JP2006279545A - Information processor, information processing method, and program therefor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an information processor that can suitably restrain copying processing and FAX processing of various kinds of documents including general documents generated and used in an office, an information processing method and a program therefor. <P>SOLUTION: A scanner 16 reads the document and outputs image data. A copying machine 1 specifies a character carrying portion in the image data outputted by the scanner, performs character recognition processing to generate 1st character information on the basis of recognized character data, and compares the 1st character information with 2nd character information as information on characters included in a document to be controlled that is referred to from document management index data 18b, thereby deciding whether the document and the document to be controlled have similar document contents. Then the copying machine 1 specifies a document to be controlled which have document contents similar to that of the document in accordance with the decision and refers to control information of the document to be controlled specified from the document management index data 18b to decide whether document processing in response to a request to process the document is performed. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program thereof capable of performing processing such as copy processing, FAX processing, and SEND processing (e-mail transmission processing) after scanning a document.

  In recent years, copying machines have become more multifunctional than just the function of copying (copying) originals. For example, a printer function that connects to a PC (Personal Computer) and performs printing in response to a print instruction from the PC, a FAX function that scans and faxes a document, and a SEND function that scans and mails a document. A copier is provided. Such a multifunctional copying machine is positioned as a portal for realizing a document solution linked with document management in the flow of digitization of documents.

  Furthermore, security considerations have become important in copying machines, and a copy suppression function has been proposed as a technique for preventing leakage of scan information.

  Various copy suppression functions have been proposed so far, and some have been implemented in copiers. For example, for the purpose of suppressing the copy of a specific manuscript such as a gift certificate or a securities, a technique for processing and outputting a manuscript such as adding additional information to the specific manuscript has been proposed (see, for example, Patent Document 1). . In Patent Document 1, as a means for determining whether or not a document is a specific document, copy suppression is performed by calculating the similarity by comparing the image data of the specific document image with the input image.

  In addition, a technique for alerting an operator to processing a highly confidential document is disclosed (for example, see Patent Document 2). In Patent Document 2, whether or not confidentiality is high is determined based on whether or not a specific symbol string such as “top secret” is included after character recognition of the original image.

  In addition, a technique is disclosed in which a copyrighted work name is given to paper in advance using a barcode or the like, and copyright information is obtained from a host computer and an operator is inquired whether to continue copying (for example, see Patent Document 3). ).

  In addition, in a device that suppresses copy output when a copy-suppressed image is included in a read image, a technique is disclosed in which the determination is performed by an external device (see, for example, Patent Document 4).

Japanese Patent Laid-Open No. 5-110815 JP 2001-266112 A JP 7-129270 A Japanese Patent Application Laid-Open No. 5-244412

  However, the technique of directly comparing image data as in Patent Document 1 can be expected to be effective for copy suppression when an image pattern such as banknotes is fixed, but when the text content is important as in a general document. The effect is thin. For example, the copy suppression function can be easily avoided simply by changing the word sequence.

  Patent Document 2 requires operations such as adding a specific character string to a confidential document in a sentence or the title in advance, and can suppress copying of a general document that does not include such a specific character string. Can not.

  In addition, in the method of Patent Document 3, additional information such as a barcode needs to be added in advance at the time of printing. For example, when copy management is necessary after paper document distribution, security management can be performed flexibly. I can't.

  Also in the apparatus of Patent Document 4, since it is determined whether or not to suppress copying by comparing image data, the effect of copying suppression of documents having similar text contents is small.

  As described above, in the above-described prior art, a document in which a barcode or a predetermined keyword is given to a document is a target, or a document including a controlled pattern such as a banknote is a target. There is a problem that it is not always effective for suppressing copy of a general document being created or used. That is, it is necessary to perform copy suppression by a method other than direct comparison of image data, comparison of fixed keywords, and copy suppression based on attached information such as a barcode.

  The present invention has been made in consideration of the above-described circumstances, and can appropriately suppress copying processing and FAX processing for various types of manuscripts including general documents created and used in an office. An information processing apparatus, an information processing method, and a program therefor are provided.

  The present invention has been made to solve the above-described problems. In the information processing apparatus according to the present invention, a document is read in response to a processing request input by the input means, and the read document is output as image data. A character information extracting means for identifying a character insertion portion from image data output by the reading means, performing character recognition processing, and outputting first character information based on the recognized character data, and a document As information about the control target document that is the target of control processing, the second character information that is information about the characters included in the control target document, and any one of one or more types of document processing for the control target document Information storage means for storing at least control information for determining whether to control processing, first character information output from the character information extraction means, and information storage means Similarity determination means for determining whether or not the document content of the document and the control target document is similar based on the second character information of the control target document to be processed, and the document and document content according to the determination of the similarity determination means A process determination unit that identifies similar control target documents, refers to the control information of the control target document specified from the information storage unit, and determines whether or not document processing is possible in response to a processing request for a document. Features.

  In the information processing method according to the present invention, a document is read in response to a processing request input by the input means, the reading document is output as image data, and the image data output in the reading step is included. The character information extraction step for identifying the character posting portion and performing the character recognition processing, outputting the first character information based on the recognized character data, and the information on the control target document to be controlled for document processing, Stores at least second character information, which is information relating to characters included in the control target document, and control information for determining which of one or more types of document processing is to be controlled for the control target document. The second character information of the control target document is referred to from the information storage means and compared with the first character information output in the character information extraction step. The similarity determination step for determining whether or not the document content of the manuscript and the control target document are similar, and the control target document whose document content is similar to the manuscript according to the determination in the similarity determination step are specified and stored as information. And a process determination step of determining whether or not the document process can be performed in response to the process request for the document with reference to the control information of the control target document specified by the means.

  A program according to the present invention is a program for an information processing apparatus, and includes a reading step for reading a document in accordance with a processing request input by an input unit and outputting image data, and image data output in the reading step. The character information extraction step for identifying the character posting portion and performing the character recognition processing, outputting the first character information based on the recognized character data, and the information on the control target document to be controlled for document processing, Stores at least second character information, which is information relating to characters included in the control target document, and control information for determining which of one or more types of document processing is to be controlled for the control target document. The second character information of the control object document is referred to from the information storage means and compared with the first character information output in the character information extraction step. Thus, the similarity determination step for determining whether the document content of the manuscript and the control target document are similar, and the control target document whose document content is similar to the manuscript are specified according to the determination of the similarity determination step, and information is stored. A program for causing a computer to execute a process determination step for determining whether or not to process a document in response to a processing request for a document with reference to control information of a control target document specified by means.

  The information processing apparatus, information processing method, and program therefor according to the present invention can appropriately suppress copy processing and FAX processing for various types of manuscripts including general documents created and used in an office.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a block diagram showing a schematic configuration of a copying machine (information processing apparatus) according to an embodiment of the present invention. In FIG. 1, reference numeral 1 denotes a copying machine, which includes a CPU 10, a ROM 12, a RAM 13, an input device 14, a display device 15, a scanner 16, a printer 17, a hard disk (HD) 18, a removable external storage device 19, and a communication device 20. The The copying machine 1 is a multifunctional copying machine having a copy function (copying function) for reading and copying an original, a FAX processing function for reading and FAXing an original, a SEND processing function for reading an original and sending it by e-mail, and the like.

  The CPU 10 is, for example, a microprocessor, and performs various operations such as image processing, character processing, search processing, and logical determination by reading and executing various programs, and each component connected to the bus 11 via the bus 11. Control elements.

  The bus 11 is a bus, and transfers an address signal and a control signal instructing each component to be controlled by the CPU 10. In addition, data transfer between each component is performed. The RAM 13 is a random access memory that can be read and written by the CPU 10, and is used as a primary storage for various data from each component. A ROM (Read Only Memory) 12 is a read-only nonvolatile memory. The ROM 12 stores, for example, a boot program that the CPU 10 executes at startup. Specifically, when the CPU 10 executes the boot program at the time of system startup, the CPU 10 loads the control program stored in the HD 18 into the RAM 13 and executes it. This control program will be described in detail later with reference to a flowchart.

  The input device 14 is a touch panel, operation buttons, or the like. The input device 14 is not limited to a touch panel or operation buttons, and may be configured with a keyboard, a mouse, or the like like a normal PC (personal computer). The display device 15 is, for example, a liquid crystal display or a CRT. In the present embodiment, a part of the input device 14 is formed on the display device 15, thereby realizing a touch panel that can be input using buttons displayed on the screen of the display device 15.

  The scanner 16 is a device that performs processing such as reading a paper document as a document and converting it into digital image data. The printer 17 is a device for printing document data and image data held in the copying machine 1. Specifically, the printer 17 prints an electronic document received by the communication device 20 via a communication line (network) and an electronic document held in the HD 18. The copying function of the copying machine 1 is realized by printing the scan image data read from the scanner 16 by the printer 17 as it is.

  An HD 18 is a hard disk, and includes a control program 18a executed by the CPU 10, a search process for performing a similar search for text content and document layout, and document management index data 18b, which is information related to an index for document management, and a similar search for text content. A word importance degree table 18c, which is data relating to the importance degree of each word when performing, is stored. Here, the similarity search of the text content and the document layout is a process of searching for the text content included in the original scanned by the scanner 16 from the text content to be managed in the document management index data 18b, This is a process of searching the document management index data 18b for a layout similar to the layout of texts and symbols included in the document scanned by the scanner 16 from the layout to be managed. It should be noted that the text content and layout to be managed in the document management index data 18b need to restrict copy processing, FAX processing, and SEND processing in the copying machine 1.

  The removable external storage device 19 is an apparatus having an interface for a recording medium that can be attached to and detached from the copying machine 1 such as a USB (Universal Serial Bus) memory device or an IC card. The removable external storage device 19 is not limited to the above configuration, and may be configured to include a drive for installing and accessing a disk-shaped recording medium such as a flexible disk, CD, or DVD, for example. The CPU 10 can use the removable external storage device 19 in the same manner as the HD 18. The removable external storage device 19 realizes data exchange with other copying machines through a removable recording medium. The control program stored in the HD 18 may be copied in whole or in part from the removable external storage device 19 as necessary.

  The communication device 20 is a network controller, and is a device that exchanges data with the outside via a communication line. The copying machine 1 operates according to various events input from the input device 14 or the like. Specifically, when an interrupt from the input device 14 or the like is supplied, an input signal is sent to the CPU 10, an event is generated accordingly, and the CPU 10 stores various commands stored in the ROM 12 or RAM 13 according to the event. And various controls are carried out by executing them.

  With the above configuration, the copying machine 1 according to the present embodiment determines whether the scanned document text content and layout are similar to the document content and layout of the document to be managed in the document management index data 18b. When it is determined that they are similar, it is possible to restrict the copy process, the FAX process, or the SEND process based on the scan image data.

FIG. 2 is a diagram showing an example of the operation flow in the copying machine 1 shown in FIG.
As shown in FIG. 2, the copying machine 1 stores in advance index data for performing similar retrieval of text contents and layout and information for security management in the document management index data 18b. Specifically, for example, when it is desired to restrict the copy processing for another minutes document having the same format and the same agenda as document A of a certain minutes, information on the text content and layout of the document A is stored in the document. Register in the management index data 18b. Details of the registration process will be described later. Thus, using the data stored in the document management index data 18b, the copying machine 1 can restrict the copy process for a document having the same text content and layout as the document A.

  For example, when an instruction to copy a document 2 that is a paper document set on the document table of the copying machine 1 is issued, the scanner 16 of the copying machine 1 scans the document 2 and outputs a scanned image. Based on this scan image, the copying machine 1 extracts the layout information and text content of the document 2 and searches the document management index data 18b, thereby performing copy processing, FAX processing, and SEND processing (hereinafter referred to as copy processing). Etc.) is generated. Then, the copier 1 determines whether or not to perform a copy process for outputting the scan image by the printer 17 in accordance with the document management information. If it is determined that copy processing or the like is to be performed, the copying machine 1 performs copy processing or the like based on the scan image.

  If it is determined that the copy process is not performed, the copying machine 1 suppresses the copy process based on the scan image and requests the security administrator to cancel the suppression of the copy process. In preparation for the case, information related to a document to be managed (for example, a document ID described later) is displayed on the display device 15 in the document management index data 18b determined to be similar.

  FIG. 3 is a diagram showing a screen transition example of the display device 15 of the copying machine 1 shown in FIG. In FIG. 3, a screen 3-1 is a screen in an initial state. The screen 3-1 includes various buttons such as a copy button 31 for starting a copy processing operation, a FAX button 32 for starting a FAX processing operation, a SEND button 33 for starting a SEND processing operation, and a setting button 34 for setting security information. Is arranged.

  For example, when the copy button 31 is pressed, it is determined whether or not the copy process can be performed on the document on the document table. When it is determined that the copy process is possible, the copying machine 1 performs a copy processing operation. If it is determined that the copy process is not possible, the copying machine 1 does not perform the copy process operation. In this case, the copying machine 1 displays a screen as shown in the screen 3-2 on the display device 15, thereby notifying the user that the copy processing operation is not performed and copying the document management index data 18b. The document ID of the document set to process suppression (for example, the document ID of the document A in the above example) can be indicated.

  Whether the copying machine 1 is a document subject to restriction such as copy processing by comparing the text content and layout included in the document rather than directly comparing the image patterns of the document as in the prior art. Judge whether or not. For this reason, the text content included in the document of the manuscript (which does not need to be restricted in copy processing) is similar to the text content of the document (hereinafter referred to as a management target document) managed by the document management index data 18b. There may be cases where the copy process is restricted by just being. In such a case, in order to clarify the basis for copy processing suppression (which management target document is used to restrict copy processing), as shown in screen 3-2, The document ID of the management target document is displayed. By doing so, the user can request the restriction of copy processing to be canceled or the restriction setting to be changed by consulting the document security administrator.

  When the FAX button 32 and the SEND button 33 in FIG. 3 are also pressed, the copying machine 1 executes the FAX function and the SEND function in the same manner as the copy button 31. If it is determined that the FAX process or the SEND process is restricted by referring to the document management index data 18b, the copying machine 1 determines that the FAX process or the SEND process is restricted as shown in screens 3-3 and 3-4 in FIG. The document ID of the management target document referenced in the document management index data 18b is displayed on the display device 15 together with the fact that the processing and the SEND processing are restricted.

  When the setting button 34 is pressed on the screen 3-1 in FIG. 3, the copying machine 1 displays a screen 3-5 shown in FIG. 3 on the display device 15. On this screen 3-5, the user can change the security information of the document managed in the document management index data 18b. If anyone can change the security information, there is no security meaning. Therefore, as shown in the screen 3-5, the copier 1 limits the authority to change the setting to only the document security administrator. The fields 35 and 36 are requested to input a login name and password, and user authentication is performed using the information.

  Further, as shown on the screen 3-5, the input field 37 is an input field for inputting a document ID to be registered. In addition, the user (document security manager) sets the attribute “permitted” or “prohibited” to the copy process, the FAX process, and the SEND process for the document specified by the document ID input in the input field 37. Can be set selectively. In the screen 3-5 in FIG. 3, “prohibited” is all selected. Finally, by pressing the setting button 38, the input security information is set in the document management index data 18b. Further, when the cancel button 39 is pressed, the setting input on the screen 3-5 becomes invalid.

FIG. 4 is a diagram illustrating an example of a document analysis function provided in the copying machine 1 according to the present embodiment.
As shown in the upper part of FIG. 4, the image data 4-1 shows an example of a scan image scanned by the scanner 16, and is a document image obtained by reading a paper document of an original by the scanner 16 and converting it into digital data. . First, the copying machine 1 performs block analysis on the image data 4-1. Block analysis is a process of dividing the document image 4-1 into rectangular blocks according to the properties of the blocks. As a result of the block analysis on the document image 4-1, the copying machine 1 divides the block into three blocks, a text block 4-2, an image block 4-3, and an image block 4-4 as shown in the lower part of FIG. The text block 4-2 is a block that is determined to be a text block by detecting that a sentence (text) is included therein. The remaining image blocks 4-3 and 4-4 are blocks that are determined to be image blocks by detecting that information (graph, photograph, etc.) other than text is included.

  In this embodiment, a method for detecting (determining) a text block or an image block is not particularly described, but various methods generally used in commercially available OCR (Optical Character Reader) software or the like are used. Good. The copying machine 1 performs character recognition processing and text extraction processing on the text block 4-2, but performs character recognition processing and text processing on the image blocks 4-3 and 4-4. The extraction process is not performed.

  Further, the copying machine 1 performs a process of extracting a keyword that is a feature of the text information based on the text information obtained as a result of the character recognition process performed on the text block 4-2. FIG. 5 is a diagram showing an example of text information extracted from the text block 4-2 in the copying machine 1 and an example of keyword data extracted from the text information.

  First, the copier 1 performs character recognition processing on the text block 4-2 of the scan image 4-1 shown in FIG. 4, and outputs text information 5-2 as OCR text information. Since it is character recognition processing, 100% accurate recognition is not always performed, and certain erroneous recognition data is included. In the figure, the character string to be “BX series” is “8 series”, and the character string to be “superphoto image quality” is “superphoto white matter”. Since such a misrecognized character cannot be matched, it is removed in advance. Since the character recognition rate in the character recognition process for word processor characters at the present time is an accurate process close to 100%, the number of misrecognized characters is small as a whole. Even if erroneously recognized words are excluded in this way, in the matching process according to the present embodiment, the sentence stays within the error range, and similar sentences can be extracted as a whole.

  There are many methods for removing erroneous recognition. Here, an example of erroneous recognition removal based on keyword extraction is shown. The copier 1 is prepared with a list of keywords (keyword dictionary) that can be analyzed in advance. Based on this keyword list, keywords included in the text information 5-2 are listed as extracted keyword data 5-3. . Since only the keywords listed in the keyword dictionary are listed, there are no unknown words, and the majority of misrecognitions are removed at this stage. Note that in the keyword dictionary, only words with specific parts of speech (nouns, proper nouns, sa-changing nouns) are registered so that the characteristics of the document can be easily understood. In the example shown in FIG. 5, “photograph”, “pursuit” and the like are picked up as shown in the keyword data 5-3, and “8 ○” not in the keyword dictionary is excluded.

  Next, the copying machine 1 determines whether the text content is similar to the text content of the management target document managed by the document management index data 18b based on the extracted keyword data 5-3. That is, the copying machine 1 stores information on keywords extracted from the text information of each management target document as information on document contents in the document management index data 18b.

  Here, details of the document management index data 18b will be described. FIG. 6 is a diagram showing a configuration example of the document management index data 18b shown in FIG. As shown in FIG. 6, the document management index data 18b is associated with a “document ID” 6-1 that specifies a management target document, “layout feature” 6-2, “text content feature” 6-3, “ Document control information "6-4 is stored.

  The “document ID” 6-1 is identification information that can uniquely identify the document (management target document). The “layout feature amount” 6-2 is information relating to the layout of the document specified by the “document ID” 6-1. The “layout feature” 6-2 is index information relating to the layout of each document for performing the above-described similarity search of document layouts. The copying machine 1 determines the similarity of the layout based on the “layout feature” 6-2. For example, the copying machine 1 converts image data of a document into a bitmap image, divides the bitmap image into n vertical and m horizontal rectangles, and sets average luminance information and color information of each rectangle as “ Stored in the document management index data 18b as "layout feature" 6-2. An example of an image feature amount for performing a similarity search is also proposed in, for example, Japanese Patent Laid-Open No. 10-260983, and this may be used.

  The “layout feature value” 6-2 is created based on a raster image received by the copying machine 1 from a PC or the like via a network during printing, and a scanned and digitized scan image at the time of copying / FAX / SEND. As described above, the copying machine 1 extracts the layout feature quantity of the document and performs “layout feature quantity” 6-2 of each management target document stored in the document management index data 18b when performing similar search of the document layout. The layout similarity is obtained by comparison.

  Next, “text content feature amount” 6-3 and “document control information” 6-4 shown in FIG. 6 will be described in detail with reference to FIGS. FIG. 7 is a diagram illustrating a configuration example of the “text content feature amount” 6-3 illustrated in FIG. As shown in FIG. 7, the “text content feature amount” 6-3 is a document vector corresponding to the text content of each management target document identified by the document ID, as index information for performing a similar search of text content. Store. The document vector is a word (keyword) included in the keyword dictionary as a dimension, and the value of each dimension of the document vector is the frequency of appearance of the word. As shown in FIG. 7, identification numbers 1, 2, 3,... Are assigned to each dimension. For example, dimension “2” is “photograph”, dimension “5” is “pursuit”, dimension. “8” corresponds to the word “model”. These words are words included in the keyword dictionary as shown in the keyword data 5-3 in FIG.

  However, in the “text content feature amount” 6-3 of the present embodiment, one word is not exactly one-dimensional, and the document vector is configured with the same or similar word group as one dimension. For example, in FIG. 7, the word “photo” is associated with the dimension “2” in addition to “photo”. The “text content feature amount” 6-3 stores, for each dimension, the appearance frequency included in the document in which the word corresponding to each dimension is specified by the document ID.

  Further, the document shown in FIG. 4 includes only one text block 4-2, but when a plurality of text blocks exist in one document, the copying machine 1 is extracted from all the text blocks. The keyword data is aggregated and information (document content feature amount) related to one document vector is created and stored in the document management index data 18b. Further, when searching for a document, the copying machine 1 creates vector data (query vector) in the same format as the document vector stored in the document management index data 18b from the scanned document serving as the search query. . As a result, the copying machine 1 compares the vector data of the scanned document with the document vector of each managed document referenced from the “text content feature value” 6-3 stored in the document management index data 18b, and determines the similarity. By searching, a similar search of sentence contents is performed.

  Next, the “document control information” 6-4 shown in FIG. 6 will be described. FIG. 8 is a diagram showing a configuration example of the “document control information” 6-4 shown in FIG. The “document control information” 6-4 stores security information indicating how to manage the document corresponding to each management target document identified by the document ID. Specifically, as security information, as shown in FIG. 8, copy processing control information 8-1 and FAX processing control information 8-2 are information that controls three types of operations in the copying machine 1 corresponding to the document ID. , SEND process control information 8-3 is stored.

  In the present embodiment, the “document control information” 6-4 is information that controls each operation in the copying machine 1 as copy processing control information 8-1, FAX processing control information 8-2, and SEND processing control information 8-3. As “0” or “1”. “1” is stored for each operation, and “0” is stored for suppression. In order to realize an embodiment in which the permission / inhibition control is changed for each user, for example, the “document control information” 6-4 is added to the three dimensions by adding a dimension of user information. This can be realized by configuring.

  In the example of FIG. 8, the document with document ID 6947 is copy process permission, FAX process permission, and SEND process permission, the document ID 6948 is only permitted with copy process, and the FAX process and SEND process are suppressed. Only the SEND process is permitted for the document with the document ID 6949, and the copy process and the FAX process are suppressed.

  Next, the vector data of the original scanned by the copying machine 1 is compared with the document vector of each managed document referred to from the “text content feature amount” 6-3 stored in the document management index data 18b, and the similarity (document The word importance level table to be referred to when obtaining the (content similarity) will be described. FIG. 9 is a diagram showing an example of the word importance table in the present embodiment. In FIG. 9, a word importance degree table 91 is a table showing the appearance frequency (appearance frequency) of each word in a document. As shown in FIG. 9, the identification number of each word (dimension) shown in “text content feature amount” 6-3 is used to identify each word. The copying machine 1 creates this word importance table 91 based on the frequency of occurrence of each word in all managed documents managed by the document management index data 18b, and is used to determine the similarity of the text contents. To do.

The copying machine 1 calculates the importance of each word as the reciprocal of the appearance frequency in the word importance table 91. Specifically, the importance w _k of the word k is _obtained by the following equation.
w _k = 1 / (frequency of word k)
Here, k = 1, 2, 3,..., N, and is a number indicating the identification number of each word (dimension) shown in “text content feature amount” 6-3.

  However, when the appearance frequency is 0, the importance of the word is also 0. This is because it is determined that a word that does not appear in any of the all management target documents managed by the document management index data 18b is not useful for similarity determination. The reason why the importance is the reciprocal of the appearance frequency is that a common word that appears frequently in many documents is relatively less important in determining the similarity of sentence contents.

Further, the copying machine 1 uses the following expression for the sentence content similarity TS (X, Q) of the management target document A and the manuscript B managed by the document management index data 18b in order to determine the similarity of documents. To calculate.

However, the document vector X of the management target document A = (x ₁ , x ₂ , x ₃ ,..., X _n ) and the query vector Q of the document B = (q ₁ , q ₂ , q ₃ ,..., Q _n ) And Here, the numbers 1 to n are identification numbers of the respective words (dimensions) shown in the “text content feature amount” 6-3. W _k is the importance of the word k.

As shown in the above formula, the sentence content similarity TS is the absolute difference in the frequency of appearance of all the words (from k = 1 to k = n) for the two documents to be compared (managed document A and manuscript B). The value multiplied by the importance w _k of the word is added and expressed as a negative value. By making it negative, the value of the sentence content similarity TS increases as the difference in appearance frequency decreases. That is, the larger the value of the sentence content similarity TS, the higher the similarity between the two documents to be compared.

  In the copying machine 1, the layout similarity LS between the management target document A and the original B is similarly increased as the similarity between both documents (the management target document A and the original B) increases. Use a formula that increases.

Further, the copying machine 1 obtains the total similarity S from the above-described sentence content similarity TS and layout similarity LS by the following expression.
S = α × TS + β × LS

  The total similarity obtained by the above formula is basically the sum of the text content similarity TS and the layout similarity LS, but the weight α depends on the importance of the text content similarity TS and the layout similarity LS. And β are added. α is a weight for the sentence content similarity, and β is a weight for the layout similarity. The values of α and β are variable and can be appropriately changed from the viewpoint of security management. If the relationship between the layout and confidentiality is low and only the text content needs to be checked, the layout similarity weight β is decreased. For example, if the layout is completely ignored, α = 1, β = 0, etc. On the other hand, if a certain security consideration is given to the layout like banknotes / securities, and if it is desired to place the same importance on the text content, α = 1, β = 1, etc. are set.

  The operation of the copying machine 1 will be described with reference to a flowchart.

  FIG. 10 is a flowchart showing the operation of the copying machine 1, more specifically, the processing procedure of the CPU 10. As shown in FIG. 10, first, in step S11-1, the CPU 10 performs a system initialization process. Specifically, the CPU 10 initializes various parameters, displays an initial screen, and the like.

  Next, in step S <b> 11-2, the CPU 10 generates some event such as an input from the input device 14 such as a touch panel or a request from a device / device connected directly or via the network via the communication device 20. This is a process of waiting in the microprocessor CPU. When an event occurs, in step S11-3, the CPU 10 determines the event that has occurred, and branches to various processes according to the type of event in step S11-4. In FIG. 10, a plurality of branch destination processes corresponding to various events are collectively expressed in the form of step S11-4.

  Specific processing in step S11-4 includes print processing, document management information setting processing, copy processing, FAX processing, and SEND processing, which will be described in detail with reference to FIGS. 11, 12, 13, 14, and 15. It becomes a part of the branch destination. As other processing, although details are not described, there are normal copying machine processing such as processing for setting the number of copies and processing for specifying a FAX destination and a SEND destination. Next, in step S11-5, the copying machine 1 performs a display process for displaying, on the display device 15, for example, the end of each process described above. This process is generally performed widely, such as an error display when there is an error and a display process when the process ends normally.

  Next, a printing process in the copying machine 1 will be described. FIG. 11 is a flowchart showing details of the printing process which is a part of the process of step S11-4 shown in FIG. The printing process in the copying machine 1 is a process that is started when an electronic file (document file) is instructed from a device such as a PC connected to the end of the network via the communication device 20. The copier 1 receives a raster image (bitmap image) of a document to be printed together with a print instruction.

  As shown in FIG. 11, first, in step S <b> 12-1, the copying machine 1 performs a normal printing process in which a printer 17 prints a received raster image of a document. Next, in step S12-2, the copying machine 1 performs block analysis on the raster image that has been subjected to printing processing, and specifies a text block and an image block.

  Next, in step S12-3, the copier 1 performs character recognition processing on the characters in the text block and extracts text information. In step S12-4, the copying machine 1 extracts a keyword from the extracted text information based on the keyword dictionary, and generates a document vector that is a text content feature amount. Next, in step S12-5, the copying machine 1 extracts a layout feature amount including an image feature amount from the raster image. Next, in step S12-6, the copying machine 1 prints the document content feature value extracted in step S12-4 and the layout feature value extracted in step S12-5 into the document management index data 18b. Is registered in association with the document ID that identifies the ID. As described above, the copying machine 1 can perform processing for registering document feature information (text content feature amount, layout feature amount) regarding a document that has been subjected to print processing in the document management index data 18b during print processing.

Next, document management information setting processing in the copying machine 1 will be described.
FIG. 12 is a flowchart showing details of the document management information setting process which is a part of the process of step S11-4 shown in FIG. As shown in FIG. 12, first, in step S13-1, the copying machine 1 displays the screen 3-5 shown in FIG. 3 on the display device 15 to thereby display the login name / password (user authentication) of the security administrator. And the user is prompted to input security information to be set for each document. In step S13-2, the copier 1 performs user authentication based on the input login name / password.

  Next, in step S13-3, the copying machine 1 determines whether the user authentication in step S13-2 has succeeded, that is, whether the authority to change the security information has been recognized by the user authentication. If the user authentication fails, the copying machine 1 ends the document management information setting process without changing the information of the document management index data 18b. If the user authentication is successful, the copying machine 1 registers the document security information in the “document control information” 6-4 of the document management index data 18b in accordance with the input information in step S13-4. After the registration process, the document management information setting process is terminated.

Next, a copy process in the copying machine 1 will be described.
FIG. 13 is a flowchart showing details of the copy process which is a part of the process of step S11-4 shown in FIG. As shown in FIG. 13, first, in step S14-1, the copying machine 1 reads a paper document on the document table with the scanner 16 to form a bitmap image. Next, in step S14-2, the copying machine 1 performs block analysis on the scanned bitmap image and separates it into text blocks, image blocks, and the like.

  Next, in step S14-3, the copying machine 1 performs character recognition processing on characters in the text block and extracts text information. Next, in step S14-4, the copying machine 1 extracts keywords from the extracted text information, and generates a query vector that is a sentence content feature amount. In step S14-5, the copying machine 1 extracts a layout feature amount such as an image feature amount from the bitmap image. Next, in step S14-6, the copying machine 1 calculates the overall similarity by obtaining the layout similarity and the sentence content similarity from the extracted feature amount as described above, and manages the most similar management target. The document ID of the document is specified.

  Next, in step S14-7, the copying machine 1 refers to the security information (“document control information” 6-4 shown in FIG. 8) of the specified document ID from the document management index data 18b. Next, in step S14-8, the copying machine 1 determines whether the referenced security information is permitted to be copied. If it is determined that the copy process is permitted, the copying machine 1 proceeds to step S14-9, performs a normal copy process, proceeds to step S14-10, and extracts the extracted document feature information ( A process of registering text content feature amounts and layout feature amounts) in the document management index data 18b is performed by a document registration process shown in FIG. If it is determined in step S14-8 that the copy process is prohibited (suppressed), the copying machine 1 proceeds to step S14-11 and determines the document ID of the management target document that is the basis for the copy process suppression. Processing to display on the display device 15 is performed.

Next, FAX processing in the copying machine 1 will be described.
FIG. 14 is a flowchart showing details of the FAX process that is a part of the process of step S11-4 shown in FIG. The processes shown in steps S15-1 to S15-7 in FIG. 14 are the same as the processes in steps S14-1 to S14-7 in FIG.

  Following step S15-7, in step S15-8, the copying machine 1 determines whether or not FAX processing is permitted in the security information. If permitted, normal FAX processing is performed in step S15-9. In step S15-10, the extracted document feature information is registered in the document management index data 18b by a document registration process shown in FIG. If the FAX processing is prohibited (suppressed) in step S15-8, the copying machine 1 proceeds to step S15-11, and displays the document ID of the management target document that is the basis for the FAX processing suppression on the display device 15. Process to be displayed.

Next, the SEND process in the copying machine 1 will be described.
FIG. 15 is a flowchart showing details of the SEND process which is a part of the process of step S11-4 shown in FIG. The processes shown in steps S16-1 to S16-7 in FIG. 15 are the same as the processes in steps S14-1 to S14-7 in FIG.

  After step S16-7, in step S16-8, the copying machine 1 determines whether or not the security information is SEND processing permitted. If permitted, the normal SEND processing is performed in step S16-9. In step S16-10, the extracted document feature information is registered in the document management index data 18b by a document registration process shown in FIG. If the SEND process is prohibited (suppressed) in step S16-8, the process advances to step S16-11, and the copying machine 1 displays the document ID of the management target document that is the basis for suppressing the SEND process on the display device 15. Process to be displayed.

Next, document registration processing in the copying machine 1 performed in steps S14-10, S15-10, and S16-10 shown in FIGS.
FIG. 16 is a flowchart showing processing (document registration processing) for registering document feature information (layout feature amount, text content feature amount) extracted in the copying machine 1 in the document management index data 18b. First, in step S17-1, the copying machine 1 registers the extracted document feature information in the document management index data 18b according to a predetermined format. In step S17-2, the copying machine 1 updates the word importance level table 91 based on the sentence content feature amount included in the document feature information.

  With the configuration described above, the copying machine 1 according to the present embodiment can determine whether or not copy processing or the like is possible based on the similarity of the text content, and thus comprehensively prohibits copy processing and the like of a document having a predetermined text content. If registered in the document management index data 18b, copy processing of documents having similar contents can be prohibited. That is, since security can be flexibly managed according to the document registered in the document management index data 18b, a copying machine (character processing device) with high operability can be provided. Furthermore, since the copying machine 1 can display the document ID of the document that is the basis for the prohibition of the copy process or the like when the copy process or the like is prohibited, the copy machine 1 can appropriately deal with the prohibition of the copy process or the like. For example, when the security administrator is requested to cancel the prohibition of copy processing or the like, if the document ID is specified, a solution according to the request can be promptly promoted. In addition, in this way, it is possible to construct a flexible system that can easily reflect the user's change request (request).

(Other embodiments)
The present invention is not limited to the above-described embodiment, and can be appropriately changed without departing from the gist of the present invention.

  In the above-described embodiment, only the operation permission / prohibition of copy processing, FAX processing, and SEND processing is assumed as a security control mode, but other implementation modes are also conceivable. For example, whether or not a watermark is imprinted on the document during each processing operation and whether or not additional information (such as “Distribution prohibited”) is added to the document may be added to the security control options.

  In addition, a message to be displayed on the display device 15 when the operation is prohibited may be designated (“This document is confidential” or the like). In this case, ON / OFF information of the message designating operation is added to the document control information, and print processing, FAX processing, SEND processing, or message display processing is performed according to the information. In this way, not only whether a replica can be created simply, but also the attention associated with the handling of the replica can be raised, and finer security management can be performed.

  Further, in the above-described embodiment, the similarity with all the management target documents managed by the document management index data 18b is determined based on the overall similarity S obtained from the layout similarity LS and the text content similarity TS, A document having a high similarity is specified. At this time, the weight α applied to the sentence content similarity TS and the weight β integrated to the layout similarity LS can be changed in a timely manner. Specific examples thereof are as follows. explain.

  For example, in some circumstances, document layout information (layout feature amount) may not be related to security control. Conversely, there are cases where layout information is important and sentence content is not important. Examples of the former are general confidential documents in the company, such as plans for strategic new products, unpatented patent specifications, etc.In such cases, the location of illustrations, logos, photographs, etc. attached to the documents Is often not important. Moreover, the latter example is a banknote, and those with different layouts can be ignored. In such a case, similarity determination in consideration of security can be realized by changing the weighting parameters α and β for similarity determination for each document. Specifically, this can be realized by registering the parameter information (values of the weighting parameters α and β) in the document management index data 18b for each document and using it. Note that the specific values of α and β registered in the document management index data 18b are specified by the user when the document is registered. By doing so, it is possible to appropriately control copy processing, FAX processing, SEND processing, and the like for documents having different properties from banknotes to general documents, and finer security management can be realized.

  In the above-described embodiment, each process of the copying machine 1 shown in FIGS. 10 to 16 is performed by reading a program for realizing the function of each process from the memory (ROM 12 or RAM 13) and executing it by the CPU 10. The function is realized.

  In order to implement the processes shown in FIGS. 10 to 16 in the copying machine 1, the present invention is not limited to the above-described configuration, and all or some of the functions of each process of the copying machine 1 are performed with dedicated hardware. It may be realized by hardware. The memory described above is not limited to the ROM 12 or the RAM 13, but is a non-volatile memory such as a magneto-optical disk device or a flash memory, a recording medium such as a CD-ROM that can only be read, and a volatile memory other than the RAM. May be configured by a computer readable / writable recording medium using a unidirectional memory or a combination thereof.

  Further, a program for realizing the function of each process of the copying machine 1 is recorded on a computer-readable recording medium, and the program recorded on this recording medium is read into a computer system and executed to execute each process. You can go. Here, the “computer system” includes an OS and hardware such as peripheral devices (scanner 16, printer 17, etc.). Specifically, after a program read from a storage medium is written to a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, the program is read based on the instructions of the program. It includes the case where the CPU of the function expansion board or function expansion unit performs part or all of the actual processing, and the functions of the above-described embodiments are realized by the processing.

  The “computer-readable recording medium” refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, and a CD-ROM, and a storage device such as a hard disk built in the computer system. Further, the “computer-readable recording medium” refers to a volatile memory (RAM) in a computer system that becomes a server or a client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line. In addition, those holding a program for a certain period of time are also included.

The program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the “transmission medium” for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.
The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

Further, a program product such as a computer-readable recording medium in which the above program is recorded can also be applied as an embodiment of the present invention. The above program, recording medium, transmission medium, and program product are included in the scope of the present invention.
The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes designs and the like that do not depart from the gist of the present invention.

1 is a block diagram illustrating a schematic configuration of a copying machine (information processing apparatus) according to an embodiment of the present invention. FIG. 2 is a diagram showing an example of an operation flow in the copying machine 1 shown in FIG. 1. FIG. 2 is a diagram showing a screen transition example of the display device 15 of the copying machine 1 shown in FIG. 1. 2 is a diagram illustrating an example of a document analysis function provided in the copying machine 1 according to the present embodiment. FIG. 3 is a diagram illustrating an example of text information extracted from a text block 4-2 in the copying machine 1 and an example of keyword data extracted from the text information. FIG. It is a figure which shows the structural example of the document management index data 18b shown in FIG. It is a figure which shows the structural example of "text content feature-value" 6-3 shown in FIG. FIG. 7 is a diagram illustrating a configuration example of “document control information” 6-4 illustrated in FIG. 6. It is a figure which shows an example of the word importance degree table in this embodiment. 4 is a flowchart showing an operation of the copying machine 1, more specifically, a processing procedure of the CPU 10. 11 is a flowchart showing details of a printing process that is a part of the process of step S11-4 shown in FIG. FIG. 11 is a flowchart showing details of a document management information setting process that is a part of the process of step S11-4 shown in FIG. 10; FIG. 11 is a flowchart showing details of a copy process that is a part of the process of step S11-4 shown in FIG. 11 is a flowchart illustrating details of a FAX process that is a part of the process of Step S11-4 illustrated in FIG. 10. 11 is a flowchart showing details of a SEND process that is a part of the process of step S11-4 shown in FIG. 6 is a flowchart showing processing (document registration processing) for registering document feature information (layout feature amount, text content feature amount) extracted in the copying machine 1 in the document management index data 18b.

Explanation of symbols

1 Copying machine 10 CPU
11 Bus 12 ROM
13 RAM
14 Input device 15 Display device 16 Scanner 17 Printer 18 HD (Hard disk)
19 Removable External Storage Device 20 Communication Device

Claims (8)

Reading means for reading a document in response to a processing request input by the input means, and outputting the read document as image data;
Character information extraction means for performing character recognition processing by specifying a character posting portion from the image data output by the reading means, and outputting first character information based on the recognized character data;
As information related to the control target document that is a target for controlling the document processing, second character information that is information related to characters included in the control target document, and one or more types of the document for the control target document Information storage means for storing at least control information for determining which of the processes is to be controlled;
Based on the first character information output by the character information extraction unit and the second character information of the control target document referenced from the information storage unit, the document contents of the manuscript and the control target document are Similarity determination means for determining whether or not they are similar;
A control target document whose document content is similar to that of the original is specified in accordance with the determination of the similarity determination unit, and the control information of the control target document specified from the information storage unit is referred to in response to the processing request for the original. An information processing apparatus comprising: processing determination means for determining whether or not document processing is possible. Layout information extracting means for extracting information relating to the layout of the document from the image data output by the reading means and outputting first layout information;
The information storage means further stores second layout information which is information relating to a layout of the control target document;
The similarity determination means is based on the first layout information output by the layout information extraction means and the second layout information referred to by the information storage means together with the similarity determination of the document contents. The information processing apparatus according to claim 1, wherein similarities of layouts are also determined.   The said 1st character information and said 2nd character information are the information regarding the specific keyword extracted from the character data of the said original and the said control object document, The Claim 1 or Claim 2 characterized by the above-mentioned. Information processing device.   The similarity determination means assigns a weight to each of the specific keywords, and whether the document contents of the document and the control target document are similar based on the first character information and the second character information The information processing apparatus according to claim 3, wherein it is determined whether or not. Display means;
Document identification information, which is information for identifying the control target document specified by the process determining unit according to the determination by the similarity determining unit when the process determining unit determines to prohibit the document processing according to the processing request. The information processing apparatus according to claim 1, further comprising display control means for displaying on the display means.   The display control means includes a control information change screen including at least an input means for inputting the document identification information of the control target document and a setting change means capable of changing the control information of the control target document. The information processing apparatus according to claim 5, wherein the information processing apparatus is displayed. A reading step of reading a document in response to a processing request input by the input means, and outputting the read document as image data;
A character information extraction step of performing character recognition processing by specifying a character placement portion from the image data output in the reading step, and outputting first character information based on the recognized character data;
As information related to the control target document that is a target for controlling the document processing, second character information that is information related to characters included in the control target document, and one or more types of the document for the control target document The first character information is output in the character information extraction step by referring to the second character information of the control target document from an information storage means for storing at least control information for determining which of the processing is to be controlled. A similarity determination step for determining whether or not the document content of the document to be controlled is similar to the character information of
In response to the determination of the similarity determination step, a control target document whose document content is similar to that of the original is specified, and the control information of the control target document specified from the information storage unit is referred to in response to the processing request for the original. An information processing method comprising: a process determination step for determining whether or not document processing is possible. A program for an information processing device,
A reading step of reading an original in accordance with a processing request input by an input means and outputting image data;
A character information extraction step of performing character recognition processing by specifying a character placement portion from the image data output in the reading step, and outputting first character information based on the recognized character data;
As information related to the control target document that is a target for controlling the document processing, second character information that is information related to characters included in the control target document, and one or more types of the document for the control target document The first character information is output in the character information extraction step by referring to the second character information of the control target document from an information storage means for storing at least control information for determining which of the processing is to be controlled. A similarity determination step for determining whether or not the document content of the document to be controlled is similar to the character information of
In response to the determination of the similarity determination step, a control target document whose document content is similar to that of the original is specified, and the control information of the control target document specified from the information storage unit is referred to in response to the processing request for the original. A program for causing a computer to execute a process determination step for determining whether document processing is possible.

Images