Information processing device and program

Abstract

To provide an information processing device and program which prevent information leakage of an image when there is an error in classification of an image in comparison to a case where at least a portion of the image is not displayed unclearly in a classification destination when classifying the image of a document.SOLUTION: An information processing device 1 comprises: an acquisition unit 111 which acquires image data indicating an image of a document read by an image reading device; a recognition unit 112 which performs optical character recognition processing to the image data acquired by the acquisition unit to recognize characters described in the document; a classification unit 113 which classifies the acquired image by using a rule defining an element of the image common to each type of the document indicated by the image; a processing unit 114 which generates an unclear image by performing obscuring processing to a region where at least one element other than the element defined by the rule used for the classification is displayed out of regions constituting the image classified by the processing unit; and a display control unit 118 which displays the unclear image generated by the processing unit on a terminal being a display device.SELECTED DRAWING: Figure 9

Description

[Technical Field]

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

[0002] There is a technology for partially hiding and displaying documents such as forms. The technology described in Patent Document 1 has an input means for receiving input of a document image to be processed and a mask image for hiding a partial area of the document image, and the document image and the mask image must be input in advance in association with each other.

[0003] The technology described in Patent Document 2 has a reading means for reading image data from a mark entry form on which blind marks are entered in positions corresponding to the positions where item information on the form is to be entered, and the blind marks must be entered on the form in advance. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-309622 [Patent Document 2] Japanese Patent Application Laid-Open No. 2009-153021 Summary of the Invention [Problem to be solved by the invention]

[0005] When scanned, form images are classified to be distributed to the person in charge of processing the form. If there is an error in the classification, the form image may be distributed to someone other than the person in charge of the form, and confidential information entered on the form may be leaked to someone other than the person in charge of the form.

[0006] To prevent information leakage of an image when an error occurs in classifying an image of a form, compared to when at least a part of the image is not displayed obscurely at the classification destination when classifying the image of the form. [Means for solving the problem]

[0007] The information processing device according to claim 1 of the present invention includes a processor, and the processor provisionally classifies an acquired image using rules that define elements of the image that are common to each type of form that the image represents, and performs the following operations without displaying the provisionally classified image on a display device: provisionally classified performing a process to obscure an area of the image in which at least one element, excluding elements determined by the rules used for classification, is displayed, and displaying the processed image on a display device; After processing The image is displayed on the display device. Therefore, the user in charge of the provisionally classified type of the image After displaying it, Applicable From the user After processing The information processing device receives an instruction regarding the classification of the image, and if the received instruction is an instruction to approve the classification, confirms the classification.

[0008] An information processing device according to claim 2 of the present invention is an information processing device in the aspect of claim 1, wherein the processor cancels the processing for at least a portion of the area when a predetermined condition is met, depending on the content of the condition.

[0009] The information processing device according to claim 3 of the present invention is an information processing device in the aspect of claim 1 or 2, in which, when the processor cancels the processing, it notifies a predetermined notification destination that the processing has been canceled.

[0010] The information processing device according to claim 4 of the present invention is an information processing device according to any one of claims 1 to 3, wherein the processor After processing When an instruction to cancel the processing for the area is received from the user as an instruction related to the classification of the image, the information processing device cancels the processing.

[0011] An information processing device according to claim 5 of the present invention is an information processing device in the aspect of claim 4, wherein the processor accepts an instruction to cancel the process when the user is authenticated.

[0012] The information processing device according to claim 6 of the present invention is an information processing device according to any one of claims 1 to 5, wherein the processor Suppose obscuring areas of the classified image that have a predetermined relationship to elements defined by the rules used for classification; After processing The image is displayed on the information processing device.

[0013] In the information processing device according to claim 7 of the present invention, in the aspect of any one of claims 1 to 6, when there are multiple candidates for classification of the acquired image, the processor classifies the image into each of the multiple types. Suppose Classify and picture The image is of the above multiple types Suppose When classified , painting There is one type of statue Suppose in a manner different from that in which it is classified, The items provisionally classified into the above multiple types The information processing device notifies the user of information relating to the classification of the image.

[0014] An information processing device according to claim 8 of the present invention is an information processing device according to claim 7, wherein the processor picture The image is of the above multiple types Suppose When classified, for each of the multiple types provisionally classified An instruction as to whether or not to approve the classification of the image is received from the user, and when an instruction to approve the classification of the image into any one of the plurality of types is received, The items provisionally classified into the above multiple types The image To other types This is an information processing device that cancels the classification.

[0015] An information processing device according to claim 9 of the present invention is an information processing device in a form described in any one of claims 1 to 8, wherein the processor cancels the classification of the image into one type when it receives an instruction to not approve the classification of the image into the one type.

[0016] The information processing device according to claim 10 of the present invention is the aspect of claim 8, wherein when the processor receives an instruction to not approve any of the classifications of the image into the plurality of types, it cancels the classification of the image into each of the plurality of types, Classification cancelled The information processing device notifies a predetermined notification destination that the type of the image is unknown.

[0017] The program according to claim 11 of the present invention includes a step of causing a computer having a processor to provisionally classify an acquired image using rules that define elements of the image that are common to each type of form that the image represents, and a step of performing the steps of: provisionally classified a step of performing a process of obscuring an area of the image in which at least one element is displayed, excluding elements determined by the rules used for classification, and displaying the processed image on a display device; After processing The image is displayed on the display device. Therefore, the user in charge of the provisionally classified type of the image After displaying it, Applicable From the user After processing The program executes the steps of: receiving an instruction regarding the classification of the image; and, if the received instruction is an instruction to approve the classification, confirming the classification. [Effects of the Invention]

[0018] According to the inventions of claims 1 and 11, when classifying images of a form, it is possible to prevent information leakage of the image when there is an error in classifying the image, compared to when at least a part of the image is not displayed obscurely at the classification destination. According to the invention of claim 2, when a predetermined condition is met, the user can check at least a portion of the contents of the area in which elements other than those specified by the rules used for classification are displayed. According to the invention of claim 3, the person receiving the notification at the notification destination can know that the obscuring process has been canceled for at least a portion of the area where elements other than those specified by the rules used for classification are displayed. According to the invention of claim 4, the user can confirm the contents of an area by instructing the cancellation of the obfuscation process for at least a portion of the area in which elements other than those defined by the rules used for classification are displayed. According to the invention of claim 5, when the user is authenticated, the user can issue an instruction to cancel the obfuscation process. According to the invention of claim 6, areas of the image of the form that have a predetermined relationship with the elements defined by the rules used for classification are difficult for the user to recognize. According to the invention of claim 7, the user can know whether or not the form classified into one type that he / she is in charge of is classified into another type. According to the invention of claim 8, when an image of a form is classified into multiple types and the classification of an image into one of those types is approved, the classification of the image into other types is canceled. According to the invention of claim 9, when the classification of an image of a form into one type is not approved, the classification of the image into that one type is cancelled. According to the invention of claim 10, when an image of a form is classified into multiple types and the classification of the image into any of those types is not approved, the classification of the image into those multiple types is canceled, and the person receiving the notification at the notification destination can know that the type of the image is unknown. [Brief explanation of the drawings]

[0019] [Figure 1] FIG. 1 is a diagram showing an example of the overall configuration of an information processing system 9. [Figure 2] FIG. 1 is a diagram showing an example of the configuration of an information processing device 1. [Figure 3] FIG. 10 is a diagram showing an example of a type DB 121. [Figure 4] FIG. 4 is a diagram showing an example of a user DB 122. [Figure 5] FIG. 10 is a diagram showing an example of a rule DB 123. [Figure 6] FIG. 2 is a diagram showing an example of a classification state DB 124. [Figure 7] FIG. 2 is a diagram showing an example of the configuration of a terminal 2. [Figure 8] FIG. 2 is a diagram showing an example of the configuration of an image reading device 4. [Figure 9] FIG. 2 is a diagram showing an example of the functional configuration of the information processing device 1. [Figure 10] FIG. 4 is a flowchart showing an example of the flow of classification operations performed by the information processing device 1. [Figure 11] 4 is a flowchart showing an example of the flow of a display operation by the information processing device 1. [Figure 12] FIG. 10 is a diagram for explaining the classification destination of an image. [Figure 13] FIG. 4 is a diagram showing an example of a list of files stored in a folder. [Figure 14] 4 is a flowchart showing an example of the flow of a reception operation by the information processing device 1. FIG. [Figure 15] FIG. 10 is a diagram showing an example of an unclear image G1. [Figure 16] FIG. 10 is a diagram showing an example of a dialog box W2 displayed to the user. [Figure 17] 10A and 10B are diagrams showing examples of an unclear image G2 and an original image G0. [Figure 18] FIG. 10 is a diagram showing an example of the flow of notification operations when classified into multiple types. DETAILED DESCRIPTION OF THE INVENTION

[0020] <Embodiment> <Configuration of information processing system> Fig. 1 is a diagram showing an example of the overall configuration of an information processing system 9. The information processing system 9 shown in Fig. 1 is a system that reads forms and assigns attributes to the forms. As shown in Fig. 1, the information processing system 9 has an information processing device 1, a terminal 2, a communication line 3, and an image reading device 4.

[0021] The information processing device 1 is a device that classifies forms by type based on an image showing the form. The information processing device 1 is, for example, a computer.

[0022] The terminal 2 is a terminal device operated by each user of the information processing system 9, and is, for example, a personal computer.

[0023] The image reading device 4 is a device that reads a document on which information is written on a medium such as paper, for example, a slip, and outputs image data showing the corresponding image.

[0024] The communication line 3 is a line that communicatively connects the information processing device 1, the terminal 2, and the image reading device 4. The communication line 3 may be, for example, a LAN (Local Area Network), a WAN (Wide Area Network), the Internet, or a combination thereof.

[0025] The number of information processing devices 1, terminals 2, communication lines 3, and image reading devices 4 in the information processing system 9 is not limited to those shown in Fig. 1. For example, the information processing device 1 may be configured as a cluster system in which multiple devices share functions.

[0026] <Configuration of information processing device> Fig. 2 is a diagram showing an example of the configuration of an information processing device 1. The information processing device 1 shown in Fig. 2 has a processor 11, a memory 12, and an interface 13. In other words, this information processing device 1 is an example of an information processing device having a memory and a processor. These components are connected to each other so that they can communicate with each other, for example, by a bus.

[0027] The processor 11 reads and executes a program stored in the memory 12 to control each part of the information processing device 1. The processor 11 is, for example, a CPU (Central Processing Unit).

[0028] The interface 13 is a communication circuit that communicatively connects the information processing device 1 to the terminal 2 and the image reading device 4 via the communication line 3, either wired or wirelessly.

[0029] The memory 12 is a storage means for storing an operating system, various programs, data, etc., which are loaded into the processor 11. The memory 12 includes a random access memory (RAM) and a read only memory (ROM). The memory 12 may also include a solid state drive, a hard disk drive, etc. The memory 12 also stores a type DB 121, a user DB 122, a rule DB 123, and a classification state DB 124.

[0030] Fig. 3 is a diagram showing an example of the type DB 121. The type DB 121 is a database that stores the types of forms. In addition to the types of forms, the type DB 121 shown in Fig. 3 also stores image data of forms classified by those types. The type DB 121 shown in Fig. 3 has a type ID list 1211 and an image data group 1212.

[0031] The type ID list 1211 stores, for each type of form, a type ID, a type name, and a classification destination in association with each other. The type ID is identification information that identifies the type of form. The type name is the name of the type of form. The classification destination is identification information such as a character string that identifies the "classification destination" where forms of the corresponding type are classified and stored, and is, for example, a path in a file system. The classification destination may be a URI (Uniform Resource Identifier).

[0032] The image data group 1212 shown in FIG. 3 is a data group associated with each of the classification destinations listed in the type ID list 1211, and stores the form ID, image data, and blur level in association with each other.

[0033] The form ID is identification information that is assigned to a form read by the image reading device 4 in a predetermined unit, such as one page.

[0034] The image data is image data showing an image of the form identified by the corresponding form ID when it is displayed under the classification destination to which this image data group 1212 is linked. If an obscuring process (hereinafter also referred to as an obscuration process) has been applied to image data showing an image of the form, this image data is image data generated by the obscuring process. An image of a form that has not been subjected to obscuring process is also called an "original image," and an image of a form that has been subjected to obscuring process is also called an "obscured image."

[0035] The blur level is information indicating the degree to which the document has become blurred by the above-described blurring process.

[0036] 4 is a diagram showing an example of the user DB 122. The user DB 122 is a database that stores users and the types of forms for which the users are responsible, in association with each other.

[0037] The user DB 122 shown in FIG. 4 stores user IDs, authentication information, and responsible information in association with each other.

[0038] The user ID is identification information that identifies a user. The authentication information is information used to authenticate a user identified by the corresponding user ID, such as a password that only the user knows.

[0039] The responsibility information is information indicating the type of form for which the user identified by the corresponding user ID is responsible. The responsibility information shown in FIG. 4 is a type ID indicating the type of form for which the user is responsible. Being responsible for a type of form means having at least the authority to view that type of form and performing work using that type of form. Note that one user may be responsible for multiple types of forms, and one type of form may be responsible for multiple users.

[0040] FIG. 5 is a diagram showing an example of the rule DB 123. The rule DB 123 is a database that stores rules used to classify forms. The rule DB 123 stores, for each type, elements that are common to images of multiple forms that are classified into a common type. These elements are included in the above-mentioned rules. The rule DB 123 shown in FIG. 5 stores columns for type ID, target, element, and condition, each associated with the other.

[0041] The type ID shown in FIG. 5 is identification information for identifying the type of the form, and is information common to the type ID in the type DB 121.

[0042] The target shown in Figure 5 is information indicating the target of the form to be inspected when classifying the type of form identified by the corresponding type ID. For example, "full text" refers to all character strings (hereinafter simply referred to as "full text") obtained by applying optical character recognition to an image showing the entire form of that type. Also, "layout" refers to the actual arrangement of each element included in that type of form, such as ruled lines, frame lines, seal impressions, character strings, etc.

[0043] The elements shown in Fig. 5 are information indicating the elements to be compared with the above-mentioned targets when classifying the type of form identified by the corresponding type ID. Also, the conditions shown in Fig. 5 are information indicating the conditions when comparing the above-mentioned targets with the elements.

[0044] For example, in the rule DB 123 shown in Fig. 5, a form of the type identified by type ID "T2" is searched for within its entire text for a character string that contains the element "receipt" and that satisfies the following conditions: size is "15pt or more," placement is "top," and match rate is "100%." If this character string is found within the entire text of the form, the form is classified into the type identified by type ID "T2."

[0045] The above-mentioned elements may be defined as either one of two or more character strings. For example, in the rule DB 123 shown in FIG. 5, a form of a type identified by type ID "T1" has an element "Placement order or Order." In this case, the information processing device 1 searches the entire text of the form for either the character string "Placement order" or the character string "Order" that satisfies the corresponding condition. If either of these character strings is found in the entire text of the form, the form is classified into the type identified by type ID "T1."

[0046] Furthermore, when the target is a full text, the element to be compared is a character string, but when the target is a layout, the element may be a pre-prepared template or template image. For example, a form of the type identified by type ID "T5" in the rule DB 123 shown in Figure 5 has its layout compared with the template image identified by Template A. If the combined match rate for all items, such as line thickness, length, placement, and number, is 95% or higher, the form is classified as the type identified by type ID "T5."

[0047] Fig. 6 is a diagram showing an example of the classification state DB 124. The classification state DB 124 is a database that stores, for each scanned form, the state in which that form is classified. The classification state DB 124 shown in Fig. 6 stores columns for form ID, form name, form data, and classification state, each associated with the other.

[0048] 6 is identification information assigned to a form, and is information common to the form ID in the type DB 121. The form name is a character string indicating the name of the form identified by the corresponding form ID.

[0049] The form data shown in FIG. 6 is a set of image data showing an image of a form identified by the corresponding form ID when it is read, and the entire text extracted from the image data.

[0050] The classification state shown in FIG. 6 is information indicating the classification state of the form identified by the corresponding form ID.

[0051] For example, in the classification state DB 124 shown in Fig. 6, the form name of the form identified by the form ID "D1" is "Form #1." This form is provisionally classified into a type identified by the type ID "T1."

[0052] Here, "provisional classification" refers to the information processing device 1 provisionally classifying form images by type using the rule DB 123. For example, a provisional classification is a classification before the classification is finalized. The information processing device 1 may request user approval when finalizing the classification of all forms. Furthermore, the information processing device 1 may decide whether to finalize the classification or make it a provisional classification depending on the degree of certainty of the classification using the rule DB 123 (also referred to as classification certainty). The classification certainty is determined, for example, by whether the matching rate exceeds a threshold, whether the types to be classified have been narrowed down to one, etc.

[0053] <Device configuration> Fig. 7 is a diagram showing an example of the configuration of the terminal 2. The terminal 2 shown in Fig. 7 has a processor 21, a memory 22, an interface 23, an operation unit 24, and a display unit 25. These components are connected to each other so that they can communicate with each other, for example, by a bus.

[0054] The processor 21 reads and executes programs stored in the memory 22 to control each part of the terminal 2. The processor 21 is, for example, a CPU.

[0055] The memory 22 is a storage means for storing an operating system, various programs, data, etc., which are loaded into the processor 21. The memory 22 includes RAM and ROM. The memory 22 may also include a solid state drive, a hard disk drive, etc.

[0056] The interface 23 is a communication circuit that connects the information processing device 1 and the image reading device 4 to the terminal 2 so that they can communicate with each other via the communication line 3, either wired or wirelessly.

[0057] The operation unit 24 is equipped with operation buttons, a keyboard, a touch panel, a mouse, and other operators for issuing various instructions, and receives operations and sends signals to the processor 21 according to the contents of the operations.

[0058] The display unit 25 has a display screen such as a liquid crystal display, and displays images under the control of the processor 21. A transparent touch panel of the operation unit 24 may be placed on top of the display screen.

[0059] The terminal 2 displays an image of a form under the control of the information processing device 1. Therefore, the terminal 2 is an example of a display device that displays an image of a form under the control of the information processing device 1.

[0060] <Configuration of image reading device> Fig. 8 is a diagram showing an example of the configuration of the image reading device 4. The image reading device 4 shown in Fig. 8 has a processor 41, a memory 42, an interface 43, an operation unit 44, a display unit 45, and an image reading unit 46. These components are connected to each other so that they can communicate with each other, for example, by a bus.

[0061] The processor 41 reads and executes a program stored in the memory 42 to control each part of the image reading device 4. The processor 41 is, for example, a CPU.

[0062] The memory 42 is a storage means for storing an operating system, various programs, data, etc., which are loaded into the processor 41. The memory 42 includes RAM and ROM. The memory 42 may also include a solid state drive, a hard disk drive, etc.

[0063] The interface 43 is a communication circuit that connects the information processing device 1 and the terminal 2 with the image reading device 4 so that they can communicate with each other via the communication line 3, either wired or wirelessly.

[0064] The operation unit 44 includes operation buttons, a touch panel, and other operators for issuing various instructions, and receives operations and sends signals to the processor 41 according to the operation contents.

[0065] The display unit 45 has a display screen such as a liquid crystal display, and displays images under the control of the processor 41. A transparent touch panel of the operation unit 44 may be placed on top of the display screen.

[0066] The image reading unit 46 includes a platen glass, an irradiation device that irradiates light onto a medium, an optical system that collects reflected light, and an imaging element such as a CMOS (Complementary Metal Oxide Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. Under the control of the processor 41, the image reading unit 16 reads an image formed on a form placed on the platen glass, generates image data representing the read image, and supplies the image data to the processor 41. A form is a medium such as paper that conveys information by forming characters, etc. on it. The image reading unit 46 may also include an automatic document feeder (ADF) that transports forms one page at a time.

[0067] <Functional configuration of information processing device> 9 is a diagram illustrating an example of the functional configuration of the information processing device 1. The processor 11 of the information processing device 1 executes a program stored in the memory 12 to function as an acquisition unit 111, a recognition unit 112, a classification unit 113, a processing unit 114, a reception unit 115, an authentication unit 116, a notification unit 117, and a display control unit 118.

[0068] The acquisition unit 111 acquires image data indicating an image of a form read by the image reading device 4 and the name of the form designated by the user, that is, the form name.

[0069] The recognition unit 112 performs optical character recognition processing on the image data acquired by the acquisition unit 111, recognizes the characters written on the form, and generates the above-mentioned full text.

[0070] The classification unit 113 classifies the acquired images using the rule DB 123. As described above, this rule DB 123 stores, for each type, rules that include elements common to images of multiple forms classified into a common type.

[0071] In other words, the processor 11 functioning as this classification unit 113 is an example of a processor that classifies acquired images using rules that define elements of the image that are common to each type of form that the image represents.

[0072] 9 classifies an image of a form into each of the multiple classification candidates. In other words, the processor 11 functioning as the classification unit 113 is an example of a processor that classifies an acquired image of a form into each of the multiple classification candidates.

[0073] Every time the classification unit 113 shown in FIG. 9 classifies a form, it stores information on the state in which the form is classified in the classification state DB 124.

[0074] The processing unit 114 refers to the classification state DB 124 and performs an obscuration process on an area that constitutes an image classified by the classification unit 113 and in which at least one element other than the element specified by the rule used for the classification is displayed.

[0075] In other words, the processor 11 functioning as this processing unit 114 is an example of a processor that performs processing to obscure the area in the image of a classified form in which at least one element is displayed, excluding the elements specified by the rules used for classification.

[0076] The processing unit 114 shown in Figure 9 reads image data of a form that is shown to have been provisionally classified into one of the types in the classification status DB 124, and identifies an area in which at least one element is displayed, excluding elements that were used when classifying the form into that type and are stored in the rule DB 123.

[0077] The processing unit 114 then performs an obfuscation process on the identified region to obscure the content written in the region. This obfuscation process may be, for example, a process called Gaussian blurring. Alternatively, this obfuscation process may be a process in which the image in the region is subjected to a logical OR or exclusive OR operation between the image and a predetermined mask pattern, and the region is overwritten with the result of the operation. In this case, the predetermined mask pattern may be, for example, a shading or a solid fill. Alternatively, this obfuscation process may be performed using an averaging filter that averages pixel values for each pixel group of a predetermined size.

[0078] The processing unit 114 stores the image data generated by the blurring process in the image data group 1212 of the type DB 121, and sets a corresponding blurring level.

[0079] The reception unit 115 receives a pair of a user ID that identifies a user and authentication information for that user via the terminal 2. The authentication unit 116 compares the received pair of the user ID and authentication information with the stored contents of the user DB 122 and attempts to authenticate the user identified by the user ID. If the authentication of the user is successful, the authentication unit 116 notifies the processing unit 114 to that effect.

[0080] Furthermore, the reception unit 115 receives user instructions regarding the classification of the form image from the terminal 2. For example, when the form image is classified into a certain type, the reception unit 115 receives an instruction from the user in charge of that type regarding whether or not to approve the classification of the form image into that type.

[0081] When an image of a form is classified into a certain type, a user in charge of that type looks at an unclear image of the form, judges whether the classification is correct or not, and instructs the information processing device 1 via a terminal 2 whether to approve the classification or not.

[0082] When the accepting unit 115 accepts an instruction from the user to approve the classification of the image of the form, the classifying unit 113 updates the classification state DB 124 to finalize the classification.

[0083] On the other hand, if the receiving unit 115 receives an instruction from the user to not approve the classification of the image of the form, the classification unit 113 updates the classification status DB 124 and cancels the classification. In other words, the processor 11 functioning as this classification unit 113 is an example of a processor that, when receiving an instruction to not approve the classification of the image of the form into one type, cancels the classification of the image into that one type. When the classification unit 113 updates the classification status DB 124 and cancels the above-mentioned classification, the processing unit 114 updates the type DB 121 according to the content of this update. As a result, the above-mentioned form will no longer be confirmed in the classification destination related to the canceled classification.

[0084] When a form image is classified into multiple types, the receiving unit 115 receives instructions from the user as to whether or not to approve the classification of the form image for each of the multiple types. Here, when the receiving unit 115 receives an instruction to approve the classification of the image into one of the multiple types, the classification unit 113 confirms the classification of the image into that "one type" and cancels the classification of the image into other types.

[0085] In other words, the processor 11 functioning as the reception unit 115 and classification unit 113 is an example of a processor that, when an image of a form is classified into multiple types, receives instructions from the user as to whether or not to approve the classification of the image for each of those multiple types, and, if it receives an instruction to approve the classification of the image into one of those multiple types, cancels the classification of the image into another type.

[0086] Furthermore, for example, the receiving unit 115 receives an instruction to cancel at least a part of the obfuscation process for the above-mentioned region.

[0087] The reception unit 115 may accept this cancellation instruction only from authenticated users and not from unauthenticated users. The processor 11 functioning as this reception unit 115 is an example of a processor that accepts an instruction to cancel the process of obscuring an area when a user is authenticated. The reception unit 115 may also determine for each form whether to accept an instruction to cancel the above-mentioned obfuscation process from a user. In this case, the reception unit 115 may determine whether user authentication is required depending on, for example, the provisional classification state of each individual form. The reception unit 115 may request user authentication when a form is classified as a highly confidential type.

[0088] When the receiving unit 115 receives an instruction to cancel at least a part of the obfuscation process for the above-mentioned region, the processing unit 114 cancels the obfuscation process in accordance with the instruction. The receiving unit 115 and the processor 11 functioning as the processing unit 114 are an example of a processor that receives an instruction from a user to cancel the process of obscuring an element written in an area where at least one element, excluding elements determined by the rules used for classification, is displayed in an image of a classified form, and cancels the process when the instruction is received from the user.

[0089] The notification unit 117 issues various notifications to predetermined notification destinations or users in accordance with the classification by the classification unit 113 and the processing by the processing unit 114.

[0090] When processing unit 114 cancels the obfuscation process in accordance with a user's instruction, notification unit 117 may notify a predetermined notification destination to that effect. As a result, for example, an administrator of information processing system 9 or the like may know that the obfuscation process has been canceled by an email or the like sent from information processing device 1. In other words, processor 11 functioning as this notification unit 117 is an example of a processor that, when the process of obfuscating an area has been canceled, notifies a predetermined notification destination that the process has been canceled.

[0091] In addition, the notification unit 117 may not provide a notification when the obfuscation process is released for a portion of the image, and may provide a notification when the obfuscation process is released for the entire image, or vice versa.

[0092] Furthermore, when a form image is classified into a plurality of types, the notification unit 117 may notify the user of information regarding the classification of the image in a manner different from when the form image is classified into one type. When a form image is classified into a plurality of types, the notification unit 117 notifies the user who is checking the form image as a person in charge of one of the plurality of types, for example, by displaying on the terminal 2 that the form image is also classified into another type.

[0093] In this case, the processor 11 functioning as this notification unit 117 is an example of a processor that notifies the user of information regarding the classification of an image when the image is classified into multiple types in a manner different from when the image is classified into one type.

[0094] Furthermore, for example, when an image of a form is classified into a plurality of types and none of the classifications of the image into the plurality of types is approved by the user, the notification unit 117 may notify a predetermined notification destination, such as an administrator of the information processing system 9, that the type of the image is unknown. Then, at this time, the classification unit 113 may cancel all of the classifications of the image of the form into the plurality of types.

[0095] In this case, the processor 11 functioning as this notification unit 117 and this classification unit 113 is an example of a processor that, when it receives an instruction to not approve any of the classifications of a document image into multiple types, cancels the classification of the image into each of those multiple types and notifies a predetermined notification destination that the type of the image is unknown.

[0096] The display control unit 118 causes the terminal 2 to display an image in accordance with the processing by the processing unit 114. For example, the display control unit 118 causes the terminal 2, which is a display device, to display an unclear image generated by the processing unit 114. The user looks at the unclear image and determines whether the form indicated by the unclear image has been classified into the type for which the user is responsible. In the unclear image, areas other than the elements used in the classification are obscured, so the user cannot grasp the content written in those areas. Furthermore, because the unclear image does not obscure the elements used in the classification, the user can confirm those elements.

[0097] <Operation of information processing device> <Classification behavior> 10 is a flow diagram showing an example of the flow of the classification operation by the information processing device 1. The processor 11 of the information processing device 1 monitors the image reading device 4 via the communication line 3 and the interface 13, and determines whether or not a new form has been read by the image reading device 4 (step S101). The processor 11 continues this determination while determining that a new form has not been read (step S101; NO).

[0098] When it is determined that a new form is to be read (step S101; YES), the processor 11 acquires the form name indicating the read form from the image reading device 4 and image data indicating an image of the form (step S102).

[0099] Processor 11 assigns a form ID to the acquired pair of form name and image data (step S103). Processor 11 also performs optical character recognition on the acquired image data to generate the character string written on the form, i.e., the above-mentioned full text (step S104). Processor 11 associates the assigned form ID, the acquired form name, image data, and the generated full text with each other and stores them in classification state DB 124.

[0100] Next, processor 11 classifies the image of the form described above using each rule with reference to rule DB 123. Processor 11 first determines whether or not there is an unused rule in rule DB 123 (step S105).

[0101] If it is determined that there is an unused rule (step S105; YES), the processor 11 judges the image of the form described above using this unused rule (step S106).

[0102] Processor 11 determines whether the form image satisfies the conditions defined in the above-mentioned rules as a result of the determination in step S106 (step S107). If it is determined that the form image does not satisfy the conditions (step S107; NO), processor 11 returns the process to step S105.

[0103] On the other hand, if it is determined that the image of the form satisfies the condition (step S107; YES), processor 11 provisionally classifies the image into the type associated with the condition (step S108), and then returns the process to step S105.

[0104] In step S108, processor 11 may classify the image of the form into the above-mentioned type depending on the degree to which the image satisfies the conditions determined in step S107. For example, if the likelihood that the image of the form will be classified into the corresponding type according to the above-mentioned rules exceeds a predetermined threshold, processor 11 may confirm the classification rather than provisionally classifying the image into that type. In this case, processor 11 does not need to ask the user for approval of the above-mentioned classification, and the user views the original image of the form that has not been subjected to obfuscation processing.

[0105] In step S105 shown in FIG. 10, if it is determined that there are no unused rules (step S105; NO), processor 11 determines whether the image of the above-mentioned form has been classified into one or more classification destinations by the processing from step S105 to step S108 (step S109).

[0106] If it is determined that the image of the form has not been classified into one or more classification destinations, i.e., has not been classified anywhere (step S109; NO), processor 11 classifies the image of the form as an unknown document (step S110) and notifies the administrator of this fact by email, short message service, etc. (step S111).

[0107] On the other hand, if it is determined that the image of the form has been classified into one or more classification destinations (step S109; YES), the processor 11 ends the process without performing the processes of steps S110 and S111.

[0108] By the above operation, the image of the form read by the image reading device 4 is classified as an unknown document if the type of the form is unknown, and if there is one or more candidate types, it is classified into one or more of those types.

[0109] <Display behavior> 11 is a flow diagram showing an example of the flow of a display operation by the information processing device 1. The processor 11 of the information processing device 1 determines whether or not the user ID and authentication information that the user input to the terminal 2 have been acquired (step S201). The processor 11 continues this determination while determining that the user ID and authentication information have not been acquired (step S201; NO).

[0110] When it is determined that the user ID and authentication information have been acquired (step S201; YES), the processor 11 compares the acquired set of user ID and authentication information with the stored contents of the user DB 122 and attempts to authenticate the user identified by this user ID (step S202).The processor 11 then determines whether the user authentication has been successful (step S203).

[0111] If it is determined that the user authentication has not been successful (step S203; NO), the processor 11 returns the process to step S201.

[0112] If it is determined that the user authentication has been successful (step S203; YES), the processor 11 accepts the user's designation of a folder and a file from the terminal 2 (step S204).

[0113] Fig. 12 is a diagram for explaining where images are classified. Through the operation shown in Fig. 10, images (also called scanned images) scanned by the image scanning device 4 are stored in folders corresponding to the respective types of forms or folders indicating unknown documents. When an authenticated user specifies a folder of the type for which the user is responsible, the processor 11 of the information processing device 1 functions as a file manager and causes the terminal 2 to display a list of images of forms stored in the specified folder.

[0114] Fig. 13 is a diagram showing an example of a list of files stored in a folder. For example, the user DB 122 shown in Fig. 4 indicates that a user with user ID "U1" is in charge of a type with type ID "T1." The type DB 121 shown in Fig. 3 indicates that the type name of the form corresponding to type ID "T1" is "Purchase Order" and that the classification destination is " / Purchase Order."

[0115] A user with user ID "U1" is authenticated by inputting his / her own user ID "U1" along with authentication information "PW1." Then, when this user specifies the classification destination " / Purchase Order" as identification information indicating the classification destination folder, the information processing device 1 causes the terminal 2 to display window W1 shown in FIG.

[0116] Window W1 shown in FIG. 13 displays icons representing the files stored in the classification destination " / Purchase Order." As shown in FIG. 13, a form file called "Form #1" has a mark K superimposed on its icon, unlike form files called "Form #3" or "Form #5." This mark K is a sign indicating that the classification certainty is low and therefore user approval is required. In other words, a file indicated by an icon with this mark K is a file representing an image of a provisionally classified form.

[0117] As shown in FIG. 11, the processor 11 determines whether the file designated by the user is a file showing an image of a provisionally classified form (step S205).

[0118] If it is determined that the file specified by the user is not a file representing an image of a provisionally classified form (step S205; NO), the classification of this file has been confirmed, so processor 11 displays the original image representing this form (step S206) and proceeds to step S208.

[0119] If it is determined that the file designated by the user is a file showing an image of a provisionally classified form (step S205; YES), the processor 11 displays an unclear image showing this form (step S207).

[0120] When executing step S207 for the first time, the processor 11 of the information processing device 1 may perform an obscuration process on the original image of the form to generate an obscured image. In this case, the generated obscured image may be stored in the image data group 1212 of the type DB 121 in association with its obscuration level.

[0121] When an unclear image is already stored in the image data group 1212 of the type DB 121, the processor 11 may read out the unclear image without performing the obscuration process and display it on the terminal 2. In addition, in step S108, the processor 11 may perform the obscuration process on the original image of the form to generate an unclear image and store it in the image data group 1212 of the type DB 121.

[0122] After displaying the unclear image showing the form, processor 11 proceeds to step S300, where it performs a process of receiving an instruction from the user (referred to as an instruction receiving process) (step S300).

[0123] Then, processor 11 determines whether a condition for terminating the processing of the specified folder or file (also referred to as a termination condition) is satisfied (step S208). The termination condition is, for example, a condition in which a user issues an instruction to terminate the processing.

[0124] If it is determined that the termination condition is not satisfied (step S208; NO), processor 11 returns the process to step S204. If it is determined that the termination condition is not satisfied (step S208; YES), processor 11 terminates the process.

[0125] <Reception operation> 14 is a flow diagram showing an example of the flow of the reception operation by the information processing device 1. In step S207 of FIG.

[0126] Fig. 15 is a diagram showing an example of an unclear image G1. The unclear image G1 shown in Fig. 15 is classified into a type of form called by the type name "purchase order". According to the type DB 121 shown in Fig. 3, the type ID that identifies this type of form is "T1". And, as shown in the rule DB 123 shown in Fig. 5, the type ID "T1" is associated with the element "order or order".

[0127] Therefore, the processor 11 of the information processing device 1 searches for the character string "order" or "order" that satisfies conditions such as size, placement, matching rate, etc. in the full text generated by performing optical character recognition on the original image of the form. If the processor 11 finds such a character string, it provisionally classifies the image of the form into a type identified by the type ID "T1."

[0128] For example, when the processor 11 provisionally classifies an image of a form identified by the form ID "D1" into a type identified by the type ID "T1", the processor 11 enters the type ID "T1" in the provisional classification column of the classification state column corresponding to the form ID "D1" in the classification state DB 124. Then, the processor 11 performs an obscuration process on image data representing an original image stored in the image column of the form data associated with the form ID "D1" in the classification state DB 124, and stores the generated obscured image in the type DB 121.

[0129] The blurred image G1 shown in Figure 15 is an image obtained by performing an obfuscation process on an area where at least one element is displayed, excluding the element "order or order" used for classification. Therefore, the area R1 where "purchase order" is displayed, including the character string "order," is not subject to the obfuscation process, while the other area R2 is subject to the obfuscation process.

[0130] Therefore, a user in charge of a type called "Purchase Order" checks the character "order," which is a common element in this type of form, and determines whether this classification is correct. This user also checks the obscured image G1, which obscures region R2, which displays elements that are not common to this type of form, and therefore does not see the confidential information contained in region R2 at the provisional classification stage. Therefore, even if the provisional classification is incorrect, the user can determine whether the provisional classification is correct without seeing the detailed contents of the form that should be classified as a type outside their responsibility.

[0131] As shown in Fig. 14, the processor 11 of the information processing device 1 receives an instruction from the user regarding whether or not to perform provisional classification (step S301). At this time, the processor 11 displays, for example, a dialog box or the like for receiving the user's instruction in addition to the unclear image G1 shown in Fig. 15.

[0132] Figure 16 is a diagram showing an example of a dialog box W2 displayed to the user. The dialog box W2 shown in Figure 16 displays buttons B1, B2, and B3 along with a message M that reads, "This form is classified as a type called 'Purchase Order'. Is this OK?"

[0133] 16 is a button on which the character string "Yes" is displayed. When the user presses this button B1, the terminal 2 transmits an instruction to the information processing device 1 to approve the above-mentioned classification.

[0134] 16 is a button on which the character string "No" is displayed. When the user presses this button B2, the terminal 2 transmits to the information processing device 1 an instruction to the effect that the above-mentioned classification is not approved.

[0135] 16 is a button on which the character string "Partial Release" is displayed. When the user presses this button B3, the terminal 2 transmits to the information processing device 1 an instruction to release the obfuscation process (also referred to as a partial release instruction) for at least a part of the region R2 on which the obfuscation process has been applied.

[0136] 14 is the partial release instruction (step S302). If it is determined that the received instruction is the partial release instruction (step S302; YES), the processor 11 releases the obfuscation process for at least a part of the area to which the obfuscation process has been applied (step S303), and the process returns to step S301.

[0137] FIG. 17 is a diagram showing an example of an unclear image G2 and an original image G0. By performing the partial cancellation described above, the unclear image G1 shown in FIG. 15 changes to the unclear image G2 shown in FIG. 17(a). In this unclear image G2, the non-obscured region R11 is larger than the region R1 shown in FIG. 15, and the obscured region R12 is smaller than the region R2 shown in FIG. 15. Therefore, the region R10 that the user could not confirm in the unclear image G1 is included in the region R11 and becomes clear. The user can determine whether this provisional classification is correct, for example, by taking into account the content of this region R10.

[0138] When it is determined that the received instruction is not a partial release instruction (step S302; NO), processor 11 determines whether the instruction is an instruction to approve the provisional classification (step S304).

[0139] If it is determined that the received instruction is an instruction to approve the provisional classification (step S304; YES), processor 11 confirms the provisional classification as the classification (step S305) and displays the original image of the form (step S306). This allows the user to view, for example, the original image G0 shown in Figure 17(b).

[0140] Then, processor 11 determines whether or not this form has been provisionally classified in a folder other than the folder specified by the user, that is, in another classification destination (step S307).

[0141] If it is determined that the form has not been provisionally classified into another classification destination (step S307; NO), processor 11 ends the process.

[0142] If it is determined that the form has also been provisionally classified into other classification destinations (step S307; YES), processor 11 cancels the provisional classification into other classification destinations (step S308) and ends the process.

[0143] On the other hand, if it is determined in step S304 that the received instruction is not an instruction to approve the provisional classification (step S304; NO), the processor 11 instructs the terminal 2 to clear the displayed screen and cancels the provisional classification of the form into the type corresponding to the folder specified by the user (step S309). As a result, for example, in the window W1 shown in Fig. 13, the icon indicating the form whose provisional classification has been canceled is deleted together with the mark K, and becomes invisible to the user.

[0144] Then, the processor 11 determines whether or not all of the classifications for the above-mentioned forms, including the confirmed classifications and the provisional classifications, have been canceled (step S310).

[0145] If it is determined that all classifications have been canceled (step S310; YES), the processor 11 classifies the image of the above-mentioned form into an unknown document (step S311) and notifies the administrator of the information processing system 9 of this fact (step S312).

[0146] If it is determined that not all of the classifications have been cancelled, that is, that some classifications remain undone (step S310; NO), processor 11 ends the process.

[0147] By performing the above operations, the information processing device 1 obscures at least a part of the image of the form at the provisionally classified classification destination in the information processing system 9. This allows the information processing device 1 to prevent information leakage of the image when there is an error in classifying the image of the form.

[0148] <Modification> The above is a description of the embodiment, but the contents of this embodiment can be modified as follows. In addition, the following modifications can be combined with each other.

[0149] <1> In the above-described embodiment, the information processing device 1 has the processor 11 configured as a CPU, but the control means for controlling the information processing device 1 may have other configurations. For example, the information processing device 1 may have various processors other than a CPU.

[0150] Here, the term "processor" refers to a processor in a broad sense, including general-purpose processors (such as the CPU mentioned above) and dedicated processors (such as GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, programmable logic device, etc.).

[0151] <2> The operations of the processors in the above-described embodiments may not only be performed by a single processor, but may also be performed by a plurality of processors located at physically separate locations working together.

[0152] Furthermore, the order of the operations of the processor is not limited to the order described in the above embodiment, and may be changed as appropriate.

[0153] <3> In the above-described embodiment, the information processing device 1 may have the functions of the terminal 2. In this case, the information processing device 1 may have configurations corresponding to the operation unit 24 and the display unit 25 of the terminal 2. In addition, the image reading device 4 may have the functions of the terminal 2.

[0154] <4> In the above-described embodiment, when an image of a form is provisionally classified into multiple types, the processor 11 does not notify the user in charge of one of the types, but it may also notify them.

[0155] 18 is a diagram showing an example of the flow of notification operations when the image of the form that the user is trying to check has been provisionally classified into multiple types. Prior to step S301, processor 11 determines whether the image of the form that the user is trying to check has also been provisionally classified into other classification destinations (step S401).

[0156] If it is determined that the image of the form has also been provisionally classified into another classification destination (step S401; YES), the processor 11 notifies the user that there is another classification destination (step S402), and proceeds to step S301.

[0157] For example, if the image of a form for a user in charge of a type called "purchase order" is provisionally classified into a type other than this type, the information processing device 1 may instruct the terminal 2 to display a message to the user saying "This form is also classified into other types." This allows the user to know that the form he or she is checking may be one that should be classified into a type other than his or her responsibility.

[0158] If it is determined that the image of the form has not been provisionally classified into any other classification destination (step S401; NO), the processor 11 skips step S402 and advances the process to step S301.

[0159] <5> In the above-described embodiment, when processor 11 receives an instruction from a user to cancel at least a portion of the obscuration process, processor 11 cancels the obscuration process in accordance with the instruction. However, when other conditions are satisfied, processor 11 may cancel the obscuration process depending on the content of the conditions. For example, when a predetermined time has elapsed since the blurred image was displayed, processor 11 may cancel the obscuration process so that at least a portion of the obscured area in the blurred image returns to being clear.

[0160] That is, this processor 11 is an example of a processor that, when a predetermined condition is met, cancels the obscuring process for at least a part of an area in accordance with the content of the condition.

[0161] <6> In the above-described embodiment, the processor 11 partially cancels the obscuration process by enlarging the non-obscured areas of the obscured image, but it may also partially cancel the obscuration process for areas that are not contiguous with the non-obscured areas.

[0162] For example, when the element used for classification is a character string, the processor 11 may cancel a part of the obfuscation process for an area in which a character string of the same size as the character string is displayed.

[0163] <7> In the above-described embodiment, the processor 11 performs an obfuscation process on an area in which at least one element is displayed, excluding elements determined by the rules used for classification. However, the processor 11 may also perform an obfuscation process on an area that has a predetermined relationship with the elements determined by the rules used for classification.

[0164] For example, when the element used for classification is a layout, the processor 11 may perform an obscuring process on an area where only characters are displayed.

[0165] That is, this processor 11 is an example of a processor that performs processing to obscure areas of the image of a classified form that have a predetermined relationship to elements defined by the rules used for classification.

[0166] <8> In the above-described embodiment, the program executed by the processor 11 of the information processing device 1 is an example of a program that causes a computer having a processor to execute the steps of: classifying an acquired image using rules that define elements of the image that are common to each type of document represented by the image; and obscuring the area of the classified image in which at least one element, excluding the elements defined by the rules used for classification, is displayed, and displaying the image on a display device.

[0167] This program may be provided in a state where it is stored on a computer-readable recording medium, such as a magnetic recording medium such as a magnetic tape or a magnetic disk, an optical recording medium such as an optical disk, a magneto-optical recording medium, a semiconductor memory, etc. This program may also be downloaded via a communication line such as the Internet. [Explanation of symbols]

[0168] 1...information processing device, 11...processor, 111...acquisition unit, 112...recognition unit, 113...classification unit, 114...processing unit, 115...reception unit, 116...authentication unit, 117...notification unit, 118...display control unit, 12...memory, 121...type DB, 1211...type ID list, 1212...image data group, 122...user DB, 123...rule DB, 124...classification state DB, 13...interface, 16...image reading unit, 2...terminal, 21...processor, 2 2...memory, 23...interface, 24...operation unit, 25...display unit, 3...communication line, 4...image reading device, 41...processor, 42...memory, 43...interface, 44...operation unit, 45...display unit, 46...image reading unit, 5...form, 9...information processing system, B1...button, B2...button, B3...button, G0...original image, G1...obscure image, G2...obscure image, R1...area, R10...area, R11...area, R12...area, R2...area

Claims

1. a processor, the processor comprising: The acquired image is provisionally classified using rules that define elements of the image that are common to each type of document represented by the image; Without displaying the provisionally classified image on a display device, an area in which at least one element of the provisionally classified image, excluding elements determined by the rules used for classification, is displayed is obscured, and the processed image is displayed on a display device; displaying the processed image on the display device to a user in charge of the type into which the image has been provisionally classified, and then receiving an instruction from the user regarding the classification of the processed image; If the received instruction is an instruction to approve the classification, the classification is confirmed. Information processing device.

2. The processor: When a predetermined condition is met, the process for at least a part of the area is cancelled according to the content of the condition. The information processing device according to claim 1 .

3. The processor: When the process is cancelled, the cancellation of the process is notified to a predetermined notification destination.

3. The information processing device according to claim 1 or 2.

4. The processor: When an instruction to cancel the processing for the area is received from the user as an instruction regarding classification of the processed image, the processing is canceled. The information processing device according to claim 1 .

5. The processor: If the user is authenticated, an instruction to cancel the process is accepted. The information processing device according to claim 4 .

6. The processor: and obscuring areas of the provisionally classified image that have a predetermined relationship to the elements defined by the rules used for classification, and displaying the processed image. The information processing device according to claim 1 .

7. The processor: If there are multiple candidates for classification of the acquired image, the image is provisionally classified into each of the multiple types; When an image is provisionally classified into the plurality of types, information about the classification of the image provisionally classified into the plurality of types is notified to the user in a manner different from that when the image is provisionally classified into one type. The information processing device according to claim 1 .

8. The processor: When the images are provisionally classified into the plurality of types, an instruction is received from a user as to whether or not to approve the classification of the images provisionally classified into the plurality of types; When an instruction to approve the classification of the image into one of the plurality of types is received, the classification of the image provisionally classified into the plurality of types into another type is canceled. The information processing device according to claim 7 .

9. The processor: If an instruction to not approve the classification of the image into one type is received, the classification of the image into the one type is canceled. The information processing device according to claim 1 .

10. The processor: When an instruction to the effect that the classification of the image into any of the plurality of types is not approved is received, the classification of the image into each of the plurality of types is cancelled, and a notification is sent to a predetermined notification destination that the type of the image whose classification has been cancelled is unknown. The information processing device according to claim 8 .

11. A computer having a processor, A step of provisionally classifying the acquired image using rules that define elements of the image that are common to each type of form represented by the image; a step of performing a process of obscuring an area in the provisionally classified image in which at least one element, excluding elements determined by the rules used for classification, is displayed, without displaying the provisionally classified image on a display device, and displaying the processed image on a display device; a step of displaying the processed image on the display device to a user in charge of the type into which the image has been provisionally classified, and then receiving an instruction from the user regarding the classification of the processed image; If the received instruction is an instruction to approve the classification, confirming the classification; A program that executes the following.

Images