Information processing device, recording medium, and computer program product

Abstract

The object of the present invention is to provide an information processing device, a recording medium, and a computer program product, which can reduce the user's work on the recognition result compared to a case where a file containing multiple identical items is read and multiple detected character strings cannot be recognized for a set item. The information processing device of the present invention includes a processor, and when a plurality of first character strings representing a first item are detected from a file in which a description column is set for an item, the processor detects a second character string representing a second item associated with the first item for each of the plurality of first character strings, and sets at least one of the detected second character strings as a second item, associated with the first item, and sets it in setting information.

Description

Technical Field

[0001] The present invention relates to an information processing device and a recording medium. Background Art

[0002] Patent document 1 discloses a form recognition device that recognizes a character string recorded in a form and comprises: an item name, which is a character string indicating a data attribute; an image input unit for inputting a form image that is a character string containing data corresponding to the item name, i.e., an item value; an item value title score calculation unit for calculating an item value title score for a character string in the form image recognized from the form image, the item value title score indicating a probability that the character string is the item value; an item value word score calculation unit for calculating an item value word score for a character string in the form image, the item value word score indicating a probability that the character string is an item value word indicating a detailed item value registered in advance; and an item value candidate selection unit for selecting a score including both the item value title score and the item value word score as an item value score (Sv), selecting a character string having an item value score higher than a predetermined threshold as an item value candidate, and selecting a character string having an item value score higher than a predetermined threshold as an item value candidate, and selecting a character string having an item value score higher than a predetermined threshold as an item value candidate. The item value score (Sv) is given; an item value candidate configuration score calculation unit calculates, for the string pair of the item value candidate in the form image, an item value candidate configuration score (Sca) representing whether the configuration relationship of the string pair is appropriate as the item value of each item value group when a combination of the item values ​​of multiple attributes related to each other in the form image is taken as an item value group; an item value candidate pair score calculation unit calculates, for the string pair of the item value candidate in the form image, an item value candidate pair score (Scp) representing an evaluation value of the rationality of the string as the item value of the item value group based on the item value score (Sv) and the item value candidate configuration score (Sca); an item value group evaluation unit evaluates the correspondence between the string in the form image and the item value group based on the item value candidate pair score (Scp), thereby identifying the string of the item value; and an output unit outputs the recognition result of the string in the form image.

[0003] [Prior art literature]

[0004] [Patent Document]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2016-051339 Summary of the invention

[0006] [Problems to be solved by the invention]

[0007] For example, there is an information processing device that reads a document entered by a user, detects set items from the entered document, and recognizes and outputs a character string associated with the detected item from the document.

[0008] However, for example, when there are multiple identical items such as names in the filled file, multiple character strings may be recognized for one item set in the setting information. As a result of reading a file with multiple identical items, the multiple detected character strings cannot be recognized for the item set in the setting information. In this case, manually performing editing work by the user to make the multiple character strings recognized for the item recognizable may not necessarily reduce the user's work.

[0009] The object of the present invention is to provide an information processing device and an information processing program, which can reduce the user's work on the recognition results compared to reading a file with multiple identical items and failing to recognize multiple detected character strings for the set items.

[0010] [Methods to solve the problem]

[0011] The information processing device of the first embodiment includes a processor, which, when detecting multiple first character strings representing first items from a file in which a record column is set for the items, detects second character strings representing second items associated with the first items for each of the multiple first character strings, and sets at least one of the detected second character strings as a second item, associated with the first item, and sets it in the setting information.

[0012] Information processing device of the second embodiment In the information processing device of the first embodiment, the processor performs at least one of the following two processes, namely: a process of displaying the detected multiple first character strings as candidates for the first item, and a process of displaying the multiple second character strings as candidates for the second item.

[0013] Information processing device of the third embodiment In the information processing device of the second embodiment, the processor executes at least one of the following two processes: a process of selecting a first item from the detected plurality of first character strings and a process of selecting a second item from the detected plurality of second character strings.

[0014] In the information processing device of the fourth embodiment, in the information processing device of any one of the first to third embodiments, the processor associates the first item with the second item based on position information of the first item and the second item in the file, or a semantic subordinate relationship between the first item and the second item.

[0015] The information processing device of the fifth embodiment is the information processing device of any one of the first to fourth embodiments, wherein the processor detects a third character string as a character string described in a description field corresponding to the setting information, associates the third character string with the setting information, and outputs the third character string.

[0016] The information processing device of the sixth embodiment is an information processing device of the fifth embodiment, and the processor performs output in any one of the following two forms, namely: in the first form, the first item included in the setting information, the second item included in the setting information, and the third character string are output separately; and in the second form, the first item and the second item included in the setting information are linked to set as a unique item, and the unique item and the third character string are output.

[0017] The information processing device according to the seventh embodiment is the information processing device according to the sixth embodiment, wherein the processor receives a selection of an output format.

[0018] In the information processing device of the 8th embodiment, in the information processing device of the 6th embodiment or the 7th embodiment, when multiple and identical first items or multiple and identical second items are set in the setting information, the processor adds a unique character to the set first item or second item respectively and sets it in the setting information.

[0019] The recording medium of the 9th embodiment stores an information processing program, which enables the computer to execute the following steps: a detection step, in which, when multiple first character strings representing first items are detected from a file in which a record column is set for the items, a second character string representing a second item associated with the first item is detected for each of the multiple first character strings; and a setting step, in which at least one of the detected second character strings is set as a second item in the setting information in association with the first item.

[0020] [Effects of the invention]

[0021] According to the information processing device of the first embodiment and the recording medium of the ninth embodiment, compared with a case where a file containing a plurality of identical items is read and a plurality of detected character strings cannot be recognized for the set items, the user's work on the recognition results can be reduced.

[0022] According to the information processing device of the second embodiment, it is possible to confirm a candidate for at least one of the detected first item and second item.

[0023] According to the information processing device of the third embodiment, it is possible to extract only necessary information from at least one of the detected candidates of the first item and the second item.

[0024] According to the information processing device of the fourth embodiment, the second item associated with the first item can be detected more appropriately compared to the case where the first item and the second item are associated without being associated based on the positional relationship or the subordinate relationship.

[0025] According to the information processing device of the fifth embodiment, even if there are a plurality of identical items, it is possible to recognize a handwritten character string for each item.

[0026] According to the information processing device of the sixth embodiment, it is possible to confirm the correspondence relationship between the setting information and the third character string.

[0027] According to the information processing device of the seventh embodiment, compared with a case where the output format cannot be selected, it is possible to acquire output data that suits the situation.

[0028] According to the information processing device of the eighth embodiment, the detected character string can be more recognizable than when the unique character is not added. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a block diagram showing an example of the hardware configuration of the information processing device according to each embodiment.

[0030] Figure 2 This is a block diagram showing an example of the functional configuration of the information processing device according to each embodiment.

[0031] Figure 3 This is a diagram showing an example of an unfilled document according to the first embodiment.

[0032] Figure 4 It is a schematic diagram showing an example of a related item database in each embodiment.

[0033] Figure 5 This is a diagram showing an example of an unfilled document in which the same group keyword is set for explanation of each embodiment.

[0034] Figure 6 This is a flowchart showing an example of information processing according to the first embodiment.

[0035] Figure 7 This is a diagram showing an example of an unfilled document according to the second embodiment.

[0036] Figure 8 This is a flowchart showing an example of information processing according to the second embodiment.

[0037] Description of Figure Numbers

[0038] 1: Information processing device

[0039] 11: CPU;

[0040] 12: ROM;

[0041] 13: RAM;

[0042] 14: Memory;

[0043] 15: Input unit;

[0044] 16: Display unit;

[0045] 17: Communication I / F;

[0046] 18: bus;

[0047] 21: Setting information production department;

[0048] 22: image input unit;

[0049] 23: Document recognition processing unit;

[0050] 24: Confirmation and correction department;

[0051] 25: result output part;

[0052] 31, 32, 33, 34: string;

[0053] 40: Associated project DB. DETAILED DESCRIPTION

[0054] [First embodiment]

[0055] Hereinafter, with reference to the accompanying drawings, an example of a method for implementing the technology of the present invention will be described in detail. In addition, the information processing device 1 of this embodiment is used as an example to describe an implementation of a server for managing data obtained by reading files and forms. However, it is not limited to the above case. The information processing device 1 can also be installed in a multi-function integrated machine with functions such as printing function, copying function, scanning function, and fax function, or a terminal such as a personal computer.

[0056] Figure 1 1 is a block diagram showing an example of the hardware configuration of the information processing device 1 according to the present embodiment. Figure 1As shown, the information processing device 1 of the present embodiment is configured to include a central processing unit (CPU) 11, a read only memory (ROM) 12, a random access memory (RAM) 13, a memory 14, an input unit 15, a display unit 16, and a communication interface (communication I / F) 17. The CPU 11, the ROM 12, the RAM 13, the memory 14, the input unit 15, the display unit 16, and the communication I / F 17 are connected to each other via a bus 18. In addition, the CPU 11 of the present embodiment is an example of a processor.

[0057] CPU11 controls the entire information processing device 1. ROM12 stores various programs and data including the information processing program used in this embodiment. RAM13 is a memory used as a work area when various programs are executed. CPU11 detects character strings and associates and stores the detected character strings by expanding and executing the programs stored in ROM12 in RAM13. As an example, memory 14 is a hard disk drive (HDD), a solid state drive (SSD) or a flash memory. In addition, information processing programs can also be stored in memory 14. Input unit 15 is a keyboard and mouse that accept input of character strings to be detected and selection of character strings. Display unit 16 is a display that displays the detected character strings as candidates to be set. Communication I / F17 sends and receives data.

[0058] Next, the functional configuration of the information processing device 1 will be described. Figure 2 This is a block diagram showing an example of the functional configuration of the information processing device 1 according to the present embodiment.

[0059] picture Figure 2 As shown, the information processing device 1 includes a setting information creation unit 21, an image input unit 22, a document recognition processing unit 23, a confirmation correction unit 24, and a result output unit 25. The CPU 11 executes an information processing program to function as the setting information creation unit 21, the image input unit 22, the document recognition processing unit 23, the confirmation correction unit 24, and the result output unit 25.

[0060] The setting information creation unit 21 receives input of unfilled file data and an item to be detected (hereinafter referred to as the "first item") contained in the file, and detects a character string representing the first item (hereinafter referred to as the "first character string") from the file in which a column for recording the item is set. When the setting information creation unit 21 detects a plurality of first character strings, the setting information creation unit 21 detects a character string (hereinafter referred to as the "second character string") representing an item (hereinafter referred to as the "second item") associated with the first item for each of the plurality of first character strings. The setting information creation unit 21 sets at least one of the detected second character strings as a second item, associates it with the first item, and sets it in the setting information.

[0061] That is, the setting information making unit 21 detects the first item input from the unfilled file data, and detects the second item associated with the first item, and sets the first item and the second item in the setting information. In establishing the association between the first item and the second item, the setting information making unit 21 establishes an association between the first item and the second item based on the position information of the first item and the second item in the file, or the semantic subordination relationship between the first item and the second item, and sets it in the setting information. The relative position of the character string (hereinafter referred to as the "third character string") to be filled in by the user's handwriting is set in the setting information. The relative position is the direction of filling in the third character string based on the first item and the second item.

[0062] The setting information creation unit 21 performs a process of displaying the detected plurality of first character strings as candidates for the first item, or a process of displaying the detected plurality of second character strings as candidates for the second item. The setting information creation unit 21 performs a process of selecting the first item from the detected plurality of first character strings, or a process of selecting the second item from the plurality of second character strings. When a plurality of identical first items or a plurality of identical second items are set in the setting information, the setting information creation unit 21 adds a unique character to each of the set first items or second items, and sets them in the setting information.

[0063] The configuration information making unit 21 of this embodiment accepts input of unfilled file data and sets the configuration information in a manner described above. However, the configuration information making unit 21 is not limited to the manner described above. When reading a filled file, the configuration information may be set by reading a character string from the filled file.

[0064] The image input unit 22 reads the filled document entered by the user in the form of an image. The document recognition processing unit 23 reads the image of the filled document from the image input unit 22, and recognizes the third character string through optical character recognition (OCR) based on the setting information. The confirmation correction unit 24 displays the recognized character string on the display unit 16 and accepts the correction of the character string.

[0065] The result output unit 25 outputs the character strings identified from the file by item. The result output unit 25 outputs the detected character strings in a form in which the first item included in the setting information, the second item included in the setting information, and the third character string are output separately (hereinafter referred to as "JSON form"). In addition, the result output unit 25 outputs the character strings in a form in which the first item and the second item included in the setting information are linked and set as a unique item and the unique item and the third character string are output (hereinafter referred to as "key-value form"). The result output unit 25 outputs the first item, the second item, and the third character string in either the JSON form or the key-value form. The output form is accepted by the setting information production unit 21 for the selection of the output form and is set in the setting information. In addition, the JSON form is an example of the first form. However, the first form is not limited to the JSON form. In addition, the key-value form is an example of the second form. However, it is not limited to the key-value form.

[0066] In addition, in the present embodiment, the following method is described, that is, the function of setting the setting information and the function of executing the OCR processing of the image input unit 22, the document recognition processing unit 23, the confirmation and correction unit 24, and the result output unit 25 are included in an integrated device. However, this method is not limited to the above method. As long as the setting information can be read when the OCR processing is executed, the function of setting the setting information and the function of executing the OCR processing can also be incorporated into different devices.

[0067] Next, before explaining the operation of the information processing device 1, Figures 3 to 6 The method for setting the setting information by the information processing device 1 is described. In addition, the file of this embodiment includes items such as "name" and "address" (hereinafter referred to as "keywords"), and items indicating the belonging of a plurality of keywords such as "person" and "agent" (hereinafter referred to as "group keywords"). In the first embodiment, the method of indicating the group keyword as the first item and the keyword as the second item is described.

[0068] First, refer to Figure 3 , a method for setting setting information by inputting a group keyword is described. Figure 3It is a diagram showing an example of an unfilled document according to the present embodiment.

[0069] As an example, something like Figure 3 As shown in FIG. 1 , the power of attorney input into the information processing device 1 as unfilled document data includes items for filling in the "address", "name", and "date of birth" of the "agent". In addition, the power of attorney includes items for filling in the "address", "name", and "date of birth" of the "principal".

[0070] For example, in the information processing device 1, "agent" is input as the document data of the power of attorney and the object to be detected as the group keyword. Figure 3 As shown, as a candidate for the first item, a first character string 31 surrounded by a single-point chain line is detected, displayed on the display unit 16, and set as the first item. Specifically, "agent" is detected from the input document data and highlighted on the display unit 16. In the case where the detected first character string 31 is one, the first character string 31 is set as the first item in the setting information. In addition, in the case where the detected first character string 31 is multiple, multiple first character strings 31 are displayed on the display unit 16, and the first character string 31 selected by the user is set as the first item in the setting information. In addition, the first character string to be selected can be one or multiple.

[0071] When the first item is set, the information processing device 1 detects the second character string 32 surrounded by the dotted line as a candidate for the second item to be associated with the first item, displays it on the display unit 16, and sets it as the second item. Specifically, the "address", "name", and "date of birth" located around the "agent" are detected and highlighted on the display unit 16. When one second character string 32 is detected, the second character string 32 is set as the second item in the setting information. In addition, when multiple second character strings 32 are detected, multiple second character strings 32 are displayed on the display unit 16, and the second character string 32 selected by the user is set as the second item in the setting information. In addition, the second character string to be selected can be one or multiple.

[0072] When the second item is set, the information processing device 1 allows the user to select the relative position of the third character string based on the position of the second item (keyword) and sets it in the setting information. The information processing device 1 allows the user to select the output format when the third character string is recognized and sets it in the setting information.

[0073] When reading the filled file, the information processing device 1 obtains the setting information of the same file as the read file, and recognizes the third character string corresponding to the first item and the second item included in the setting information from the written file. The information processing device 1 outputs the first item, the second item, and the third character string based on the output format set in the setting information.

[0074] In this embodiment, a method of establishing an association with a second character string located around a first item as a second item is described. However, it is not limited to the above method. The direction of detecting the second character string 32 may also be specified with the first item as a reference. Specifically, the information processing device 1 may detect the second character string 32 based on the relative position (direction) with the first item as a reference, or may establish an association between the first item and the second item based on the semantic subordinate relationship between the first item and the second item.

[0075] Next, refer to Figure 4 , based on the semantic subordinate relationship, the establishment of the association between the first item and the second item is explained. Figure 4 It is a schematic diagram showing an example of the related item database (hereinafter referred to as "related item DB") 40 according to the present embodiment.

[0076] As an example, something like Figure 4 As shown, the related item DB 40 stores group keywords and keywords as information indicating the semantic subordinate relationship between the first item and the second item. The group keyword of the related item DB 40 stores items indicating the belonging items that a plurality of keywords are grouped together, and the keywords of the related item DB 40 stores candidates for items that belong to the group keyword and whose relationship is recognized. That is, the group keyword and keywords whose subordinate relationship is recognized are defined and stored in advance in the related item DB 40. For example, in the "guarantor" as the group keyword, "name", "address", "telephone number", "name", "number", "current address" and other candidates are associated and stored as keywords subordinate to "guarantor". The information processing device 1 compares the items included in the file with the information obtained from the related item DB to detect the second character string 32.

[0077] Specifically, when the information processing device 1 detects the second character string 32 based on the semantic subordinate relationship, it retrieves and obtains the keyword associated with the group keyword set in the first item from the related item DB 40. The information processing device 1 compares the items included in the file and the obtained keywords, and when there is a matching item, it highlights the matching item as the second character string 32.

[0078] In addition, in this embodiment, the method of pre-storing in the related item DB 40 is described. However, the present invention is not limited to the above method. The first item and the second item set in the setting information may be stored in the related item DB 40 as information indicating a semantic subordinate relationship.

[0079] Next, refer to Figure 5 , the case where the same group keyword is set in the setting information is explained. Figure 5 This is a diagram showing an example of an unfilled document in which the same group keyword is set for explaining the present embodiment.

[0080] As an example, something like Figure 5 As shown, the identity guarantee form input into the information processing device 1 as unfilled document data includes items for filling in the "current address", "occupation", "name" and "relationship to the principal" of the "guarantor".

[0081] The information processing device 1 receives the group keyword "guarantor" as the document data of the identity guarantee and the object of detection. Figure 5 As shown, the first character string 33 and the first character string 34 surrounded by the single-point chain line are detected and displayed as candidates for the first item on the display unit 16. When the user selects the first character string 33 and the first character string 34, the information processing device 1 sets the first character string 33 and the first character string 34 as the first item. The information processing device 1 detects the second character string 32 as a candidate for the second item associated with the first character string 33 and the first character string 34, displays it on the display unit 16, and sets the second character string 32 selected by the user as the second item in the setting information.

[0082] The information processing device 1 selects a plurality of group keywords as the first item or the second item, and when the selected group keywords are the same, unique characters are added to each group keyword so that the group keywords become unique, and are set in the setting information. Figure 5As shown, in the identity guarantee form as the document data, a plurality of "guarantors" are included as group keywords, and are detected as the first character string 33 and the first character string 34. When the user selects the first character string 33 and the first character string 34, "1" is added to the "guarantor" representing the first character string 33, and "2" is added to the "guarantor" representing the first character string 34, and set in the setting information. That is, when the OCR processing is performed based on the setting information, the "current address", "occupation", "name", and "relationship with the person" of "guarantor 1" and the "current address", "occupation", "name", and "relationship with the person" of "guarantor 2" are output. In addition, in the present embodiment, a method of adding a unique character when the group keywords are the same is described. However, it is not limited to the method described. In the case of the same keyword, a unique character may also be added. In addition, in the present embodiment, a method of adding a number as a unique character is described. However, it is not limited to the method described. A unique symbol may be added, and a character obtained by combining a unique number and a symbol may be added.

[0083] Next, refer to Figure 6 , the function of the information processing program of this embodiment is explained. First, Figure 6 is a flowchart showing an example of information processing in this embodiment. CPU 11 reads and executes the information processing program from ROM 12 or memory 14, thereby executing Figure 6 The information processing shown. Figure 6 The information processing shown is executed when, for example, document data is input and an execution instruction of an information processing program is input.

[0084] In step S101, CPU 11 determines whether some document data has been input. If document data has been input (step S101: Yes), CPU 11 moves to step S102. On the other hand, if document data has not been input (step S101: No), CPU 11 waits until document data has been input. Here, the user inputs document data, and inputs either an instruction to set setting information or an instruction to perform OCR processing, and either an output format of JSON format or key-value format.

[0085] In step S102, CPU 11 determines whether the user inputs an instruction to set the setting information or an instruction to perform OCR processing. When an instruction to set the setting information is input (step S102: Yes), CPU 11 moves to step S103. On the other hand, when an instruction to perform OCR processing is input (step S102: No), CPU 11 moves to step S116.

[0086] In step S103 , the CPU 11 acquires the input document data.

[0087] In step S104 , the CPU 11 acquires candidates for the input first item.

[0088] In step S105 , the CPU 11 detects a first character string included in the document data using the input candidate for the first item.

[0089] In step S106, the CPU 11 highlights the detected first character string. Here, the user selects the first character string.

[0090] In step S107 , the CPU 11 sets the first character string selected by the user as the first item.

[0091] In step S108, CPU 11 determines whether a plurality of first items are set. If a plurality of first items are set (step S108: Yes), CPU 11 proceeds to step S109. On the other hand, if a plurality of first items are not set (step S108: No), CPU 11 proceeds to step S110.

[0092] In step S109 , the CPU 11 adds unique characters to the plurality of set first items and stores the characters.

[0093] In step S110 , the CPU 11 detects a second character string that is a candidate for a second item to be associated with the first item from the input document data.

[0094] In step S111, CPU 11 highlights the detected second character string. Here, the user selects the second character string and inputs the relative position of the third character string based on the second character string (keyword). In addition, in this embodiment, the method of inputting the relative position is described. However, it is not limited to the method. It can also be set to a method where the relative position is not input. In the case where the relative position is not input, CPU 11 detects the third character string in all directions based on the second character string (keyword).

[0095] In step S112 , the CPU 11 sets the second character string selected by the user as the second item.

[0096] In step S113 , the CPU 11 obtains the relative position of the third character string with respect to the second item (keyword).

[0097] In step S114 , the CPU 11 acquires the output format selected by the user, either the JSON format or the key-value format.

[0098] In step S115 , the CPU 11 sets the first item, the second item, the relative position, and the output format in the setting information and stores the setting information.

[0099] In step S116, the CPU 11 determines whether to perform OCR processing. When the OCR processing is performed (step S116: Yes), the CPU 11 moves to step S117. On the other hand, when the OCR processing is not performed (step S116: No), the CPU 11 ends the information processing.

[0100] In step S117 , the CPU 11 acquires setting information.

[0101] In step S118 , the CPU 11 acquires the relative position from the setting information.

[0102] In step S119 , the CPU 11 detects the third character string filled in the document data based on the acquired relative position.

[0103] In step S120, CPU 11 determines whether the output format set in the setting information is a key-value format. If it is a key-value format (step S120: Yes), CPU 11 moves to step S121. On the other hand, if it is a JSON format (step S120: No), CPU 11 moves to step S122.

[0104] In step S121 , the CPU 11 acquires the first item and the second item set in the setting information and connects them.

[0105] In step S122 , the CPU 11 acquires the first item and the second item set in the setting information.

[0106] In step S123 , the CPU 11 outputs the first item, the second item, and the third character string based on the output format.

[0107] As described above, according to this embodiment, by setting the group keyword and the keyword, the same items included in the file can be identified. Therefore, even if a file containing multiple identical items is read, setting information capable of identifying multiple detected character strings can be generated for the set items.

[0108] [Second embodiment]

[0109] In the first embodiment, a method of setting a group keyword in the first item and setting a keyword in the second item is described. In this embodiment, a method of setting a keyword in the first item and setting a group keyword in the second item is described. In addition, a block diagram showing the hardware configuration of the information processing device 1 of this embodiment (see Figure 1), a block diagram showing the functional configuration of the information processing device 1 (see Figure 2 ) is the same as the first embodiment, and therefore, the description thereof is omitted. Figure 4 ) and a diagram showing an unfilled document for illustrating setting the same group keyword (refer to Figure 5 ) is the same as the first embodiment, and therefore the description is omitted.

[0110] Reference Figure 7 , a method of inputting a keyword and setting setting information according to the second embodiment is described. Figure 7 : is a diagram showing an example of an unfilled document according to the second embodiment. Figure 7 The unpopulated file pair shown Figure 3 The same components in the Figure 3 The same symbol is used and its description is omitted.

[0111] As an example, something like Figure 7 As shown, the power of attorney, which is unfilled document data, is provided with items for filling in the "address", "name", and "date of birth" of the "agent". In addition, the power of attorney is provided with items for filling in the "address", "name", and "date of birth" of the "principal".

[0112] Assume that in the information processing device 1, "name" is input as a keyword as the document data of the request and the object of detection. Figure 7 As shown, the first character string 31 surrounded by a single-point chain line is detected as a candidate for the first item, and is displayed on the display unit 16 and set as the first item. Specifically, "name" is detected from the input file data and highlighted on the display unit 16. In the case where the detected first character string 31 is one, the first character string 31 is set as the first item in the setting information. In addition, in the case where the detected first character string 31 is multiple, multiple first character strings 31 are displayed on the display unit 16, and the first character string 31 selected by the user is set as the first item in the setting information. In addition, the selected first character string can be one or multiple.

[0113] When the first item is set, the information processing device 1 detects the second character string 32 surrounded by the dotted line as a candidate for the second item to be associated with the first item, displays it on the display unit 16, and sets it as the second item. Specifically, "agent" and "person" located around "name" are detected and highlighted on the display unit 16. When one second character string 32 is detected, the second character string 32 is set as the second item in the setting information. In addition, when multiple second character strings 32 are detected, multiple second character strings 32 are displayed on the display unit 16, and the second character string 32 selected by the user is set as the second item in the setting information. In addition, the selected second character string can be one or multiple.

[0114] When the second item is set, the information processing device 1 allows the user to select the relative position of the third character string based on the position of the first item (keyword) and sets it in the setting information. The information processing device 1 allows the user to select the output format when the third character string is recognized and sets it in the setting information.

[0115] When reading the filled file, the information processing device 1 obtains the setting information of the same file as the read file, and recognizes the third character string corresponding to the first item and the second item included in the setting information from the written file. The information processing device 1 outputs the first item, the second item, and the third character string based on the output format set in the setting information.

[0116] Next, refer to Figure 8 , the function of the information processing program of this embodiment is explained. Figure 8 is a flowchart showing an example of information processing in the second embodiment. The CPU 11 reads and executes the information processing program from the ROM 12 or the memory 14, thereby executing Figure 8 The information processing shown. Figure 8 The information processing shown in the figure is executed when, for example, the information processing device 1 is started and an execution instruction of the information processing program is input. Figure 8 in Figure 6 The identification process is the same as shown, with the addition of Figure 6 The same symbol is used and its description is omitted.

[0117] In step S124, the CPU 11 sets a plurality of second items (group keywords) and determines whether they are the same. If a plurality of second items (group keywords) are set and are the same (step S124: Yes), the CPU 11 moves to step S125. On the other hand, if a plurality of second items (group keywords) are not set or are not the same (step S124: No), the CPU 11 moves to step S113.

[0118] In step S125 , the CPU 11 adds unique characters to the plurality of set second items and stores the characters.

[0119] According to the present embodiment, the setting information can be set by inputting a keyword. As described above, according to the present embodiment, the same effects as those of the first embodiment can be achieved.

[0120] In addition, the configuration of the information processing device 1 described in the above embodiment is an example and may be modified as appropriate within the scope of the gist.

[0121] Furthermore, the flow of program processing described in the above-described embodiments is merely an example, and unnecessary steps may be deleted, new steps may be added, or the processing order may be changed without departing from the gist of the invention.

[0122] In addition, in each of the above embodiments, the so-called processor refers to a processor in a broad sense, including, for example, general-purpose processors such as a central processing unit (CPU), special-purpose processors such as a graphics processing unit (GPU), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), and a programmable logic device.

[0123] In addition, the actions of the processors in the above embodiments are not only performed by one processor, but may also be performed by multiple processors in physically separated locations working together. In addition, the order of the actions of the processors is not limited to the order described in the above embodiments, but may also be changed as appropriate.

[0124] In addition, in the above-mentioned embodiments, the embodiment in which the information processing program is pre-stored (installed) in the memory 14 is described, but the present invention is not limited to the above-mentioned embodiment. The program can also be provided in the form of recording on a recording medium such as a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), and a universal serial bus (USB) memory. In addition, the program can also be provided in the form of being downloaded from an external device via a network.

Claims

1. An information processing device, characterized in that: A processor is provided, and the processor When a plurality of first character strings indicating a first item are detected from a file in which a description column is provided for an item, a second character string indicating a second item associated with the first item is detected for each of the plurality of first character strings. at least one of the detected second character strings is set as the second item in the setting information in association with the first item; A third character string is detected as a character string written by a user and written in a description column corresponding to the setting information, and the third character string is outputted in association with the setting information.

2. The information processing device according to claim 1, characterized in that: The processor executes at least one of a process of displaying the detected plurality of first character strings as candidates for the first item and a process of displaying the detected plurality of second character strings as candidates for the second item.

3. The information processing device according to claim 2, characterized in that: The processor executes at least one of a process of selecting the first item from the plurality of first character strings detected and a process of selecting the second item from the plurality of second character strings.

4. The information processing device according to any one of claims 1 to 3, characterized in that: The processor associates the first item with the second item based on location information of the first item and the second item in the file or a semantically subordinate relationship between the first item and the second item.

5. The information processing device according to claim 1, wherein: The processor outputs in any one of the following two forms, namely: in a first form, the first item included in the setting information, the second item included in the setting information, and the third character string are output separately; and in a second form, the first item and the second item included in the setting information are linked to set as a unique item, and the unique item and the third character string are output.

6. The information processing device according to claim 5, characterized in that: The processor receives a selection of the output format.

7. The information processing device according to claim 5 or 6, characterized in that: When a plurality of identical first items or a plurality of identical second items are set in the setting information, the processor adds a unique character to each of the set first items or the set second items and sets the characters in the setting information.

8. A recording medium storing an information processing program, characterized in that: The information processing program causes the computer to execute the following steps: a detection step of, when a plurality of first character strings representing a first item are detected from a file having a description column for an item, detecting a second character string representing a second item associated with the first item for each of the plurality of first character strings; a setting step of associating at least one of the detected second character strings with the first character string as the second item and setting the second item in setting information; as well as A step of detecting a third character string which is a character string written by a user and recorded in a recording field corresponding to the setting information, and outputting the third character string in association with the setting information.

9. A computer program product, comprising an information processing program, characterized in that The information processing program causes the computer to execute the following steps: a detection step of, when a plurality of first character strings representing a first item are detected from a file having a description column for an item, detecting a second character string representing a second item associated with the first item for each of the plurality of first character strings; a setting step of associating at least one of the detected second character strings with the first character string as the second item and setting the second item in setting information; as well as A step of detecting a third character string which is a character string written by a user and recorded in a recording field corresponding to the setting information, and outputting the third character string in association with the setting information.

Images