Information processing method

Abstract

An information processing method according to an embodiment includes: acquiring a modification policy for each of at least one input unit of a first legal document, acquiring at least one modified input unit after modification using at least one cue generated based on at least the input unit and the modification policy for the input unit and a natural language processing model, and processing the at least one modified input unit by using the at least one cue generated based on the at least one cue generated based on the at least one cue generated based on the at least one input unit and the modification policy for the input unit. At least one modification input unit is output.

Description

Technical Field

[0001] Embodiments of the present invention relate to an information processing method. Background Art

[0002] In the past, for example, there were systems that assisted users in reviewing documents. Users modified the document while referring to the review results output by the system. This placed a heavy workload on users. There is room for further improvement in reducing this workload. Summary of the Invention

[0003] Technical issues to be solved by the invention

[0004] One embodiment of the present invention is made in view of the above situation, and aims to reduce the workload of users in a system that assists users in reviewing documents.

[0005] Technical solutions to solve technical problems

[0006] The information processing method of the implementation method comprises: obtaining modification guidelines for at least one input unit of the first legal document respectively, using at least one prompt and natural language processing model generated based at least on the input unit and the modification guidelines for the input unit, obtaining at least one modified input unit after modification, and outputting the at least one modified input unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 This is a diagram showing an overview of an example of processing in the modification suggestion system 100 according to the embodiment.

[0008] Figure 2 1 is a diagram showing the structure of a modification suggestion system 100 according to an embodiment.

[0009] Figure 3 This is a diagram showing an example of modification policy data.

[0010] Figure 4A This is a block diagram showing an example of the hardware configuration of the information processing device 10 according to the embodiment.

[0011] Figure 4B This is a block diagram showing an example of the hardware configuration of the terminal device T1 according to the embodiment.

[0012] Figure 5 A diagram showing an example of functional blocks in the processor 21 .

[0013] Figure 6 1 is a diagram showing an example of a document review screen 60 displayed as a web browser screen on the display device 30 of the terminal device T1 during the document review process. DETAILED DESCRIPTION

[0014] One embodiment will be described below with reference to the drawings.

[0015] In this specification, the term "unit" refers not only to a physical unit but also includes cases where the functions of the unit are implemented by software. Furthermore, the functions of a single unit or device may be implemented by two or more physical units, devices, or software, and the functions of two or more units or devices may be implemented by a single physical unit, device, or software.

[0016] Figure 1 This is a diagram showing an overview of an example of processing in the modification suggestion system 100 as one embodiment.

[0017] The modification suggestion system 100 of the present embodiment is an information processing system implemented by a modification suggestion program, and is an information processing system for suggesting modifications to the contents of a target item of a contract, which is a support target document.

[0018] For example, when entering into a contract, the parties reach an agreement. Once the parties have reached an agreement, one or both parties may review and amend the contract. For example, in the case of a contract between businesses, the legal department responsible for contract review will review the contract content and make revisions as necessary. Contract review is sometimes also referred to as confirmation, examination, or review.

[0019] Legal documents processed by the modification suggestion system 100 of this embodiment include, for example, documents containing legal content that produces predetermined legal effects, including standards for determining whether the legal content or form is preferred or not. Examples include contracts, applications, memoranda, company regulations, and policies. This embodiment uses contracts as an example. Legal documents may also be referred to as auxiliary documents, as appropriate.

[0020] In the modification suggestion system 100 of this embodiment, the legal document for which modification is recommended can be processed by a computer, for example, a document in an electronic medium (electronic document). This electronic document can be created using predetermined electronic document creation software, or a paper contract converted to electronic form using predetermined image analysis technology (e.g., OCR (Optical Character Recognition) technology).

[0021] The modification suggestion system 100 of this embodiment provides a document creation assistance service. The document creation assistance service is, for example, a service that includes at least any of the following: performing a document review process on an auxiliary target document on a web browser and providing the results to the user; automatically modifying the document using the results of the document review process and presenting the results as modification candidates (modification suggestion processing); performing document editing in response to instructions from the user; saving the edited document or providing the edited document to the user; editing additional information associated with the auxiliary target document (e.g., meta information, annotation information, chat information, formatting information, etc.); and creating a new document (including copying).

[0022] In particular, the modification suggestion processing performed by the modification suggestion system 100 of this embodiment utilizes an artificial intelligence model that uses natural language. Here, an artificial intelligence model that uses natural language refers to a natural language processing model, such as the Generative Pre-trained Transformer (GPT). This natural language processing model takes natural language text, called prompts, as input and outputs natural language text automatically generated in response to the prompts.

[0023] As the natural language processing model used in the modification suggestion system 100 of the present embodiment, for example, natural language processing models disclosed in https: / / arxiv.org / abs / 2203.02155 and https: / / openai.com / blog / chatgpt / can be used.

[0024] Furthermore, the modification suggestion system 100 of this embodiment automatically generates prompts (natural language strings used to query the natural language processing model) for input into the natural language processing model during modification suggestion processing, based on at least one input unit generated from the auxiliary object document and the modification policy for that input unit. Here, the input unit is, for example, a sentence in terms of clauses, paragraphs, or items, which can be generated by segmenting the auxiliary object document according to predetermined standards. Furthermore, the modification policy refers to information indicating the policy for modifying the input unit, and may be composed of natural language such as "Delete words such as '○○'," "Must add words such as '××'," "As a mandatory provision," or "As an instructional clause."

[0025] For example, it is possible to obtain a modification policy by referring to a rule that defines a combination of a category of sentences (for example, a sentence that specifies a purpose, a sentence that specifies a basis for rights, a sentence that specifies a period, and the like) and a modification policy in a plurality of patterns. In addition, the rule is created by, for example, an expert lawyer or the like and is managed by a database. The combination of the category of sentences and the modification policy managed by the database can be added / modified at any time as needed. In addition, for example, it is also possible to obtain a modification policy by a learning model that takes an input unit as input and outputs a modification policy. In addition, it is also possible to obtain it by a combination of processing using a learning model and processing using a rule base of a database. In addition, for example, the database includes information corresponding to a plurality of example sentences and a plurality of modification policies. The modification suggestion system 100 can obtain a modification policy for at least one input unit based on the similarity between at least one input unit and a plurality of example sentences. In addition, as example sentences, sentences before modification and sentences after modification can be included.

[0026] exist Figure 1 In the figure, as a modification suggestion process, an example is shown including input unit generation process, classification process, prompt creation process as preprocessing, natural language processing and modification statement presentation process. In the input unit generation process, for example, a clause segmentation process using a clause classifier is performed. In the classification process, for example, the category of the clause obtained by the segmentation process is classified by a classifier. In the prompt creation process, for example, a prompt including an input unit and a modification policy is created with reference to a database. In the natural language processing, for example, a modification statement is obtained using a prompt including an input unit and a modification policy and a natural language processing model. In the modification statement presentation process, for example, the modification statement obtained in the natural language processing is presented to the user as a modification candidate. That is, in the natural language processing, multiple modification candidates are generated as candidates for at least one input unit after modification using at least one prompt and a natural language processing model. In the modification statement presentation process, the generated multiple modification candidates are output (presented). It is also possible to save multiple modification candidates and output the saved multiple modification candidates in response to an instruction from the user.

[0027] In addition, if Figure 1 As shown, the natural language processing model used in natural language processing is sometimes stored in an external information processing device 200 connected to the modification suggestion system 100 via a network and having at least one processor and memory. In addition, the natural language processing model is sometimes provided by the model supplier in the form of an API or the like. In addition, the external information processing device 200 is provided with, for example, Figure 4A The same structure as the information processing device.

[0028] In this specification, document review processing refers to the process of analyzing the appropriateness of information contained in an auxiliary document, for example, based on certain criteria, and outputting the results. For example, document review processing includes checking and examining the appropriateness of information contained in an auxiliary document based on certain criteria. Specifically, it includes comparing words and phrases in the document with a pre-prepared checklist and outputting the comparison results or the criticisms contained in the checklist.

[0029] Furthermore, in the modification suggestion process, input units such as those included in prompts from a natural language processing model can be generated by segmenting the entire text of the auxiliary target document into units such as clauses. Furthermore, input units such as those included in prompts from a natural language processing model can also be generated by targeting sentences such as clauses, subclauses, or items that have been determined to be inappropriate or require revision through, for example, document review processing.

[0030] The modification suggestion system 100 of this embodiment obtains at least one modified input unit in the modification suggestion process using at least one prompt word generated based on at least the input unit and the modification policy for the input unit and a natural language processing model.

[0031] Therefore, according to this embodiment, constraints based on modification guidelines can be imposed on the natural language processing model, allowing modification input units to be obtained in accordance with the modification guidelines. As a result, compared to natural language processing using prompts that do not include modification guidelines as input, more specific and accurate modification statements can be obtained. In contrast, when natural language processing using prompts that do not include modification guidelines as input, the resulting modification statements often strongly depend on the training data of the natural language processing model used.

[0032] Users who accept the document creation assistance service provided by this embodiment can confirm / discuss the modified documents that are automatically generated as candidates for modification in the modification suggestion process on the browser screen. In addition, as long as the user confirms the displayed modification or selects the desired modification, the auxiliary object document can be revised based on the review results. In particular, even when revising legal documents such as contract documents that require professional knowledge, it is possible to obtain candidates for modification statements with high accuracy in accordance with the modification guidelines, and revise the auxiliary object document through selection operations. As a result, the user's workload when revising the auxiliary object document can be greatly reduced.

[0033] Figure 2 This figure shows the structure of a modification suggestion system 100 as one embodiment. The modification suggestion system 100 is an information processing system connected to a terminal device T1 via a network such as the Internet so as to be communicable. The modification suggestion system 100 will be described in detail later.

[0034] The terminal device T1 is, for example, a computer used by a user of the modification suggestion system 100 , and may be a smartphone, a tablet terminal, a personal computer, or the like.

[0035] For example, a user accesses the revision suggestion system 100 via terminal device T1 and uploads a contract, an example of a legal document, to the revision suggestion system 100. The user then receives revision suggestion information regarding the target items in the contract via terminal device T1. In this specification, a contract may be referred to as a legal document as appropriate.

[0036] Figure 2 Although only one terminal device T1 is shown in the figure, the number of terminal devices T1 is not limited thereto.

[0037] Next, the modification suggestion system 100 will be described in detail. The modification suggestion system 100 of this embodiment includes a storage unit 110 , a contract acquisition unit 120 , an input unit generation unit 130 , a modification policy information generation unit 150 , a modification suggestion input information (prompt) generation unit 160 , and a modification suggestion unit 170 . Figure 2 Each of the components shown can be realized by using a storage area or by having a processor execute a program stored in the storage area, for example.

[0038] The storage unit 110 of this embodiment stores information processed in the modification suggestion system 100. The storage unit 110 can store, for example, contract information, input unit information, and policy information described later. The storage unit 110 can be, for example, a memory.

[0039] The contract acquisition unit 120 of the present embodiment acquires, for example, contract information related to a contract and stores it in the storage unit 110. The contract acquisition unit 120 can acquire electronic data of a contract.

[0040] Here, the contract information is information related to the contract, including, for example, status information, position information, contract type information (also collectively referred to as meta-information) and contract content information.

[0041] The status information in this embodiment indicates the status of a contract, for example, information indicating the status of contract amendments. Examples of status information include "Other Party Draft" indicating a draft (e.g., a first draft) of the other party to the contract, "Other Party Amendment" indicating a contract that has been amended by the other party to the contract, and "Review Completed" indicating that the company (the business entity to which the user belongs) has completed and confirmed the contract.

[0042] The position information in this embodiment is information indicating the position of the contract, for example, information indicating the position of the company (the business entity to which the user belongs). Examples of position information include "client" indicating the client in a business contract and "discloser" indicating the party that discloses confidential information in a confidentiality agreement.

[0043] The contract type information in this embodiment is information indicating the type of contract, and may be, for example, "business entrustment contract" or "confidentiality contract".

[0044] The contract details information in this embodiment is information (for example, character data) indicating the contents of the contract.

[0045] The contract acquisition unit 120 of this embodiment can acquire contract information from the terminal device T1, for example. That is, the user provides (uploads) a contract to the revision suggestion system 100 via the terminal device T1, and the contract acquisition unit 120 can acquire the contract information of the uploaded contract.

[0046] In this case, the contract acquisition unit 120 can, for example, acquire contract information from the user through operation of the terminal device T1. In this case, upon receiving the contract upload from the terminal device T1, the contract acquisition unit 120 can accept input (e.g., keyboard input or selection of a system-preset item) of at least a portion of the contract information (e.g., status information, position information, and contract type information) from the user to acquire the contract information.

[0047] Alternatively, the contract acquisition unit 120 may acquire contract information from another information processing system. In this case, for example, a user may provide the contract information to the other information processing system via the terminal device T1, and the contract acquisition unit 120 may acquire the contract information provided by the other information processing system. Examples of other information processing systems include contract management systems, document management systems, and cloud storage devices.

[0048] In addition, the contract acquisition unit 120 may, for example, analyze the contract content information to acquire at least a portion of the contract information (eg, status information, position information, and contract type information).

[0049] The contract information stored in the storage unit 110 includes, for example, a contract ID, a sequence ID, status information, position information, contract type information, and contract content information.

[0050] The contract ID in this embodiment is information identifying the contract processed in the modification suggestion system 100. The contract ID is identification information assigned to each contract so that it can be distinguished between the contracts before and after modification. In other words, the contract ID is information that uniquely identifies the contract (i.e., electronic document) acquired by the contract acquisition unit 120.

[0051] The sequence ID in this embodiment is information identifying a contract represented by a contract handled by the revision suggestion system 100. Specifically, the sequence ID is a unit for managing, for example, a series of contracts that have been drafted, revised, and agreed upon (i.e., multiple contracts, such as a contract being drafted for contract conclusion, a contract in the process of revision, and a contract that has been agreed upon).

[0052] The contract acquisition unit 120 of this embodiment can, for example, generate a serial ID in response to a user operation on the terminal device T1. Specifically, when a user uploads a pre-amended contract, a specific serial ID (e.g., a serial ID corresponding to the virtual folder or a serial ID identical to the serial ID of the first pre-amended contract) can be generated based on the fact that the pre-amended contract is uploaded to a contract management area (e.g., a virtual folder managed by the amendment suggestion system 100).

[0053] For example, the serial ID of the present embodiment can be used in the following manner. During the negotiation of the contents of a contract, the other party sometimes wants to further modify the contents of the user's draft contract that have been proposed for modification. The contract or the draft contract is sent by the other party, for example, by email. However, directly deleting the other party's modified contents, although it can be said to be advantageous as the contents of the contract, is sometimes not advisable from the perspective of negotiation. In this case, referring to the contents of the contract with the same serial ID (i.e., the previous version), it is possible to make the input modification policy more compromising than the policy applicable to the previous version, to make the expression of the contract calmer, or to make the annotations generated to match the modification suggestions more comprehensive. In addition, by retaining information on the previous version of the contract under review, it is possible to reduce the possibility of, for example, re-raising previous compromise points and making it difficult for negotiations to progress.

[0054] In addition, when a contract related to the contract subject to review is formulated, for example, when the same or related content is stipulated in two or more contracts, such as a pre-renewal contract concluded before the contract subject to review, a basic contract when the contract subject to review is a separate contract, a joint research and development contract, and a joint invention patent application contract, if there are contracts with the same counterparty, the content of these contracts and the negotiation status can be taken into consideration.

[0055] These contents may be considered at the stage of generating the revision policy or at the stage of generating the prompt words described later. However, generating them as prompt words simplifies the process and is therefore preferred.

[0056] The contract acquisition unit 120 of this embodiment may extract information based on, for example, the contracting parties in the contract, the contract creation date, and the contract information of the contract (eg, status information, position information, contract type information, and contract content information).

[0057] The input unit generation unit 130 of the present embodiment divides the contract content according to the items included in the contract based on the contract information, and stores the input units in the storage unit 110.

[0058] Here, the input unit can be, for example, the entire contract text, or a unit obtained by dividing the contract into components such as a title, a beginning, a body, a signature, etc., and the components of the contract, and can also correspond to the articles included in the contract. That is, the input unit generation unit 130 can divide the contract content by, for example, "article" or "paragraph".

[0059] The input unit generation unit 130 can, for example, analyze the contract content and divide the contract content into items based on the positions of characters corresponding to the input units (such as the characters "article" or "paragraph"). In addition, the input unit generation unit 130 may not divide all contracts into input units, nor divide all items of a contract into items. That is, the input unit generation process performed by the input unit generation unit 130 can be only for some contracts, or only for a part of a contract. In addition, the input unit generation unit can merge some of the divided units or some of the divided units into one as needed. For example, one legal argument is sometimes stipulated in multiple articles. In this case, when dividing by article as described above and obtaining the modification guidelines item by item and making modification suggestions, it is sometimes difficult to obtain appropriate modification guidelines and make modification suggestions. In this case, it is preferable to merge the parts with similar legal arguments so that the modification guidelines can be appropriately obtained using rules or learned models.

[0060] In addition, before these processes, information required for document review such as text data can be extracted from the received document data, or text data can be extracted from image data using processes such as OCR.

[0061] When the contract acquisition unit 120 has acquired the contract information of a contract, the input unit generation unit 130 can divide the contract before modification into items, and generate input unit information representing the content before modification of each input unit.

[0062] The input unit information stored in the storage unit 110 includes, for example, an input unit ID, a contract ID, and input unit information.

[0063] The input unit ID of the present embodiment is information for identifying the item information processed in the modification suggestion system 100. The input unit information of the present embodiment is information representing the content corresponding to the input unit, for example, information representing the content of each clause.

[0064] The modification policy information generation unit 150 of this embodiment generates information related to the policy of how to best modify a contract. For example, a document review process is performed on the contract to generate document review information. For example, the document review information is based on information obtained by analyzing the document according to the rules or standards applied to the document (such as certain regulations, laws, and conventions). For example, as review information of a contract such as the present embodiment, there can be cited (1) a comment on whether the terms contained in the document (the contract in this embodiment) are favorable or unfavorable to the user (the party), (2) opinions related to the modification and deletion of the terms contained in the contract, (3) a comment on the lack of items that should usually be included in the contract and suggestions for items that should be added, (4) information on the importance and recommendation level of the items of each review result, etc. In addition, format information such as whether the style of the sentence conforms to the standard and whether the prescribed terminology is used can also be included.

[0065] In this embodiment, the revision policy information generation unit 150 performs a document review process using the contract data (an example of the first legal document data) received from the terminal device T1. Specifically, as part of the document review process, the analysis unit 151 generates document review information (described later) regarding the document data. The document review information is an example of analysis information.

[0066] The analysis unit 151 of this embodiment is included in the modification policy information generation unit 150, and, for example, extracts information required for generating modification policy information contained in a document (document data). Various techniques can be used in the method of extracting information from document data. For example, keyword retrieval of document data can be performed to extract characters and numbers contained near the keywords. In addition, information can be extracted through morphological analysis, syntactic analysis, semantic analysis, and context analysis. Furthermore, information can be extracted through natural language processing using machine learning. In addition, the received document can also be processed to generate modification policy information without extracting the information required for generating the above-mentioned policy information.

[0067] Furthermore, various techniques can be employed to generate document review information executed by the revision policy information generation unit 150. For example, it is preferable to use the extracted information to generate document review information using a rule base based on rules designed by humans, particularly expert lawyers. Alternatively, a learning model can be used that takes the extracted information as input and outputs the corresponding document review information. Furthermore, a combination of a rule base-based approach and a learning model can be employed.

[0068] Furthermore, the revision policy information generation unit 150 can also utilize meta-information associated with the contract to generate document review information appropriate to the user's (party's) perspective. Furthermore, the analysis unit 103 can also generate document review information by referencing the content of other documents (e.g., other versions of the auxiliary document, other contracts related to the contract, etc.). Meta-information includes both information assigned to the document itself by the document creator and information assigned by the user, such as by inputting it separately from the document.

[0069] The meta-information of this embodiment includes, for example, document ID, document type (such as transaction basic contract, confidentiality contract, business delegation contract, etc.), version, creation date and time, update date and time, upload date and time, creator, updater, deadline and at least one of the document IDs of the associated document.

[0070] The modification policy information generation unit 150 of this embodiment generates a prompt. The prompt is based on, for example, the sentence of the input unit and the modification policy instruction, wherein the modification policy instruction is based on the document review information for the input unit. Specifically, the modification policy information generation unit 150 generates a prompt using natural language descriptions such as "This input is (the sentence divided into input units)" and "Instruction is (the modification policy)."

[0071] The prompt language thus obtained is input into a natural language processing model to obtain a modified input unit after the input unit is modified.

[0072] In addition, the natural language processing model may be stored in an information processing device connected to the system via a network. In addition, the natural language processing model may be provided by the model provider in the form of an API or the like.

[0073] Figure 4A 1 is a block diagram showing an example of the hardware configuration of the information processing device 10 according to the embodiment. Figure 4A As shown, the information processing device 10 is a computer, and includes, as an example, a processor 11 , a main storage device (memory) 13 , an auxiliary storage device (memory) 15 , a network interface 17 , a device interface 18 , and a bus 19 connecting the components.

[0074] Figure 4A The information processing device 10 shown in the figure includes only one component, but the same component may be included in multiple components. Figure 4AAlthough a single information processing device 10 is shown, the software may be installed on multiple computers, each of which executes the same or different portions of the software. In this case, a distributed computing method may be employed, in which the computers communicate via a network interface 17 or the like and execute processing. In other words, the information processing device 10 of this embodiment may be configured as a system that implements the various functions described below by having one or more computers execute instructions stored in one or more storage devices.

[0075] The various operations of the information processing device 10 can be performed by parallel processing using one or more processors, or using multiple computers via a network. In addition, various operations can also be distributed to multiple computing cores within the processor and executed by parallel processing. In addition, part or all of the processing, units, etc. disclosed in the present invention can also be executed by at least one of the processors and storage devices set on the cloud that can communicate with the information processing device 10 via the network. In this way, the processing of the document creation assistance system S of this embodiment can be in the form of parallel computing performed by one or more computers.

[0076] The processor 11 can be, for example, an electronic circuit (processing circuit, Processing circuit, Processing circuitry, CPU (Central Processing Unit, Central Processing Unit), GPU (Graphics Processing Unit, Graphics Processing Unit), FPGA (Field Programmable Gate Array, Field Programmable Gate Array) or ASIC (Application Specific Integrated Circuit, Application Specific Integrated Circuit), etc.) of the information processing device 10 including a control device and an operating device. In addition, the processor 11 can also be a semiconductor device including a dedicated processing circuit, etc. The processor 11 is not limited to an electronic circuit using electronic logic elements, but can also be implemented by an optical circuit using optical logic elements. In addition, the processor 11 can include an operating function based on quantum computing.

[0077] The processor 11 can perform calculations based on data and software (programs) input from various devices within the information processing device 10, and output calculation results and control signals to each device. The processor 11 can control the various components of the information processing device 10 by executing the operating system (OS) and applications of the information processing device 10.

[0078] The information processing device 10 of this embodiment can be implemented by one or more processors 11. Here, the processor 11 can refer to one or more electronic circuits configured on a single chip, or one or more electronic circuits configured on two or more chips or two or more devices. When using multiple electronic circuits, each electronic circuit can communicate via wired or wireless communication.

[0079] The main storage device 13 is a storage device that stores, for example, instructions executed by the processor 11 and various data. The information stored in the main storage device 13 is read by the processor 11. The auxiliary storage device 15 is a storage device other than the main storage device 13. In addition, these storage devices refer to any electronic components that can store electronic information, and can be semiconductor memories. Semiconductor memories can be either volatile memories or non-volatile memories. The storage device for storing various data used in the information processing device 10 of this embodiment can be implemented by the main storage device 13 or the auxiliary storage device 15, or can be implemented by a built-in memory built into the processor 11. For example, the storage unit of this embodiment can be implemented by the main storage device 13 or the auxiliary storage device 15.

[0080] A plurality of processors can be connected (coupled) to one storage device (memory), or a single processor 11 can be connected. A plurality of storage devices (memories) can be connected (coupled) to one processor. When the information processing device 10 of this embodiment includes at least one storage device (memory) and a plurality of processors connected (coupled) to the at least one storage device (memory), a structure in which at least one of the plurality of processors is connected (coupled) to at least one storage device (memory) can be included. In addition, the structure can be implemented by the storage devices (memories) and processors 11 included in a plurality of computers. In addition, a structure in which the storage device (memory) and the processor 11 are integrated can also be included (for example, a cache memory including an L1 cache and an L2 cache).

[0081] The network interface 17 is, for example, an interface for connecting to the network N wirelessly or by wire. As the network interface 17, any appropriate interface such as an interface that complies with existing communication standards can be used. Information can be exchanged with an external device connected via the network N through the network interface 17. In addition, the network N can be any network such as a WAN (Wide Area Network), a LAN (Local Area Network), a PAN (Personal Area Network), or a combination thereof, as long as it is a network that exchanges information between the information processing device 10 and an external device. As an example of a WAN, there is the Internet, as an example of a LAN, there are IEEE802.11, Ethernet (registered trademark), etc., as an example of a PAN, there are Bluetooth (registered trademark), NFC (Near Field Communication), etc.

[0082] The device interface 18 is an interface such as a USB (Universal Serial Bus) that directly connects to output devices such as display devices, input devices, and external devices. Furthermore, the external device may be a storage device (memory), a network storage device, or a storage device such as a HDD. Furthermore, the external device may be a device that has some of the functions of the components of the information processing device 10 of this embodiment. In other words, the information processing device 10 can transmit or receive some or all of the processing results of the external device.

[0083] Figure 4B 1 is a block diagram showing an example of the hardware configuration of the terminal device T1 according to the embodiment. Figure 4B As shown, the terminal device T1 is a computer, and as an example, includes a processor 21, a main storage device (memory) 23, an auxiliary storage device (memory) 25, a network interface 27, a device interface 28, a bus 29 connecting the various components, a display device 30 connected to the device interface 28, and an input device 31 connected to the device interface 28. The specific hardware configurations of the processor 21, the main storage device 23, the auxiliary storage device 25, the network interface 27, the device interface 28, and the bus 29 are the same as those of the processor 11, the main storage device 13, the auxiliary storage device 15, the network interface 17, the device interface 18, and the bus 19, respectively, and therefore their description is omitted.

[0084] The display device 30 is a display device such as an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube), a PDP (Plasma Display Panel), or an organic EL (Electroluminescence) panel. Based on instructions from the processor 21, the display device 30 displays, for example, the document review screen and document editing screen described below.

[0085] The input device 31 is, for example, a keyboard, a mouse, a touch panel, etc. The user can use the input device 31 to input various editing instructions, for example, in the document editing process described later. The input device 31 sends the input instructions to the processor 21.

[0086] Furthermore, the terminal device T1 may be equipped with other external devices (eg, a camera, a microphone, a motion capture device, various sensors, etc.) connected via the device interface 18 in order to operate and edit document data.

[0087] Figure 5 This diagram shows an example of functional blocks in the processor 21. The processor 21 includes, for example, a second control unit 40 and a browser unit 42 as functions implemented by the processor 21. The functions implemented by the second control unit 40 and the browser unit 42 are stored as programs in, for example, the main storage device 23 or the auxiliary storage device 25. The processor 21 can implement the functions related to the second control unit 40 and the browser unit 42 by reading and executing the programs stored in the main storage device 23 or the auxiliary storage device 25.

[0088] The second control unit 40 activates the browser unit 42 in response to an instruction from the user, for example.

[0089] The browser unit 42 is, for example, a general web browser and executes processing according to HTML (Hyper Text Markup Language) data or scripts (eg, JavaScript (registered trademark)). When started, the browser unit 42 sends an initial access URL to the information processing device 10 and accesses it.

[0090] The browser unit 42 of this embodiment displays data, including text data and image data, received from the information processing device 10 on the display device 30 of the terminal device T1 in a predetermined format. More specifically, during document review processing, the browser unit 42 displays document review information, document data, and additional information received from the information processing device 10 on the display device 30 of the terminal device T1 in a predetermined format based on layout information. Furthermore, during document editing processing, the browser unit 42 of this embodiment displays document review information, editing data, and additional information received from the information processing device 10 on the display device 30 of the terminal device T1 in a predetermined format based on layout information.

[0091] Figure 6 FIG. 6 is a diagram showing an example of a document review screen 60 displayed as a web browser screen on the display device 30 of the terminal device T1 during the document review process. Figure 6 As shown, in the document review screen 60 of this embodiment, the auxiliary target document is displayed in the document display area 61 , additional information such as change history and comments is displayed in the additional information area 67 , and document review information is displayed in the document review area 62 .

[0092] For example, an edit button 68 for instructing to start document editing is displayed in the document display area 61. A scroll bar 64 is displayed next to the additional information area 67 that displays additional information. The scroll bar 64 is used to scroll the auxiliary object document displayed in the document display area 61 and the additional information displayed in the additional information area 67 in the vertical direction.

[0093] The user clicks a button displayed on the screen to start document review processing. The system accesses the database, performs document review processing, and obtains revision guidelines for each input unit. Figure 3 This is an example of a database that is subject to the revised policy.

[0094] At this time, you can obtain all the modification policies set for the input unit category (such as the type of clause), or you can obtain the modification policies for the relevant parts of the input unit of the auxiliary object document, but from the perspective of review convenience, it is preferable to display some modification policies.

[0095] Next, based on the input units of the auxiliary target document and the revision guidelines for that unit, a prompt is generated for obtaining the revision input units. For example, the prompt may be a natural language prompt such as "Please revise Article A according to the content of Critique A." This prompt is input into the natural language processing model, and the revision input units generated based on the prompt are obtained as output. If the natural language processing model is external to the system, the system uses a network such as the Internet to transmit and receive data with an information processing device equipped with the natural language processing model.

[0096] The generation of the prompt of the natural language processing model can be performed after the review process and before the user instructs to obtain the modified input unit by clicking the button 69 indicating the generation of the modified input unit, or it can be generated after the user instructs. Figure 6 The "Modification Guidelines" in boxes such as 623 correspond to the modification guidelines in this manual, and the "Modification Example" in box 623 corresponds to the "Example Sentence" in this manual. Furthermore, a prompt can be generated based on optional modification guidelines. Optional guidelines can include any of the following: making the text of the modified output unit as close as possible to the text of the input unit; making the modified output unit more user-friendly than the modification guidelines; and omitting a portion of the modification guidelines from the modified output unit. These optional guidelines can be displayed. The user can select the desired policy from the displayed optional guidelines.

[0097] In addition, a button 69 may be provided to indicate the creation of modified input units for each of the multiple input units or modification policies. This allows the user to obtain modified input unit information for any input unit they deem necessary. This is advantageous, for example, when the creation of modified input units is based on a volume-based charge and the user wishes to adjust the number of generated items.

[0098] Next, the system sends information including the above-mentioned modified input unit to the user. The system applies the information to the input unit or the contract automatically, for example, based on a user instruction such as clicking a button 70 indicating that the modified text will be applied to the draft contract. For example, the input unit in the auxiliary object document displayed in the browser is replaced with the modified input unit. Before and after the replacement, the user can edit the modified input unit and instruct to generate the modified input unit again. In addition, the obtained modified input unit and the desired instruction can be input into the natural language processing model to obtain a more preferred modified input unit. In addition, it is also possible to use at least one prompt and multiple different natural language processing models, each natural language processing model generates at least one modified input unit, and each natural language processing model outputs at least one modified input unit. In addition, it is also possible to save the at least one modified input unit generated by each natural language processing model, and output the saved at least one modified input unit in response to an instruction from the user.

[0099] Furthermore, a button 70 may be provided to indicate whether or not to apply each of the plurality of modification input units. This allows the user to confirm the modification input information and apply the modification input unit information to the input unit deemed necessary. Furthermore, before outputting the at least one modification input unit, it is also possible to check whether the at least one acquired modification output unit meets the modification output criteria, including the modification policy.

[0100] Furthermore, the following annotation information and chat information can be associated with the auxiliary object document of this embodiment.

[0101] In this embodiment, annotation information associated with a document is additional information created by at least one user involved in the creation of the document, and is managed, for example, in association with each version of the document. While annotation information associated with a document is typically different from annotations created by the document creation software, it may also include annotations created by the document creation software as needed.

[0102] In this embodiment, chat information refers to additional information generated by multiple users involved in the creation of a document using a chat function, such as associated with multiple versions of a document. This additional information is usually text data, but may also include other data forms such as images and sounds.

[0103] The user can save, for example, an edited contract and can use it by exporting it as a Word or PDF file, downloading it, sending it from the system, or sending it as a URL.

[0104] While the embodiments of the present disclosure have been described in detail above, these embodiments are presented as examples and are not intended to be limiting. Various modifications, such as additions, changes, substitutions, partial deletions, and combinations, are possible with respect to each embodiment. These embodiments and their modifications are intended to be within the scope of the invention as set forth in the claims and their equivalents.

Claims

1. An information processing method comprising: Obtaining a modification policy for at least one input unit of the first legal document, Obtaining at least one modified input unit after modification using at least one prompt generated based on at least the input unit and the modification policy for the input unit and a natural language processing model, The at least one modified input unit is output.

2. The information processing method according to claim 1, wherein: The modification policy is acquired by referring to a database.

3. The information processing method according to claim 2, comprising: In acquiring the modification policy, determining a category of each of the at least one input unit by a classifier, The database includes information corresponding to a plurality of categories and a plurality of modification policies. The modification policy is acquired using the determined category and the database.

4. The information processing method according to claim 2, comprising: Referencing the database, obtaining the modification policy and the example sentence for each of the at least one input unit, The prompt is created based on the obtained example sentence.

5. The information processing method according to claim 4, comprising: The database includes information corresponding to a plurality of example sentences and a plurality of modification policies. Based on the similarity between the at least one input unit and the plurality of example sentences, the modification policy is respectively acquired for the at least one input unit. The information processing method according to claim 5 , wherein: The example sentences include sentences before modification and sentences after modification.

7. The information processing method according to claim 1, comprising: generating a plurality of modification candidates as candidates for the modified at least one input unit using the at least one prompt word and the natural language processing model, A plurality of modification candidates are output.

8. The information processing method according to claim 7, comprising: saving a plurality of said modification candidates, The plurality of modification candidates stored are output in response to an instruction from a user.

9. The information processing method according to claim 1, comprising: using the at least one prompt and a plurality of different natural language processing models, generating the modified at least one input unit for each of the natural language processing models, The modified at least one input unit is outputted per each of the natural language processing models.

10. The information processing method according to claim 9, comprising: saving the modified at least one input unit generated by each of the natural language processing models, The saved modified at least one input unit is output in response to an instruction from a user.

11. The information processing method according to claim 1, wherein: The first legal document is a contract.

12. The information processing method according to claim 11, wherein: The contract is a contract sent by the other party of the contract.

13. The information processing method according to claim 1, wherein: The at least one input unit is any one of an article, a clause, and an item.

14. The information processing method according to claim 1, wherein: Before outputting the at least one modification input unit, it is checked whether the acquired at least one modification output unit satisfies a modification output standard including the modification policy.

15. The information processing method according to claim 1, wherein: Information is sent to display a button that enables replacing the input unit of the first legal document with an output input unit.

16. The information processing method according to claim 1, wherein: The prompt is further generated based on the modified optional policy.

17. The information processing method according to claim 16, wherein: The optional guidelines include any of the following: making the literal of the modified output unit as close as possible to the literal of the input unit; making the modified output unit more favorable to the user than the modified policy; And causing the modification output unit to omit a portion of the modification policy.

18. The information processing method according to claim 16, wherein: A display is provided to enable the user to select the optional policy.

Images