Document processing program, information processing device and document processing method

Abstract

To provide a document processing program, an information processing device and a document processing method that extract information from document information and displays the extracted information even when a document contains unstructured tables.SOLUTION: A document processing server device 1 functions as: table information extraction means 101 that structures information contained in table portions in document information 111 based on the configuration of the table portions, and extracts it as table information 113; reference information generation means 102 that generates reference information 114 for referencing the information in the table information 113; and information extraction means 103 that extracts at least the information in the table portions from the text portions and table portions contained in the document information 111 using the reference information 114 based on a predetermined condition.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a document processing program, an information processing device, and a document processing method. [Background technology]

[0002] Conventional technology involves extracting information from image data of paper documents based on predetermined patterns. An information processing device has been proposed that extracts item names and corresponding character data (for example, For example, see Patent Document 1.

[0003] The information processing device disclosed in Patent Document 1 is capable of detecting the length of vertical lines in a table written in a document or the like, and the size of each frame. Calculate the width, area, etc. of the item and compare them to determine whether the item frame is on the right side of the vertical ruled line or if the width is narrow and the area is large. Based on the regularity that the product is small, an item frame is extracted and the character pattern within the item frame is recognized. By performing this process, the item name is obtained. In addition, the data frame is By extracting these, the item names are associated with the data. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 10-116314 Summary of the Invention [Problem to be solved by the invention]

[0005] However, according to the information processing device disclosed in the above-mentioned Patent Document 1, characters are written in the data frame. Even if the table is inserted, the item frame and data frame are distinguished from each other and the table data is read. It does not match images with table data, nor does it extract specific information from table data. Therefore, the position or the position on the table image where the type of information according to the content of the document is written is The problem is that it is not possible to indicate the range.

[0006] The object of the present disclosure is to provide a more user-friendly document processing program, information processing program, and The present invention provides an information processing device and a document processing method. [Means for solving the problem]

[0007] In order to achieve the above object, one aspect of the present disclosure provides the following document processing program: An information processing device and a document processing method are provided.

[0008] [1] When executed by a computer, The information contained in the table part of the document information is structured based on the structure of the table part and is then converted into table information. Extract, generating reference information for referencing information in the table information; Of the text portion and table portion included in the document information, at least the information in the table portion and extracting the information based on a predetermined condition using the reference information. A word processing program that makes the data work. [2] The information contained in the table part of the document information is structured based on the structure of the table part and is then converted into table information. table information extraction means for extracting the table information; a reference information generating means for generating reference information for referencing information in the table information; Of the text portion and table portion included in the document information, at least the information in the table portion and functioning as an information extraction means for extracting the above-mentioned reference information based on a predetermined condition. An information processing device that [3] a memory configured to store document information in addition to predetermined instructions; Based on the instructions stored in the memory, The information contained in the table portion of the document information stored in the memory is extracted based on the structure of the table portion. The data is then structured and extracted as table information. generating reference information for referencing information in the table information; Of the text portion and table portion included in the document information, at least the information in the table portion extracting information based on a predetermined condition using the reference information; a processor configured to perform processing for: An information processing device comprising: [4] The information contained in the table part of the document information is structured based on the structure of the table part and is then converted into table information. and extracting the generating reference information for referencing information in the table information; Of the text portion and table portion included in the document information, at least the information in the table portion and extracting the document using the reference information based on a predetermined condition. Processing method. [Effects of the Invention]

[0009] According to various embodiments of the present disclosure, a more user-friendly document processing program, information processing It is possible to provide an apparatus and a document processing method. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a schematic diagram showing an example of the configuration of a document processing system according to an embodiment. [Figure 2] FIG. 2 is a block diagram showing an example of the configuration of the document processing server device according to the embodiment. [Figure 3] FIG. 3 is a schematic diagram showing an example of the structure of document information. [Figure 4] FIG. 4 is a schematic diagram showing an example of the configuration of table extraction conditions. [Figure 5] FIG. 5 is a schematic diagram showing an example of the configuration of table information. [Figure 6] 6(a) to 6(c) are schematic diagrams for explaining an example of document information processing in the table information extraction operation. [Figure 7] 7(a) to 7(f) are schematic diagrams for explaining another example of document information processing in the table information extraction operation. [Figure 8] 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. [Figure 9] 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. [Figure 10] 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. [Figure 11] 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. [Figure 12] 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. [Figure 13] FIG. 13 is a flowchart showing the inspection operation of the document processing server device. DETAILED DESCRIPTION OF THE INVENTION

[0011] [Embodiment Mode] (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.

[0012] The document processing system 5 includes a document processing server device 1, a terminal 2, and a terminal 3 connected to a network. The terminal 2 is configured by connecting to each other so that they can communicate with each other via a network 4. The terminal 3 is operated by a user who wishes to create, check document contents and / or review documents. Operated by other users who wish to create, verify and / or review documents However, it is not limited to this. The user of terminal 2 and the user of terminal 3 share document information. For example, users can revise and approve a contract until they reach a mutually agreeable agreement. It is a repetitive process, mainly used to understand the content of the document information created by one user. The document processing system 5 is used to process the document information created by one user. You may use a document processing system 5 to have the published content reviewed, or The document processing system 5 may also be used to compare the two pieces of document information.

[0013] The document processing server device 1 is a server-type information processing device, and responds to requests from the terminals 2 and 3. It operates in response to the CPU (Ce Central Processing Unit (CPU) and HDD (Hard Disk Drive) The document processing server device 1 is equipped with electronic components such as a Furthermore, it does not have to be composed of a single information processing device, but rather multiple information processing devices operating in cooperation with each other. It may be a cloud service or may be operated by any cloud service. In addition, the functions of the document processing server device 1 are realized within the terminal 2 and / or the terminal 3. Good

[0014] Terminal 2 and terminal 3 are PCs (Personal Computers) and tablet terminals. Such information processing devices include a CPU or flash memory that has the function of processing information within the main body. It is equipped with electronic components such as flash memory.

[0015] The network 4 is a communication network capable of high-speed communication, for example, the Internet. wired or wireless networks such as intranets, LANs (Local Area Networks), etc. It is a line communication network.

[0016] In the above configuration, as an example, the document processed by the document processing server device 1 is a legal document such as a contract. The document is in the legal field, and one or both users are not legal experts but need to draft a contract. A person who is an important person, or a legal professional such as a lawyer who has knowledge of drafting contracts. For example, one or both users may be employees of the company's sales department or the company's legal department. He is a member.

[0017] After uploading document information from terminal 2 or terminal 3 to document processing server device 1, To reduce the workload of users when creating contracts, or to help users create contracts on their own In order to do so, the document processing server device 1 extracts important items for the contract from the document information, and Furthermore, the contract is reviewed using the extracted items. 3 via the document processing server device 1 or by other means such as e-mail. Request a contract review by sending a request to By editing the document information on the server device 1, the opinions and review results of both users are reflected. Even if the system is configured to be able to perform tasks such as creating contracts good.

[0018] In this embodiment, the document processing server device 1 processes the table portion and the main text of the document information including the table. Important items are extracted from each part, and the extracted items are used to Review the following:

[0019] Although the terminal 2 and the terminal 3 are shown as single units, multiple units may be connected to the network 4. Similarly, these may be operated by multiple users. .

[0020] (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.

[0021] The document processing server device 1 is composed of a CPU and other components, and controls each part and executes various processes. The control unit 10 executes the program, and the storage medium such as a flash memory stores information. a storage unit 11 for storing the data, and a communication interface for communicating with the outside via a network 4. The communication unit 12 functions as a communication device.

[0022] The control unit 10 is configured with a processor such as a CPU, and a storage unit 11 is configured with a memory. The control unit 12 is electrically connected to the communication unit 12, which functions as a communication interface. 10 executes a document processing program 110, which will be described later, to operate as a contract acceptance means 100, Table information extraction means 101, reference information generation means 102, information extraction means 103, contract review means 104 and display control means 105.

[0023] The contract receiving means 100 receives a contract from the terminal 2 or the terminal 3 as document information 111. The contract acceptance means 100 accepts the contract and stores it in the storage unit 11. The document information 111 is document information such as a contract that includes a table, and at least the table portion is organized in rows and columns. It is assumed that there is no structural information that defines the arrangement and sequence of information such as The above information may be provided.

[0024] The table information extraction means 101 extracts table information from the table portion of the document information 111 based on the table extraction condition information 112. The extracted information is structured and stored in a storage unit as table information 113. Store in 11.

[0025] The reference information generating means 102 converts the information in the structured table information 113 into the document information 111. The reference information 114 used when referring to the image is generated and stored in the storage unit 11 .

[0026] The information extraction means 103 extracts the following from the table portion and the text portion other than the table portion of the document information 111: Important information for the contract (information that should be included, information that should not be included, information that would be better to include) The extracted information is recorded as extracted information 115 based on review condition information 116 that defines the review condition information (information to be reviewed, etc.). The information extraction means 103 stores the extracted information in a predetermined manner. It is also acceptable to correct the information and unify it.

[0027] The contract review means 104 selects the contract from the extracted information 115 based on the review condition information 116. The contents are reviewed to generate review result information 117, which is stored in the storage unit 11.

[0028] The display control means 105 displays the document information 111, the table information 113, and the extracted information 115 in the storage unit 11. The output results of each of the means 100-104 are displayed on the display units of the terminals 2 and 3 in a predetermined manner. The display method will be described in detail later.

[0029] The storage unit 11 is composed of a memory such as a flash memory, a processor, etc. The controller 10 is electrically connected to a control unit 10 and a communication unit 12 that functions as a communication interface. The storage unit 11 is a document processing unit that causes the control unit 10 to operate as each of the above-mentioned means 100-105. processing program 110, document information 111, table extraction condition information 112, table information 113, reference information 114, extracted information 115, review condition information 116, review result information 117, etc. do.

[0030] FIG. 3 is a schematic diagram showing an example of the configuration of the document information 111. As shown in FIG.

[0031] The document information 111 is, for example, a contract, and includes a title 111a1 of the contract and a preface 111b. 111a2, a table section 111a3 summarizing the contract terms, and the following clause 112a4... It has the following.

[0032] FIG. 4 is a schematic diagram showing an example of the configuration of the table extraction condition information 112. As shown in FIG.

[0033] The table extraction condition information 112 is information that defines the conditions for extracting table information, and identifies the conditions. The condition ID for distinguishing between the two, the condition indicating the content of the condition, and the result indicating the action to be taken when the condition is met. For example, as shown in the condition ID "001", the table is structured as follows: Items in the same column are items in the same hierarchy of the structure, so that the leftmost items in the table part 111a3 of FIG. The column items "Building description", "Object of lease", and "Leasing conditions" are the item names. As shown in condition ID "002", the table structure is such that multiple items in the same column are If it belongs to a frame, it is made a subordinate item of the item name of the left column, and the table part 111a3 of FIG. The second item from the left in the same column, for example, "location and scope of the object," "floor area of ​​the object," (Wall center calculation)" is a subordinate item of the item name "Object of lease". As shown in the table, when the item names are "trustor" and "trustee," the structure is the same. This is the name of the hierarchy item.

[0034] FIG. 5 is a schematic diagram showing an example of the configuration of the table information 113.

[0035] The table information 113a has a structure as shown in FIG. 5, for example, and includes the item names, dependent items, and As explained in Figure 4, the title and description are "Building description" and "Object of lease". "Lease conditions" is the item name of the structure, and the subordinate item names of each of these items and each subordinate item The table information 113a includes the item name, subordinate item name, and description content. However, the structure name should be in accordance with the table structure.

[0036] (Operation of document processing system) Next, the operation of the embodiment will be explained as follows: (1) basic operation, (2) table information extraction operation, (3) contract review The following explanation will be divided into view operations. If the same operation is achieved when replaced with

[0037] (1) Basic operation First, the user accesses the terminal to log in to the service provided by the document processing server device 1. Terminal 2 receives input of information such as a user ID and password from the user. When the authentication information is received, the authentication information is transmitted to the document processing server device 1 together with an authentication request.

[0038] The document processing server device 1 receives authentication information such as a user ID and password from the terminal 2. When the request is received, the user ID and password registered in advance are sent to the The information is referenced and the requester is authenticated as a user.

[0039] Next, once the user has logged in to the service, the document information of the contract is transferred to the document processing server. The user operates the terminal 2 to upload the document information to the server device 1. The terminal 2 then The data is uploaded to the management server device 1.

[0040] The document processing server device 1 receives and stores document information 111 from a terminal 2 operated by a client. The data is stored in the memory unit 11.

[0041] When the document processing server device 1 receives document information from the terminal 2 (FIG. 13, S1), the document processing server device 1 performs the following steps: The document processing server device 1 starts the table information extraction operation shown in A comparison request may be accepted along with the status of the contract, and a comparison may be made based on the type of contract and the status of the contract. The information to be extracted is changed depending on the contract, and the information within the review is Change the content.

[0042] (2) Table information extraction operation FIG. 13 is a flowchart showing the inspection operation of the document processing server device 1.

[0043] First, the table information extraction means 101 extracts the table portion 111a of the document information 111 as shown in FIG. Information is extracted from the three parts, and the extracted information is structured and displayed based on the table extraction condition information 112. The information is stored in the storage unit 11 as information 113 (S2).

[0044] The table information extraction means 101 may recognize the table portion 111a3 from the document information 111 as follows: For example, a method for recognizing the layout of items in a table from lines, etc., and a method for recognizing text in the table portion 111a3 The method of recognizing text is OCR (Optical Character Recognition). Examples of such technologies include, but are not limited to, the use of a holographic laser.

[0045] In addition, the structure and text contents of the table part 111a3 extracted by the table information extraction means 101 are The method of structuring into the table information 113 is the same as that explained in FIG. For items that meet the conditions of 112, the content indicated in the results is carried out. The column 101 is a table portion 11 for each item name, subordinate item name, and description content of the structure of the table information 113. 1a3) and range information (width and height, etc.) of the relevant text Add it and remember it.

[0046] Next, the reference information generating means 102 converts the information in the structured table information 113 into the document information 11 1, the reference information 114 to be used when referring to the data on the network is generated and stored in the storage unit 11 (S 3).

[0047] 6(a) to 6(c) illustrate an example of processing of document information 111 in table information extraction operation. FIG.

[0048] FIG. 6(a) is reference information 114a showing an example of the reference information 114, which indicates the "contract period". This indicates a reference to a cell in a table that contains

[0049] Based on the reference information 114a, the information extraction means 103, which will be described next, extracts the information as shown in FIG. Then, the node corresponding to the "contract period" in the structure of the table information 113a is identified, and the From the linked position information and range information, as shown in FIG. 6(c), The position and range 115a2 of the

[0050] Next, the information extraction means 103 extracts the table portion and the text portion other than the table portion of the document information 111. Based on the review condition information 116, important information for the contract (information to be included) , information that should not be included, information that should be included, etc.) are extracted and set as extracted information 115. The data is stored in the storage unit 11 (S4). The data is extracted from the table portion based on the type of contract and the status as described above. Generate reference information 114 from a single or multiple phrases determined based on the situation. In addition, extraction from the text portion is performed in a singular or plural form based on the type and status of the contract. Extract multiple words and phrases from the text. This includes not only extraction but also detection of non-description. The information extraction means 103 corrects the extracted information in a predetermined manner to unify the descriptions. For example, in the table information 113a, the "contract period" may be "January 1, 2018" The period is four years from the date of the contract to December 31, 2021. However, extracted information 115 is " "Date" is "January 1, 2018", "End date" is "December 31, 2021", "Expiration date" The period can be corrected to "4 years" and extracted. You can also unify the dates to the Gregorian calendar.

[0051] Next, the user selects the document information for which they want to check the information extracted from the uploaded document information. The terminal 2 is operated to select the document information. The terminal 2 sends the document information selection request to the document processing server device 1. Send a request.

[0052] The display control means 105 of the document processing server device 1 receives the request to select document information, and A screen for selecting information is displayed on the display unit of the terminal 2 (not shown).

[0053] The user selects and extracts document information while referring to the screen for selecting document information described above. The terminal 2 requests the display of the document information together with the selected document information. A display request is sent to the document processing server device 1.

[0054] The display control means 105 of the document processing server device 1 receives a display request from the terminal 2 and displays the document. Based on the information 111, the table information 113, the reference information 114, and the extracted information 115, for example, As shown in FIG. 8, the screen displayed on the display unit of the terminal 2 is controlled.

[0055] FIG. 8 shows the table information extracted by the display control means 105 and displayed on the display unit of the terminal 2 or 3. FIG. 10 is a schematic diagram showing an example of the configuration of a displayed screen.

[0056] The screen 104e includes a display field 104e1 for displaying the contents of the document information 111 and a display field 104e2 for displaying the extracted information 111. The display field 104e2 displays the contents of the extracted information 115. The contents of the contract are displayed, specifically, the title is "Fixed-term Building Lease Agreement" and the conclusion date is The date is "January 1, 2018", the end date is "December 31, 2021", and the expiration date is " "4 years" and the items selected by the user will be displayed differently from other items. By selecting Display 104e 21 In addition, the selection display 104e 21 The corresponding item The position and range in the document information 111 to be highlighted are referenced by the reference information 114. 04e 11 This becomes:

[0057] The user refers to the screen 104e for referring to the extracted information 115, and selects the extracted information. 115 to confirm the details of the contract and the location and scope of the contract in which the details are stated. do.

[0058] Up to this point, we have explained a table where item names are arranged in columns. However, as a variation of the table, In the case of a table where item names are set for rows and columns and the contents of the items are determined by the combination of the item names, The following explains this.

[0059] 7(a) to 7(f) illustrate another example of processing the document information 111 in the table information extraction operation. FIG.

[0060] As shown in FIG. 7(a), the table portion 111b shows, for example, the "period" of "Company A" as "XX~ It is a table in which the contents of the items are determined by the combination of the item names in the rows and columns, such as "XX". do.

[0061] FIG. 7(b) shows table information 113b extracted from the table portion 111b. The table portion 111b has a structure in which the rows and columns each have an item name. ", "Company A", and "Company B" are the row item names, and correspondingly, column item name 1 is "Period", "○ Column name 2 is "Price", "100 yen", "999 yen", etc. It has a structure like this.

[0062] FIG. 7(c) is reference information 114b showing an example of the reference information 114, which includes "price" and "B This indicates a reference to a cell in a table identified by "Company."

[0063] Based on the reference information 114b, the information extracting means 103 extracts the table information 1 as shown in FIG. Node 115b1 that corresponds to column item name 2 "Price" and row item name "Company B" in the structure of 13b From the cell (location information and range information) associated with the node 115b1, 7(e), the cell 115b2 in the table portion 111b is identified, and the Thus, the extracted result 115b3 is "999 yen."

[0064] (3) Contract review operation Users then review the document based on information extracted from the uploaded document. The user operates the terminal 2 to select the document information he or she wishes to request. The terminal 2 is connected to the document processing server device 1. Sends a request to select document information.

[0065] The display control means 105 of the document processing server device 1 receives the request to select document information, and A selection screen is displayed on the display unit of the terminal 2 (not shown).

[0066] The user selects the document information while referring to the screen for selecting the document information, and then The terminal 2 displays the information review results together with the identifier of the selected document information. The display request is transmitted to the document processing server device 1 .

[0067] The contract review means 104 of the document processing server device 1 receives a display request from the terminal 2. Then, for the selected document information, the extracted information 115 is extracted based on the review condition information 116. The contents are reviewed, and review result information 117 is generated and stored in the storage unit 11 (S5). The contract review means 104 may also include the review condition information 116, such as the contract type, The review is carried out by selecting the conditions to be used depending on the creator's position, etc.

[0068] Next, the display control means 105 displays document information 111, table information 113, reference information 114, and extracted information. Based on the information 115 and the review result information 117, for example, as shown in the following FIG. The screen is displayed and controlled on the second display unit.

[0069] FIG. 9 shows the display of the terminal 2 or 3 by the display control means 105 during the contract review operation. 10 is a schematic diagram showing an example of the configuration of a screen displayed on the display unit. FIG.

[0070] The screen 104a includes a display field 104a1 for displaying the contents of the document information 111 and a review result field 104a2 for displaying the contents of the document information 111. The display field 104a2 displays the contents of the information 117. The contents of the review result information 117 reviewed for the extracted items in the table portion of the information 111 are Display box 104a 21 , 104a 22 , 104a 23 Specifically, , display box 104a 21 If so, the point is, "It is determined whether the commission fee includes or excludes tax. ", Correction policy "Added distinction between tax-inclusive and tax-exclusive prices", Correction example "(Price) (1) Consumption In the case of excluding tax, the client will pay the contractor a certain amount in the form of "●● yen and..." as compensation for the work. Also, the display box 104a 21 , 104a 22 , 104a 23 Corresponding to Position and range 104a in document information 111 11 , 104a 12 , 104a 13 But see The information 114 is highlighted and referenced. 21 , 1 04a 22 , 104a 23 An explanation of the correction may also be displayed.

[0071] The user refers to the screen 104a for referring to the review result information 117 described above, From the contents of the review result information 117, problems in the contract and keywords or will review the position and scope of the statement in the contract and make edits as necessary.

[0072] The review result information 117 includes information on the correspondence between the table portion and the text portion in the contract, the type of the contract, etc. The content of the review will vary depending on the type, the creator's position, etc., so other examples will be explained below. Note that Fig. 9 shows the case where information is extracted only from the table portion, and Fig. 10 shows the case where information is extracted from both the table portion and the 9 and 10 show the case where information is extracted from multiple A common review is conducted for each position, and reviews according to position are shown in Figures 11 and 12. This is being done.

[0073] FIG. 10 shows the display of the terminal 2 or 3 by the display control means 105 during the contract review operation. 10 is a schematic diagram showing an example of the configuration of a screen displayed on a display unit. FIG.

[0074] The screen 104b includes a display field 104b1 for displaying the contents of the document information 111 and a review result field 104b2 for displaying the contents of the document information 111. The display field 104b2 displays the contents of the information 117. The contents of the review result information 117 reviewed for the extracted items in the table portion of the information 111 are Display box 104b 21 , 104b 22 For the extracted items in the text part, The contents of the reviewed review result information 117 are displayed in a display box 104b. 23 As shown in. Also, display box 104b 21 , 104b 22 , 104b 23 Document information corresponding to 11 Location and range in 104b 11 , 104b 12 , 104b 13 However, based on reference 114 The text is highlighted and referenced accordingly.

[0075] For example, display box 104b 21 So, what is the point of the matter? "Rent payment date is fixed. "Not specified", correction policy "Add the above", correction example "(Rent) 1. The rent is ●● yen per month. The tenant must notify the landlord by the date of each month. In the result information 117, the "rent payment due date" related to the pointed out content is in the text other than the table part. The point is also made taking into consideration whether it is specified in the text section. S104b 21 , 104b 22 , 104b 23 You may also want to display an explanation of the modifications. .

[0076] FIG. 11 shows the display of the terminal 2 or 3 by the display control means 105 during the contract review operation. 10 is a schematic diagram showing an example of the configuration of a screen displayed on a display unit. FIG.

[0077] The screen 104c includes a display field 104c1 for displaying the contents of the document information 111 and a review result field 104c2 for displaying the contents of the document information 111. The display field 104c2 displays the contents of the information 117. The contents of the review result information 117 reviewed for the extracted items in the table portion of the information 111 are Display box 104c respectively 21 , 104c 22 , 104c 23 Then, extract the text part The contents of the review result information 117 reviewed for the output item are displayed in a display box 104c2. 4. Also, display box 104c 21 , 104c 22 , 104c 23 , 104 c 24 The position and range 104c in the document information 111 corresponding to 11 , 104c 12 , 104 c 13, 104c 14 is highlighted and referenced based on the reference information 114.

[0078] For example, display box 104c 21 So, what is the point of the comment "Commission fee according to the performance ratio"? The amount is not specified", Correction policy "Add the above", Correction example "(Price) 1. Consignor will pay the contractor ¥●● (tax included) as compensation for this work by the date of ●● / ● / 20●●. " is displayed from the perspective of the trustee, and the relevant points are Regarding whether the "commission fee" related to the content is specified in the text part other than the table part, The indication is given taking into consideration the above. 21 , 104c 22 , 104 c 23 An explanation of the correction may also be displayed.

[0079] FIG. 12 shows the display of the terminal 2 or 3 by the display control means 105 during the contract review operation. 10 is a schematic diagram showing an example of the configuration of a screen displayed on a display unit. FIG.

[0080] The screen 104d includes a display field 104d1 for displaying the contents of the document information 111 and a review result field 104d2 for displaying the contents of the document information 111. The display field 104d2 displays the contents of the information 117. The contents of the review result information 117 reviewed for the extracted items in the table portion of the information 111 are Display box 104d respectively 21 , 104d 22 For the extracted items in the text part, The contents of the reviewed review result information 117 are displayed in a display box 104d. 23 As shown in. Also, display box 104d 21 , 104d 22 , 104d 23 Document information corresponding to 11 Location and range in 104d 11 , 104d 12 , 104d 13 However, based on reference 114 The text is highlighted and referenced accordingly.

[0081] For example, display box 104d 21 So, the point being made that "the work accompanying the outsourced work is also ,The ,specific ,description ,of ,the ,job ,content ,is ,not ,specified. "Added all work incidental to the commissioned work," and revised example: "(Contract content) The consignor shall The following business (hereinafter referred to as "this business") will be entrusted to the client, and the client will be represented as a client. In the review result information 117, the “Contract work” related to the content of the findings is Also, consider whether the "related business" is specified in the text other than the table. Also, the display box 104d 21 , 104d 22 , 104d 23 Furthermore An explanation of the correction may be displayed.

[0082] (Effects of the embodiment) According to the above embodiment, when the document information 111 includes a table, the table extraction condition information 11 2, the table is structured and extracted as table information 113, and the table information 11 3 and the corresponding position in the document information 111, and Therefore, even if an unstructured table is included, the reference information 114 is generated. Even if the document information is not displayed, the extracted information 115 can be extracted from the document information 111 and the extracted portion can be displayed.

[0083] Furthermore, information is extracted from the table portion and text portion of the document information 111 to generate extracted information 1 15 is generated, and the extracted information 115 is reviewed by the contract review means 104. This allows you to review contracts not only in the text but also in the tables. can be done.

[0084] [Other embodiments] The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit of the present invention. Various modifications are possible.

[0085] For example, document information 111 is not limited to contracts, but can be divided into components, such as legal documents. The present invention can be applied to documents or instruction manuals for the product itself. In addition, the components are not limited to clauses, paragraphs, and items, but may also be words, letters, or symbols, or may be paragraphs, sentences, or It may be a chapter.

[0086] In the above embodiment, the functions of the means 100-105 of the control unit 10 are realized by a program. However, all or part of each means may be realized by hardware such as ASIC. The programs used in the above embodiments may be stored on a recording medium such as a CD-ROM and provided. Furthermore, the steps described in the above embodiments can be replaced, deleted, added, etc. This is possible within the scope of the invention. [Explanation of symbols]

[0087] 1: Document processing server device 2, 3: Terminal 4: Network 5: Document processing system 10: Control section 11: Storage section 12: Communications Department 100: Contract acceptance method 101:Table information extraction means 102: Reference information generation means 103: Information extraction means 104: Contract review method 105: Display control means 110: Word processing program 111: Document information 112:Table extraction condition information 113:Table information 114: Reference Information 115: Extracted information 116: Review condition information 117: Review result information

Claims

1. 1. A computer-implemented document processing method comprising: extracting information included in a table portion showing the contract contents in a list format in document information related to the contract as table information including at least one column item and description content in the contract corresponding to that item based on a configuration related to the item in at least one column included in the table portion; and extracting information from at least the table portion of the text portion and the table portion contained in the document information.

2. A step of generating reference information for referencing information in table information corresponding to information included in a table portion of the document information; 2. The document processing method according to claim 1, further comprising: 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.

3. A document processing method as described in claim 1 or 2, wherein the step of extracting information in the table portion of the document information refers to the information contained in the table portion based on predetermined conditions and recognizes the structure of the table portion.

4. A document processing method described in any one of claims 1 to 3, further comprising a step of reviewing the information in the extracted table portion based on predetermined review conditions.

5. The document processing method according to claim 1 , wherein the table of the document information is not pre-structured.

6. A document processing method described in any one of claims 1 to 5, further comprising a step of highlighting information in the table portion of the document information, or a step of marking the information in the table portion of the document information.

7. A table information extraction means for extracting information contained in a table portion showing the contract contents in a list format within document information relating to a contract as table information including items in at least one column contained in the table portion and the description contents in the contract corresponding to said items, based on the configuration of items in said at least one column contained in the table portion; 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.

8. 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 showing the contract contents in a list format within the document information related to the contract stored in the memory based on a configuration related to the items in at least one column included in the table portion as table information including the items in the at least one column and the description content in the contract corresponding to the 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:

9. When executed by a computer, extracting information included in a table portion showing the contract contents in a list format within document information related to the contract as table information including items in at least one column included in the table portion and the description contents in the contract corresponding to the items, based on a configuration related to the items in the at least one column included in the table portion; 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.

Images