Document processing program, information processing apparatus, and document processing method

Abstract

To provide a document processing program, an information processing apparatus, and a document processing method that extract a character string indicating the content of a document from document information, and even when there is a difference in writing in the extracted character string, integrally manage the relevant portions.SOLUTION: A document processing server 1 has: information extraction means 102 that extracts a character string indicating the content of a document from document information 111 together with information on a position in the document information 111 to obtain extraction information 113; normalization means 103 that normalizes the content of each item of the extraction information 113 to obtain normalized extraction information 114; and display control means 104 that displays the content of the normalized extraction information 114 while indicating the relevant position in the document information 111 on the basis of the information on the position of the extraction information 113.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] As a conventional technique, an information processing device has been proposed that detects keywords from a contract and notifies a contractor of risks in advance (for example, see Patent Document 1).

[0003] The information processing device disclosed in Patent Document 1 detects predetermined keywords from within a contract document, recognizes important points for the user making the contract from among the detected keywords, and presents the important points together with risks to allow the user to decide whether or not to conclude the contract. In addition, when the information processing device detects a contract renewal deadline or the like from within the contract document, it presents an renewal settings screen and allows the user to decide whether or not to notify the user of the renewal. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2018 / 042548 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the information processing device disclosed in the above-mentioned Patent Document 1 detects keywords from a contract to notify the contractor of risks in advance and allows the contractor to decide whether or not to notify the contractor of contract renewal, but there is a problem in that it cannot respond when there are notations in the detected keywords. Also, when one wants to know the description in the contract that corresponds to the detected keywords, if there are notations in the detected keywords, there is a problem in that it is not possible to centrally manage all the relevant parts.

[0006] In view of the above-mentioned conventional techniques, an object of the present disclosure is to provide a document processing program, an information processing device, and a document processing method that are easier to use. [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, information processing device, and document processing method.

[0008] [1] Computer, an extraction means for extracting a character string indicating the content of a document from the document information together with position information within the document information; a normalization means for normalizing the character string extracted by the extraction means to obtain normalized extracted information; a document processing program for causing the content of the normalized extraction information to function as a display control means for displaying a corresponding position of the document information based on the position information; [2] further functioning as a division means for dividing document information into unit information by predetermined units; The extraction means extracts a character string indicating the content of the document together with position information of the unit information, The document processing program according to [1], wherein the display control means displays the contents of the normalized extraction information by indicating the corresponding positions of the unit information based on position information of the unit information. [3] The document processing program according to claim 1 or 2, wherein the extraction means registers a specified character string in the document information as extracted information. [4] The document processing program according to any one of [1] to [3], wherein the display control means displays the normalized extraction information, the unit information, and the document information in association with each other. [5] The document processing program according to any one of [1] to [4], wherein the computer is communicatively connected to one or more terminals via a network. [6] The document processing program according to any one of [1] to [5], wherein the computer is connected to one or more terminals via a wireless communication network. [7] An extraction means for extracting a character string indicating the content of a document from the document information together with position information within the document information; a normalization means for normalizing the character string extracted by the extraction means to obtain normalized extracted information; an information processing apparatus comprising: a display control means for displaying the contents of the normalized extraction information, based on the position information, while indicating the corresponding position of 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 a character string indicating the content of the document from the document information together with position information within the document information; The extracted character string is normalized to obtain normalized extracted information; displaying the contents of the normalized extraction information, indicating the corresponding position of the document information based on the position information; a processor configured to perform operations for: An information processing device comprising: [9] An extraction step of extracting a character string indicating the content of the document from the document information together with position information within the document information; a normalization step of normalizing the extracted character string to obtain normalized extracted information; and displaying the contents of the normalized extraction information based on the position information to indicate the corresponding position of the document information. Effect of the Invention

[0009] According to various embodiments of the present disclosure, it is possible to provide a document processing program, an information processing device, and a document processing method that are easier to use. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a schematic diagram showing an example of a configuration of a document processing system according to an embodiment. [Diagram 2] FIG. 2 is a block diagram showing an example of the configuration of the document processing server device according to the embodiment. [Diagram 3] FIG. 3 is a schematic diagram showing an example of the configuration of document information. [Figure 4] FIG. 4 is a schematic diagram showing an example of the configuration of the extraction information. [Diagram 5] FIG. 5 is a schematic diagram showing an example of the configuration of normalized extraction information. [Figure 6] FIG. 6 is a schematic diagram for explaining an example of the information extraction operation process. [Figure 7] FIG. 7 is a schematic diagram for explaining an example of the operation of the normalization means. [Figure 8] FIG. 8 is a schematic diagram showing a display example of the display control means. [Figure 9] FIG. 9 is a schematic diagram showing an example of a screen displayed when extraction information is registered in response to an operation. [Figure 10] FIG. 10 is a flowchart showing the information extraction operation of the document processing server device. [Figure 11] FIG. 11 is a flowchart for explaining the display processing operation. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] [Embodiment Mode] (Document Processing System Configuration) FIG. 1 is a schematic diagram showing an example of a configuration of a document processing system according to an embodiment.

[0012] 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 by a user who wishes to manage documents, create documents, check document contents, and / or review documents, and terminal 3 is operated by another user, but is not limited to this. The user of terminal 2 and the user of terminal 3 handle document information, such as contracts, and use the document processing system 5 mainly to manage document information created by one or both users, as well as to manage document information after the contract is concluded, and to check and understand the content of the document information.

[0013] The document processing server device 1 is a server-type information processing device that operates in response to requests from the terminals 2 and 3, and includes electronic components such as a CPU (Central Processing Unit) having functions for processing information within its main body, an HDD (Hard Disk Drive), and a flash memory. Note that the document processing server device 1 does not necessarily need to be configured as a single information processing device, and may be a device in which multiple information processing devices operate in cooperation with each other, or a device that operates using any cloud service. Furthermore, the functions of the document processing server device 1 may be realized within the terminals 2 and / or 3.

[0014] The terminal 2 and the terminal 3 are information processing devices such as PCs (Personal Computers) and tablet terminals, and include electronic components such as a CPU having a function for processing information within the main body, a flash memory, and the like.

[0015] The network 4 is a communication network capable of high-speed communication, and is, for example, a wired or wireless communication network such as the Internet, an intranet, or a LAN (Local Area Network).

[0016] In the above configuration, as an example, the document processed by the document processing server device 1 is a document in the legal field such as a contract, and one or both of the users is a person who is not a legal expert but needs to create a contract, or a legal expert such as a lawyer who has knowledge of creating contracts. Also, for example, one or both of the users is an employee of the company's sales department or an employee of the company's legal department.

[0017] As a basic operation, after document information is uploaded from terminal 2 or terminal 3 to document processing server device 1, the document information is managed in document processing server device 1, and the contents of the document information are confirmed by accessing document processing server device 1 from terminal 2 or terminal 3, but at this time, in order to reduce the burden of confirmation work on the user or to assist the user in creating a contract, the document processing server device 1 extracts information from the document information and displays the extracted information in a format that helps the user understand the contents. Specific examples of display methods will be described later.

[0018] In this embodiment, the document processing server device 1 mainly extracts information indicating the contract status from the document information, and presents the extracted information to one or both users. In the following, a clause may be referred to as a "provision." The embodiment will be described below.

[0019] Although the terminal 2 and the terminal 3 are illustrated as being singular, a plurality of terminals may be connected to the network 4, and similarly, these may be operated by a plurality of 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 equipped with a control unit 10 which is composed of a CPU and the like and controls each part and executes various programs, a memory 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 via a network 4.

[0022] The control unit 10 is composed of a processor such as a CPU, and is electrically connected to a storage unit 11 composed of a memory, and a communication unit 12 functioning as a communication interface. The control unit 10 executes a document processing program 110 described later, thereby functioning as a contract reception means 100, a contract division means 101, an information extraction means 102, a normalization means 103, a display control means 104, and the like.

[0023] The contract receiving means 100 receives a contract from the terminal 2 or the terminal 3 as document information 111 and stores it in the storage unit 11. The document information 111 may be image information such as a PDF in which text is laid out, or may be information such as a text file or Word file that includes text data.

[0024] If the document information 111 is information other than text, the contract division means 101 converts it into text using OCR (Optical Character Recognition) or the like, then divides the document information 111 into contract components such as title, preface, and article units, and stores them as unit information 112 in the storage unit 11. Note that the unit of division for article units is not limited to articles, and may be clauses and items, or a set of multiple articles, clauses, and items that have a unity of meaning. Also, clauses and items that have a unity of meaning across different articles and clauses may be used.

[0025] The information extraction means 102 extracts information representing the contract contents from the unit information 112 and stores it in the storage unit 11 as extracted information 113 .

[0026] The normalization means 103 normalizes the contents of the extracted information 113 extracted by the information extraction means 102 by standardizing keywords, standardizing the description format, supplementing with reference to other information, inference based on other information, name matching, etc., and stores the normalized extracted information 114 in the storage unit 11. For supplementing with reference to other information, the contract end date is calculated from the contract start date and expiration date. For inference based on other information, for example, a corporate number is estimated based on the company name, date, address, etc. The name matching process is performed by comparing keywords in a dictionary (keyword list) using Levenshtein distance and keyword similarity, and setting the closest ones as normalized strings.

[0027] The display control means 104 controls the display of the document information 111, the unit information 112, the extraction information 113 and the normalized extraction information 114 in the storage unit 11, and the output results of the means 100-103 on the display units of the terminals 2 and 3 in a predetermined manner. The display method will be described in detail later.

[0028] The storage unit 11 is composed of a memory such as a flash memory, and is electrically connected to the control unit 10 composed of a processor, etc., and the communication unit 12 functioning 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 100-104, document information 111, unit information 112, extraction information 113, normalized extraction information 114, etc.

[0029] FIG. 3 is a schematic diagram showing an example of the configuration of the document information 111. As shown in FIG.

[0030] The document information 111a is, for example, a contract, and has, as unit information 112 divided by the contract dividing means 101, a contract title 112a1, a preface 112a2, and a plurality of subsequent articles (article units) 112a3, 112a4, 112a5, etc. Furthermore, the article (article unit) 112a4 includes a plurality of clauses (article units) 112a41, 112a42.

[0031] FIG. 4 is a schematic diagram showing an example of the configuration of the extraction information 113. As shown in FIG.

[0032] The extracted information 113 is information extracted by the information extraction means 102, and has an extraction ID for identifying the extracted information, the extracted information extracted from the unit information 112, an extraction item which is the item to which the extracted information belongs, and a reference location which is location information within the unit information 112.

[0033] FIG. 5 is a schematic diagram showing an example of the configuration of the normalized extraction information 114. As shown in FIG.

[0034] The normalized extraction information 114 is information obtained by normalizing the extraction information 113 using the normalization means 103, and includes an extraction ID, extraction information, and normalized extraction information obtained by normalizing the extraction information.

[0035] (Operation of document processing system) Next, the operation of the first embodiment will be explained by dividing it into (1) basic operation, (2) information extraction operation, and (3) extracted information display operation. In the following, the operation will be explained with terminal 2 as the operation target, but if the operation is similar even when terminal 3 is used instead, the explanation will be omitted.

[0036] (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 an authentication request together with the information to the document processing server device 1.

[0037] When the document processing server device 1 receives an authentication request from the terminal 2 together with information such as a user ID and password, it refers to user information (not shown) including a pre-registered user ID and password, and authenticates the requester as a user.

[0038] Next, when the user has completed logging in to the service, the user operates the terminal 2 to upload the document information of the contract to the document processing server device 1. The terminal 2 uploads the document information to the document processing server device 1.

[0039] (2) Information extraction operation Fig. 10 is a flowchart showing the information extraction operation of the document processing server device 1. Fig. 6 is a schematic diagram for explaining an example of the information extraction operation process.

[0040] The contract receiving means 100 of the document processing server device 1 receives document information 111 from the terminal 2 operated by the client, and stores it in the storage unit 11 (S1).

[0041] Next, the contract division means 101 of the document processing server device 1 divides the document information 111a into each component of the contract as shown in FIG. 3, and structures the unit information 112a (S2). As an example, the document information 111a is image information such as a PDF (Portable Document Format) file obtained by scanning the original contract, and the contract division means 101 first converts the document information 111a into text using a method such as an OCR (Optical Character Reader). The contract division means 101 divides the text information into title 112a1, preface 112a2, clause units 112a3 to 112a7..., clause units 112a41, 112a42..., etc. The contract division means 101 may further divide the target document information 111a into issue units, and uses units suitable for the structure of the document information 111a to generate unit information 112a. The above division is performed using techniques such as machine learning and regular expressions. Furthermore, the division is not necessarily an essential operation item, and the subsequent operation may be performed without division.

[0042] Next, the information extraction means 102 extracts information expressing the contract contents from the unit information 112a, which is a structured document, together with the location information of the reference destination of the unit information 112a as extracted information 113a1-113a5... (extracted information 113a), and stores the extracted information in the storage unit 11 (S3). Note that the extraction of the above information is performed using a technique such as named entity recognition using a conditional random field.

[0043] Next, the normalization means 103 normalizes the contents of the extracted information 113a extracted by the information extraction means 102 by standardizing keywords, supplementing by referring to other information, and performing the processing shown in Fig. 7 below, and stores the normalized extracted information 114a1 to 114a5... (normalized extracted information 114a) in the storage unit 11 (S4). The normalized extracted information 114a is managed by items such as title, party 1, party 2, date of conclusion, start date, end date, full text, etc. The normalization of the above information is performed by comparing keywords in a dictionary (keyword list) using techniques such as Levenshtein distance and keyword similarity.

[0044] FIG. 7 is a schematic diagram for explaining an example of the operation of the normalization means 103. As shown in FIG.

[0045] When the normalization means 103 receives a date written in the Japanese calendar, such as "July 1, 2017," in an extraction item related to a date as the extracted information 113, it normalizes the date to a date written in the Gregorian calendar, such as "July 1, 2017," as the normalized extracted information 114. Note that even if the extracted information 113 is written in the Gregorian calendar, normalization is performed in the same way when the order of writing is different, such as "2017 / 7 / 1," "7 / 1 / 2017," or "July 1, 2017."

[0046] In addition, when the normalization means 103 receives an entry including a period such as "one year from July 1, 2017" in an extraction item related to a date as the extracted information 113, it normalizes it to a date corresponding to the end date such as "June 30, 2018" as the normalized extracted information 114.

[0047] In addition, when the normalization means 103 receives a specific description such as "...This contract shall be renewed under the same conditions, and the same shall apply thereafter," in an extracted item regarding renewal as the extracted information 113, it normalizes it to a concise description such as "Automatic renewal available" as the normalized extracted information 114.

[0048] In addition, when the normalization means 103 receives the party status and party name such as "LegalForce Co., Ltd." in the extraction item related to the parties as the extracted information 113, it normalizes it to the parties as "LegalForce Co., Ltd." as the normalized extracted information 114.

[0049] In addition, when the normalization means 103 receives as extraction information 113 the position of the party in an extraction item related to the parties, such as "The person listed at the end of this contract (omitted) LegalForce Co., Ltd." and the name of the party listed in that position, it normalizes the name of the party to "LegalForce Co., Ltd." as normalized extraction information 114.

[0050] In addition, when the normalization means 103 receives a pair of parties such as "LegalForce Co., Ltd. (hereinafter referred to as "Party A") and Attorney Nozomi Tsunoda (hereinafter referred to as "Party B") enter into a consulting agreement (hereinafter referred to as "this agreement") as follows" in an extracted item related to the parties as extracted information 113, it normalizes the pair of parties to "LegalForce Co., Ltd. / Nozomi Tsunoda" as normalized extracted information 114.

[0051] In addition, when the normalization means 103 receives, as the extracted information 113, an extraction item related to a period, an expiration date and period such as "The expiration date of this agreement shall be one year from the date of conclusion of this agreement....Date of conclusion: January 1, 2020", it normalizes it to the start date of conclusion, such as "January 1, 2020", as normalized extracted information 114.

[0052] In addition, the information extraction means 102 and the normalization means 103 perform extraction and normalization automatically as described above, but as shown in Figure 9 below, extraction and normalization of proper nouns, dates, periods, etc. may also be performed in response to user operations.

[0053] FIG. 9 is a schematic diagram showing an example of a screen displayed when extraction information is registered in response to an operation.

[0054] The screen 103b has an input field 103b1 for the user to input a character string that he / she wishes to search, a check field 103b2 for registering all search results, check fields 103b24, 103b25, 103b26... for registering each search result, a registration button 103b3 for registering the search results checked in the check field, and search results 103b4, 103b5, 103b6... Since each search result 103b4, 103b5, 103b6... has the same configuration, the configuration of the search result 103b4 will be explained as a representative. The search result 103b4 has a button 103b41 for registering the search result as the title of the contract, a button 103b42 for registering the search result as the name of the parties, a button 103b43 for registering the search result as the start date, a button 103b44 for registering the search result as the end date, and a display field 103b45 for displaying the character string of the search result.

[0055] The user inputs the character string they wish to search for into input field 103b1 on screen 103b, checks the contents of search results 103b4, 103b5, 103b6..., checks check fields 103b2, 103b24, 103b25, 103b26... for the test results they wish to register, selects buttons 103b41 to 103b44 as appropriate, and presses registration button 103b3 to perform the registration operation.

[0056] The information extraction means 102 and the normalization means 103 register the checked character string in the extraction information 113 and the normalized extraction information 114 .

[0057] (3) Extracted information display operation Next, the user operates the terminal 2 to select a contract in order to request a reference to the contents of a desired contract from the document processing server device 1. The terminal 2 requests the document processing server device 1 to select a contract and to refer to the contents of the selected contract.

[0058] When the display control means 104 of the document processing server device 1 receives a request to select a contract and to refer to the contents of the contract, it processes and displays the normalized extraction information 114a together with the document information 111a and the unit information 112a.

[0059] FIG. 8 is a schematic diagram showing a display example of the display control means 104. As shown in FIG.

[0060] Screen 104a is a screen displayed by display control means 104, and has a document information display field 104a1 that displays document information 111a, which is the original contract, a structured document display field 104a2 that displays unit information 112a, which is a structured document, and a normalized extraction information display field 104a3 that displays normalized extraction information 114a, which is normalized extraction information, for each item.

[0061] Next, the user operates the terminal 2 to select a desired item from the normalized extraction information display field 104a3. The terminal 2 requests the document processing server device 1 to select an item of the normalized extraction information 114a.

[0062] FIG. 11 is a flowchart for explaining the display processing operation.

[0063] When display control means 104 receives an item selection of normalized extraction information 114a (S10), it selects normalized extraction information 104a32, which is the selected item, acquires position information by referring to the reference position of extraction information 113a (S11), and indicates and displays character string 104b2 at the corresponding position in unit information 104a22 in structured document display column 104a2, which is a structured document (S12).

[0064] The user checks the character string 104b2 at the corresponding position, and checks the position of the corresponding position in the unit information 112a, the position of the corresponding position in the document information 111a, and the like.

[0065] (Effects of the embodiment) According to the embodiment described above, document information 111 is converted into text and structured, character strings indicating the contents of the document are extracted from structured unit information 112 to produce extracted information 113, and then each character string in extracted information 113 is normalized to produce normalized extracted information 114. The contents of normalized extracted information 114 are displayed together with the corresponding positions in unit information 112. Therefore, even if there is a variation in the notation of the extracted character strings, the corresponding parts can be managed in a centralized manner.

[0066] In addition, the display of document information 111, unit information 112, and normalized extraction information 114 is controlled in association with each other, so that the position information of the extracted character string in unit information 112 can be confirmed, and it can be confirmed that the character string is certainly written in document information 111, which is the original.

[0067] [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.

[0068] For example, the document information 111 is not limited to a contract, but may be a legal document itself or a document in a field other than law, such as an instruction manual, as long as information can be extracted from it, and the present invention can be applied to the same. Furthermore, the components are not limited to clauses, paragraphs, and items, but may be words, characters, and symbols, or may be paragraphs and sentences. Furthermore, the language of the document information 111 is not limited to Japanese or English, and the present invention can be applied to other languages ​​as long as they can form sentences from which information can be extracted.

[0069] In the above embodiment, the functions of the means 100-104 of the control unit 10 are realized by a program, but all or part of the means may be realized by hardware such as ASIC. Also, the program used in the above embodiment may be stored in a recording medium such as a CD-ROM and provided. Also, the steps described in the above embodiment may be replaced, deleted, added, etc., without changing the gist of the present invention. [Industrial Applicability]

[0070] To provide a document processing program, an information processing device, and a document processing method that extract a character string indicating the contents of a document from document information and manages relevant parts in a unified manner even if the extracted character string has notational variations. [Explanation of symbols]

[0071] 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: Contract division method 102: Information extraction means 103: Normalization means 104: Display control means 110: Word processing program 111: Document information 112: Unit information 113: Extraction information 114: Normalized extraction information

Claims

1. The computer obtaining a character string corresponding to an extraction item from the obtained document information; acquiring normalized extracted information by performing normalization on at least one of the character strings, including at least one of standardizing keywords, standardizing description formats, supplementing with reference to other information, inference based on other information, and name matching processing; enabling a user to specify the extracted items on a terminal; displaying on the terminal a character string corresponding to the extracted item in the document information, which is specified by an operation of the user; A document processing method comprising:

2. The document processing method described in claim 1, further comprising the computer displaying the document information, including information on the position of a character string corresponding to the normalized extraction information specified by the user, and the normalized extraction information on the same screen of the terminal.

3. The document processing method described in claim 1, further comprising the computer displaying the normalized extraction information on the terminal together with the name of the item to which the normalized extraction information belongs.

4. A document processing method as described in any one of claims 1 to 3, further comprising the computer registering a specified character string in the document information as extracted information.

5. A document processing method described in any one of claims 1 to 4, further comprising the computer communicating with the terminal via a network.

6. A document processing method described in any one of claims 1 to 5, further comprising the computer obtaining unit information by dividing the document information based on articles, paragraphs, or items.

7. A document processing method described in any one of claims 1 to 6, wherein the document information is a contract.

8. A processor comprising: From the acquired document information, obtain the character string corresponding to the extracted item, acquiring normalized extracted information by performing normalization on at least one of the character strings, including at least one of standardizing keywords, standardizing description formats, supplementing with reference to other information, inference based on other information, and name matching processing; enabling an operation of specifying the extracted items on a user's terminal; displaying on the terminal a character string corresponding to the extracted item in the document information, which is specified by the user's operation; The information processing device is configured as follows.

9. A memory configured to store document information in addition to predetermined instructions; Based on the instructions stored in the memory, Acquire a character string corresponding to the extracted item from the document information; acquiring normalized extracted information by performing normalization on at least one of the character strings, including at least one of standardizing keywords, standardizing description formats, supplementing with reference to other information, inference based on other information, and name matching processing; enabling an operation of specifying the extracted items on a user's terminal; displaying on the terminal a character string corresponding to the extracted item in the document information, which is specified by the user's operation; a processor configured to perform processing for: An information processing device comprising:

Images