Information processing device and computer program product

Abstract

The information processing device and computer program product of the present invention can confirm the presence or absence of a specific image that should exist in a document without opening the document file. The image forming device (10) comprises: a document type determination unit (13) that determines the type of the document based on the read image of the document; a keyword acquisition unit (14) that acquires keywords corresponding to the determined document type from a keyword information storage unit (22); an image extraction unit (15) that extracts images that match the set search conditions as imprints in accordance with each keyword; a determination unit (16) that determines the presence or absence of imprints based on the image extraction result of the image extraction unit (15); and a determination result output unit (17) that outputs the determination result by including the determination result of the determination unit (16) for each keyword in the file name of the document.

Description

Technical Field

[0001] The present invention relates to an information processing device and a computer program product. Background Art

[0002] In recent years, image retrieval technology for retrieving images by specifying search terms in the same way as character strings has become popular. As a technology for setting keywords for images, for example, the following technology has been proposed: for images contained in a document in which character strings and images are mixed, words with high feature degrees are extracted from paragraphs describing each image extracted from the document as keywords to create an index, and images corresponding to the keywords in the index that match the input search terms are obtained (for example, Patent Document 1). In addition, the following technology has been proposed: Hypertext Markup Language (HTML) articles are analyzed, and for each image information, the closer the word is to the image information, the higher the score is given, and the image information is displayed in descending order of the scores of the words that match the specified search keyword (for example, Patent Document 2). In addition, Patent Documents 3 to 6 have been proposed.

[0003] In addition, the above-mentioned prior art is a technology that uses keywords to find images based on the premise that there are images in documents, etc., but on the contrary, sometimes it is desired to confirm whether there is a specific image that should exist in a document corresponding to a predetermined keyword, such as an imprint formed by a stamp. In this case, the document file must be opened to display it on the screen to confirm whether the document contains an image.

[0004] [Prior art literature]

[0005] [Patent Document]

[0006] Patent Document 1: Japanese Patent Application Publication No. 2010-205060

[0007] Patent Document 2: Japanese Patent Laid-Open No. 11-224256

[0008] Patent Document 3: Japanese Patent Application Publication No. 2001-337993

[0009] Patent Document 4: Japanese Patent Laid-Open No. 06-162107

[0010] Patent Document 5: Japanese Patent Application Publication No. 2010-286882

[0011] Patent Document 6: Japanese Patent Application Publication No. 2018-092459 Summary of the invention

[0012] [Problems to be solved by the invention]

[0013] However, the operation of opening a document file and displaying it on a screen in order to confirm the presence or absence of a specific image that should be in the document is time-consuming and troublesome.

[0014] An object of the present invention is to confirm the presence or absence of a specific image that should exist in a document without opening the document file.

[0015] [Technical means to solve the problem]

[0016] The information processing device of the present invention includes a processor, which determines the type of the document based on the read image of the processing object document, and obtains specific text corresponding to the type of the processing object document and associated with the specific image that should exist in the document by referring to specific text information. The specific text information is set for each document type and is information related to the specific text associated with the specific image that should exist in the document. The processor determines the presence or absence of a specific image that should exist in the processing object document in association with the specific text based on whether an image that meets pre-set search conditions can be extracted from the read image corresponding to the acquired specific text.

[0017] Furthermore, the processor presents a result of determination on the presence or absence of a specific image that should exist in association with the acquired specific character in the processing target document.

[0018] Furthermore, the processor sets the acquired specific characters and a determination result of the presence or absence of a specific image that should be associated with the specific characters in the processing target document as a group and includes them in the file name of the document.

[0019] Furthermore, the processor generates a file including a set of the acquired specific characters and a result of determining whether a specific image that should be associated with the specific characters exists in the processing target document.

[0020] Moreover, when the processor is able to extract an image that matches a pre-set exploration condition from the read image of the document corresponding to the acquired specific text, the processor extracts the image as a specific image that should exist in the processing object document in association with the specific text, and generates a file containing a group of the acquired specific text and the extracted image.

[0021] Moreover, in the information processing device of the present invention, the exploration condition includes at least one of the following conditions, namely: a condition for determining a specific image that should exist in association with the acquired specific text within the processing object document; or a condition for indicating the positional relationship between the specific text and a specific image that should exist in association with the specific text within the processing object document.

[0022] Furthermore, the condition for determining the specific image includes a condition related to at least one of a color or a shape included in the specific image.

[0023] Furthermore, the specific image is a print.

[0024] The computer program product of the present invention includes a computer program that enables a computer to implement the following functions: determining the type of the processing target document by analyzing the read image of the processing target document; obtaining specific text corresponding to the type of the processing target document and associated with a specific image that should exist in the document by referring to specific text information, wherein the specific text information is set with specific text associated with a specific image that should exist in the document for each document type; and determining the presence or absence of a specific image that should exist in the processing target document in association with the specific text based on whether an image that meets pre-set search conditions can be extracted from the read image corresponding to the acquired specific text.

[0025] [Effects of the Invention]

[0026] According to the invention described in claim 1, the presence or absence of a specific image that should exist in a document can be checked without opening the document file.

[0027] According to the invention described in claim 2, it is possible to confirm the result of determination of the presence or absence of a specific image that should be associated with a specific character in a document.

[0028] According to the invention described in claim 3, the determination result of whether or not a specific image that should be associated with a specific character exists in a document can be confirmed by the file name without opening the document file.

[0029] According to the invention described in claim 4, when there are a plurality of specific characters corresponding to the document type or when there are a plurality of documents to be processed, the determination result of the presence or absence of the specific image can be confirmed collectively.

[0030] According to the invention described in claim 5, when there is a specific image associated with specific characters, the specific image can be presented as a result of determination that there is a specific image.

[0031] According to the invention described in claim 6, it is possible to identify a specific image that should exist in association with specific characters.

[0032] According to the invention described in claim 7, a specific image that should exist in association with specific characters can be identified based on color or shape.

[0033] According to the invention described in claim 8, it is possible to determine whether or not there is a print that should exist in the document.

[0034] According to the invention described in claim 9, the presence or absence of a specific image that should exist in a document can be confirmed without opening the document file. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a block diagram showing the structure of an information processing device according to an embodiment of the present invention.

[0036] Figure 2 FIG. 4 is a diagram showing the hardware configuration of the image forming apparatus in this embodiment.

[0037] Figure 3 It is a diagram showing an example of the data structure of keyword information stored in the keyword information storage unit in the present embodiment.

[0038] Figure 4 It is a diagram showing an example of the data structure of the search condition information stored in the search condition information storage unit in this embodiment.

[0039] Figure 5 : is a flowchart showing the image presence / absence determination process in this embodiment.

[0040] Figure 6 This is a diagram showing a schematic layout of a document in which document types are classified into drawings in the present embodiment.

[0041] Figure 7 It is a diagram showing search conditions prepared in advance in this embodiment.

[0042] Figure 8 It is a diagram showing an example of individually setting search conditions in this embodiment.

[0043] [Explanation of Symbols]

[0044] 1: Network

[0045] 10: Image forming device

[0046] 11: Scanning data acquisition unit

[0047] 12: Text recognition processing unit

[0048] 13: Document type determination department

[0049] 14: Keyword acquisition department

[0050] 15: Image extraction unit

[0051] 16: Judgment Department

[0052] 17: Judgment result output unit

[0053] 21: Document type information storage unit

[0054] 22: Keyword information storage unit

[0055] 23: Exploration condition information storage unit

[0056] 24: Output format information storage unit

[0057] 31: CPU

[0058] 32: Address data bus

[0059] 33: Operation panel

[0060] 34: Scanner

[0061] 35: Hard disk drive (HDD)

[0062] 36: Printer Engine

[0063] 37: Network interface (I / F)

[0064] 38: RAM

[0065] 39: ROM

[0066] 40: External media interface (I / F) DETAILED DESCRIPTION

[0067] Hereinafter, preferred embodiments of the present invention will be described based on the drawings.

[0068] Figure 1 This is a block diagram showing a configuration of an embodiment of an information processing device of the present invention. In this embodiment, an image forming device having a built-in computer as an information processing device is described as an example.

[0069] Figure 2 1 is a hardware configuration diagram of the image forming apparatus 10 in this embodiment. The image forming apparatus 10 may be formed by a multifunction machine equipped with various functions such as a copy function and a scanner function. Figure 2In the image forming apparatus 10, the central processing unit (CPU) 31 controls the operation of various mechanisms such as the scanner 34 and the printer engine 36 according to the program stored in the read-only memory (ROM) 39. The address data bus 32 is connected to various mechanisms that are the control objects of the CPU 31 to communicate data. The operation panel 33 accepts instructions from the user and displays information. The scanner 34 reads the original document set by the user. The hard disk drive (HDD) 35 stores the electronic documents read by the scanner 34. The printer engine 36 prints the image on the output paper according to the instructions from the control program executed by the CPU 31. The network interface (I / F) 37 is connected to the network 1 and is used for sending electronic data generated by the image forming apparatus 10, receiving emails sent to the image forming apparatus 10, and accessing the image forming apparatus 10 via a browser. The random access memory (RAM) 38 is used as a working memory when executing a program or as a communication buffer when sending and receiving electronic data. The ROM 39 stores various programs related to the control of the image forming device 10 or the sending and receiving of electronic data. By executing various programs, each component described later performs a prescribed processing function. The external medium interface (I / F) 40 is an interface with an external memory device such as a universal serial bus (USB) memory and a flash memory. The hardware structure of the image forming device 10 in this embodiment may be the same as a certain structure in the past.

[0070] return Figure 1 The image forming apparatus 10 in this embodiment includes a scan data acquisition unit 11, a character recognition processing unit 12, a document type determination unit 13, a keyword acquisition unit 14, an image extraction unit 15, a determination unit 16, a determination result output unit 17, a document type information storage unit 21, a keyword information storage unit 22, a search condition information storage unit 23, and an output format information storage unit 24. In addition, components not used for explanation in this embodiment are omitted from the figure.

[0071] The scan data acquisition unit 11 acquires scan data (hereinafter also referred to as "read image") of a document read using a scanner 34. The document processed in the present embodiment is a document in which text characters containing specific characters and specific images are mixed. The so-called "specific characters" refer to text characters that are set for each type of document and are associated with a specific image that should exist in the document. In the present embodiment, the specific characters are referred to as "keywords". Moreover, in the present embodiment, as an example of a "specific image", an image of an imprint is assumed for explanation. The document processed in the present embodiment should contain an imprint by stamping, but sometimes the stamp may be forgotten and the imprint is not included. In addition, strictly speaking, what is located on the paper document is an imprint, and what is contained in the read image of the paper document is an image of the imprint, so the image of the imprint corresponds to the "specific image", but for the sake of convenience of explanation, the record corresponding to the "specific image" is sometimes described as an imprint.

[0072] The character recognition processing unit 12 performs character recognition by using an optical character reader (OCR) function, thereby extracting a character string (i.e., text characters) recorded in the read document. The document type determination unit 13 determines the type of the document based on the read image of the read document. The keyword acquisition unit 14 acquires a keyword associated with a print that should exist in the document corresponding to the type of the document by referring to specific character information, which is information related to specific characters (i.e., keywords) associated with a specific image (i.e., print) that should exist in the document. The specific character information is stored in the keyword information storage unit 22 as keyword information.

[0073] The image extraction unit 15 extracts an image that matches the search condition from the read image in accordance with the keyword acquired by the keyword acquisition unit 14. The search condition information related to the search condition is pre-set in the search condition information storage unit 23. The determination unit 16 determines whether there is a trace that should exist in association with the keyword in the processing target document based on whether the image extraction unit 15 can extract the image. The determination result output unit 17 outputs the determination result according to the specified output format. The output format information related to the output format is pre-set in the output format information storage unit 24.

[0074] Figure 3 2 is a diagram showing an example of the data structure of keyword information stored in the keyword information storage unit 22 in the present embodiment. The keyword information corresponds to each document type and includes one or more keywords corresponding to the document type.

[0075] Figure 42 is a diagram showing an example of the data structure of the search condition information stored in the search condition information storage unit 23 in the present embodiment. The search condition information is set for each document type. Figure 4 FIG. 1 shows an example of setting search condition information when the document type is drawings. In the search condition information, a search condition is set in association with each keyword corresponding to the document type. Figure 3 The examples are the approver, drafter, structure, designer and drawing checker, but if Figure 4 In the example, when the document type is a drawing, a search condition is set for each keyword. The search condition corresponding to each keyword includes a "condition for an image" for determining a trace that should exist in association with the acquired keyword in the processing target document, and a "positional relationship" for indicating a positional relationship between the keyword and the trace that should exist in association with the keyword in the processing target document. In addition, at least one of the "condition for an image" and the "positional relationship" may be included. Figure 4 In the setting example shown, the same item value is set for each keyword, but different search conditions may be specified depending on the layout of the document. The "condition for the image" may include a condition related to at least one of the color or shape included in the print. Figure 4 In the setting example shown, the “red circle” includes both red and a circular shape.

[0076] In addition, the document type information storage unit 21 and the output format information storage unit 24 will be described together with the description of their operations.

[0077] Each component 11 to component 17 in the image forming apparatus 10 is realized by the cooperative operation of a computer built into the image forming apparatus 10 and a program executed by a CPU 31 mounted on the computer. Furthermore, each storage unit 21 to storage unit 24 is realized by a HDD 35 mounted on the image forming apparatus 10. Alternatively, a RAM 38 or an external storage component may be used via a network.

[0078] Moreover, the program used in this embodiment can of course be provided through a communication component, or can be stored in a computer-readable recording medium such as a read-only CD (Compact-Disk Read-Only-Memory, CD-ROM) or a USB memory. The program provided from the communication component or the recording medium is installed in the computer, and the computer's CPU executes the program in sequence to achieve various processing.

[0079] The position of the stamp may be different depending on the type of document or the format of the document, but in the document processed in this embodiment, the stamp contains the imprint. However, depending on the situation, the following situation may occur: the document cannot be processed as a formal document due to forgetting to stamp. Therefore, in this embodiment, even if the document files are not opened one by one, it can be confirmed whether the stamp is forgotten.

[0080] Next, the operation of this embodiment will be described. In the following, the process of determining the presence or absence of a characteristic specific image (i.e., a print) in this embodiment will be described using Figure 5 The flowchart shown is used for explanation.

[0081] First, when the user causes the scanner 34 to read a document to be processed, the scan data acquisition unit 11 acquires the read image of the document (step S101). Then, the character recognition processing unit 12 performs character recognition using the OCR function to extract the character string recorded in the read document (step S102). When performing OCR, pre-processing such as uprighting of the read image or cleaning to remove the background color may also be performed.

[0082] Next, the document type identification unit 13 identifies the type of the document (step S103 ). Specifically, the document type is identified using any of the following methods.

[0083] First, when a data code such as a Quick Response (QR) code (registered trademark) for identifying the document format or identification information of the document is attached to the document, the data code is read. At this time, the document type corresponding to the data code is stored in the document type information storage unit 21 in association with the data code as document type information, and the document type determination unit 13 determines the type of the document by comparing the data code obtained from the read image with the data code included in the document type information.

[0084] Second, the type of document is determined by inference by analyzing the read image of the document, especially the layout. For example, the position of the grid lines on the document is detected and the layout of the grid lines is obtained. The type of document is inferred based on the layout of the grid lines. Or, in the case where the grid lines form a table, the names of the items contained in the table are extracted. At this time, in the document type information storage unit 21, for the type of document, a list of item names of the table is associated and stored as document type information, and the document type determination unit 13 determines the type of document by inference by comparing the list of item names of the table obtained from the read image with the list of item names contained in the document type information, thereby referring to the matching rate of the item names, etc.

[0085] Third, the file name in the document is extracted by analyzing the read image of the document. Generally speaking, the file name is recorded in the document, and its recording position is located in the top section or the center of the top of the document. Moreover, it is marked with brackets, or the text size is large. Therefore, the character string with such characteristics is inferred to be the file name for extraction. At this time, in the document type information storage unit 21, the file name is stored as document type information in association with the type of the document, and the document type determination unit 13 determines the type of the document by inference by comparing the file name obtained from the read image with the file name contained in the document type information.

[0086] Fourth, when the scanner 34 reads the document, the user is allowed to specify the document type. More specifically, when the scan data acquisition unit 11 reads the document, the document type determination unit 13 displays an input screen for the document type on the operation panel 33, and the user inputs the document type according to the input screen. Alternatively, the document type information storage unit 21 stores selection candidates for the document type, and when the scan data acquisition unit 11 reads the document, the document type determination unit 13 displays a selection screen for the document type on the operation panel 33. On the selection screen, the document types read from the document type information storage unit 21 are displayed in a list. And the document type determination unit 13 determines the document type as the document type selected by the user.

[0087] When the document type determination unit 13 determines the document type by any method, the keyword acquisition unit 14 acquires the keywords set corresponding to the determined document type from the keyword information storage unit 22 (step S104). Figure 3 In the illustrated setting example, when the document type specified by the document type specifying unit 13 is drawing, the keyword acquiring unit 14 acquires approver, drafter, structure, designer, and drawing checker from the keyword information storage unit 22 .

[0088] Next, the image extraction unit 15 repeatedly performs the following processing for each keyword obtained. First, an unprocessed keyword that has not yet been subjected to the following processing is selected (step S105). The order of the selected keywords does not need to be particularly limited. Then, the image extraction unit 15 compares the selected keyword with the character string obtained by the text recognition processing implemented in step S102 to determine the position of the keyword on the document. In addition, the text recognition processing can be re-implemented at this point in time without using the result of the text recognition processing implemented in step S102. Then, the image extraction unit 15 obtains the search conditions corresponding to the keyword that is the processing object and the type of document is drawing from the search condition information storage unit 23. For example, when the keyword is "approver", the image extraction unit 15 determines the position of the document printed as "approver". And, based on Figure 4In the example of setting the search condition shown in FIG. 1 , an image is extracted that is within 3 cm from the printing position of the keyword "approver" in the document, and is red in color and circular in shape (i.e., round) (step S106). In addition, the image extraction unit 15 confirms that there is a human name in the image. In addition, in the present embodiment, if there is a character string in the circle, it is inferred that the character string is a human name, but it can also be strictly verified by comparing it with a human name dictionary, etc., that it is not a company name or date, etc., but an actual name.

[0089] The determination unit 16 determines whether there is a mark associated with the keyword in the document by referring to the image extraction result of the image extraction unit 15. That is, when the image extraction unit 15 can extract an image that matches the search condition (Y in step S107), the determination unit 16 regards the image as a mark and determines that there is a mark (step S108). On the other hand, when the image that matches the search condition cannot be extracted (N in step S107), the determination unit 16 determines that there is no mark (step S109).

[0090] Figure 6 This is a diagram showing a schematic layout of a document whose document type is classified as drawing. Figure 6 In the document, there is a designated stamping area at the lower right of the document, and the person who needs to stamp should stamp there. Keywords are printed above the stamping area, and the user can confirm the stamping position based on the keywords. In addition, Figure 6 , a stamped stamp column 2 and an unstamped stamp column 3 are shown. A stamp should be confirmed at a position set with reference to the size of the stamp column, for example, within 3 cm below the printing position of the keyword, so if an image exists as in the stamp column 2, it is determined that there is a stamp. On the other hand, if no image exists as in the stamp column 3 (assuming the position of the keyword "drawing"), it is determined that there is no stamp.

[0091] The same processing is performed on the keywords that have not been processed as described above (N in step S110, steps S105 to S109). When the processing is performed on all the keywords acquired by the keyword acquisition unit 14 (Y in step S110), the determination result output unit 17 presents the determination result of the presence or absence of the imprint by the determination unit 16 (step S111). Specifically, the determination result is output using any of the output formats exemplified below.

[0092] First, in the first output format, the determination result is included in the file name of the document. The output format information stored in the output format information storage unit 24 defines a naming rule for the document file. For example, if the following naming rule is set in the output format information, that is, a keyword and a determination result of the presence or absence of a trace that should exist in association with the keyword are set as a group and included in the file name, such as "original file name + keyword + determination result", then when the original file name is "ABC", the keyword is "approver", and the trace is confirmed, the document file is named "ABC_approver_yes" according to the naming rule. On the other hand, when the original file name is "ABC", the keyword is "drawing", and the trace is not confirmed, the document file is named "ABC_drawing_no". In addition, "_" is a separator character for dividing each item value, but the separator character does not need to be limited to this. Moreover, the file name may not necessarily include a separator character. Moreover, when there are multiple keywords, multiple groups of keywords and the determination results of the presence or absence of a trace that should exist in association with the keyword are included in the file name, such as "ABC_approver_yes_drawing_no_...".

[0093] By including the determination result in the file name of the document in this way, the determination result of the presence or absence of a print can be confirmed without opening the document to refer to the content of the document.

[0094] In the second output format, a file containing the determination result is generated. In the output format information stored in the output format information storage unit 24, it is defined that a file (hereinafter referred to as "determination result file") is generated, and the file includes a keyword and a group of determination results of the presence or absence of the imprint that should exist in association with the keyword. In the case where the group of keywords and determination results is included in the file name as described above, when the number of keywords is large, the file name may become very long. Therefore, by adopting the second output format, it is possible to avoid the file name from becoming too long. In order to confirm the determination result, it may be necessary to open the determination result file. However, if the determination result file includes determination results for multiple documents, when confirming the determination results for multiple documents, it is only necessary to open one determination result file, and there is no need to open multiple document files one by one. Moreover, if the determination result file is generated independently of the document file, it is convenient to manage the presence or absence of the imprint. The determination result file is, for example, made as a comma separated values ​​(CSV) file. In addition, when generating a determination result file shared by multiple documents, it is preferred to associate the document name with the keyword and the determination result and register it in the determination result file.

[0095] The third output format is roughly the same as the second output format. However, in the second output format, as a judgment result, "yes" or "no" is included in the judgment result file. In contrast, in the third output format, when the judgment result is that there is an imprint, the imprint image itself is included in the file. That is, if there is an image that matches the search condition of the keyword, this image is regarded as an imprint and extracted from the read image of the document, and the keyword and the imprint associated with the keyword are set as a group and included in the file. In this way, not only can the presence or absence of an imprint be confirmed, but also the imprint itself can be confirmed if there is an imprint. Moreover, in the case where other images are mistakenly regarded as imprints and extracted, the user can confirm that it is a mistake. In addition, in the case of no imprint image, there is no image associated with the keyword, so that the judgment result can be confirmed as "no".

[0096] Here, additional explanation is given on the setting of exploration conditions.

[0097] The search condition information storage unit 23 must have search condition information set in advance. However, in the present embodiment, three methods of setting the search conditions included in the search condition information are provided.

[0098] First, conditions that can be designated as exploration conditions are prepared in advance (also referred to as "pre-set exploration conditions"), and an exploration condition is selected from the presets. Figure 7 The preset exploration conditions are shown. Among the preset exploration conditions, generally common conditions are set in combination. For example, in the case of a date stamp, the following specific conditions are preset, namely: the shape of the imprint is circular; the circular shape is divided into three segments; and the middle segment is the date. If this specific condition is feasible, the user only needs to select the preset date stamp as the exploration condition. Therefore, even if detailed conditions such as the shape of the imprint being circular are not set one by one, the exploration conditions can be set efficiently.

[0099] Second, search conditions are set one by one. In the first setting method, it is not possible to perform specific settings individually, so the second setting method enables individual settings. Figure 8 An example of individually setting search conditions is shown in . As the condition items to be set, color, position relative to a keyword, etc. can be set for each footprint. Figure 4 The setting examples shown follow this setting method.

[0100] Third, the exploration conditions are set more specifically. Examples of the exploration conditions that can be set are as follows: Figure 7The same, but the set content is more specific. For example, if the keyword is approver, then the manager who is in a certain degree of important position (post) becomes the approver, and the responsibility is also heavy. Therefore, for the keyword of approver, the seal image of the manager is pre-registered as the search condition of the seal (individual). In this way, when the seal to be approved is determined relative to a certain keyword, by pre-registering the image of this seal, a higher precision judgment result can be obtained. That is, even if the image presumed to be the imprint is arranged near the keyword "approver", if it does not match the image of the seal of the registered manager, the judgment result is still "none".

[0101] As described above, in this embodiment, the type of document is determined based on the read image of the document, and the keyword corresponding to the determined document type is obtained. Although it depends on the setting of the exploration condition, as long as there is an image near the keyword, it is inferred as a print associated with the keyword and the determination result of the presence of the print is obtained. In this way, in this embodiment, as long as the type of document can be determined and the keyword associated with the print can be determined, the presence or absence of the print can be determined, so it can be adapted to any document format. That is, it is not affected by the document format, so it is possible to obtain the determination result of the presence or absence of the print without having to deal with multiple types of document formats individually.

[0102] In addition, it is also conceivable that there are multiple character strings identical to the keyword in the document. In this case, conditions for specifying the keyword associated with the footprint from the multiple character strings may be preset to automatically select a character string, or the user may be allowed to select a character string.

[0103] In the above description, a print is used as an example as a specific image, but it is not limited to prints, and it can also be applied to various images such as logos, photos, maps, etc. If the presence or absence of a photo or a drawing is used as an example, the keyword is set to " Figure 1:" or the like. More specifically, a character string consisting of three elements, ① a character such as a picture, ② a number, and ③ a colon, is set as an evaluation value. It is sufficient to determine whether there are photos or drawings in the vicinity (up, down, left, and right). As for determining whether there are photos or drawings, since there is a technique for performing area determination in the prior art, it is sufficient to use this technique. In order to confirm not only the presence or absence of photos or drawings, but also whether they are photos or drawings corresponding to the characters that become keywords, as an example of correspondence, for example, photos or drawings that represent the contents of the keywords may be extracted from the text of the description that may be included in the description of the photos or drawings, and determine whether there are photos or drawings corresponding to the extracted description content. In this case, for example, it is possible to predetermine the corresponding text with the text that serves as the keyword. The photos or drawings related to the text extracted based on the text of the content of the description can also be used to create an article using artificial intelligence, and the degree of consistency with this article can be checked. The article uses text to explain what is recorded based on the structure of the photo or drawing. If a specific description is given, for example, when the caption of the photo records "Photo 1: Dog", and "dog" is set as the keyword, the existing image processing technology can be used to extract photos located around the caption (for example, a rule of priority can be set for above or below), and the extracted photos can be input into the artificial intelligence that determines the content of the photo, thereby obtaining a determination result of whether it is a dog. Alternatively, after receiving the determination result of the content of the photo, it can be determined whether the photo itself is really a dog. Moreover, for example, if taking the example of a map, in the case where the caption records " Figure 1 : Map of Tokyo", when the word Tokyo is extracted as a keyword, it is also possible to determine whether the correct map is configured based on whether the word "Tokyo" or place names related to Tokyo (such as Ginza, Roppongi, etc., which are located in Tokyo) are included in the map image. In this way, the present invention is an invention for determining whether a specific image corresponding to the word serving as a keyword is configured, and the specific image is of course not limited to the imprint, and whether a specific image is configured includes not only including the determination of whether the content of the image corresponds to the keyword as long as the image is configured.

[0104] Furthermore, in the present embodiment, since the read image of the document is used, the image forming device 10 is described as an example of the information processing device, but it may also be a computer such as a general-purpose personal computer (PC) that receives the read image of the document and performs processing.

[0105] In the described implementation mode, the so-called processor refers to a processor in a broad sense, including a general-purpose processor (e.g., a central processing unit (CPU)) or a dedicated processor (e.g., a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a programmable logic element, etc.).

[0106] Furthermore, the actions of the processor in the above-described embodiment may be performed not only by one processor but also by a plurality of processors located at physically separate locations in cooperation. Furthermore, the order of the actions of the processor is not limited to the order described in the above-described embodiment but may also be appropriately changed.

Claims

1. An information processing device, It is characterized in that Including processor, The processor determines the type of the document according to the read image of the document to be processed, By referring to specific text information, specific text associated with a specific image that should exist in the document corresponding to the type of the processing target document is obtained, wherein the specific text information is set for each document type and is information related to the specific text associated with the specific image that should exist in the document. The presence or absence of a specific image that should be associated with the specific text in the processing target document is determined based on whether an image that meets a preset search condition can be extracted from the read image corresponding to the acquired specific text, The processor presents a result of determining whether or not a specific image that should be associated with the acquired specific text exists in the processing target document. The processor groups the acquired specific text and the determination result of whether or not a specific image that should be associated with the specific text exists in the processing target document, and includes it in the file name of the document, or generates a file that includes the acquired specific text and the determination result of whether or not a specific image that should be associated with the specific text exists in the processing target document.

2. The information processing device according to claim 1, It is characterized in that When the processor is able to extract an image that matches a preset search condition from the read image corresponding to the acquired specific character, the processor extracts the image as a specific image that should exist in association with the specific character in the processing target document, And a file including a group of the acquired specific text and the extracted image is generated.

3. The information processing device according to claim 1, It is characterized in that The exploration condition includes at least one of the following conditions, namely: a condition for determining a specific image that should exist in association with the acquired specific text within the processing object document; or a condition representing the positional relationship between the specific text and a specific image that should exist in association with the specific text within the processing object document.

4. The information processing device according to claim 3, It is characterized in that The condition for determining the specific image includes a condition related to at least one of a color or a shape included in the specific image.

5. The information processing device according to any one of claims 1 to 4, It is characterized in that The specific image is a print.

6. A computer program product comprising a computer program for causing a computer to implement the following functions: By analyzing the read image of the processing object document, the type of the processing object document is determined; Acquire specific text associated with a specific image that should exist in the document, corresponding to the type of the processing target document, by referring to specific text information, wherein the specific text information is set with specific text associated with a specific image that should exist in the document for each document type; and The presence or absence of a specific image that should be associated with the specific text in the processing object document is determined based on whether an image that meets the preset exploration conditions can be extracted from the read image corresponding to the acquired specific text, and the determination result of the presence or absence of a specific image that should be associated with the acquired specific text in the processing object document is prompted. In the function of prompting the judgment result of whether or not a specific image that should be associated with the acquired specific text exists in the processing object document, the acquired specific text and the judgment result of whether or not a specific image that should be associated with the acquired specific text exists in the processing object document are set as a group and included in the file name of the document, or a file is generated, which includes the group of the acquired specific text and the judgment result of whether or not a specific image that should be associated with the acquired specific text exists in the processing object document.

Images