the print monitoring program 102 will be described with reference to FIG.
[0065]
First, if there is any notification to the print monitoring program 102, the type of notification is determined in step S201, and if it is determined that the type of notification is the notification of the start of application printing, the application 106 is determined in step S202. The print application name, printer driver name, print port, CPU usage rate, number of jobs waiting to be printed, single-sided / double-sided, printer name, page number, print start time, etc. 206, 208 to 210) and the received print information (print information 201 to 206, 208 to 210 shown in FIG. 8A) and the current time are used as the print start time (print information 210) as the print record database 104. Is set, and the process ends.
[0066]
If it is determined in step S201 that the type of notification is a printer driver print end notification, in step S203 the size of the print data notified from the printer driver 107 (the print information shown in FIG. 207) and the size of the received print data (the print information 207 shown in FIG. 8B) and the current time are stored in the print record database 104 as the driver end time (the print information 211 shown in FIG. 8B). Set and end the process.
[0067]
If it is determined in step S201 that the type of notification is a printer print start notification, in step S204, the current time is set in the print record database 104 as the printer start time (print information 212). To end.
[0068]
If it is determined in step S201 that the type of notification is a notification of the end of printer printing, in step S205, based on the print information 210 and 211 in the print record database 104 and the current time, the actual “ The “printing time required” and the “printing time of the printer” are calculated, set as the printing times 301 and 302 in the print record database 104, and the process ends.
[0069]
The operation of the learning data creation program 103 shown in FIG. 2 will be described below with reference to FIGS.
[0070]
FIG. 9 is a flowchart illustrating an example of a third control processing procedure in the printing time prediction apparatus of the present invention, and corresponds to the operation of the learning data creation program 103 illustrated in FIG. It is assumed that the processing of this flowchart is executed by the CPU 1 based on a program stored in the HD 11 or another recording medium shown in FIG. It is assumed that the processing of this flowchart is periodically executed at predetermined intervals. Further, steps S301 to S303 indicate steps.
[0071]
FIG. 10 is a diagram showing an input signal and a teacher signal of the learning data creation program 103 shown in FIG.
[0072]
Note that FIG. 10A corresponds to the input signal and the teacher signal when learning the total printing required time (printing time 301), and FIG. 10B shows when the printer printing time (printing time 302) is learned. Corresponding to the input signal and the teacher signal.
[0073]
Hereinafter, the operation of the learning data creation program 103 will be described with reference to FIG.
[0074]
When the learning data creation program 103 is started, in step S301, a print application name, a printer driver name, a print port, a CPU usage rate, the number of jobs waiting to be printed, one-sided / two-sided, the size of the print data, The name, the number of pages, etc. (print information 201 to 209 shown in FIG. 10), the total print time, and the print time of the printer (print time 301, print time 302 shown in FIG. 10) are read.
[0075]
Next, in step S302, as shown in FIG. 10A, a print application name, a printer driver name, a print port, a CPU usage rate, a print waiting job, one-sided / two-sided, print data size, a printer name, and the number of pages And the like (print information 201 to 209) are used as input signals to a prediction engine described later, and the total printing required time (printing time 301) is used as a teacher signal to make a learning engine described later learn the prediction of the total printing required time. The time learning data 105a is created.
[0076]
Also, as shown in FIG. 10B, the print application name, printer driver name, print port, CPU usage rate, single-sided / double-sided, print data size, printer name, number of pages, etc. (print information 201 to 204, 206 209) as input signals to a prediction engine described later, and using the printing time of the printer (printing time 302) as a teacher signal, the learning engine described later learns the prediction of the printing time of the printer, and outputs the printing time learning data 105b of the printer. create.
[0077]
Next, in step S303, the created learning data 105 (total printing required time learning data 105a, printer printing time learning data 105b) is stored (saved) in the HD 11 or the learning data storage area in the RAM 2 and the process ends. I do.
[0078]
Hereinafter, the above-described prediction engine will be described.
[0079]
In the present embodiment, a prediction engine using a neural network will be described as an example of a prediction engine. However, any prediction engine that can predict a printing time from the above-described input signal and learning data uses a neural network. However, the present invention is applicable to other prediction engines.
[0080]
For example, a configuration using a prediction engine using a genetic algorithm, a prediction engine using a data mining technique, or a prediction engine using a regression analysis may be used.
[0081]
In this embodiment, a case where a hierarchical neural network and an error back propagation method (back propagation) are used as an example of a learning method for the hierarchical neural network will be described as an example of the neural network. The possible neural network configurations and learning methods are not limited to these.
[0082]
First, prior to the description of the neural network in the present embodiment, an outline of the hierarchical neural network will be described. A neural network, as translated as a neural network, is an information processing system that imitates a human neural network, and an engineering neuron model corresponding to a nerve cell is called a unit.
[0083]
FIG. 11 is a diagram showing a configuration of a neuron model (unit) of a neural network.
[0084]
As shown in the figure, the unit usually uses a multi-input, one-output element. A signal is transmitted in only one direction and a certain weight (connection weight: w ₁ , ..., w _j , ..., w _N ) Is added to the unit. The weight indicates the strength of the connection between the units. The strength of the connection between the units can be changed by learning. Each weighted input value (w ₁ × x ₁ + ... + w _j × x _j + ... + w _N × x _N The value X obtained by subtracting the threshold value θ from the sum total of the above is output after being deformed by the response function f (X). The output value y of the unit is as shown in the following (Equation 1).
[0085]
(Equation 1)

X input to the unit is deformed in accordance with the response characteristic f (X) of the unit, and a sigmoid function frequently used as a response function is shown in FIG.
[0086]
FIG. 12 is a diagram illustrating a sigmoid function.
[0087]
FIG. 13 is a diagram illustrating an example of a hierarchical neural network.
[0088]
As shown in FIG. 13, in the hierarchical neural network, each unit U (indicated by “○” in the figure) is hierarchized into an input layer La, an intermediate layer Lb composed of one or more layers, and an output layer Lc. I have.
[0089]
The connection between the units U is a connection between the respective layers La, Lb, and Lc, there is no connection in the same layer, and a signal is transmitted in only one direction from the input to the output.
[0090]
Normally, the unit U of the input layer La does not have a sigmoid characteristic or a threshold, and the input value appears in the output as it is. The output value of the neural network is expressed in a very simple form as shown in the following (Equation 2).
[0091]
(Equation 2)

As a learning algorithm (learning engine) of the hierarchical neural network, a connection weight between the intermediate layer Lb and the output layer Lc using the steepest descent method so as to minimize the square error between the teacher signal and the output signal. A backpropagation learning rule (backpropagation) for sequentially changing the threshold value, the threshold value, the connection weight between the input layer La and the intermediate layer Lb, and the threshold value is often used. it can.
[0092]
FIG. 14 is a diagram showing an example of a neural network that can be used for the prediction engine of the printing time prediction device of the present invention.
[0093]
Hereinafter, the predicted printing time display program shown in FIG. 5 will be described with reference to FIG.
[0094]
In the process of estimating the total required printing time shown in steps S102 and S103 in FIG. 5, the print information shown in FIGS. 6A and 6B is used as an input signal of the input layer La, and the total required printing time learning data 105a is used. Is the connection weight W of the neural network. _ij , V _j To predict the total required printing time.
[0095]
In the step of estimating the printing time of the printer shown in step S104 of FIG. 5, the printing information shown in FIG. 6C is used as the input signal of the input layer La, and the printing time learning data of the printer is used as the connection weight of the neural network. W _ij , V _j As the printing time of the printer.
[0096]
Next, the learning data creation program shown in FIG. 9 will be described with reference to FIG.
[0097]
In the learning step shown in step S302 in FIG. 9, first, the print information read from the print record database 104 (FIG. 10A) is used as an input signal of the input layer La to predict the total required printing time (output of the output layer Lc). Signal, and the printing time read from the print record database 104 (FIG. 10A) is used as a teacher signal. The steepest descent method is used to minimize the square error between the teacher signal and the output signal of the neural network. Weight between the intermediate layer Lb and the output layer Lc using _j And the threshold value, the connection weight W between the input layer La and the intermediate layer Lb _ij And the threshold value are sequentially changed to obtain the connection weight W _ij , V _j (Total printing required time learning data 105a) is created (error back propagation learning algorithm).
[0098]
The print information read from the print record database (FIG. 10B) is used as an input signal of the input layer La to predict the print time of the printer (the output signal of the output layer Lc). (FIG. 10 (b)) is used as a teacher signal. The steepest descent method is used between the intermediate layer Lb and the output layer Lc so that the square error between the teacher signal and the output signal of the neural network is minimized. Coupling load V _j And the threshold value, the connection weight W between the input layer La and the intermediate layer Lb _ij And the threshold value are sequentially changed to obtain the connection weight W _ij , V _j (Printing time learning data 105b of the printer) is created (error back propagation learning algorithm).
[0099]
Finally, in step S303 in FIG. 9, the entire required printing time learning data 105a and the printing time learning data 105b of the printer are stored, and the learning data creation program ends.
[0100]
As described above, the actual required printing time (not just the operating time of the printer) from when the user instructs printing from the application (after the user presses the print button) until the printer finishes printing is calculated. Can be notified to the user.
[0101]
In addition, even when the document being printed exists (already), the required printing time can be calculated in consideration of the time until the printing is completed.
[0102]
Furthermore, at the time of printing, the print monitoring program always collects print information and required print time, and learns and makes predictions using the data, so that highly accurate prediction can be performed.
[0103]
In addition, even at the start of printing, the predicted print end predicted time can be displayed on the screen, and further, when printing progress is changed during printing, the prediction is re-predicted, and a more accurate print time is displayed. be able to.
[0104]
Even when printing from a general application that does not support the function of notifying the print information to the estimated print time display program, when the print data arrives at the printer driver, the printer driver sends the print information to the estimated print time display program. By notifying, the time when the printer driver receives the print data is determined to be the start of input printing, and the required printing time can be estimated. In this case, the required printing time is defined as the time from when the printer driver receives the print data to when the printing by the printer is completed, not the time when the user instructs the printing.
[0105]
Further, when a neural network is used as the prediction engine, the required printing time can be represented by a very simple mathematical expression as shown in the above (Equation 2), and therefore complicated calculations and searches are performed to estimate the required printing time. No need. Therefore, since no load is imposed on the apparatus, the print processing is not affected by the prediction processing, and the print time can be optimally predicted by the learning processing while considering the aging of the printer.
[0106]
Further, even when the data for prediction is small, a value close to a certain degree can be obtained.
[0107]
Therefore, the user does not need to check the printer to determine whether the printing has been completed since the printing end time is known.
[0108]
In addition, when there are a plurality of printers, it is possible to know which printer finishes printing first.
[0109]
Further, since a printer having a short printing time is frequently selected, the printer can be used efficiently.
[0110]
Further, the printing time prediction device of the present invention can be operated on a print server or the like, and can be used by all users.
[0111]
Further, it is also possible to configure so that only print prediction / display (not actually printing) can be performed from an application or a printer driver, and the print time can be predicted even when printing is not performed. According to one instruction from the user, the printing time is predicted and displayed for all available printers at that time, and the optimum printer is selected before printing so that printing is possible. Good.
[0112]
Further, the printing time prediction device of the present invention may be incorporated in a comprehensive printing system (entire printing management software).
[0113]
Further, the printing time estimating apparatus of the present invention can be applied to an output center (a department or a company which handles a large number of high-speed printers by using high-speed printers corresponding to departments and companies in a company related to output such as a printer). For example, it is possible to predict an end time in printing a large amount of data such as a large amount of data, and it is possible to perform printing with an efficient printer.
[0114]
Further, a configuration in which the above-described embodiments (application examples) are combined is also included in the present invention.
[0115]
Hereinafter, the configuration of a data processing program that can be read by the information processing apparatus (printing time prediction apparatus) according to the present invention will be described with reference to a memory map shown in FIG.
[0116]
FIG. 15 is a diagram illustrating a memory map of a recording medium that stores various data processing programs that can be read by the information processing device (printing time prediction device) according to the present invention.
[0117]
Although not shown, information for managing a group of programs stored in the recording medium, for example, version information, a creator, and the like are also stored, and information that depends on the OS or the like on the program reading side, for example, identifies and displays the program. Icons and the like may also be stored.
[0118]
Further, data dependent on various programs is also managed in the directory. In addition, when a program or data to be installed is compressed, a decompression program or the like may be stored.
[0119]
The functions shown in FIG. 5, FIG. 7, and FIG. 9 in the present embodiment may be executed by a host computer by a program installed from the outside. In this case, the present invention is applied even when a group of information including a program is supplied to the output device from a recording medium such as a CD-ROM, a flash memory, or an FD, or from an external recording medium via a network. Things.
[0120]
As described above, the recording medium storing the program codes of the software for realizing the functions of the above-described embodiments is supplied to the system or the apparatus, and the computer (or CPU or MPU) of the system or the apparatus stores the recording medium in the recording medium. It goes without saying that the object of the present invention is also achieved by reading and executing the program code.
[0121]
In this case, the program code itself read from the recording medium implements the novel function of the present invention, and the recording medium storing the program code constitutes the present invention.
[0122]
As a recording medium for supplying the program code, for example, a flexible disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD-R, DVD-ROM, magnetic tape, nonvolatile memory card, ROM, EEPROM, A silicon disk or the like can be used.
[0123]
When the computer executes the readout program code, not only the functions of the above-described embodiments are realized, but also an OS (Operating System) running on the computer based on the instruction of the program code. It goes without saying that a part or all of the actual processing is performed and the functions of the above-described embodiments are realized by the processing.
[0124]
Further, after the program code read from the recording medium is written into a memory provided on a function expansion board inserted into the computer or a function expansion unit connected to the computer, the function expansion is performed based on the instruction of the program code. It goes without saying that a CPU or the like provided in the board or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above-described embodiments.
[0125]
Further, the present invention may be applied to a system including a plurality of devices or to an apparatus including a single device. Needless to say, the present invention can be applied to a case where the present invention is achieved by supplying a program to a system or an apparatus. In this case, by reading out a recording medium storing a program represented by software for achieving the present invention to the system or apparatus, the system or apparatus can enjoy the effects of the present invention. .
[0126]
Further, by downloading and reading out a program represented by software for achieving the present invention from a database on a network by a communication program, the system or apparatus can enjoy the effects of the present invention. .
[0127]
【The invention's effect】
As described above, according to the present invention, when print processing is executed from an application program, each print information of the document to be printed and the print processing of the document are started by the application program or the printer driver. And print data including a first print time indicating the time required until the printer finishes printing, and prepares learning data based on each of the registered print record data to prepare a document to be printed. Estimating a first printing time of a printing process for the document based on each piece of printing information and the created learning data, thereby calculating an actual required printing time after the user instructs printing. Even if there is already a document being printed, it is possible to predict the printing time in consideration of the time until the preceding printing process is completed and the aging of the printer. Rukoto an effect such as can.
[Brief description of the drawings]
FIG. 1 is a block diagram illustrating a configuration of an information processing apparatus to which a print time prediction apparatus according to an embodiment of the present invention can be applied.
FIG. 2 is a block diagram illustrating a configuration of a printing time prediction apparatus according to an exemplary embodiment of the present invention.
FIG. 3 is a diagram illustrating an example of a print record database illustrated in FIG. 2;
FIG. 4 is a diagram showing a sequence in the print time prediction device, application, printer driver, and printer shown in FIG.
FIG. 5 is a flowchart illustrating an example of a first control processing procedure in the printing time prediction device of the present invention.
6 is a diagram showing an input signal and an output signal of the predicted printing time display program shown in FIG.
FIG. 7 is a flowchart illustrating an example of a second control processing procedure in the printing time prediction device of the present invention.
8 is a diagram showing data set (registered) in a print storage database by the print monitoring program shown in FIG.
FIG. 9 is a flowchart illustrating an example of a third control processing procedure in the printing time prediction device of the present invention.
10 is a diagram showing an input signal and a teacher signal of the learning data creation program shown in FIG.
FIG. 11 is a diagram showing a configuration of a neuron model (unit) of a neural network.
FIG. 12 is a diagram showing a sigmoid function.
FIG. 13 is a diagram illustrating an example of a hierarchical neural network.
FIG. 14 is a diagram showing an example of a neural network that can be used for a prediction engine of the printing time prediction device of the present invention.
FIG. 15 is a diagram illustrating a memory map of a storage medium storing various data processing programs that can be read by the information processing device (printing time prediction device) according to the present invention.
FIG. 16 is a diagram showing a conventional print time estimation range.
[Explanation of symbols]
100 Printing time prediction device
101 Estimated print time display program
102 Print monitoring program
103 Learning Program
104 print record database
105a, 105b Learning data
106 Application
107 Printer Driver
108 Spooler
2000 Printer

Claims (7)

When print processing is executed from the application program, the print information of each document to be printed and the time required from when the application program or the printer driver starts the print processing of the document until when the printer finishes printing are displayed. Storage means for storing and managing a plurality of print record data including a first print time;
Learning means for creating learning data based on each print record data stored in the storage means,
A prediction unit that predicts a first printing time of a printing process on the document based on each print information of the document to be printed and learning data created by the learning unit;
A printing time prediction device, comprising: The predicting unit re-predicts the first printing time based on each print information that can be obtained at the time when the progress of the printing process changes,
2. The printing time estimating apparatus according to claim 1, further comprising a notifying unit that notifies the first printing time predicted by the predicting unit for each prediction. The print record data stored in the storage unit also includes a second print time indicating a time required from when the printer starts the printing process of the document to when the printing is completed,
The predicting unit predicts the second printing time based on each print information that can be obtained at the time when the printer starts the printing process,
The printing time estimating apparatus according to claim 2, wherein the notifying means also notifies the second printing time predicted by the predicting means. The learning means includes a prediction result of the prediction means based on each print information in each print record data stored in the storage means, a first print time in each print record data stored in the storage means, The printing time prediction device according to claim 1, wherein the learning data is created based on a second printing time. When print processing is executed from the application program, the print information of each document to be printed and the time required from when the application program or the printer driver starts the print processing of the document until when the printer finishes printing are displayed. A registration step of registering print record data including a first print time;
A learning step of creating learning data based on each of the registered print record data;
A prediction step of predicting a first printing time of a printing process on the document based on each print information of the document to be printed and the created learning data;
A printing time prediction method, comprising: A program for executing the printing time prediction method according to claim 5. A recording medium storing a program readable by a computer, wherein the program executes the print time prediction method according to claim 5.

Images