Document processing method, document processing program, and document processing system

Abstract

To provide a document processing method that can easily identify documents in a derivation relationship.SOLUTION: A processor 1001 acquires information on the details of a target document, and compares the information on the details of the target document with information on the details of each template document, to determine whether a derivation source template document, which is estimated to be a derivation source document of the target document, is present in the template documents.SELECTED DRAWING: Figure 11

Description

[Technical field]

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

[0002] A conventional document processing device is described in the following Patent Document 1. When editing, such as addition or deletion, is performed on certain document data, this document processing device displays the document data so that the edited portion can be visually identified. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 5-20320 Summary of the Invention [Problem to be solved by the invention]

[0004] Documents such as contracts are sometimes created based on a predetermined template document. When a document such as a contract is repeatedly edited, the original template document may become unclear. With the document processing device described in Patent Document 1, it may be difficult to identify the original template document. Note that this problem is not limited to the case where a template document from which a document is derived is specified, but may also occur when a document derived from a predetermined template document is specified.

[0005] An embodiment of the present disclosure provides a document processing method capable of easily identifying documents in a derived relationship. [Means for solving the problem]

[0006] In one embodiment of the document processing method, a processor acquires content information of a target document and compares the content information of the target document with the content information of each of the template documents to determine whether the template document contains a template document that is presumed to be the document from which the target document is derived.

[0007] According to this configuration, it is possible to easily identify documents that have a derivative relationship. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of a method for creating a contract. [Diagram 2] 1 is a block diagram showing a schematic configuration of a document processing system according to an embodiment. [Diagram 3] FIG. 2 is a block diagram showing a schematic configuration of a document management server device according to the embodiment. [Figure 4] FIG. 2 is a diagram illustrating an example of contract management information according to an embodiment. [Diagram 5] FIG. 2 is a block diagram showing a schematic configuration of an identification model according to an embodiment. [Figure 6] FIG. 2 is a diagram illustrating an example of contract management information according to an embodiment. [Figure 7] FIG. 4 is a diagram illustrating an example of a screen displayed on the terminal device according to the embodiment. [Figure 8] FIG. 4 is a diagram illustrating an example of a screen displayed on the terminal device according to the embodiment. [Figure 9] FIG. 4 is a diagram illustrating an example of a screen displayed on the terminal device according to the embodiment. [Figure 10] 4 is a sequence chart showing an example of the operation of the document processing system according to the embodiment. [Figure 11] FIG. 2 is a block diagram showing a hardware configuration of a computer according to an embodiment. [Figure 12] FIG. 11 is a diagram showing an example of a screen displayed on a terminal device according to a first modified example of the embodiment. [Figure 13] FIG. 11 is a diagram showing an example of a screen displayed on a terminal device according to a second modified example of the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an embodiment of a document processing method, a document processing program, and a document processing system will be described with reference to the drawings. In order to facilitate understanding of the description, the same components in each drawing are denoted by the same reference numerals as much as possible, and duplicated descriptions will be omitted. <Embodiment> First, an overview of the document processing system of this embodiment will be described.

[0010] (Overview of document processing system) In this embodiment, a contract will be used as an example of the document. Documents such as contracts may be created from documents used as templates or prescribed formats (sometimes referred to as model documents in this specification). As the model documents, as shown in Fig. 1, the company's own model documents D11 to D14 or the other party's model documents D21 to D24 with which documents are exchanged may be used.

[0011] In this specification, the company's template documents D11 to D14 are template documents used in the company, for example, created in the company and used as standard documents. The other party's template documents D21 to D24 are template documents of the other party to the contract.

[0012] As in this embodiment, multiple types of template documents may be provided for one party. For example, multiple types may be set according to the type of contract (confidentiality agreement, service contract, basic transaction agreement, etc.) and the position of the contract (for example, whether the party disclosing or receiving confidential information, whether the party entrusting or delegating in a service contract, etc.).

[0013] On the other hand, when reviewing the contents of the created specified contract D30, the burden of the review work varies greatly depending on whether the contract is derived from one of the company's templates D11 to D14. Specifically, if the specified contract is derived from one of the company's templates D11 to D14, the company's legal department already has past knowledge and similar cases related to the review, so the company can review the specified contract using those knowledge and similar cases. In addition, the company's template documents are often basically advantageous to the company, and clauses that have not been amended can be omitted from substantial review. Therefore, if the specified contract is derived from one of the company's templates D11 to D14, the workload of reviewing the contract is likely to be light. On the other hand, if the specified contract is a contract of the other party (in this embodiment, a contract derived from one of the templates D21 to D24), there is a risk that there is little knowledge about the contents or that it contains relatively many clauses that are disadvantageous to the company, so the burden of reviewing the contract tends to be heavy.

[0014] Thus, in contract review work, there is a demand to specify whether or not the contract is derived from one of the company's template documents D11 to D14. To meet such demand, the document processing system of this embodiment judges whether or not a template document from which the target contract is derived exists among the company's multiple template documents D11 to D14, and if such a template document exists, presents that contract.

[0015] (Document Processing System Configuration) Next, the configuration of the document processing system of this embodiment will be described. The document processing system 10 of the present embodiment shown in FIG. 2 is a system that manages documents created by a user. The user is, for example, a company that requests document information to be managed in the document processing system 10, or a person in charge of the company. A document is information that is recorded on the assumption that it will be referenced. Examples of documents include official documents, contracts, minutes, rules, notices, regulations, and rules. The language of the document does not matter, and includes those written in Japanese, English, Chinese, and the like. The format of the information of each document is not particularly limited, and may be, for example, a data file created by a specific word processing software, or text data extracted from the data file.

[0016] 2, the document processing system 10 of this embodiment includes a document management server device 20 and a terminal device 30. The document management server device 20 and the terminal device 30 are connected via a network line N so as to be able to communicate with each other.

[0017] The document management server device 20 is a server-type information processing device, and operates in response to requests from the terminal device 30. The document management server device 20 does not necessarily have to be configured as a single information processing device, and may be configured as a plurality of information processing devices operating in cooperation with each other, or may be configured to operate using any cloud service. The functions of the document management server device 20 may also be realized within the terminal device 30.

[0018] The terminal device 30 is an information processing device such as a PC (Personal Computer) or a tablet terminal. The network line N is a communication network capable of high-speed communication, such as the Internet, an intranet, or a wired or wireless communication network such as a LAN (Local Area Network).

[0019] In the document processing system 10, account information is assigned to each user. The account information includes an identification number and a password. This account information is transmitted from the terminal device 30 to the document management server device 20 when logging in to the system of the document management server device 20, and is used for authenticating the user in the document management server device 20. If this authentication is successful, the user can use various services provided by the document management server device 20. For example, the user can upload and store content information of a contract created by the user in the document management server device 20. In addition, the document management server device 20 may store content information of a contract transmitted from an arbitrary electronic conclusion service. The content information of the contract stored in the document management server device 20 is, for example, content information of a contract after it has been concluded. Furthermore, the user can view contracts created by the user in the past and search for a desired contract from among multiple contracts by operating the terminal device 30 and accessing the database of the document management server device 20.

[0020] (Configuration of the document management server device) Next, the configuration of the document management server device of this embodiment will be described. 3, the document management server device 20 of the present embodiment includes a storage unit 21, a communication unit 22, and a control unit 23. The storage unit 21, the communication unit 22, and the control unit 23 are electrically connected to each other.

[0021] The storage unit 21 stores various programs and various data for operating the document management server device 20. For example, the storage unit 21 stores a document database 210, a template database 211, and a classification model 212.

[0022] The document database 210 stores, for example, contract management information. As shown in FIG. 4, the contract management information includes, for example, a document ID, a sequence ID, order information, status information, and document content information. The document ID is, for example, information for identifying target document information to be processed in the document processing system 10. The sequence ID is, for example, information for identifying a sequence. The sequence is, for example, information indicating a series of revision processes. A plurality of target document information belonging to the same sequence indicates that they belong to the same series of revision processes. The order information is, for example, information indicating the order of revisions numerically. The content information is, for example, information indicating the content of the contract (for example, text, figures, tables). The content information of the contract is, for example, created or uploaded by a user or another user belonging to the same organization who can share, for example, document data.

[0023] In the template database 211, for example, for each user, content information of multiple template documents registered by the user is linked and stored. Multiple template documents linked to a user correspond to the company's template documents. The content information of the company's template documents is, for example, created or uploaded by the user. Note that the company's template document may be any document that is treated as a template. For example, the document may be registered by another user belonging to the same organization, or may be registered by a user of a different organization from the user (for example, a legal advisor) or a system vendor, etc.

[0024] The identification model 212 of this embodiment is a machine learning model that identifies whether or not the contract to be investigated is derived from a specified company template and outputs the identification result, and specifically, outputs the identification result when the content information of the contract to be investigated and the content information of the specified company template are input. For example, as shown in Fig. 5, the identification model 212 has a feature generating unit 212a and a classifying unit 212b.

[0025] The feature quantity generating unit 212a of this embodiment compares the content information of the contract to be investigated with the content information of a predetermined company template document, and generates a feature quantity V a,x For example, the feature generating unit 212a vectorizes the content information of the contract to be investigated and the content information of the specified company template document by BoW (Bag of Words). Then, the feature generating unit 212a calculates the deletion token Td, the addition token Ta, and the common token Tc by comparing the vector Wx of the contract to be investigated with the vector Wa of the specified company template document. The deletion token Td is a word that is deleted in the contract to be investigated when the specified company template document is used as a reference, and can be expressed as "Wa\Wx". The addition token Ta is a word that is added to the contract to be investigated when the specified company template document is used as a reference, and can be expressed as "Wx\Wa". The common token Tc is a word that is common between the specified company template document and the contract to be investigated, and can be expressed as "Wa∩Wx". The feature generator 212a performs one-hot encoding on the calculated deletion token Td, addition token Ta, and common token Tc to calculate their one-hot vectors. The feature generator 212a then combines the one-hot vectors of the deletion token Td, addition token Ta, and common token Tc to generate a feature V a,x Generate the feature vector V a,x is a high-dimensional sparse vector.

[0026] The classification unit 212b of this embodiment uses the feature quantity V generated by the feature quantity generating unit 212a. a,xBased on this, the classification unit 212b determines whether the contract under investigation is classified into the first class or the second class, and outputs the determination result. The first class is a class to which the contract under investigation belongs when it is presumed to have been derived from a specified company template document. The second class is a class to which the specified contract belongs when it is presumed not to have been derived from a specified company template document. Therefore, if the classification unit 212b determines that the contract under investigation belongs to the first class, it can be determined that the contract under investigation is derived from a specified company template document. On the other hand, if the classification unit 212b determines that the contract under investigation belongs to the second class, it can be determined that the contract under investigation is not derived from a specified company template document.

[0027] In addition, when content information of a single contract to be investigated and content information of multiple company template documents are input, the identification model 212 of this embodiment outputs an identification result corresponding to each of the multiple company template documents.

[0028] A trained model is used as the discriminative model 212. The training of the discriminative model 212 is performed, for example, by training the discriminative model 212 based on a predetermined corpus. The corpus is a database obtained by structuring documents for training the discriminative model 212. The corpus includes positive example data and negative example data. The positive example data includes, for example, sample data of a template document, sample data of a contract created from the template document, and label information indicating that the data is a positive example. As the sample data of the contract, content information of one of a plurality of contracts of different versions created from the template document may be used. The negative example data includes, for example, sample data of a template document, sample data of a contract not created from the template document, and label information indicating that the data is a negative example.

[0029] The corpus for training the discriminative model 212 can be generated, for example, from a data set of content information of template documents and contracts uploaded to the document database 210 by users belonging to multiple organizations.

[0030] 3 performs various communications with, for example, the terminal device 30. The communication unit 22 acquires, for example, operation information performed by a user on the terminal device 30. The communication unit 22 also transmits, to the terminal device 30, various types of image information to be displayed on the terminal device 30.

[0031] The control unit 23 controls, for example, the document management server device 20. The control unit 23 includes, as functional components realized by executing a program stored in the storage unit 21, a document acquisition unit 230, a determination unit 231, a linking unit 232, and a display control unit 233.

[0032] The document acquisition unit 230 acquires, for example, content information of a contract to be investigated for the presence or absence of a template. For example, when an operation is performed by a user on the terminal device 30 to designate one of a plurality of contracts accessible to the user stored in the document database 210 as a contract to be investigated, the document acquisition unit 230 acquires content information of the contract to be investigated designated by the user from the document database 210. Note that, instead of the user designating a contract or performing an operation to instruct an investigation, the system may automatically perform the operation and suggest the contract to the user. For example, when a user displays a certain contract, the document may be acquired and the subsequent determination may be performed.

[0033] The determination unit 231 determines, for example, whether or not there is a company template document presumed to be the origin of the contract to be investigated acquired by the document acquisition unit 230 among a plurality of company template documents stored in the template database 211. Specifically, the determination unit 231 inputs the content information of the contract to be investigated acquired by the document acquisition unit 230 and the content information of each of the plurality of company template documents stored in the template database 211 to the identification model 212. Then, based on the discrimination result of the identification model 212, the determination unit 231 determines whether or not there is a company template document presumed to be the origin of the contract to be investigated.

[0034] The linking unit 232 executes a process of linking the company template determined by the determining unit 231 to be the derivation source with the contract to be investigated, for example, based on the user's operation on the terminal device 30. For example, when an operation of linking a specific company template with a contract registered in the document database 210 in the form shown in FIG. 4 is performed, the linking unit 232 links the information of the company template with the contract management information in the form shown in FIG. 6. For example, as shown in FIG. 6, a document ID or document content information corresponding to the company template is added to the contract management information of the contract to be investigated. Also, for example, the sequence ID of the company template may be assigned the same sequence ID as the contract. Also, in this case, "0" may be assigned to the sequence information of the company template. In other words, the company template may be linked as the first version of the contract to be investigated.

[0035] In addition, when the determining unit 231 determines that an original in-house template document exists, the linking unit 232 may perform a process of automatically linking the original in-house template document with the contract document being investigated.

[0036] The display control unit 233 generates display information for displaying, for example, a screen for designating a contract to be investigated and a screen showing the determination result of the determination unit 231 on the terminal device 30. Next, examples of screens displayed on the terminal device 30 by the display control unit 233 will be described.

[0037] Fig. 7 shows an example of an operation screen 40 displayed on the terminal device 30. As shown in Fig. 7, the operation screen 40 is provided with, for example, a search file display area 41, a display button 42, and a search button 43.

[0038] For example, the file name of the contract to be investigated is displayed in the investigation file display area 41. By operating the investigation file display area 41, the user can specify one of the multiple contracts stored in the document database 210 as the investigation target.

[0039] The display button 42 is a button that is operated when viewing the contents of the contract that is the subject of investigation specified in the investigation file display area 41, for example.

[0040] The investigation button 43 is a button for investigating whether or not there is a company template document that is presumed to be the origin of the contract to be investigated. When the user operates the investigation button 43, the judgment unit 231 performs a judgment process of the company template document. At this time, the contents displayed on the operation screen 40 differ depending on the judgment result of the judgment unit 231.

[0041] For example, when the determination unit 231 obtains a determination result that there is no in-house template document presumed to be the origin of the contract to be investigated, the display control unit 233 further provides, for example, a determination result display area 44 as shown in Fig. 8 on the operation screen 40. For example, the determination result display area 44 displays, by means of text or the like, that it has been determined that there is no in-house template document.

[0042] On the other hand, when the determination unit 231 obtains a determination result that there is a company template document that is presumed to be the origin of the contract to be investigated, the display control unit 233 further provides, for example, candidate display areas 45a and 45b as shown in Fig. 9 on the operation screen 40. In the candidate display areas 45a and 45b, for example, all company template documents that are presumed to be the origin of the contract to be investigated are displayed. Fig. 9 illustrates an example in which two company template documents that are presumed to be the origin of the contract to be investigated are found.

[0043] As shown in FIG. 9, the candidate display areas 45a and 45b are provided with, for example, candidate file display areas 450a and 450b, display buttons 451a and 451b, and link buttons 452a and 452b for each of the candidate in-house template documents from which the files are derived.

[0044] In the candidate file display areas 450a and 450b, for example, the file names of the company's template documents that are candidates for the derivation source are displayed.

[0045] The display buttons 451a and 451b are buttons that are operated when viewing the contents of candidate in-house template documents from which the contract is derived, for example. By providing these buttons, the user can operate the display buttons 451a and 451b to display the contents of the candidate in-house template documents, and determine which in-house template document is appropriate to register as the source of the contract.

[0046] The linking buttons 452a and 452b are buttons that are operated, for example, when linking the company's template document of the derivation source candidate to the contract to be investigated. For example, when the user operates the linking button 452a of "candidate 1", the linking unit 232 links the "template document A" of "candidate 1" to the contract to be investigated.

[0047] (Example of document processing system operation) Next, an example of the operation of the document processing system 10 of this embodiment will be described. As shown in FIG. 10, in the document processing system 10 of this embodiment, first, the user operates the terminal device 30 to select the contract to be investigated (step S10), and information about the contract to be investigated selected by the user is transmitted from the terminal device 30 to the document management server device 20 (step S11).

[0048] In the document management server device 20 of this embodiment, when the information of the contract to be investigated selected by the user is received by the communication unit 22 (step S20), the document acquisition unit 230 acquires the content information of the contract to be investigated from the document database 210 (step S21). Next, the determination unit 231 acquires the content information of each of the multiple company template documents from the template database 211 (step S22). Then, the determination unit 231 inputs the content information of the contract to be investigated and the content information of each of the multiple company template documents into the identification model 212 to determine whether or not there is a company template document that is presumed to be the origin of the contract to be investigated (step S23), and transmits display information indicating the determination result or the reflection result to the terminal device 30 (step S24).

[0049] When the terminal device 30 of this embodiment receives display information indicating the determination result or the reflection result transmitted from the document management server device 20 (step S12), it displays the determination result (step S13). Then, when an operation is performed on the terminal device 30 to link the candidate company template document from which the derivation origin is made to the contract to be investigated (step S14), the terminal device 30 transmits an instruction for the linking operation to the document management server device 20 (step S15).

[0050] In the document management server device 20 of this embodiment, when the communication unit 22 receives an instruction for a linking operation (step S25), the linking unit 232 executes a process of linking the contract to be investigated with the company's template document that is a candidate for the derivation source (step S26). This allows the user to easily associate the company's template document with the contract to be investigated, and makes it possible to easily review the contract to be investigated by referring to, for example.

[0051] (Hardware configuration of document processing system) Next, an example of a hardware configuration in which the document management server device 20 and the terminal device 30 are realized by a computer 1000 will be described with reference to Fig. 11. Fig. 11 is a diagram showing an example of the hardware configuration of the computer 1000.

[0052] 11, the computer 1000 includes, for example, a processor 1001, a memory 1002, a storage device 1003, an input I / F unit 1004, a data I / F unit 1005, a communication I / F unit 1006, and a display device 1007. Note that the computer 100 may include a plurality of each of the processor 1001, the memory 1002, the storage device 1003, the input I / F unit 1004, the data I / F unit 1005, the communication I / F unit 1006, and the display device 1007.

[0053] The computer 1000 may be, for example, a server computer, a personal computer (e.g., desktop, laptop, tablet, etc.), a media computing platform (e.g., cable, satellite set-top box, digital video recorder, etc.), a handheld computing device (e.g., PDA, email client, etc.), or some other type of computing or communications platform.

[0054] The processor 1001 is a control unit that controls various processes in the computer 1000 by executing programs stored in the memory 1002, for example.

[0055] The memory 1002 is a storage medium such as a RAM (Random Access Memory), etc. The memory 1002 temporarily stores the program code of the program executed by the processor 1001 and data required when the program is executed.

[0056] The storage device 1003 is a non-volatile storage medium such as a hard disk drive (HDD), a flash memory, etc. The storage device 1003 stores an operating system and various programs for implementing the above-mentioned components.

[0057] The input I / F unit 1004 is a device for receiving input from a user. The input I / F unit 1004 is, for example, a keyboard, a mouse, a touch panel, various sensors, a wearable device, etc. The input I / F unit 1004 may be connected to the computer 1000 via an interface such as a USB (Universal Serial Bus).

[0058] The data I / F unit 1005 is a device for inputting data from outside the computer 1000. The data I / F unit 1005 is, for example, a drive device for reading data stored in various storage media. The data I / F unit 1005 may be provided outside the computer 1000. When the data I / F unit 1005 is provided outside the computer 1000, the data I / F unit 1005 is connected to the computer 1000 via an interface such as a USB.

[0059] The communication I / F unit 1006 is a device for performing data communication via a network such as the Internet, either wired or wirelessly, with an external device of the computer 1000. The communication I / F unit 1006 may be provided outside the computer 1000. When the communication I / F unit 1006 is provided outside the computer 1000, the communication I / F unit 1006 is connected to the computer 1000 via an interface such as a USB.

[0060] The display device 1007 is a device for displaying various types of information. The display device 1007 is, for example, a liquid crystal display, an organic EL (Electro-Luminescence) display, a display of a wearable device, or the like. The display device 1007 may be provided outside the computer 1000. When the display device 1007 is provided outside the computer 1000, the display device 1007 is connected to the computer 1000 via, for example, a display cable. Furthermore, when a touch panel is adopted as the input I / F unit 1004, the display device 1007 may be configured integrally with the input I / F unit 1004.

[0061] (Actions and Effects of the Document Processing System of the Present Embodiment) As described above, the document processing system 10 of this embodiment includes the document acquisition unit 230, the determination unit 231, and the display control unit 233. The document acquisition unit 230 acquires content information of the contract (target document) to be investigated. The determination unit 231 compares the content information of the contract to be investigated with the content information of each of the multiple company template documents registered in the template database 211 to determine whether or not there is an original company template document that is presumed to be the original of the target document among the multiple company template documents. When the display control unit 233 determines that there is an original company template document among the multiple company template documents, it displays the company template document determined to be the original, for example, as shown in FIG. 9. According to this configuration, the company's own template document that is determined to be the derivative of the contract being investigated is displayed, making it possible to easily identify documents that are in a derivative relationship.

[0062] When the display control unit 233 determines that the original company template document does not exist among the multiple company template documents, it displays the determination result on the operation screen 40 of the terminal device 30. According to this configuration, if the original company template document does not exist, the user can recognize the fact.

[0063] The determination unit 231 determines whether or not a template document from which a derivation originates exists among a plurality of company template documents by using the identification model 212 (machine learning model). According to this configuration, it is possible to more appropriately determine whether or not a derived template document exists among a plurality of company template documents.

[0064] When comparing the contents of the contract to be investigated with the contents of a prescribed company template document registered in the template database 211, the identification model 212 calculates the difference between the contents of the contract to be investigated and the contents of the prescribed company template document as a feature quantity V a,x The extracted feature vector V a,x Based on the feature quantity V, the system classifies whether a specific in-house template document is a derived template document or not. a,x is generated based on the deletion token Td, the addition token Ta, and the common token Tc. According to this configuration, it is possible to more appropriately construct the identification model 212 capable of determining whether or not a derived template document exists among a plurality of company template documents.

[0065] The document processing system 10 further includes a linking unit 232. When an operation for linking the original company template document and the contract to be investigated is performed, the linking unit 232 executes a linking process between them. This configuration makes it easier to manage the correspondence between the original in-house template document and the contract being investigated.

[0066] (First Modification) Next, a first modification of the document processing system 10 of the embodiment will be described. In the document processing system 10 of this modification, when the display button 451a corresponding to the candidate template document shown in Fig. 9 is operated by the user, the display control unit 233 displays a screen on the terminal device 30 that allows the contents of the contract to be investigated to be compared with the contents of the company's candidate template document from which it is derived. Fig. 12 shows an example of the comparison screen 50.

[0067] 12, the comparison screen 50 is provided with a candidate display area 51 and a survey target display area 52. The candidate display area 51 displays the file name, etc. of the company template document that is a candidate for derivation and its content information. The survey target display area 52 displays the file name, etc. of the contract that is the survey target and its content information.

[0068] The display control unit 233 generates display information that can display highlighting M1, M2 on the display unit of the terminal device 30, which marks the parts that differ in the content information of the company's template document that is a candidate for derivation, which is displayed in the candidate display area 51, and the content information of the contract that is the target of investigation, which is displayed in the investigation target display area 52.

[0069] In this way, the document processing system 10 of this modification can display the content information of the contract to be investigated and the content information of the company's template document of the candidate from which the contract is derived on one screen. The display control unit 233 also displays the parts that differ between the content information of the contract to be investigated and the content information of the company's template document of the candidate from which the contract is derived so that they can be recognized.

[0070] According to this configuration, the user can more easily determine whether or not the company's template document presented as a candidate for the derivation source is a document that was used as a template for the contract being investigated.

[0071] (Second Modification) Next, a second modification of the document processing system 10 of the embodiment will be described. The document processing system 10 may determine whether or not there is a contract derived from a specified template document among multiple contracts registered in the document database 210, and present the determination result to the user.

[0072] Specifically, the document acquisition unit 230 of this modified example acquires content information of a template document to be investigated to see whether a derived contract exists. For example, when an instruction to designate one of a plurality of company template documents stored in the template database 211 as a survey target is given automatically by the system or by a user operation on the terminal device 30, the document acquisition unit 230 acquires content information of the designated survey target template document from the template database 211.

[0073] Furthermore, the determination unit 231 of this modification determines, by the identification model 212, whether or not there is a contract that is presumed to be a derivative of the template document to be investigated acquired by the document acquisition unit 230, among the multiple contracts stored in the document database 210. The identification model 212 of this modification can use a machine learning model that is the same as or similar to the identification model 212 of the above embodiment.

[0074] Furthermore, if the display control unit 233 of this modified example determines that a derivative contract exists among multiple contracts, it displays the contract determined to be the derivative on the operation screen 60 in a form such as that shown in Figure 13.

[0075] According to this configuration, the contracts that are determined to be derived from the template document being investigated are displayed, making it possible to easily identify documents that are in a derived relationship.

[0076] <Other embodiments> The present disclosure is not limited to the above specific examples. Feature value V a,x may be any token that uses at least one of the deletion token Td, the addition token Ta, and the common token Tc.

[0077] Documents that are processed by the document processing system 10 are not limited to contracts, but may also be official documents, minutes, rules, notices, regulations, and bylaws.

[0078] In the above embodiment, the document processing system 10 displays the file name of the in-house template document as shown in FIG. 9 when there is a company template document that is presumed to be the origin of the contract to be investigated. The document processing system 10 may display any information related to the company template document, not limited to the file name of the company template document. For example, the document processing system 10 may display content information of the origin company template document, or display related information related to the company template document, such as notes linked to the origin company template document. The notes include, for example, notes on how to write a contract obtained when reviewing various contracts derived from the company template, amendments to the contract, etc.

[0079] The functional configurations of the document management server device 20 and the terminal device 30 may be provided only in the document management server device 20, only in the terminal device 30, or in both the document management server device 20 and the terminal device 30. For example, the document acquisition unit 230, the determination unit 231, the linking unit 232, and the display control unit 233 of the document management server device 20 may be provided in the terminal device 30. Furthermore, the document processing system 10 may include a plurality of document management server devices 20 and a plurality of terminal devices 30.

[0080] The above specific examples, to which a person skilled in the art may make appropriate design modifications, are also included within the scope of the present disclosure as long as they have the features of the present disclosure. The elements of each of the above specific examples, as well as their arrangements, conditions, shapes, etc., are not limited to those exemplified and can be modified as appropriate. The elements of each of the above specific examples can be combined as appropriate as long as no technical contradictions arise. [Explanation of symbols]

[0081] 10: document processing system, 210: document database, 211: template database, 212: identification model (machine learning model), 230: document acquisition unit, 231: judgment unit, 233: display control unit, 1001: processor.

Claims

1. The processor: Acquire content information of the target document, By comparing the content information of the target document with the content information of each of the template documents, it is determined whether or not the template document includes a template document that is presumed to be a document from which the target document is derived. Document processing methods.

2. The template document is plural. The document processing method according to claim 1 .

3. If the template document from which the original is derived exists in the template document, or if it is determined that the template document from which the original is derived does not exist in the template document, the determination result is displayed.

3. The document processing method according to claim 1.

4. The processor further comprises: A machine learning model is used to determine whether the template document from which the original is derived is present among the plurality of template documents.

3. The document processing method according to claim 1.

5. When comparing content information of the target document with content information of a predetermined template document registered in the database, the machine learning model extracts a difference between the content information of the target document and the content information of the predetermined template document as a feature amount, and determines whether the predetermined template document is the template document from which the target document is derived based on the extracted feature amount.

5. The document processing method according to claim 4.

6. The processor further comprises: The content information of the target document and the content information of the template document from which the target document is derived are displayed on one screen.

3. The document processing method according to claim 1.

7. The processor further comprises: When the content information of the target document and the content information of the derived template document are displayed on one screen, the different parts between the content information of the target document and the content information of the derived template document are displayed in a recognizable manner. The document processing method according to claim 6.

8. The target document and the template document are contract documents.

3. The document processing method according to claim 1.

9. The processor: Obtain content information of the template document, By comparing content information of the template document with content information of each of a plurality of documents registered in a database, it is determined whether or not there is a template document that is presumed to be a derived document of the template document among the plurality of documents; When it is determined that a document derived from the template document exists among the plurality of documents, information related to the document determined to be the derived document is displayed. Document processing methods.

10. The processor: Acquire content information of the target document; By comparing content information of the target document with content information of each of a plurality of template documents registered in a database, it is determined whether or not there is a template document presumed to be a source document of the target document among the plurality of template documents; When it is determined that the derived template document exists among the plurality of template documents, information related to the derived template document is displayed. Word processing program.

11. a document acquisition unit for acquiring content information of a target document; a determination unit that determines whether or not a template document that is presumed to be the source of the target document is present among the plurality of template documents by comparing content information of the target document with content information of each of a plurality of template documents registered in a database; a display control unit that displays information related to the template document determined to be the derivation source when it is determined that the template document from which the derivation originates is present among the plurality of template documents. Document processing system.

Images