JP7784822B2 - Document processing program, information processing device, and document processing method - Google Patents

Description

This disclosure relates to a document processing program, an information processing device, and a document processing method.

In the prior art, an information processing device has been proposed that extracts item names and corresponding text data from image data of paper documents based on predetermined patterns (see, for example, Patent Document 1).

The information processing device disclosed in Patent Document 1 calculates the length of the vertical lines of a table in a document, the width and area of each box, and compares these to extract item boxes based on patterns such as item boxes being to the right of vertical lines or having narrow widths and small areas. It then performs a recognition process on the character patterns within the item boxes to obtain item names. Furthermore, it associates item names with data by extracting data boxes from the right or bottom of the item boxes.

Japanese Patent Application Publication No. 10-116314

However, the information processing device disclosed in the aforementioned Patent Document 1 can distinguish between item frames and data frames in a table and read the table data, even if text is written in the data frames. However, it does not match the table image with the table data, nor does it extract specific information from the table data. As a result, it is unable to indicate the position or range on the table image where the type of information corresponding to the document content is written.

The purpose of this disclosure is to provide a user-friendly document processing program, information processing device, and document processing method, taking into account the above-mentioned conventional technology.

In order to achieve the above-mentioned objective, one aspect of the invention disclosed herein provides the following document processing program, information processing device, and document processing method.

[1] When executed by a computer,
extracting information contained in a table portion of the document information as table information by structuring the information based on the configuration of the table portion;
generating reference information for referencing information in the table information;
A document processing program for causing the computer to function to extract information in at least the table portion of the text portion and table portion contained in the document information using the reference information based on predetermined conditions.
[2] A table information extraction means for structuring information included in a table portion of document information based on the configuration of the table portion and extracting the information as table information;
a reference information generating means for generating reference information for referencing information in the table information;
an information processing device that functions as information extraction means that extracts information in at least the table portion of the text portion and the table portion included in the document information using the reference information based on a predetermined condition;
[3] a memory configured to store document information in addition to predetermined instructions;
Based on the instructions stored in the memory,
extracting information contained in a table portion of the document information stored in the memory as table information by structuring the information based on the configuration of the table portion;
generating reference information for referencing information in the table information;
extracting information in at least the table portion of the text portion and the table portion included in the document information using the reference information based on a predetermined condition;
a processor configured to perform processing for:
An information processing device comprising:
[4] A step of structuring information included in a table portion of the document information based on the configuration of the table portion and extracting the information as table information;
generating reference information for referencing information in the table information;
and extracting information in at least the table portion of the text portion and the table portion contained in the document information using the reference information based on a predetermined condition.

Various embodiments of the present disclosure make it possible to provide a more user-friendly document processing program, information processing device, and document processing method.

FIG. 1 is a schematic diagram showing an example of the configuration of a document processing system according to an embodiment. FIG. 2 is a block diagram showing an example of the configuration of a document processing server device according to an embodiment. FIG. 3 is a schematic diagram showing an example of the structure of document information. FIG. 4 is a schematic diagram showing an example of the configuration of table extraction conditions. FIG. 5 is a schematic diagram showing an example of the configuration of table information. 6A to 6C are schematic diagrams for explaining an example of document information processing in the table information extraction operation. 7A to 7F are schematic diagrams for explaining another example of document information processing in the table information extraction operation. FIG. 8 is a schematic diagram showing an example of the configuration of a screen displayed on the display unit of the terminal by the display control means as a result of the table information extraction operation. FIG. 9 is a schematic diagram showing an example of the configuration of a screen displayed on the display unit of the terminal by the display control means during the contract review operation. FIG. 10 is a schematic diagram showing an example of the configuration of a screen displayed on the display unit of the terminal by the display control means during the contract review operation. FIG. 11 is a schematic diagram showing an example of the configuration of a screen displayed on the display unit of the terminal by the display control means during the contract review operation. FIG. 12 is a schematic diagram showing an example of the configuration of a screen displayed on the display unit of the terminal by the display control means during the contract review operation. FIG. 13 is a flowchart showing the inspection operation of the document processing server device.

[Embodiment]
(Document processing system configuration)
FIG. 1 is a schematic diagram showing an example of the configuration of a document processing system according to an embodiment.

This document processing system 5 is configured by connecting a document processing server device 1, a terminal 2, and a terminal 3 via a network 4 so that they can communicate with each other. Terminal 2 is operated, for example, by a user who wishes to create a document, check its contents, and/or review it, and terminal 3 is operated by another user who wishes to create a document, check its contents, and/or review it, but this is not limited to this. The user of terminal 2 and the user of terminal 3 repeatedly revise and approve document information, such as a contract, until they reach a mutually agreeable agreement. The document processing system 5 is primarily used to understand the content of document information created by one user. Alternatively, the document processing system 5 may be used to have the content of document information created by another user reviewed, or it may also be used to compare any two pieces of document information.

The document processing server device 1 is a server-type information processing device that operates in response to requests from terminals 2 and 3. It includes electronic components such as a central processing unit (CPU), a hard disk drive (HDD), and flash memory, all of which have functions for processing information. The document processing server device 1 does not necessarily have to be a single information processing device; it may be a system in which multiple information processing devices work together, or it may be operated by any cloud service. Furthermore, the functions of the document processing server device 1 may be implemented within terminals 2 and/or 3.

Terminals 2 and 3 are information processing devices such as PCs (Personal Computers) and tablet terminals, and are equipped with electronic components such as a CPU and flash memory that have the functionality to process information within the main body.

Network 4 is a communication network capable of high-speed communication, such as a wired or wireless communication network such as the Internet, an intranet, or a LAN (Local Area Network).

In the above configuration, as an example, the documents processed by the document processing server device 1 are legal documents such as contracts, and one or both of the users are people who are not legal experts but need to create contracts, or legal experts such as lawyers who have knowledge of creating contracts. Also, for example, one or both users may be employees of the company's sales department or legal department.

After uploading document information from terminal 2 or 3 to document processing server device 1, in order to reduce the user's workload when creating a contract or to support the user in creating a contract independently, document processing server device 1 extracts important items for the contract from the document information and reviews the contract using the extracted items. Furthermore, terminal 2 or 3 may be configured to request a contract review by sending a request to terminal 3 or 2 via document processing server device 1 or by other means such as email, and to edit the document information on document processing server device 1 from terminal 2 and terminal 3, thereby enabling tasks such as creating a contract that reflects the opinions and review results of both users.

In this embodiment, the document processing server device 1 extracts important items from both the table portion and the main text portion of document information that includes tables, and then uses the extracted items to review the contract. This embodiment is described below.

Furthermore, while terminal 2 and terminal 3 are shown as single units, multiple units may be connected to network 4, and similarly, multiple users may operate these units.

(Configuration of document processing server device)
FIG. 2 is a block diagram showing an example of the configuration of the document processing server device 1 according to the embodiment.

The document processing server device 1 comprises a control unit 10, which is composed of a CPU and other components and controls each component while executing various programs; a storage unit 11, which is composed of a storage medium such as a flash memory and stores information; and a communication unit 12, which functions as a communication interface for communicating with the outside world via the network 4.

The control unit 10 is composed of a processor such as a CPU, and is electrically connected to a storage unit 11 composed of memory, and a communication unit 12 that functions as a communication interface. By executing a document processing program 110 (described below), the control unit 10 functions as a contract acceptance unit 100, a table information extraction unit 101, a reference information generation unit 102, an information extraction unit 103, a contract review unit 104, a display control unit 105, and the like.

The contract reception means 100 receives a contract from terminal 2 or 3 as document information 111 and stores it in the memory unit 11. In the following explanation, it is assumed that the document information 111 received by the contract reception means 100 is document information such as a contract that includes a table, and that at least the table portion does not have structural information that defines the arrangement and alignment of information such as rows and columns, but it is also possible to receive information that has structural information assigned in advance.

The table information extraction means 101 extracts information from the table portion of the document information 111 according to the table structure based on the table extraction condition information 112, structures the extracted information, and stores it in the memory unit 11 as table information 113.

The reference information generation means 102 generates reference information 114 that is used when referencing information in the structured table information 113 in the document information 111, and stores it in the memory unit 11.

The information extraction means 103 extracts information important to the contract (information that should be included, information that should not be included, information that is better to include, etc.) from the table portion and the text portion other than the table portion of the document information 111 based on review condition information 116, and stores this information in the memory unit 11 as extracted information 115. The information extraction means 103 may also modify the extracted information in a predetermined manner to standardize the description.

The contract review means 104 reviews the contents of the extracted information 115 based on the review condition information 116, generates review result information 117, and stores it in the memory unit 11.

The display control means 105 controls the display of the document information 111, table information 113, and extraction information 115 in the storage unit 11, as well as the output results of each means 100-104, on the display units of terminals 2 and 3 using a predetermined method. Details of the display method will be described later.

The storage unit 11 is composed of memory such as flash memory, and is electrically connected to the control unit 10, which is composed of a processor, etc., and the communication unit 12, which functions as a communication interface. The storage unit 11 stores a document processing program 110 that causes the control unit 10 to operate as each of the above-mentioned means 100-105, document information 111, table extraction condition information 112, table information 113, reference information 114, extraction information 115, review condition information 116, and review result information 117.

Figure 3 is a schematic diagram showing an example of the structure of document information 111.

The document information 111 is, for example, a contract, and has a contract title 111a ₁ , a preface 111a ₂ , a table portion 111a ₃ summarizing the contract terms, and clauses 112a ₄ . . . following these.

Figure 4 is a schematic diagram showing an example of the configuration of table extraction condition information 112.

Table extraction condition information 112 is information defining conditions for extracting table information, and includes a condition ID for identifying the condition, a condition indicating the content of the condition, and a result indicating the action to be taken when the condition is met. For example, as shown in condition ID "001," the table is structured such that items in the same column on the left side of the table are items at the same structural level, and the items "Building Description,""LeasingObject," and "Leasing Conditions" in the same column on the left side of table portion _111a3 in FIG. 3 are item names. Also, as shown in condition ID "002," the table is structured such that when multiple items in the same column belong to the same left-hand column, they are subordinate items to the name of the left-hand column item. Therefore, the items in the same column second from the left of table portion _111a3 in FIG. 3, such as "Location and Scope of Object" and "Floor Area of Object (Wall Center Calculation)," are subordinate items to the item name "Leasing Object." As shown in condition ID "003," the table is structured such that when the item names are "Settlor" and "Consignee," they are subordinate items to the name of the item at the same structural level.

Figure 5 is a schematic diagram showing an example of the configuration of table information 113.

Table information 113a has, as an example, the structure shown in Figure 5, and includes item names, subordinate item names, and description content within the table. As explained in Figure 4, "Building description," "Object of lease," and "Leasing conditions" are the item names of the structure, and each of these items has subordinate item names and further description content for each subordinate item name. Note that table information 113a is not limited to item names, subordinate item names, and description content, but also has a structure name that matches the structure of the table.

(Operation of document processing system)
Next, the operation of the embodiment will be explained by dividing it into (1) basic operation, (2) table information extraction operation, and (3) contract review operation. In the following, the operation will be explained assuming that terminal 2 is the operation target, but if the operation is similar even when terminal 3 is used instead, the explanation will be omitted.

(1) Basic Operation First, a user operates the terminal 2 to log in to a service provided by the document processing server device 1. Upon receiving input of information such as a user ID and password from the user, the terminal 2 transmits the information and an authentication request to the document processing server device 1.

When the document processing server device 1 receives an authentication request from the terminal 2 along with information such as a user ID and password, it references user information (not shown) including pre-registered user IDs and passwords, and authenticates the requester as a user.

Next, once the user has logged in to the service, they operate terminal 2 to upload the contract document information to document processing server device 1. Terminal 2 then uploads the document information to document processing server device 1.

The document processing server device 1 accepts document information 111 from the terminal 2 operated by the client and stores it in the memory unit 11.

When the document processing server device 1 receives document information from the terminal 2 (FIG. 13, S1), it begins the table information extraction operation described below. The document processing server device 1 may also receive a comparison request along with the contract type and contract position, and will change the information to be extracted based on the contract type and contract position, and will change the review content in "(3) Contract Review Operation" described below.

(2) Table Information Extraction Operation FIG. 13 is a flowchart showing the inspection operation of the document processing server device 1.

First, as shown in FIG. 3, the table information extraction means 101 extracts information from the table portion _111a3 of the document information 111, structures the extracted information based on the table extraction condition information 112, and stores it in the storage unit 11 as table information 113 (S2).

Methods by which the table information extraction means 101 recognizes the table portion _111a3 from the document information 111 include, for example, a method of recognizing the arrangement of items in the table from ruled lines, etc., and a method of recognizing text in the table portion _111a3 using a technique such as OCR (Optical Character Recognition), but are not limited to these.

4, the method for structuring the structure and text contents of the table portion _111a3 extracted by the table information extraction means 101 into table information 113 is performed according to the contents specified in the results for the items that match the conditions of the table extraction condition information 112. The table information extraction means 101 associates the position information (coordinates, etc.) and range information (width, height, etc.) of the corresponding text in the table portion _111a3 with each item name, subordinate item name, and description content of the structure of the table information 113 and stores them.

Next, the reference information generation means 102 generates reference information 114 to be used when referencing the information in the structured table information 113 in the document information 111, and stores this in the memory unit 11 (S3).

Figures 6(a) to 6(c) are schematic diagrams illustrating an example of processing document information 111 during table information extraction operations.

Figure 6(a) shows reference information 114a, an example of reference information 114, which refers to a cell in a table containing "contract period."

Using the reference information 114a, the information extraction means 103, which will be described next, identifies a node corresponding to the "contract period" in the structure of the table information 113a, as shown in FIG. 6(b), and, from the position information and range information associated with the node, identifies a position and range _115a2 in the table portion _111a3 , as shown in FIG. 6(c).

Next, the information extraction means 103 extracts information important to the contract (information that should be included, information that should not be included, information that is preferable to include, etc.) from the table portion and the text portion other than the table portion of the document information 111 based on the review condition information 116, and stores the extracted information 115 in the memory unit 11 (S4). Extraction from the table portion is performed by generating reference information 114 from one or more words or phrases determined based on the type and status of the contract, as described above. Extraction from the text portion involves extracting one or more words or phrases determined based on the type and status of the contract from the text portion. Note that the term "extraction" as used above refers not only to the extraction of stated content, but also to the detection of content that is not stated. The information extraction means 103 may also modify the extracted information using a predetermined method to unify the content. For example, in table information 113a, the "contract period" is "four years from January 1, 2018 to December 31, 2021," but the extracted information 115 is corrected to have the "conclusion date" set to "January 1, 2018," the "end date" set to "December 31, 2021," and the "expiration date" set to "four years." It is also possible to unify the dates to the Gregorian calendar, for example.

Next, the user operates terminal 2 to select the document information for which they wish to view the extracted information from the uploaded document information. Terminal 2 then sends a document information selection request to the document processing server device 1.

The display control means 105 of the document processing server device 1 receives a request to select document information and displays a screen for selecting document information on the display unit of the terminal 2 (not shown).

The user refers to the document information selection screen described above, selects document information, and requests that the document information be displayed along with the extracted information. The terminal 2 then sends a display request to the document processing server device 1 along with the identifier of the selected document information.

The display control means 105 of the document processing server device 1 receives a display request from the terminal 2 and controls the display of the screen on the display unit of the terminal 2 based on the document information 111, table information 113, reference information 114, and extraction information 115, for example, as shown in Figure 8 below.

Figure 8 is a schematic diagram showing an example of the screen configuration displayed on the display unit of terminal 2 or 3 by the display control means 105 as a result of the table information extraction operation.

The screen 104e has a display field _104e1 that displays the contents of the document information 111 and a display field _104e2 that displays the contents of the extracted information 115. The display field _104e2 displays the contents of the extracted information 115, specifically, displaying the title as "Fixed-Term Building Lease Agreement," the signing date as "January 1, 2018," the expiration date as "December 31, 2021," and the expiration date as "4 years." The item selected by the user is displayed differently from the other items, resulting in a selected display _104e21 . Furthermore, the position and range in the document information 111 corresponding to the item selected and displayed as the selected display _104e21 are referenced by the reference information 114 and are highlighted as a highlighted display _104e11 .

The user refers to screen 104e, which is used to view the extracted information 115 described above, and checks the contract details and the location and scope of the contract in which those details are stated from the contents of the extracted information 115.

Up until now, we have been describing tables in which item names are arranged in columns, but below we will explain a variation of the table, in which item names are arranged in rows and columns, and the content of the item is determined by the combination of item names.

Figures 7(a) to (f) are schematic diagrams illustrating other examples of processing document information 111 during table information extraction operations.

As shown in Figure 7(a), the table portion 111b is a table in which the contents of items are determined by a combination of row and column item names, such as "Company A"'s "Period" being "XX to XX."

Figure 7(b) shows table information 113b extracted from table portion 111b. As an example, the structure has item names in the rows and columns, with "Item," "Company A," and "Company B" in the first row of table portion 111b being the row item names, and corresponding column item name 1 being "Period," "XX to XX," and "●● to ●●," and column item name 2 being "Price," "100 yen," and "999 yen."

Figure 7 (c) shows reference information 114b, an example of reference information 114, which indicates a reference to a cell in a table identified by "Price" and "Company B."

Using the reference information 114b, the information extraction means 103 identifies a node _115b1 corresponding to the column item name 2 "Price" and the row item name "Company B" in the structure of the table information 113b, as shown in FIG. 7(d), and identifies a cell _115b2 in the table portion _111b from the cell (position information and range information) associated with the node 115b1, as shown in FIG. 7(e), and obtains "999 yen" as the extraction result _115b3 , as shown in FIG. 7(f).

(3) Contract Review Operation Next, the user operates the terminal 2 to select document information for which the user wishes to request a review based on the information extracted from the uploaded document information. The terminal 2 transmits a document information selection request to the document processing server device 1.

The display control means 105 of the document processing server device 1 receives a request to select document information and displays a screen for selecting document information on the display unit of the terminal 2 (not shown).

The user refers to the document information selection screen described above, selects document information, and requests that the review results for the document information be displayed. The terminal 2 sends a display request to the document processing server device 1 along with the identifier of the selected document information.

The contract review means 104 of the document processing server device 1 accepts a display request from the terminal 2, reviews the contents of the extracted information 115 for the selected document information based on the review condition information 116, generates review result information 117, and stores it in the memory unit 11 (S5). The contract review means 104 selects conditions to use from the review condition information 116 according to the type of contract, the position of the creator, etc., and performs the review.

Next, the display control means 105 controls the display of the screen on the display unit of the terminal 2 based on the document information 111, table information 113, reference information 114, extraction information 115, and review result information 117, as shown in Figure 9 below, for example.

Figure 9 is a schematic diagram showing an example of the screen configuration displayed on the display unit of terminal 2 or 3 by the display control means 105 during the contract review operation.

The screen 104a has a display field _104a1 for displaying the contents of the document information 111 and a display field _104a2 for displaying the contents of the review result information 117. In the display field _104a2 , the contents of the review result information 117 reviewed for the extracted items in the table portion of the document information 111 are shown in display boxes _104a21 , _104a22 , and _104a23 , respectively. Specifically, in the case of the display box _104a21 , the pointed out content is "It is not specified whether the commission fee is inclusive of tax or exclusive of tax," the correction policy is "Add a distinction between inclusive of tax and exclusive of tax," and the correction example is "(Price) (1) If consumption tax is exclusive, the client shall pay the contractor XX yen and ... as compensation for this work." Furthermore, the positions and ranges _104a11 , _104a12 , and _104a13 in the document information 111 corresponding to the display boxes _104a21 , _104a22 , and _104a23 are highlighted and referenced based on the reference information 114. Furthermore, an explanation of the correction contents may be further displayed in the display boxes _104a21 , _104a22 , and _104a23 .

The user refers to screen 104a for viewing the review result information 117 described above, and from the contents of the review result information 117, checks the issues with the contract and the location and scope in the contract where keywords or sentences related to those issues are written, and makes edits as necessary.

The review result information 117 varies depending on the correspondence between the table and text sections of the contract, the type of contract, the position of the creator, etc., so other examples will be explained below. Note that Figure 9 shows a case where information was extracted from only the table section, while Figure 10 shows a case where information was extracted from both the table and text sections. Also, Figures 9 and 10 show a common review conducted from multiple positions, while Figures 11 and 12 show reviews conducted according to position.

Figure 10 is a schematic diagram showing an example of the screen configuration displayed on the display unit of terminal 2 or 3 by the display control means 105 during the contract review operation.

The screen 104b has a display field _104b1 for displaying the contents of the document information 111 and a display field _104b2 for displaying the contents of the review result information 117. In the display field _104b2 , the contents of the review result information 117 reviewed for the extracted items in the table portion of the document information 111 are displayed in display boxes _104b21 and _104b22 , respectively, and the contents of the review result information 117 reviewed for the extracted items in the text portion are displayed in display box _{104b23 .} In addition, the positions and ranges 104b11, _104b12 , and _104b13 in the document information 111 corresponding to the display boxes _104b21 , _104b22 , and _104b23 are highlighted and referenced based on the reference information 114.

For example, display box _104b21 displays the following: "Rent payment date is not specified," the correction policy "Add the above," and the correction example "(Rent) 1. The rent is XX yen per month, and the tenant must pay the landlord by XX day of each month..." The correction is made taking into consideration whether the "rent payment date" related to the correction is specified in a text portion other than the table portion in review result information 117. In addition, an explanation of the correction content may be further displayed in display boxes _104b21 , _104b22 , and _104b23 .

Figure 11 is a schematic diagram showing an example of the screen configuration displayed on the display unit of terminal 2 or 3 by the display control means 105 during the contract review operation.

The screen 104c has a display field _104c1 that displays the contents of the document information 111 and a display field _104c2 that displays the contents of the review result information 117. In the display field _104c2 , the contents of the review result information 117 reviewed for the extracted items in the table portion of the document information 111 are displayed in display boxes _104c21 , _104c22 , and _104c23 , respectively, and the contents of the review result information 117 reviewed for the extracted items in the text portion are displayed in display box _104c24 . In addition, the positions and ranges _104c11 , _104c12 , _104c13 , and _104c14 in the document information 111 that correspond to the display boxes _104c21 , _104c22 , _104c23 , and _104c24 are highlighted and referenced based on the reference information 114.

For example, display box _104c21 displays the following from the perspective of the contractor: "The commission fee amount corresponding to the performance ratio has not been determined," the correction policy "Add the above," and the example correction "(Price) 1. The contractor will pay the contractor XX yen (tax included) as compensation for this work by XX/XX/20XX, ..." The correction is made taking into consideration whether the "commission fee amount" related to the correction is determined in a text portion other than the table portion in the review result information 117. Furthermore, an explanation of the correction content may be further displayed in display boxes _104c21 , _104c22 , and _104c23 .

Figure 12 is a schematic diagram showing an example of the screen configuration displayed on the display unit of terminal 2 or 3 by the display control means 105 during the contract review operation.

The screen 104d has a display field _104d1 for displaying the contents of the document information 111 and a display field _104d2 for displaying the contents of the review result information 117. In the display field _104d2 , the contents of the review result information 117 reviewed for the extracted items in the table portion of the document information 111 are displayed in display boxes _104d21 and _104d22 , respectively, and the contents of the review result information 117 reviewed for the extracted items in the text portion are displayed in display box _{104d23 .} In addition, the positions and ranges 104d11, _104d12 , and _104d13 in the document information 111 corresponding to the display boxes _104d21 , _104d22 , and _104d23 are highlighted and referenced based on the reference information 114.

For example, the display box _104d21 displays the following points from the client's perspective: "It is not specified that work incidental to the outsourced work is included in the work content," the correction policy "Add 'all work incidental to the specific outsourced work' to the work content," and the correction example "(Outsourced work) The client outsources the following work (hereinafter referred to as 'this work') to the contractor, ..." The points are also made taking into consideration whether the "work incidental to the outsourced work" related to the points in question is specified in the text part other than the table part in the review result information 117. Furthermore, an explanation of the correction content may be further displayed in the display boxes _104d21 , _104d22 , and _104d23 .

(Effects of the embodiment)
According to the above-described embodiment, when the document information 111 includes a table, the table is structured based on the table extraction condition information 112 and extracted as table information 113, and information in the table information 113 is associated with a corresponding position in the document information 111 to generate reference information 114 for referencing this information. Therefore, even if the document information 111 includes an unstructured table, it is possible to extract extracted information 115 from the document information 111 and present the extracted portion.

Furthermore, information is extracted from the table and text portions of the document information 111 to generate extracted information 115, and the contract review means 104 reviews the extracted information 115, making it possible to review the contract including not only the text portion but also the table portion.

Other Embodiments
The present invention is not limited to the above-described embodiment, and various modifications are possible without departing from the spirit of the present invention.

For example, document information 111 is not limited to contracts, but may be legal documents or instruction manuals, etc., as long as they can be divided into components, and the present invention can be applied to these as well. Furthermore, components are not limited to articles, clauses, and numbers, but may also be words, characters, symbols, paragraphs, or sentences.

In the above embodiment, the functions of each of the means 100-105 of the control unit 10 are implemented by a program, but all or part of each means may also be implemented by hardware such as an ASIC. The program used in the above embodiment may also be stored on a recording medium such as a CD-ROM and provided. Furthermore, the steps described in the above embodiment may be rearranged, deleted, or added without changing the gist of the present invention.

1: Document processing server device 2, 3: Terminal 4: Network 5: Document processing system 10: Control unit 11: Storage unit 12: Communication unit 100: Contract acceptance means 101: Table information extraction means 102: Reference information generation means 103: Information extraction means 104: Contract review means 105: Display control means 110: Document processing program 111: Document information 112: Table extraction condition information 113: Table information 114: Reference information 115: Extraction information 116: Review condition information 117: Review result information

Claims (10)

When executed by a computer,
extracting information included in a table portion of the document information based on a configuration of the table portion, which is a configuration related to one or more dependent items in a first column among a plurality of items in a plurality of columns included in the table portion , and one or more dependent items in a second column that are dependent on the one or more dependent items ;
extracting information from at least the table portion of the text portion and the table portion included in the document information;
A document processing program for causing the computer to function as described above. When executed by the computer,
generating reference information for referencing information in table information corresponding to information included in a table portion of the document information;
extracting information in at least the table portion of the text portion and the table portion included in the document information using the reference information;
2. The document processing program according to claim 1, further causing the computer to function as follows: The document processing program according to claim 1 or 2, wherein the method for extracting information contained in a table portion of the document information involves referencing the information contained in the table portion based on predetermined conditions and recognizing the structure of the table portion. When executed by the computer,
4. The document processing program according to claim 1, further causing the computer to function so as to review the extracted information in the table portion based on a predetermined review condition. A document processing program according to any one of claims 1 to 4, wherein the table portion of the document information is not pre-structured. The document processing program according to any one of claims 1 to 5, wherein the document information includes information related to a contract. When executed by the computer,
The information included in the table portion of the document information is highlighted or a notice is added to the information included in the table portion of the document information.
7. The document processing program according to claim 1, further causing the computer to function as follows: a table information extraction means for extracting information included in a table portion of document information based on a configuration of the table portion, which is a configuration related to one or more dependent items in a first column among a plurality of items in a plurality of columns included in the table portion, and one or more dependent items in a second column that are dependent on the one or more dependent items ;
and an information processing device that functions as information extraction means for extracting information on at least the table portion out of the text portion and the table portion included in the document information. a memory configured to store document information in addition to predetermined instructions;
Based on the instructions stored in the memory,
extracting information included in a table portion of the document information stored in the memory based on a configuration of the table portion, which is a configuration relating to one or more dependent items in a first column among a plurality of items in a plurality of columns included in the table portion , and one or more dependent items in a second column that are dependent on the one or more dependent items ;
extracting information from at least the table portion of the text portion and the table portion included in the document information;
a processor configured to perform processing for:
An information processing device comprising: 1. A computer-implemented document processing method comprising:
extracting information included in a table portion of document information based on a configuration of the table portion, which is related to one or more dependent items in a first column among a plurality of items in a plurality of columns included in the table portion, and one or more dependent items in a second column that are dependent on the one or more dependent items ;
and extracting information from at least the table portion of the text portion and table portion contained in the document information.