Information processing apparatus, information processing method, computer readable medium, and computer program product

Abstract

The present application provides an information processing device, an information processing method, and a computer readable medium. The information processing device has a processor that controls a display portion in a manner that arranges and displays an identification result and a collation result, wherein the identification result is a result obtained by identifying an image in which a character string is written, and the collation result is a result obtained by collating the identification result with a database that is registered in advance.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and a computer-readable medium. BACKGROUND

[0002] In the past, an information processing apparatus that performs information processing of character recognition on an image video of a form optically read has been known. For example, a form data input processing apparatus is disclosed in Japanese Patent Application Publication No. 2005-18678, which is characterized by having: a reading unit that optically reads a form of a reading target to generate an image video; a field region detecting unit that detects a field region of the image video based on form definition information of the form stored in advance; a character recognizing unit that performs character recognition on a character video included in each field in accordance with each field region detected by the detecting unit, and assigns a corresponding character code in a case where the character can be recognized; a collating unit that collates a character string composed of the characters recognized by the character recognizing unit for all the fields with a character string used in the form, and outputs recognition state information indicating that the field is a misread field in a case where the collation result is a character string that cannot be used in the form; and a display unit that displays a character font corresponding to the character code assigned by the character recognizing unit in comparison with a field video, based on the recognition state information output by the collating unit, in a manner that enables the misread field to be recognized as a correctly read field. SUMMARY

[0003] In a case where a user recognizes a character string written by handwriting or the like through character recognition processing (OCR), the recognition result does not necessarily coincide with the character string intended by the user. For example, in a case where any of a plurality of character strings prescribed in a system is written, the character string intended by the user is any of the plurality of character strings prescribed in the system. Therefore, the character string written by the user is recognized through OCR, a database (DB) in which the plurality of character strings prescribed in the system are registered is used to determine a character string corresponding to the recognition result and display the character string. However, it is difficult for the user to determine whether the displayed candidate of the character string is a result of character recognition or a result of character recognition and collation.

[0004] An object of the present disclosure is to provide an information processing apparatus, an information processing method, and a computer-readable medium in which a user can distinguish between a result of recognizing an image in which a character string is written and a collation result of the recognition result.

[0005] According to a first aspect of the present disclosure, there is provided an information processing apparatus having a processor that controls a display section in a manner of arranging and displaying an identification result and a collation result, the identification result being a result of identifying an image in which a character string is written, the collation result being a result of collating the identification result with a database that is registered in advance.

[0006] According to a second aspect of the present disclosure, the processor controls the display section in a manner of displaying the identification result and the collation result in a manner of indicating a correspondence between the identification result and the collation result.

[0007] According to a third aspect of the present disclosure, the manner of indicating the correspondence is a manner of displaying the identification result and the collation result using a dependency image that indicates a dependency relationship between the identification result and the collation result.

[0008] According to a fourth aspect of the present disclosure, the processor controls the display section in a manner of displaying different collation results as the collation result.

[0009] According to a fifth aspect of the present disclosure, the processor controls in a manner of displaying the collation results in a manner of being able to select any of the collation results, and displays the selected collation result as the collation result corresponding to the identification result on the display section.

[0010] According to a sixth aspect of the present disclosure, the processor displays, as the collation results, a collation result whose degree of coincidence with the identification result exceeds a threshold value.

[0011] According to a seventh aspect of the present disclosure, the processor controls the display section in a manner of displaying the collation results in an order from high to low in terms of the degree of coincidence.

[0012] According to an eighth aspect of the present disclosure, the processor controls in a manner of, in a case where a collation result whose degree of coincidence exceeds a first threshold value that is prescribed in advance as the threshold value cannot be acquired, acquiring a plurality of collation results whose degrees of coincidence exceed a second threshold value that is lower than the first threshold value, and displaying no-correspondence information indicating that a collation result coinciding with the identification result cannot be acquired, and a collation result whose degree of coincidence exceeds the second threshold value.

[0013] According to a ninth aspect of the present disclosure, there is provided a computer-readable medium storing a program that causes a computer to execute a process in which a display section is controlled in a manner of arranging and displaying an identification result and a collation result, the identification result being a result of identifying an image in which a character string is written, the collation result being a result of collating the identification result with a database that is registered in advance.

[0014] According to a tenth aspect of the present disclosure, there is provided an information processing method, wherein a display unit is controlled in a manner that arranges and displays an identification result obtained by identifying an image in which a character string is written and a collation result obtained by collating the identification result with a database registered in advance.

[0015] (EFFECTS)

[0016] According to the first, ninth, and tenth aspects, the user can distinguish and grasp the result obtained by identifying the image in which the character string is written and the collation result obtained by collating the identification result.

[0017] According to the second aspect, the user can confirm the correspondence between the identification result and the collation result, as compared with a case where the correspondence is not considered.

[0018] According to the third aspect, the user can intuitively confirm the relevance of the identification result and the collation result, as compared with a case where the dependence relationship between the identification result and the collation result is not represented by the image.

[0019] According to the fourth aspect, the user can confirm the collation result related to the identification result, as compared with a case where only one collation result is displayed.

[0020] According to the fifth aspect, the user can display the desired collation result, as compared with a case where only the collation result corresponding to the identification result is displayed.

[0021] According to the sixth aspect, the accurate collation result can be displayed for the identification result, as compared with a case where the multiple collation results are displayed without considering the degree of coincidence of the collation for the identification result.

[0022] According to the seventh aspect, the user can intuitively confirm the degree of coincidence, as compared with a case where the relationship between the multiple collation results is not considered.

[0023] According to the eighth aspect, the character close to the candidate without a corresponding candidate in the database can be confirmed. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 is a diagram illustrating a schematic configuration of a form system according to an embodiment.

[0025] Figure 2 is a diagram illustrating an example of an electrical schematic configuration of an information processing apparatus according to an embodiment.

[0026] Figure 3 is a diagram illustrating an example of a functional configuration of an information processing apparatus according to an embodiment.

[0027] Figure 4 FIG. 1 is an example of a setting screen showing reading definition settings.

[0028] Figure 5 FIG. 2 is an example of an image of a setting region included in the setting screen showing reading definition settings, Figure 5 (A) of FIG. 3 shows an image before settings, Figure 5 (B) of FIG. 3 shows an image after settings.

[0029] Figure 6 FIG. 4 is a flowchart showing an example of a flow of information processing based on an information processing program according to the embodiment.

[0030] Figure 7 FIG. 5 is an example of a confirmation correction screen according to the embodiment.

[0031] Figure 8 FIG. 6 is an example of a confirmation correction screen according to the embodiment.

[0032] Figure 9 FIG. 7 is an example of a confirmation correction screen according to the embodiment.

[0033] Figure 10 FIG. 8 is an example of an image including a dependency relationship between a recognition result and a collation result.

[0034] Figure 11 FIG. 9 is an example of an image including a dependency relationship between a recognition result and a collation result.

[0035] Figure 12 FIG. 10 is an example of an image of a confirmation screen including a case where a collation result is not extracted.

[0036] Figure 13 FIG. 11 is an example of a setting screen related to data conversion.

[0037] Figure 14 FIG. 12 is an example of a setting screen related to data conversion. DETAILED DESCRIPTION

[0038] Hereinafter, an example of an embodiment for implementing the technology of the present disclosure will be described in detail with reference to the drawings. In addition, sometimes, components and processes that have the same function with respect to actions, effects, and functions are denoted by the same reference numerals in all the drawings, and repeated description is appropriately omitted. Each drawing is merely schematically shown to the extent that the technology of the present disclosure can be sufficiently understood. Therefore, the technology of the present disclosure is not limited to the illustrated examples. Also, in the embodiment, sometimes, description is omitted with respect to structures not directly related to the present disclosure and well-known structures.

[0039] [First Embodiment]

[0040] Figure 1 is a diagram showing an outline configuration of a form system 10 to which the present embodiment pertains.

[0041] As shown in Figure 1 , the form system 10 includes an information processing apparatus 20, a client terminal 40, and an input apparatus 60. These apparatuses are connected with a network not shown, and can communicate with each other via the network. As an example, the network applies the Internet, a LAN (Local Area Network), a WAN (Wide Area Network), a WAN (Wide Area Network), and the like.

[0042] The information processing apparatus 20 manages a flow of a series of processes of performing an OCR (Optical Character Recoition) process on image data of a plurality of files containing forms, which are input through the input apparatus 60, and outputting a result of the OCR process to a predetermined output destination. The detailed configuration and the role of the information processing apparatus 20 will be described later.

[0043] The client terminal 40 transmits various instructions related to the OCR process to the information processing apparatus 20. Among the various instructions, as an example, there are included an instruction to start reading of information of the image data, and an instruction to display a result of reading the information of the image data, and the like. Also, the client terminal 40 displays various information such as a result of the OCR process performed by the information processing apparatus 20, and a notification related to the OCR process, in accordance with the various instructions received. As an example, the client terminal 40 applies a general-purpose computer apparatus such as a server computer or a PC (Personal Computer). In Figure 1 , only one client terminal 40 is prepared, but it is not limited thereto, and a plurality of client terminals 40 can be prepared, and as an example, the client terminals 40 can be used differently according to each process.

[0044] The input apparatus 60 inputs image data to be an object of the OCR process to the information processing apparatus 20. As an example, the input apparatus 60 applies a general-purpose computer apparatus such as a server computer or a PC, and an image forming apparatus having a scanning function, a printer function, a facsimile function, and the like. In addition, the image data can be input from the client terminal 40 to the information processing apparatus 20 in addition to the input apparatus 60.

[0045] Next, an outline of the form system 10 will be described.

[0046] The form system 10 is a system in which the information processing apparatus 20 performs OCR processing on image data input via the input apparatus 60 and outputs the result of the OCR processing to a predetermined output destination.

[0047] The information processing apparatus 20 manages various processes of (1) business design and application verification, (2) data input, (3) data reading, (4) form discrimination confirmation revision, (5) reading result confirmation revision, (6) business check, (7) data output, and (8) return in the OCR processing. In the present embodiment, the OCR processing includes not only processes of reading characters and symbols and the like from image data but also post-processing such as correction of characters.

[0048] As an example of management of various processes, the processes of (1) business design and application verification, (2) data input, (3) data reading, (6) business check, and (7) data output are respectively automatically executed by the information processing apparatus 20. In addition, as an example of management of various processes, the processes of (4) form discrimination confirmation revision and (5) reading result confirmation revision are respectively accepted through input by a user via the client terminal 40. In addition, as an example of management of various processes, the process of (8) return has a case where it is automatically executed by the information processing apparatus 20 and a case where it is accepted based on input by a user via the client terminal 40.

[0049] In the process of (1) business design and application verification, a job rule including a reading definition setting, an output setting, and a business check setting is made. In the reading definition setting, as an example, a reading range as a range of information to be read in the process of "(3) data reading" of image data is set. More specifically, as an example, a definition of reading a value of an item from the right side of the item extracted as a keyword as a value can be set. In the output setting, as an example, a file format and an output destination of output data to be output in the process of "(7) data output" are set. In the business check setting, as an example, a necessary input item in a form to be detected as a detection object in the process of "(6) business check" and the number of characters that can be input and the like are set.

[0050] In the process of (2) data input, input of image data from the input apparatus 60 is accepted. The input image data is registered as a job as a unit of execution of the process of "(3) data reading".

[0051] In the processing of (3) data reading, using the job rule for the job being executed selected by the user from the job rules created in the processing of "(1) business design and operation verification", reading of information of the image data within the job is performed. As an example, in this processing, form discrimination (hereinafter, referred to as "form discrimination") of the form included in the image data within the job and reading of the characters and marks within the reading range are performed.

[0052] In the processing of (4) form discrimination confirmation revision, based on the result of the form discrimination performed in the processing of "(3) data reading", the image data within the job is divided into records representing the form included in the job. Thereafter, in this processing, the divided records are displayed, and confirmation revision of the form discrimination based on the user is accepted.

[0053] In the processing of (5) reading result confirmation revision, the reading result of the characters and marks within the reading range performed in the processing of "(3) data reading" is displayed, and confirmation revision of the reading result based on the user is accepted.

[0054] In the processing of (6) business check, by the business check setting included in the job rule for the job selected by the user from the job rules created in the processing of "(1) business design and operation verification", errors in the previous processes are detected. The detection result can also be prompted to the user.

[0055] In the processing of (7) data output, using the output setting included in the job rule for the job selected by the user from the job rules created in the processing of "(1) business design and operation verification", output data is created, and the generated output data is output to the output destination specified in advance.

[0056] In the processing of (8) return, from the processing performed in the OCR processing, the processing one stage or more stages before is returned. As an example, regarding the return, in the execution of various processes such as "(4) form discrimination confirmation revision" and "(5) reading result confirmation revision", the instruction is performed from the client terminal 40 by the user. In addition, regarding the return, as an example, according to the result of the check based on the manager performed between the processing of "(6) business check" and "(7) data output", the instruction is performed from the client terminal 40 by the manager.

[0057] In the aforementioned OCR process, the "(1) Business Design and Application Verification" process is executed before the "(3) Data Reading" process, i.e., before the application of the form system 10. Furthermore, the "(1) Business Design and Application Verification" process can also be executed during the application of the form system 10 after the "(3) Data Reading" process. As an example, before the application of the form system 10, the operating rules created in the "(1) Business Design and Application Verification" process can be appropriately modified based on the results of the "(5) Reading Result Confirmation and Correction" process during the application of the form system 10.

[0058] (Information processing device)

[0059] Next, refer to Figure 2 An example of the structure of the information processing device 20 will be described. Figure 2 This diagram illustrates an example of the schematic electrical structure of the information processing apparatus 20 according to this embodiment. The information processing apparatus 20 is, for example, a general-purpose computer device such as an application server computer or a PC.

[0060] Specifically, such as Figure 2 As shown, the information processing device 20 includes a computer main body 21. The computer main body 21 includes a CPU (Central Processing Unit) 22, RAM (Random Access Memory) 23, ROM (Read-Only Memory) 24, a storage unit 25, and input / output ports (I / O) 26. The CPU 22, RAM 23, ROM 24, storage unit 25, and I / O 26 are interconnected via a bus.

[0061] Furthermore, the I / O 26 is connected to a functional unit comprising the following components: a communication unit 27, which can communicate with an external device; an operation input unit 28, which can perform user-based operation input; and a display unit 29, which can display images. These functional units can communicate with the CPU 22 via the I / O 26.

[0062] The computer main body 21 can be configured as a sub-control section that controls part of the operation of the information processing apparatus 20, or can be configured as part of a main control section that controls the operation of the entire information processing apparatus 20. Part or all of each module of the computer main body 21 is configured using, for example, an integrated circuit such as an LSI (Large Scale Integration) or an IC (Integrated Circuit) chip set. Each of the above-described modules can be configured using a separate circuit, or can be configured using a circuit in which part or all of the modules are integrated. Each of the above-described modules can be provided integrally with each other, or part of the modules can be provided separately. Also, part of each of the above-described modules can be provided separately. The integration of the computer main body 21 is not limited to an LSI, and a dedicated circuit or a general-purpose processor can be used.

[0063] The information processing program 25P for causing the information processing apparatus 20 to function as the information processing apparatus of the present disclosure is stored in the storage section 25. The CPU 22 reads out the information processing program 25P from the storage section 25 and expands it in the RAM 23 to execute processing. Thus, the information processing apparatus 20 in which the information processing program 25P is executed functions as the information processing apparatus of the present disclosure. The information processing program 25P can also be provided by a recording medium such as a CD-ROM. In addition, the specific processing of the information processing apparatus 20 will be described later.

[0064] As the storage section 25, for example, a secondary storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like is used.

[0065] The information processing program 25P can also be stored in the ROM 24. Also, for example, the information processing program 25P can be installed in the information processing apparatus 20 in advance. The information processing program 25P can also be implemented by installing program information stored in a non-volatile storage medium or published via a network not shown in the information processing apparatus 20 as appropriate. As examples of the non-volatile storage medium, a CD-ROM (Compact Disc Read Only Memory), an optical magnetic disk, an HDD, a DVD-ROM (Digital Versatile Disc Read Only Memory), a flash memory, a memory card, or the like can be assumed.

[0066] Also, in the storage section 25, a system program 25S for realizing each function of the OCR processing in the information processing apparatus 20 is stored. The CPU 22 reads out the system program 25S from the storage section 25 and expands it in the RAM 23 to execute the OCR processing. Thus, the information processing apparatus 20 in which the system program 25S is executed functions in a manner that it can execute a system function based on the OCR processing.

[0067] In addition, in the present embodiment, the information processing program 25P and the system program 25S are described as separate programs, but the information processing program 25P can also be executed as a program included as a part of the system program 25S.

[0068] Also, in the storage section 25, a database (DB) 25D in which data usable in the information processing apparatus 20 is stored is stored. The database 25D functions as an example of a storage section in which a plurality of strings (for example, items and item values) prescribed in advance and used in a system outside are registered. The database 25D is not limited to being stored in the storage section 25. For example, it can also be stored in advance in an external apparatus not shown, and inquired or written to the external apparatus not shown via a communication line.

[0069] The communication section 27 is connected to a communication network and is configured to be able to communicate between the information processing apparatus 20 and an external apparatus. The "communication network" is a concept including a network in which data is transmitted and received between devices via a communication line based on at least one of wired connection and wireless connection. For example, a narrow-area communication network (for example, LAN: Local Area Network) in which data is transmitted and received in a base of an enterprise, and a wide-area communication network (for example, WAN: Wide Area Network) in which data is transmitted and received through a public communication line, such as the Internet, can be cited.

[0070] The operation input section 28 is provided with, for example, a keyboard, a mouse, or the like for operation input.

[0071] The display section 29 is, for example, a liquid crystal display (LCD: Liquid Crystal Display), an organic EL (Electro Luminescence) display, or the like. The display section 29 can also apply a touch panel having the function of the operation input section 28. The operation input section 28 and the display section 29 receive various instructions from a user of the information processing apparatus 20. The display section 29 displays various information, such as a result of processing executed in accordance with an instruction received from the user, a notification for processing, and the like.

[0072] Figure 3 is a block diagram showing an example of a functional structure of the information processing apparatus 20 according to the present embodiment.

[0073] like Figure 3 As shown, the CPU 22 of the information processing apparatus 20 in this embodiment functions as the information processing apparatus of this disclosure by executing the information processing program 25P. The information processing apparatus of this disclosure includes functional units that function as various parts of the acquisition unit 220, the verification unit 222, and the display control unit 224.

[0074] The acquisition unit 220 is a functional unit that acquires information representing the recognition result obtained by recognizing an image containing a string. In one example of the information representing the recognition result, information representing the recognition result obtained by recognizing characters in an image containing a string in a form is used.

[0075] The verification unit 222 is a functional unit that verifies the recognition result acquired by the acquisition unit 220, that is, it verifies the information representing the recognition result against information such as representation strings pre-registered in the database 25D. The verification unit 222 includes a function to extract one or more pieces of information (e.g., string information) corresponding to the information representing the recognition result from the database 25D. The function of extracting one or more pieces of information (e.g., string information) from the database 25D uses a known extraction process that extracts information that matches the information representing the recognition result. This known extraction process can use similarity determination processing between strings and semantic distance determination processing between strings. Details of the processing for implementing the extraction function from the database 25D will be described later.

[0076] The display control unit 224 is a functional unit that arranges and displays information representing the identification result obtained by the acquisition unit 220 and information representing the verification result obtained by the verification unit 222 in at least a portion of the display unit 29.

[0077] Next, the function of the information processing apparatus 20 according to this embodiment will be explained.

[0078] In this embodiment, the information processing device 20 performs a process to confirm and correct the reading results of OCR processing on image data containing multiple documents with forms, which is input through the input device 60. Figure 1 The process shown in (5) will be explained. That is, the reading results of characters and symbols within the reading range performed in the data reading process will be displayed, and the processing related to the confirmation and correction of the reading results based on the user will be explained.

[0079] For example, in a case where any of a plurality of strings prescribed in an external system is described in a form, it is assumed that a string described by handwriting or the like is any of the plurality of strings prescribed in the external system. Therefore, a string corresponding to a recognition result of character recognition of a string described by the user is determined using a database (DB) registered in the external system, and is displayed. However, the recognition result of character recognition does not necessarily coincide with a string intended by the user. Therefore, the user has difficulty in determining whether a candidate of a string displayed as a reading result is a recognition result of character recognition or a collation result of collating a string recognized by character recognition.

[0080] Therefore, in the present embodiment, the display section 29 is controlled in a manner in which a recognition result obtained by recognizing an image in which a string is described, and a collation result as a result of collating the recognition result with a database registered in advance are arrayed and displayed.

[0081] In the present disclosure, "arraying and displaying a recognition result and a collation result" is a concept of a display process including a process of displaying in a manner in which an image indicating a recognition result and an image indicating a collation result are not overlapped on the same screen. As an example of the display of arraying and displaying, an example in which the image indicating the recognition result and the image indicating the collation result are displayed in a manner in which the user can be collectively prompted in at least a part of a region of the display section 29 can be given.

[0082] Further, "a reading result" is a concept including a recognition result (for example, a string) of character recognition, and a collation result (for example, a string) obtained by collating using a database in which a plurality of strings are registered. The collation result includes a string determined as a collation result by collating a string of a recognition result of character recognition using a database in which a plurality of strings prescribed in an external system are registered, and displayed.

[0083] In addition, in the present embodiment, a reading definition setting is set by the user in advance with respect to a job rule. With reference to Figure 4 and Figure 5 The reading definition setting is described.

[0084] Figure 4 and Figure 5 An example of a setting screen is shown. Figure 4 is a drawing showing an example of a setting screen of a reading definition setting set by a user. Figure 5 is a drawing showing an example of an image of a setting region included in a setting screen of a reading definition setting, Figure 5 (A) of shows an image before setting, Figure 5 (B) of shows an image after setting.

[0085] like Figure 4 As shown, the settings screen 80 includes: a scanned image (hereinafter referred to as a scanned image) containing an image that will be the object of OCR processing (hereinafter referred to as an object image), a scanned image 800 of a form, for example, and an image of a setting area set by the user (hereinafter referred to as a setting image) 802. In the settings screen 80, a range image 801 representing the area of ​​the image that will be the object of OCR processing is also displayed in the scanned image 800.

[0086] like Figure 5 As shown in (A), the set image 802 includes a display area 803 and a display area 804. The recognition result obtained by performing character recognition on the image of the object to be processed by OCR, which is shown in the range image 801, is displayed in display area 803. Figure 5 In the display area, area 803 is the display area corresponding to the item labeled "OCR Result". Display area 804 displays the results corresponding to the setting of whether or not candidate corrections were performed. Figure 5 In the middle, display area 804 is the display area corresponding to the item marked as "identification result", and is the display area for displaying the verification result.

[0087] Furthermore, the setting image 802 includes a setting region 805 for candidate correction based on verification and a setting region 806 for data transformation based on verification.

[0088] The setting area 805 for verification-based candidate correction includes radio buttons, a display area for verification data, and a display area for correction results. Verification-based candidate correction refers to the execution of correction processing that extracts and displays string information corresponding to the recognition results of the object image from the database 25D. The radio buttons in the setting area 805 are used to set whether to perform verification-based candidate correction. Figure 5 In the process, one can choose either "to proceed" or "not to proceed".

[0089] The data verification display area is activated when the radio button is set to "Proceed," allowing you to set the categories, types, etc., of the data contained in database 25D. In addition to setting settings related to data categories, types, etc., the data items can also be set. The calibration result display area is also activated when the radio button is set to "Proceed," displaying the results of candidate calibrations based on the verification.

[0090] Therefore, if the execution of candidate corrections based on verification is specified in the radio button, such as Figure 5 As shown in (B), it is possible to set the verification data (in Figure 5The case where "customer list - company name" is set is shown in (B) of FIG. 8. Also, the result of the candidate correction based on the collation is displayed in the display area of the correction result (in (B) of FIG. 8, the result of the candidate correction based on the collation is displayed as "Fuji Xerox Co., Ltd."). Figure 5 The case where "customer list - company name" is set is shown in (B) of FIG. 8. Also, the result of the candidate correction based on the collation is displayed in the display area of the correction result (in (B) of FIG. 8, the result of the candidate correction based on the collation is displayed as "Fuji Xerox Co., Ltd.").

[0091] Also, the processing of the candidate correction based on the collation can be executed in the case where the radio button of the setting area 805 of the candidate correction based on the collation is set to "execute", and the processing can be executed in the case where a new instruction is given after the execution is set. In the present embodiment, the processing is executed in accordance with an instruction based on the pressing of the refresh button 807.

[0092] The setting area 806 of the data conversion based on the collation includes a radio button, a display area of data for conversion, and a display area of a conversion result. The data conversion based on the collation indicates execution of a conversion process of determining identification information such as a code corresponding to the character string information on which the candidate correction based on the collation is executed from the database 25D and displaying the same. The radio button of the setting area 806 is a radio button for setting whether or not to execute the data conversion based on the collation (in (B) of FIG. 8, either one of "execute" and "do not execute" can be selected). Figure 5

[0093] The display area of data for conversion is activated in the case where the radio button is set to "execute", and it is possible to set a classification of the category, the kind, or the like of the data included in the database 25D. The display area of the conversion result is also activated in the case where the radio button is set to "execute", and the result of the data conversion based on the collation is displayed.

[0094] Therefore, in the case where the execution of the data conversion based on the collation is designated in the radio button, as shown in (B) of FIG. 8, it is possible to set the data for conversion (in (B) of FIG. 8, the case where "customer list - company code" is set is shown). Also, the result of the data conversion based on the collation is displayed in the display area of the conversion result (in (B) of FIG. 8, the case where the code "DB001" corresponding to "Fuji Xerox Co., Ltd." is displayed is shown). Figure 5 Figure 5 Figure 5 Therefore, in the case where the execution of the data conversion based on the collation is designated in the radio button, as shown in (B) of FIG. 8, it is possible to set the data for conversion (in (B) of FIG. 8, the case where "customer list - company code" is set is shown). Also, the result of the data conversion based on the collation is displayed in the display area of the conversion result (in (B) of FIG. 8, the case where the code "DB001" corresponding to "Fuji Xerox Co., Ltd." is displayed is shown).

[0095] Also, the processing of the data conversion based on the collation can be executed in the case where the radio button of the setting area 806 of the data conversion based on the collation is set to "execute", and the processing can be executed in the case where a new instruction is given after the execution is set. In the present embodiment, the processing is executed in accordance with an instruction based on the pressing of the refresh button 807.

[0096] Next, the information processing executed in accordance with the read definition set as the job rule by the user will be described in detail. ​​​

[0097] Figure 6 is an example of a flowchart showing a flow of information processing based on the information processing program 25P according to the present embodiment.

[0098] First, if the information processing device 20 is instructed to start the information processing program 25P, the CPU 22 executes each of the following steps.

[0099] In step S100, information indicating a recognition result of a scanned image in which a form in which a character string is written is recognized is acquired. The information indicating the recognition result can be obtained from an execution result of a process (process (3) shown in FIG. 8) of reading data from an OCR process that is processed by execution of the system program 25S in the information processing device 20. Figure 1 The process of acquiring the information indicating the recognition result is an example of a function of the acquisition section 220 shown in FIG. 7. Figure 3

[0100] In step S102, the information indicating the recognition result acquired in step S100 is collated with information indicating a character string or the like that has been registered in the database 25D, and information indicating a collation result is acquired. The process of acquiring the information indicating the collation result is an example of a function of the collation section 222 shown in FIG. 7. Figure 3

[0101] Specifically, in step S102, first, an extraction process of extracting one or more pieces of information (for example, character string information) corresponding to the information indicating the recognition result from the database 25D is executed. The extraction process is a process of extracting information that matches the information indicating the recognition result. In the extraction process, a degree of matching between a character string that is the information indicating the recognition result and a character string that has been registered in the database 25D is derived, and information indicating a registered character string that exceeds a degree of matching that is specified in advance is extracted from the database 25D. As an example of the extraction process, it is possible to be implemented by a known process of deriving a degree of similarity between character strings and a determination process of determining a case in which the derived degree of similarity exceeds a degree of similarity that is specified in advance. Also, it is possible to be implemented by a known process of deriving a distance of meaning between character strings and a determination process of determining a case in which the derived distance of meaning exceeds a distance that is specified in advance.

[0102] In step S104, a confirmation correction screen for causing a user to confirm the information indicating the acquired recognition result and the information indicating the collated collation result is displayed. In addition, in step S102, in a case in which a plurality of pieces of information indicating collation results are extracted, information having a higher degree of matching than other information, that is, information having the highest degree of matching is determined as the information indicating the collation result and is displayed.

[0103] Figure 7 ​​This is a diagram showing an example of a confirmation and correction screen according to this embodiment. Figure 7 This is an example of a form view showing a screen containing a scanned image 800 of a form as a confirmation correction screen 81.

[0104] The confirmation correction screen 81 includes: a scanned image 800 of the form, and an image of a confirmation correction area (hereinafter referred to as the confirmation correction image) 810 that allows the user to confirm and correct the recognition results. In the confirmation correction screen 81, for the scanned image 800, a range image 801 representing the reading range of the area of ​​the image that is the object of OCR processing is also displayed.

[0105] The image 810 is confirmed to include a display area 811 for each item predefined as a reading range. Figure 7 In the example shown, each item, categorized by delivery date, registration information, and address, has a display area 811. Each display area 811 displays images related to the item name, scanned image, recognition result, confidence level, and confirmation, respectively. For example, the display area 811 for the item name "Delivery Date" includes an image 812 representing the item name, a scanned image 813, an image 814 representing the recognition result, an image 815 representing the confidence level, and an image 816 for allowing the user to set the end of the item confirmation process.

[0106] exist Figure 7 In the confirmation and correction image 810 shown, the verification result based on the recognition result is displayed as image 814 representing the "recognition result". The string displayed as image 814 is displayed in a way that can be corrected by the user. Furthermore, image 815, representing the degree of certainty, is an image representing the aforementioned degree of matching; specifically, it is an image representing an indicator of the degree of matching between the information (string) representing the recognition result and the information (string) registered in database 25D. Figure 7 The image shows a situation indicating a high degree of agreement, such as an image indicating that the agreement exceeds a threshold. Image 816 is an image showing a checkbox used by the user to set the status of the project confirmation. Image 816 is controlled so that when the user points to image 816 at the end of the project confirmation, the checkbox changes to a selected state.

[0107] Here, as described above, when the execution of the data transformation process based on verification is set, the display area for the transformation data is activated to display the result of the data transformation based on verification.

[0108] Figure 8 This is an example of a confirmation and correction screen shown when the execution of data transformation processing based on verification is set.

[0109] As Figure 8 indicated, a migration process from the confirmation correction image 810X in which the information is not displayed in the display area of the transformation result to the confirmation correction image 810Y in which the result of the data transformation based on the collation is displayed is shown in a case where the execution of the data transformation processing based on the collation is set. Specifically, as the confirmation correction image 810Y, a case where the code "MS-05B" corresponding to "あんぱん" is displayed in the display area of the transformation result is shown.

[0110] However, as described above, in a case where the user confirms the confirmation correction image 810, it is difficult to determine whether the candidate of the string displayed as the read result is the recognition result of the character recognition or the collation result of the collation performed using the string of the character recognition. Therefore, in the present embodiment, control of arranging and displaying the recognition result obtained by recognizing the image in which the string is recorded and the collation result as a result of collating the recognition result with the database registered in advance is executed.

[0111] Specifically, in Figure 6 indicated in step S106, the CPU 22 determines whether or not the confirmation instruction for the string displayed as the read result is instructed by determining the information from the operation input section 28. In a case where the affirmative determination is made in step S106, after the control of arranging and displaying the recognition result and the collation result based on the database 25D on the same screen is executed in step S108, the process is transferred to step S110. On the other hand, in a case where the negative determination is made in step S106, the process is transferred to step S110.

[0112] In step S110, it is determined whether or not the information processing is ended based on the information from the operation input section 28 indicating the end instruction based on the user operation or the information indicating that the confirmation correction for all items is ended. In a case where the negative determination is made in step S110, the process is returned to step S104, and in a case where the affirmative determination is made, the series of processes based on the information processing program 25P is ended.

[0113] Figure 9 is a diagram showing an image example of the confirmation screen of the recognition result and the collation result in the confirmation correction screen according to the present embodiment. The image of the confirmation screen is further displayed in a case where the confirmation instruction for the string displayed as the read result is instructed in the confirmation correction screen.

[0114] In Figure 9In the example shown, in the display area 811 of the confirmation revised image 810, as an example of a project name, information related to the project of "product name 1" is displayed. Also, the confirmation revised image 810 includes an icon image 820 for indicating a user instruction of confirmation of a confirmation result and a collation result in each of the display areas 811 of the projects that are prescribed in advance as a reading range, to the right of the image 814 indicating the recognition result. Also, below the image 814 indicating the recognition result, an image 821 indicating attribute information related to information extracted from the database 25D as a collation result is displayed.

[0115] By a user operation, when the icon image 820 is instructed to be selected (for example, clicked), an image 822 of a confirmation screen is displayed in association with the icon image 820. In Figure 9 In the example shown, the image 822 of the confirmation screen is displayed within a speech bubble image from the icon image 820.

[0116] The image 822 of the confirmation screen includes an image 823 indicating a recognition result based on character recognition, and an image 824 indicating a collation result based on the database 25D for the recognition result. The image 822 of the confirmation screen controls to arrange and display the recognition result based on character recognition and the collation result based on the database 25D for the recognition result in the same screen.

[0117] In Figure 9 In the example shown, the image 823 indicating the recognition result includes string information of the recognition result ("ampai") and attribute information indicating that the string information is a recognition result based on character recognition ("OCR result"). Also, the image 824 indicating the collation result includes string information of the collation result and attribute information indicating that the string information is a candidate of a string extracted from the database 25D. The collation result displayed as the image 814 indicating the recognition result is a collation result in which the degree of coincidence exceeds a threshold value (for example, the maximum value) among the collation results displayed in the image 822 of the confirmation screen. In Figure 9 In the example shown, candidates of a plurality of strings extracted from the database 25D are displayed in order from the collation result in which the degree of coincidence is the maximum value.

[0118] The candidates of the string extracted from the database 25D can also be set in advance in a priority order, and the candidates are arranged in the priority order with respect to the extracted string.

[0119] By displaying the recognition result and the collation result on the same screen in this way, the user can confirm the respective results with respect to how the reading process is performed in character recognition (OCR) and what kind of candidates are extracted in collation.

[0120] As described above, the control to display the recognition result and the collation result on the same screen is performed. In the present embodiment, the display can be performed in a manner in which the dependency relationship of the recognition result and the collation result can be confirmed. Further, the collation result displayed as the image 814 representing the recognition result can be any one candidate selected from the collation results based on the candidates of the plurality of strings.

[0121] Figure 10 is a diagram illustrating an example of an image including the dependency relationship of the recognition result and the collation result in the confirmation screen.

[0122] As illustrated in Figure 10 , the image 822 as an example of the image of the confirmation screen includes an arrow image 830 representing the dependency relationship of an image 823 of the recognition result based on the character recognition and an image 824 representing the collation result. Further, the image 824 representing the collation result is displayed in a manner in which any one candidate selected from the collation results based on the candidates of the plurality of strings can be selected. In Figure 10 , a selection image 840 representing the first candidate (string information "anpan", the collation result recorded as attribute information "candidate (1) based on DB collation") is illustrated.

[0123] In addition, as illustrated in Figure 11 , by displaying the image 850 representing the dependency relationship of the recognition result and each candidate as the collation result differently, the user can confirm the degree of dependency of the recognition result and each candidate as the collation result. In the example illustrated in Figure 11 , a case in which the image 850 representing the dependency relationship of the recognition result and each candidate as the collation result is displayed in a display manner in which the line type of the arrow image is different is illustrated. At this time, the dependency relationship is illustrated to be weaker in the order of the solid line, the single dash line, and the double dash line.

[0124] In the above-described processing, one or more information (for example, string information) corresponding to the information representing the recognition result, that is, information as the information in which the degree of coincidence exceeds the threshold value predetermined in advance, is extracted from the database 25D. However, sometimes the information registered in the database 25D does not include the information in which the degree of coincidence exceeds the threshold value predetermined in advance. In this case, the information corresponding to the information representing the recognition result cannot be extracted from the database 25D. Therefore, in the present embodiment, in a case where the collation result in which the degree of coincidence exceeding the first threshold value predetermined as the threshold value cannot be extracted, a plurality of collation results in which the degree of coincidence exceeding the second threshold value lower than the first threshold value can be extracted. In this case, the display unit 29 can be controlled to display the no corresponding information representing that the collation result coinciding with the recognition result cannot be acquired and the collation result in which the degree of coincidence exceeding the second threshold value.

[0125] Figure 12 is a diagram showing an example of the image of the confirmation screen including the case where the collation result cannot be extracted.

[0126] As shown in Figure 12 , the image 822, which is an example of the image of the confirmation screen including the case where the collation result cannot be extracted, includes an image 860 indicating that the collation result that matches the recognition result cannot be acquired. In Figure 12 , as the non-correspondence information, each of the string information "no correspondence" and the attribute information "candidate based on DB collation (0)" is recorded. Also, in Figure 12 , a case where the image 862 including an image indicating the relationship between the recognition result and the non-correspondence information is displayed in a display manner in which the line type of the arrow image is different is shown.

[0127] As described above, according to the present embodiment, by displaying the recognition result and the collation result on the same screen, the user can confirm the respective results with respect to how the reading process is performed in the character recognition and what kind of candidate is extracted in the collation.

[0128] In addition, the information processing apparatus 20 of the present embodiment is configured to be able to perform data output based on the CSV (Comma Separated Value) format. Therefore, in the present embodiment, the process of displaying the recognition result and the collation result on the same screen is performed, and after the recognition result is determined, the setting related to data conversion at the time of outputting data (for example, a CSV file) to an external system can be performed. An example of data conversion is CSV conversion.

[0129] Figure 13 and Figure 14 shows an example of a setting screen related to data conversion. Figure 13 is a diagram showing an example of a setting screen for setting, with respect to each information including the recognition result, for example, the data format at the time of outputting data as a CSV file. Figure 14 is a diagram showing an example of a setting screen related to one item (column A in Figure 14 ) in the file. As shown in Figure 13 and Figure 14 , by performing the setting related to data output conversion, the reading result (for example, the recognition result) and the information corresponding to the reading result can be automatically or manually output.

[0130] The information processing apparatus according to the present embodiment has been described above. The present embodiment can also be a program for causing a computer to execute the functions of each part possessed by the information processing apparatus. The present embodiment can also be a storage medium that the computer can read, in which the program is stored.

[0131] Furthermore, the configuration of the information processing apparatus described in the above-described embodiments is one example, and can be changed as appropriate without departing from the gist thereof.

[0132] Also, the flow of the processing of the program described in the above-described embodiments is one example, and an unnecessary step can be deleted, a new step can be added, or the processing order can be changed, within a range not departing from the gist thereof.

[0133] Also, in the above-described embodiments, the case where the processing related to the embodiments is implemented by a software configuration by a computer through execution of a program has been described, but is not limited thereto. The embodiments can be implemented by a hardware configuration, a combination of a hardware configuration and a software configuration, for example.

Claims

1. An information processing apparatus having a processor, wherein the processor controls a display section in a manner that arranges and displays an identification result obtained by identifying an image in which a character string is written and a collation result obtained by collating the identification result with a database registered in advance, and displays a setting area of a collation-based candidate correction and a setting area of a collation-based data transformation, in the setting area of the collation-based candidate correction, whether to perform the collation-based candidate correction is accepted from a user, in a case where the collation-based candidate correction is specified to be performed by the user, collation-use data can be set, and the collation-use data is displayed in the setting area of the collation-based candidate correction, in the setting area of the collation-based data transformation, whether to perform the collation-based data transformation is accepted from the user, in a case where the collation-based data transformation is specified to be performed by the user, transformation-use data can be set, and the transformation-use data is displayed in the setting area of the collation-based data transformation. 2.The information processing apparatus according to claim 1, wherein the processor controls the display section in a manner that displays the identification result and the collation result in a manner that indicates a correspondence between the identification result and the collation result. 3.The information processing apparatus according to claim 2, wherein the manner that indicates the correspondence is a manner that displays the identification result and the collation result using a dependency image that indicates a dependency relationship between the identification result and the collation result. 4.The information processing apparatus according to any one of claims 1 to 3, wherein the processor controls the display section in a manner that displays different collation results as the collation result. 5.The information processing apparatus according to claim 4, wherein the processor controls in a manner that displays the different collation results in a manner that enables any of the collation results to be selected, and displays the selected collation result as the collation result corresponding to the identification result on the display section. 6.The information processing apparatus according to claim 4, wherein the processor displays, as the different collation results, collation results whose degrees of coincidence with the identification result exceed a threshold value. 7.The information processing apparatus according to claim 6, wherein the processor controls the display section in a manner that displays the different collation results in an order from high to low in the degrees of coincidence. 8.The information processing apparatus according to claim 6 or 7, wherein the processor controls in a manner that, in a case where a collation result whose degree of coincidence exceeds a first threshold value predetermined as the threshold value cannot be acquired, a plurality of collation results whose degrees of coincidence exceed a second threshold value lower than the first threshold value are acquired, and no-correspondence information indicating that a collation result coinciding with the identification result cannot be acquired and the collation results whose degrees of coincidence exceed the second threshold value are displayed. 9.A computer-readable medium storing a program that causes a computer to execute processing, wherein In the processing, arranging and displaying the recognition result and the collation result, the recognition result being a result of recognizing an image in which a character string is written, the collation result being a result of collating the recognition result with a database registered in advance, in the setting area of the collation-based candidate correction, whether or not to perform the collation-based candidate correction is accepted from the user, in a case where the execution of the collation-based candidate correction is specified by the user, collation data can be set, and the collation data is displayed in the setting area of the collation-based candidate correction, in the setting area of the collation-based data conversion, whether or not to perform the collation-based data conversion is accepted from the user, in a case where the execution of the collation-based data conversion is specified by the user, conversion data can be set, and the conversion data is displayed in the setting area of the collation-based data conversion.

10. An information processing method, wherein arranging and displaying the recognition result and the collation result, the recognition result being a result of recognizing an image in which a character string is written, the collation result being a result of collating the recognition result with a database registered in advance, in the setting area of the collation-based candidate correction, whether or not to perform the collation-based candidate correction is accepted from the user, in a case where the execution of the collation-based candidate correction is specified by the user, collation data can be set, and the collation data is displayed in the setting area of the collation-based candidate correction, in the setting area of the collation-based data conversion, whether or not to perform the collation-based data conversion is accepted from the user, in a case where the execution of the collation-based data conversion is specified by the user, conversion data can be set, and the conversion data is displayed in the setting area of the collation-based data conversion.

11. A computer program product including a program which causes a computer to execute processing, in the processing, The display section is controlled in a manner in which the recognition result as follows and the collation result as follows are arranged and displayed, and a set region of a candidate correction based on collation and a set region of data conversion based on collation are displayed. the recognition result being a result of recognizing an image in which a character string is written, the collation result being a result of collating the recognition result with a database registered in advance, in the setting area of the collation-based candidate correction, whether or not to perform the collation-based candidate correction is accepted from the user, in a case where the execution of the collation-based candidate correction is specified by the user, collation data can be set, and the collation data is displayed in the setting area of the collation-based candidate correction, in the setting area of the collation-based data conversion, whether or not to perform the collation-based data conversion is accepted from the user, in a case where the execution of the collation-based data conversion is specified by the user, conversion data can be set, and the conversion data is displayed in the setting area of the collation-based data conversion. In a case where execution of the collation-based data conversion is specified by the user, conversion data can be set, and the conversion data is displayed in a setting area of the collation-based data conversion.

Images