Document correction program, document correction device and document correction method

Abstract

To provide a document correction program for supporting flexible correction according to an individual document.SOLUTION: A document correction program using a sentence generation model to propose correction of a document based on an evaluation of the document, causes a computer to function as an acquisition part, an instruction generation part and a proposal part. The acquisition part acquires draft information relating to a draft of the document and evaluation information representing an evaluation of the draft, the instruction generation part generates a correction instruction relating to the draft based on the draft information and the evaluation information and transmits it to the sentence generation model, and the proposal part transmits correction proposal information for correcting the draft based on output of the sentence generation model.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a document correction program, a document correction device, and a document correction method. [Background technology]

[0002] A high level of expertise is required for the evaluation and creation of documents, particularly legal documents such as contracts and regulations. In light of this background, there are known technologies for checking legal documents and technologies for supporting the revision of legal documents based on the checking.

[0003] For example, Patent Document 1 describes a technology that accepts input of information on review results for legal documents and makes corrections. The technology described in Patent Document 1 can correct legal documents by replacing corresponding parts with recommended sentences registered in advance. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2020-080132 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the technology described in Patent Document 1 has a problem that it can only handle content that is expected in advance, and it is difficult to flexibly make corrections to suit individual documents, because the corrections are made by partially replacing the recommended sentences with those that have been registered in advance. Therefore, the present invention aims to solve the above problems. [Means for solving the problem]

[0006] In order to solve the above problem, a document correction program is provided for utilizing a sentence generation model to suggest corrections to a document based on an evaluation of the document, the program causing a computer to function as an acquisition unit, an instruction generation unit, and a proposal unit, the acquisition unit acquiring draft information regarding a draft of the document and evaluation information indicating an evaluation of the draft, the instruction generation unit generating correction instructions regarding the draft based on the draft information and evaluation information and transmitting them to the sentence generation model, and the proposal unit transmitting correction proposal information for correcting the draft based on the output of the sentence generation model.

[0007] With this configuration, the document draft can be supported for revision using the text generation model based on the evaluation of the document draft. This makes it possible to flexibly suggest revisions according to the contents of the document, making it easier to revise the document. In particular, even in the revision of documents that require expertise, such as legal documents, the text generation model makes it easy for users to make revisions themselves, making it possible to improve the efficiency of tasks such as creating and reviewing contracts.

[0008] In a preferred form of the invention, the document is a legal document including a plurality of clauses, and the evaluation information includes a result of evaluating the draft with respect to each clause and / or the relationship between the plurality of clauses.

[0009] With this configuration, it is possible to suggest revisions to a document written by clause based on an evaluation of the contents of each clause or the relationship between multiple clauses, and to support more appropriate revisions. For example, when a set of regulations is defined by multiple clauses, the regulations that span multiple clauses can be appropriately evaluated by treating the clauses as a group and checking the relationships between the clauses. Furthermore, by sending an instruction to revise the draft to the text generation model using the evaluation as evaluation information, appropriate revisions can also be proposed for such a group of multiple clauses.

[0010] In a preferred embodiment of the present invention, the evaluation information includes an evaluation regarding any one of unnecessary clauses, missing information, and contents of clauses.

[0011] With this configuration, it is possible to propose appropriate revisions based on an evaluation of whether a clause should be deleted, a clause should be added, or the content of a clause should be revised.

[0012] In a preferred embodiment of the present invention, the instruction generation unit generates, as the modification instruction, a sentence that describes instructions regarding the modification for each clause or for each group of multiple clauses that defines a set of regulations, and transmits the generated sentence to the sentence generation model.

[0013] With this configuration, it is possible to appropriately transmit an instruction to amend a legal document divided into clauses for each clause or for each group of clauses that defines a set of provisions, making it easier to execute amendments appropriate for a legal document that includes multiple clauses.

[0014] In a preferred form of the present invention, the evaluation information includes a risk level for each of the issues raised about the draft, and the instruction generation unit generates, as the correction instruction, an instruction to correct the draft for issues that are at or above a predetermined risk level, and transmits the correction instruction to the writing generation model.

[0015] With this configuration, it is possible to propose modifications to high-risk parts. This makes it possible to propose modifications separately for low-risk parts and parts for which the user should consider whether or not to modify them, depending on the risk level.

[0016] In a preferred form of the present invention, the evaluation information includes an evaluation statement in which an evaluation of the draft is described in natural language, and the instruction generation unit generates a sentence based on the draft, the evaluation statement, and a previously prepared instruction statement as the correction command and transmits the correction command to the sentence generation model.

[0017] With this configuration, sentences in natural language can be generated as correction commands, so that correction suggestions can be made, for example, by using an interactive sentence generation model that outputs sentences in response to input sentences.

[0018] In a preferred form of the present invention, the computer is further made to function as a re-evaluation unit, which obtains a revision proposal for the draft as an output of the sentence generation model, obtains re-evaluation information indicating an evaluation of the revision proposal, determines whether or not the evaluation satisfies a preset criterion, and if the criterion is satisfied, causes the suggestion unit to transmit the revision proposal information, and if the criterion is not satisfied, causes the instruction generation unit to generate a revision instruction for the revision proposal and transmit it to the sentence generation model based on the revision information and re-evaluation information based on the revision proposal.

[0019] By configuring in this way, we can avoid sending correction proposals that still have problems, and if there are problems, we can reevaluate the correction proposals and make corrections again, which is expected to improve the quality of the correction proposals.

[0020] In a preferred embodiment of the present invention, the re-evaluation unit causes the suggestion unit and the instruction generation unit to repeatedly obtain re-evaluation information and transmit modification instructions until the evaluation of the modification proposal satisfies a preset criterion.

[0021] With this configuration, evaluation and correction can be repeated until the criteria are met, further reducing the occurrence of problems where incomplete parts remain after correction, and enabling higher quality correction suggestions to be made.

[0022] In a preferred embodiment of the present invention, the reevaluation information includes a risk level for each of the issues raised for the proposed revision, and the criteria includes that the risk levels of all of the issues raised for the proposed revision are equal to or lower than a predetermined risk level.

[0023] With this configuration, corrections can be repeated until there are no issues pointed out that are at or above a predetermined risk level, thereby improving the quality of correction suggestions.

[0024] In a preferred form of the present invention, when a preset termination condition is met, the re-evaluation unit terminates the repeated re-evaluation and causes the suggestion unit to transmit the revision proposal information, even if the evaluation of the revision proposal does not satisfy a criterion.

[0025] By adopting such a configuration, infinite loops and excessively repetitive processing can be avoided, and a reduction in the processing load can be expected.

[0026] In a preferred embodiment of the present invention, the command generation unit receives an input of a request for correction from a user, generates the correction command based on the request, and transmits the correction command to the sentence generation model.

[0027] With this configuration, it is possible to propose modifications that reflect the user's wishes. For example, when making a contract with a specific party, there may be multiple possible modification patterns, such as making modifications aggressively (to the party's advantage) or to establish an equal relationship. By accepting the user's wishes and generating a modification command, it is possible to make a modification proposal that is more in line with the user's wishes, even in such cases.

[0028] In a preferred embodiment of the present invention, the document is a legal document relating to an agreement with a specific party, and the instruction generation unit obtains background information indicating at least one of the relationship with the party, the type of the agreement, and the wishes of the parties regarding the agreement, generates the modification instruction based on the background information, and transmits it to the sentence generation model.

[0029] With such a configuration, it becomes possible to make more appropriate revision proposals based on the relationship with the other party, the type of arrangement, the requests of the parties, etc. For example, by specifying a contract type as the type of arrangement, it becomes possible to propose more appropriate revisions taking the contract type into consideration. Furthermore, for example, when concluding a confidentiality agreement, it becomes possible to propose revisions that are advantageous to the user by selecting whether oneself is the discloser or the recipient of information as the relationship with the other party. Furthermore, by selecting, as the request of the parties, for example, whether to be forceful toward the other party (to make the content advantageous to oneself) or to make the content equal, it becomes possible to make revision proposals that reflect the request.

[0030] In a preferred embodiment of the present invention, the draft information is information relating to a draft generated by a model.

[0031] With this configuration, users can complete the document creation process from drafting to editing without having to do it themselves, which makes it easy for users to create legal documents that require expertise, such as contracts.

[0032] In a preferred form of the invention, the document is a legal document relating to an agreement with a specific party, and the draft information is information about a draft generated by the model based on prior information indicating at least one of the relationship with the party, the type of the agreement, and the parties' wishes regarding the agreement.

[0033] With this configuration, it is possible to create a draft based on the relationship with the other party, the type of agreement, the requests of the parties, etc. This is expected to have an effect of improving the quality of the final document. Effect of the Invention

[0034] According to the present invention, it is possible to support flexible revisions tailored to individual documents. [Brief description of the drawings]

[0035] [Figure 1] 1 is a diagram showing a configuration of a document correction system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of the document correction system according to the embodiment of the present invention. [Diagram 3] FIG. 2 is a diagram illustrating a functional configuration of the document correction system according to the embodiment of the present invention. [Figure 4] FIG. 4 is a sequence diagram illustrating an example of a processing procedure of the document correction system according to the embodiment of the present invention. [Diagram 5] 13 is a display example of an evaluation screen of the document correction system according to the embodiment of the present invention. [Figure 6] 10 is a flowchart showing a processing procedure related to a reevaluation process of the document revision system according to the embodiment of the present invention. [Figure 7] 13 is a display example of a correction suggestion screen of the document correction system according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0036] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The document correction system of the present invention will now be described with reference to the accompanying drawings, in which preferred embodiments are shown, although the invention may be embodied in many different forms and is not limited to the embodiments set forth herein.

[0037] For example, in this embodiment, the configuration, operation, etc. of the document correction system will be described, but similar effects can be achieved by a document correction device, a document correction system, or a method executed by a document correction device, a document correction program, etc. In this embodiment, the document correction system takes the form of so-called cloud computing, in which the document correction program is executed in a server (document correction device) connected to the client terminal via a network in order to realize its functions in a client terminal (user terminal device).

[0038] The document correction program may be provided to a computer device as a computer-readable non-transient storage medium or may be provided downloadable from an external server in order to cause an arbitrary computer device to function as a document correction device. The document correction program may also be an add-on (plug-in) program in document editing software such as Microsoft Word (registered trademark).

[0039] In this embodiment, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In this embodiment, "information" is represented, for example, by a physical value of a signal value representing a voltage or current, a high or low signal value as a binary bit set consisting of 0 or 1, or a quantum superposition (so-called quantum bit), and communication and calculation can be performed on the circuit in the broad sense. The circuit in the broad sense is a circuitry realized by appropriately combining a circuit, a processor, a memory, and the like. For example, it is a circuitry including any of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), and the like.

[0040] <Definition> First, definitions of terms will be described. The present invention is a technology for supporting document correction by utilizing a sentence generation model. A sentence generation model refers to any model capable of outputting a sentence. As a sentence generation model, a model generated by machine learning can be typically used. In this embodiment, a case will be described in which a conversational sentence generation model is used, which receives a sentence and generates a sentence as a response to the input sentence.

[0041] More specifically, the sentence generation model is a machine learning model for natural language processing, and is a model that has a function of generating sentences based on input information. For example, the sentence generation model is a machine learning model based on a Transformer model having a self-attention mechanism. The Transformer model is, for example, a GPT (Generative Pre-trained Transformer) model. The sentence generation model can perform learning using a large data set, making it possible to perform not only general natural language generation tasks but also highly specialized sentence generation tasks. For example, the sentence generation model can be a model trained using a large data set using the GPT-3 or GPT-4 algorithm developed by OpenAI (for example, a ChatGPT model generated by combining learning using a large data set and reinforcement learning using a reward prediction model). In addition, in this embodiment, an example of text information is described as the input to the model, but image information or audio information may also be input.

[0042] In this embodiment, the document is assumed to be a legal document such as a contract, a rule, or a regulation. Some legal documents include units divided into articles, clauses, and items, and in this embodiment, each of these units is called a "clause." In this embodiment, the legal document is a contract. Examples of the contract include documents that exert contractual effects, such as non-disclosure agreements, sales contracts, and real estate lease agreements. Furthermore, this embodiment is not limited to contracts, and the legal document may be, for example, a rule, a rule, or a notice. Examples of the rule include documents of legal norms such as work regulations. Examples of the notice include documents of policy declarations such as privacy. In addition, legal documents include documents that are somehow related to law, such as notices and powers of attorney.

[0043] In the following, a draft refers to a rough draft of a document. In the present invention, information about a draft is called draft information, and the draft information includes information indicating the contents of sentences that constitute at least a part of the draft. For example, the draft information may include only information about clauses to be revised or clauses related to the revised parts, or the draft information may include information about the entire text of the draft.

[0044] In this embodiment, a correction command is sent to the sentence generation model to output a correction proposal for the draft, which is then used to make a proposal for correcting the draft. The correction proposal may be for the entire text of the draft, or may be for a portion of the text that is to be corrected.

[0045] The correction command is information indicating a command for causing the writing generation model to output information regarding the correction of the draft. In this embodiment, since a conversational writing generation model that receives a sentence as an input is used, a sentence or a sentence in a natural language is generated and transmitted as a correction command. Then, the sentence or sentence output by the writing generation model as an answer is received, and a correction suggestion is made.

[0046] <System configuration> Next, the configuration of the document correction system of this embodiment will be described. FIG. 1 is a diagram showing the configuration of the document correction system of this embodiment. As shown in FIG. 1, the document correction system 0 includes a document correction device 1 and a user terminal device 2, and the document correction device 1 is configured to be able to communicate with a text generation device 3 via a communication network NW. The document correction device 1 and the user terminal device 2 are also configured to be able to communicate with each other via the communication network NW. The document correction device 1 operates as a server, and the user terminal device 2 operates as a client terminal. The text generation device 3 is an external server device that provides a text generation model. Note that the document correction device 1 may be configured to store a text generation model and to be able to correct a document without using an external device, or a part or all of the processing executed by the document correction device 1 in this embodiment may be executed in the user terminal device 2.

[0047] In this embodiment, the communication network NW is an IP (Internet Protocol) network, but there is no restriction on the type of communication protocol, and further, there is no restriction on the type and scale of the network.

[0048] It is possible to use a general-purpose server computer or a personal computer as the document correction device 1. It is also possible to configure the document correction device 1 using a plurality of computers.

[0049] A smartphone, a tablet terminal, a personal computer, a wearable device, etc. can be used as the user terminal device 2. The user terminal device 2 has an application (a web browser application or a dedicated application) for making a request to the document correction device 1 and receiving a response, and uses a document correction program executed in the document correction device 1 via this application.

[0050] Based on a request sent from an application of the user terminal device 2, the document correction device 1 sends data in a predetermined format as various display information to the application of the user terminal device 2. The data in the predetermined format is, for example, data in a JSON (JavaScript Object Notation) format or an XML format. The application of the user terminal device 2 renders the display data based on the received data, and displays information such as evaluation information and correction suggestions on the display of the user terminal device 2.

[0051] For example, when executing a display process of revision suggestion information and other information on a web browser application of the user terminal device 2, the web browser application first transmits an HTTP (Hypertext Transfer Protocol) request to a web server and receives an HTTP response including the file requested by the HTTP request. The received file is display information including the revision suggestion information, indicates the contents or instructions of the web page to be displayed, and is described using a markup language such as HTML (Hypertext Markup Language). A script, which is a program executed on the web browser application, may be attached to the received file. The web browser application draws (renders) a web page in the display area based on the received file. If a script is attached to the file, the browser executes the script and displays the web page according to the execution result.

[0052] <Hardware configuration> 2A is a diagram showing an example of the hardware configuration of the document correction device 1. The document correction device 1 includes a control unit 101, a storage unit 102, and a communication unit 103 as the hardware configuration.

[0053] The control unit 101 includes one or more processors such as a CPU, and controls the overall operation and processing of the document correction device 1 by executing the document correction program according to the present invention, an OS, browser software, and other applications.

[0054] The storage unit 102 is a hard disk drive (HDD), a read only memory (ROM), a random access memory (RAM), etc., and stores the document correction program according to the present invention and data used when the control unit 101 executes processing based on the program. The control unit 101 executes processing based on the document correction program stored in the storage unit 102, thereby realizing a functional configuration described below.

[0055] The communication section 103 executes communication control with the communication network NW, and performs input required for operating the document editing device 1 and output related to the operation results.

[0056] 2(b) is a diagram showing an example of the hardware configuration of the terminal device 90 (user terminal device 2). Similarly, the terminal device 90 includes, as its hardware configuration, a control unit 901, a storage unit 902, a communication unit 903, an input unit 904, and an output unit 905.

[0057] The control unit 901 of the terminal device 90 includes one or more processors such as a CPU, and controls the overall operation and processing of the terminal device 90. The storage unit 902 of the terminal device 90 is a HDD, ROM, RAM, etc., and stores the above-mentioned applications and data used when the control unit 901 executes processing based on a program. The communication unit 903 of the terminal device 90 controls communication with the network. The input unit 904 of the terminal device 90 is a mouse, keyboard, etc., and inputs operation requests from the user / provider to the control unit 901. The output unit 905 of the terminal device 90 is a display, etc., and displays the results of processing by the control unit 901, etc.

[0058] <Functional configuration> Next, the functional configuration according to this embodiment will be described with reference to Fig. 3. The document correction device 1 includes, as its functional configuration, an acquisition unit 11, an instruction generation unit 12, an evaluation unit 13, and a proposal unit 14. In this embodiment, the evaluation unit 13 functions as the evaluation unit and re-evaluation unit of the present invention. This is a specific implementation of information processing by software stored in the storage unit 102 using hardware (such as the control unit 101). For example, the control unit 101 reads out the document correction program stored in the storage unit 102, expands it in a temporary storage area (such as a RAM) of the storage unit 102, etc., executes it, and controls the communication unit 103, etc., thereby implementing the functions of the document correction device 1.

[0059] The acquisition unit 11 acquires draft information related to the document draft and evaluation information indicating the evaluation of the draft. The draft information is acquired based on the information of the draft transmitted from the user terminal device 2. Specifically, for example, the draft information can be acquired by accepting an operation of designating at least a part of the contents of the draft when the user uploads a file containing the document draft. Note that when the entire draft is to be corrected, the operation of designating the part to be corrected may be omitted. Also, for example, the configuration may be such that the user uploads a part of the document draft to be corrected and the draft information is acquired for that part.

[0060] Here, the user can also use the draft created using the model. In this embodiment, a case will be described in which the same sentence generation model as the sentence generation model used for correcting the draft is used as the model for generating the draft. For example, the document correction device 1 receives advance information from the user terminal device 2 and transmits a draft generation command based on the information to the model, thereby obtaining the draft generated by the model. In addition, a sentence generation model different from the sentence generation model used for correcting the draft may be used as the model for generating the draft.

[0061] For example, when the document is a legal document regarding an agreement with a specific party, the prior information may include information such as the relationship with the party, the purpose of the agreement, the type of the agreement, the requests of the parties regarding the agreement, the content of the agreement, and a template for the legal document. The agreement here refers to a contract, a rule, a regulation, and the like. The relationship with the party refers to the position in the agreement, such as the discloser or recipient of information in a confidentiality agreement. The type of the agreement may include the contract type, atypical contract, or the type of regulation or rule stipulated in the legal document, and the request of the parties may include a preference for a contract that is advantageous to the party or an equal contract, or any other arbitrary request. The prior information may be input in a format in which the user selects from preset options, or may be text information freely written in natural language.

[0062] The advance information may also be term sheet information indicating the contents of a term sheet used in contract negotiations. A term sheet is an arrangement in tabular form of the contents agreed upon with the other party regarding the main items of a contract or the contents of a proposal, and the term sheet information is information including the contents described in the term sheet. The advance information may also be question information based on the questions and question results generated by questioning software that asks questions about the contents to be included in a legal document (e.g., a contract).

[0063] Moreover, the evaluation information is information indicating the evaluation of the draft. In this embodiment, the evaluation unit 13 of the document correction device 1 executes evaluation of the draft, and the result is acquired by the acquisition unit 11 as evaluation information. However, the present invention is not limited to this, and the evaluation information may be acquired from an external device or the user terminal device 2. The process of evaluation regarding the draft and the evaluation information will be described in detail later.

[0064] The acquisition unit 11 of this embodiment further acquires background information on the background of the contract or the like stipulated by the target legal document. The background of the contract or the like includes information such as the relationship with the other party, the purpose of the agreement, the type of the agreement, the requests of the parties regarding the agreement, the contents to be agreed upon, and a template for the legal document. As the background information, information similar to the above-mentioned prior information can be acquired. In this embodiment, evaluation and generation of correction instructions are performed based on such background information.

[0065] That is, for example, when the document is a legal document regarding an arrangement with a specific party, the background information may include information such as the relationship with the party, the purpose of the arrangement, the type of arrangement, the requests of the parties regarding the arrangement, the content of the arrangement, and a template for the legal document. Here, the arrangement refers to a contract, a rule, a regulation, and the like. The relationship with the party refers to the position in the arrangement, for example, the discloser or recipient of information in a confidentiality agreement. The type of arrangement may include the contract type or atypical contract, the type of regulation or rule, and the like stipulated in the legal document, and the requests of the parties may include wishes such as whether the contract should be advantageous to the party or an equal contract, comments received from the other party to the arrangement, and other arbitrary requests.

[0066] The background information may be input in a format in which the user selects from preset options, or may be text information freely written in natural language. The background information may be generated by a text generation model that receives a legal document and an extraction command to extract background information from the legal document. For example, the extraction command is a command to estimate a contract type to which the input legal document corresponds from among multiple predetermined contract types.

[0067] The command generating unit 12 generates a revision command for the draft based on the draft information and evaluation information acquired by the acquiring unit 11, and transmits the generated command to the writing generation model. In this embodiment, input is made to the writing generation model by transmitting a revision command to the writing generation device 3 that provides the writing generation model. The command generating unit 12 in this embodiment generates a revision command as a sentence in a natural language, using the draft information and evaluation information. The process of generating a revision command will be described in detail later.

[0068] The evaluation unit 13 functions as a re-evaluation unit of the present invention, and receives a proposed revision of the draft from the text generation device 3 as an output of the text generation model in response to the revision command. Then, it obtains re-evaluation information indicating an evaluation of the proposed revision, and judges whether or not the evaluation satisfies a preset criterion. In this embodiment, the evaluation unit 13 (re-evaluation unit) performs an evaluation of the revision proposal and generates re-evaluation information as a result, but it is also possible to transmit the revision proposal to an external evaluation device and obtain re-evaluation information from the evaluation device as the evaluation result.

[0069] If the evaluation satisfies the criteria, the evaluation unit 13 (re-evaluation unit) causes the proposal unit 14 to transmit revision proposal information. On the other hand, if the evaluation does not satisfy the criteria, the evaluation unit 13 instructs the instruction generation unit 12 to generate a revision command for the revision proposal based on the revision information and re-evaluation information for the revision proposal. The instruction generation unit 12 then transmits the revision command to the sentence generation model, which then generates a revision proposal for the revision proposal.

[0070] The evaluation unit 13 (reevaluation unit) of this embodiment is configured to repeat obtaining and evaluating a revision proposal until the evaluation of the revision proposal satisfies a predetermined criterion or a termination condition is satisfied. As the predetermined criterion, for example, it is possible to set that the risk level for each of the issues mentioned below contained in the reevaluation information is equal to or lower than a predetermined risk level. As the termination condition, for example, it is assumed to set an upper limit on the number of repetitions or a lower limit on the number of characters changed by the revision. The details of the reevaluation process will be described later.

[0071] The suggestion unit 14 transmits the revision suggestion information based on the output of the sentence generation model in response to the revision command. In this embodiment, in accordance with the determination result by the evaluation unit 13 (re-evaluation unit), display information including the revision suggestion information is transmitted to the user terminal device 2, whereby the user terminal device 2 displays the revision suggestion.

[0072] The suggestion unit 14 of this embodiment generates revision proposal information including sentences in a natural language to assist in revising the draft based on the output of the sentence generation model acquired by the evaluation unit 13 (re-evaluation unit). Details of the revision proposal information and the display contents on the user terminal device 2 will be described later.

[0073] <Processing Procedure> Next, referring to FIG. 4, the process from creating a draft of a contract to proposing a revision in the document revision system of this embodiment will be described in detail. FIG. 4 is a sequence diagram showing an example of a processing procedure by the document revision device 1, the user terminal device 2, and the text generation device in the document revision system of this embodiment. Note that the process shown here is an example, and omissions and modifications may be made without changing the gist of the present invention. In addition to contracts, documents that may be targeted include other legal documents such as regulations, and other documents. In the following example, both the creation of a draft and the creation of a revision proposal described below are performed using the same text generation model, but they may be created using different models.

[0074] (1) Drafting Steps S401 to S406 are processes related to creating a draft. Note that this process is not essential, and the processes from step S407 onwards may be performed using a draft created by the user himself / herself, a draft generated using an external machine learning model, or a draft contract received from a party to whom a contract is to be concluded.

[0075] First, in step S401, the user terminal device 2 accepts input of advance information from the user and transmits it to the document editing device 1. As advance information, the relationship with the other party to whom the contract is to be concluded, the purpose of the contract, the type of the contract, the requests of the parties regarding the contract, and the like are assumed. Specifically, when a confidentiality agreement is concluded when presenting information to a business partner, examples of the relationship with the other party include "discloser of information," the type of the contract is the contract type "confidentiality agreement," and the requests of the parties include arbitrary requests such as "I want to make a strong contract (advantageous to my position)." In addition, it is preferable that the names or titles of the contracting parties and the designations in the contract (Party A, Party B), etc. are also input as advance information. In addition, term sheet information indicating the contents of a term sheet used in contract negotiations, and question information based on questions about the contents to be included in the legal document and the answers to those questions may be further acquired as advance information.

[0076] The input of the advance information is typically assumed to be made by the user selecting from options, but may also be made by the user freely writing text in a natural language.

[0077] Next, in step S402, the command generator 12 generates a creation command for making the sentence generation model create a draft based on the prior information. Since the sentence generation model of this embodiment is a conversational model that receives a sentence in a natural language as an input and generates a sentence as a response, the creation command is generated as a sentence in a natural language.

[0078] More specifically, the command generating unit 12 can generate a creation command by generating a sentence that combines a prepared instruction sentence and a wording specified based on the prior information. Also, for example, a configuration may be adopted in which an instruction sentence is prepared in advance for each option of the prior information and stored in the storage unit of the document modification device 1, an instruction sentence is selected from the prior information according to the contract type, and the command generating unit 12 generates a sentence that combines the instruction sentence and the wording specified based on the prior information as a generation command.

[0079] More specifically, when the prior information is input by selection, a word corresponding to the selected prior information is identified. For example, a corresponding word is set in advance for each option of the prior information, so that the word corresponding to the selected prior information can be identified. Then, the command generating unit 12 generates a creation command based on those words and a command statement separately registered in advance in the storage unit of the document correction device 1. On the other hand, when the advance information is input as free text, the creation command may be generated using the input advance information and a command statement prepared in advance.

[0080] Here, it is preferable to store a character string describing a rule for document creation according to the prior information as a word corresponding to the prior information. For example, in a legal document, the legal meaning may differ between describing an exception in a sentence of a provision and describing a disclaimer separately after the sentence. By combining words that specify rules for such a description method according to the prior information, an appropriate legal document can be created. Note that, among a plurality of document creation rules corresponding to each piece of prior information, the document correction device 1 may determine a document creation rule to be included in the creation command based on the prior information, or a configuration may be adopted in which a plurality of document creation rules are included in the creation command and a statement to use an appropriate document creation rule from the plurality of document creation rules based on the prior information is included in the creation command, thereby determining a document creation rule to be used by the text generation model.

[0081] As the instruction sentence, for example, "Please create a document based on the following conditions" or "Enter the advance information indicating the arrangement of the contract. Please create an appropriate contract sentence based on the following rules" can be stored in the storage unit of the document correction device 1 in advance. Alternatively, an instruction sentence can be prepared for each contract type as an option for the advance information, and information corresponding to the advance information can be included in the instruction sentence, such as "Please create a confidentiality agreement based on the following conditions." Then, by generating a sentence in which the instruction sentence is followed by a word based on the advance information, a creation command can be generated to instruct the sentence generation model to create a draft.

[0082] When the creation command is generated, the process proceeds to step S403, where the command generation unit 12 transmits the generated creation command to the text generation device 3. The transmission of the creation command to the text generation device 3 in step S403 corresponds to the transmission of the creation command to the text generation model. When the text generation device 3 receives the creation command, it inputs the creation command to the text generation model. This causes the text generation model to output a draft of the contract (step S404).

[0083] The writing generation device 3 transmits the draft output by the writing generation model to the document correction device 1 in step S405. Then, in step S406, the document correction device 1 transmits the draft to the user terminal device 2. By the above process, the user can obtain a draft of the desired contract by only inputting the advance information. Note that step S406 and steps S407 to S410 described next may be omitted, and the process may be performed consistently up to the revision of the draft without waiting for an instruction from the user.

[0084] (2) Draft evaluation Next, the evaluation process of the draft will be described. Steps S407 to S409 are processes related to the evaluation of the draft. This process is for acquiring evaluation information indicating the evaluation of the draft. In this embodiment, as described below, the evaluation unit 13 evaluates the draft, but the evaluation information may be acquired by having an external device evaluate the draft, or the evaluation information may be acquired by receiving the evaluation information from the user terminal device 2 together with the draft information.

[0085] In step S407, the user terminal device 2 transmits an evaluation request to the document editing device 1. The evaluation request includes draft information and background information related to the draft. The draft information transmitted here is information including at least the contents of the draft to be evaluated, and in this embodiment, a document file describing the draft of the contract is uploaded. The background information is information related to the background of the document. For example, the background information includes the relationship with the other party in the arrangement indicated by the target legal document, the type of the arrangement, the requests of the parties regarding the arrangement, etc. The background information can be information with the same content and format as the advance information in draft creation described above.

[0086] In the document correction device 1, the acquisition unit 11 receives the evaluation request, and the evaluation unit 13 evaluates the draft based on the draft information and the background information. The draft may be evaluated by any method, such as evaluation by a machine learning model or evaluation by a rule base. As an example, in this embodiment, a method of evaluating clauses based on rules in accordance with the background information is used.

[0087] In particular, in this embodiment, the contract type and contractual position of the background information and the title of each clause in the draft are used to evaluate the content of each clause and the relationship between multiple clauses. Here, multiple clauses refer to a group of multiple clauses that define a set of regulations. For example, within a group, the presence or content of clause B is determined according to the content of clause A, and clause C is confirmed based on the result. By specifying that the evaluation process branches according to the content, the relationship between multiple clauses can be evaluated on a rule-based basis.

[0088] The draft is evaluated based on whether it contains unnecessary clauses (or clauses that are disadvantageous to the party in relation to the other party in the background information), whether there are clauses that should be added, whether the content of the clauses is appropriate, etc.

[0089] In this embodiment, the issues raised in the draft are identified by linking the issues with the above rules and registering them in advance in the storage unit of the document correction device 1. Specifically, for each issue raised, the above-mentioned evaluation rule, the type of the issue (either deletion, addition, or content modification of a clause), the details of the issue, and the risk level are stored in advance in the storage unit.

[0090] The comments are statements proposing modifications to the draft or pointing out problems, such as "Is it necessary to stipulate a consultation clause?" or "Isn't the period for which confidentiality obligations are imposed set longer than necessary?". In addition, the comments may include explanatory text about the clause related to the comment or template information for that clause. The risk level is information indicating the degree of risk assumed for each comment. The risk level may be fixed (unchangeable) on the system side, or may be changeable by user input.

[0091] Examples of risk level settings are as follows. Issues that are likely to become problems after the contract and that are related to important rights and obligations of the company can be set to risk level "A". Examples include "intellectual property ownership", "scope of damages", and "definition of confidential information". Issues that are unlikely to become problems even if they are missing can be set to risk level "C". Examples include "confidential information exceptions" and "intermediate reporting obligations". Issues that do not fall under A and C among multiple groups can be set to risk level "B". Note that risk levels may be set for each issue, or may be risks determined based on the wording of the clause. For example, risk levels may be set based on a judgment of whether the company is favorable or unfavorable based on the wording of the clause.

[0092] As described above, the evaluation unit 13 executes the evaluation process and creates evaluation information indicating the evaluation of the draft. The evaluation information includes, for each of one or more issues identified in the above process, the clause in the draft corresponding to the issue, the details of the issues, and a risk level. When obtaining evaluation information from an external device or the user terminal device 2, evaluation information including, for each issue, the clause in the draft corresponding to the issue, the details of the issues, and a risk level is also obtained. As described above, the details of the issues include information written in natural language, and this description corresponds to the evaluation statement in the present invention.

[0093] The contract may be evaluated using a text generation model. The text generation model may be the same as or different from the text generation model used for draft creation or the text generation model used for revision. For example, the document revision device 1 acquires draft information and background information, reads out evaluation rules to be used for contract evaluation that are stored in advance based on the background information, generates evaluation commands based on the draft information and evaluation rules according to the background information, transmits the evaluation command to the text generation device 3, and acquires the evaluation result (evaluation information) of the contract generated by the text generation device 3. The evaluation command is generated as a text in a natural language. This is expected to reduce the effect of the influence on the evaluation due to variations in writing and differences in expression of the text. In addition, it is expected that an appropriate evaluation can be performed by using an evaluation rule (e.g., an evaluation rule set for each contract type) read out based on background information (e.g., a contract type) from among a plurality of evaluation rules.

[0094] Furthermore, evaluation by the sentence generation model and evaluation by the rule base may be performed simultaneously. In this case, if the evaluation by the sentence generation model and the evaluation by the rule base are different, it is preferable to perform processing to prioritize the evaluation by the rule base. This makes it possible to guarantee a minimum evaluation by the rule base even if there is uncertainty in the evaluation by machine learning. Note that the document correction device 1 may determine an evaluation rule to be included in the correction command based on the background information from among a plurality of evaluation rules corresponding to each background information, or a configuration may be adopted in which the evaluation rule to be used by the sentence generation model is determined by including a plurality of evaluation rules in the evaluation command and including a statement to use an appropriate rule from the plurality of rules based on the background information in the evaluation command.

[0095] When the evaluation unit 13 finishes evaluating the draft, in step S409 the evaluation unit 13 transmits evaluation information to the user terminal device 2. When the user terminal device 2 receives the evaluation information, the evaluation information is subjected to display processing, and the processing result is displayed on the display.

[0096] Fig. 5 shows an example of an evaluation screen displayed on the user terminal device 2 as a result of the evaluation information display process. The evaluation screen W5 displays an overview of the document draft and an overview of the evaluation results at the top of the screen. The contents of the draft identified by the draft information are displayed on the left side of the screen. In addition, a "Edit read contents" button is provided, and if there is an error in the contents identified from the draft information, the contents can be edited by selecting this button.

[0097] The right side of the screen displays the evaluation results based on the evaluation information. For each issue, the type of issue (whether it is a deletion, addition, or modification of a clause), an explanation, and a template for the applicable clause are displayed.

[0098] For each pointed out item, a differently shaped point mark W51 is attached for each type of point, and a serial number for each type is displayed. Similar point marks W51 are also displayed with the serial number in the corresponding part of the pointed out item in the draft on the left side of the screen, so that the user can recognize the position in the draft that corresponds to the pointed out item, and the corresponding part in the draft is highlighted or the like. In the example of Figure 5, circles indicate points for revision of the contents of clauses, and triangles indicate points for missing clauses.

[0099] The indication mark W51 is displayed in a different color depending on the risk level. By operating the risk filter operation section W52, the indications to be displayed can be filtered according to the risk level. In FIG. 5, the indication is displayed when the risk level is "B" or higher, that is, indications of A or B are displayed.

[0100] Additionally, a collective correction button W53 and an individual correction button W54 are displayed together with the evaluation results. When the user selects one of these buttons, a correction request is sent in step S410 in Fig. 4. The range of correction instructions varies depending on the button selected.

[0101] There are three types of batch correction buttons W53: "Create revision proposals for all items at once," "Create revision proposals for item A," and "Create revision proposals for items AB." When "Create revision proposals for all items at once" is selected, a correction request is sent for all issues. When "Create revision proposals for item A" is selected, a correction request is sent for issues with a risk level of A. When "Create revision proposals for items AB" is selected, a correction request is sent for issues with a risk level of A and issues with a risk level of B. When the individual correction button W54 displayed for each issue is selected, a correction request is sent for that issue.

[0102] In addition, in this embodiment, when the collective correction button W53 or the individual correction button W54 is selected, a request for correction from the parties concerned is further accepted. For example, for a problem that has multiple possible correction policies, the user can select one of them to accept a request for correction. Alternatively, when a correction request is made for multiple problems using the collective correction button W53, a rough policy such as "bullish (highly favorable to the company)", "neutral", or "bearish (more favorable to the company than before the correction, but more favorable to other companies)" may be selected. At this time, a correction command may be generated to generate only a correction proposal for the policy selected by the user, or a correction command may be generated to generate a correction proposal for all policies. Such a request may also be input by free text.

[0103] (3) Corrective action Next, the process of correcting the draft will be described. When a correction request is received as described above, the acquisition unit 11 acquires the draft information and the evaluation information in step S410. The acquisition unit 11 of this embodiment further acquires the above-mentioned background information and information on requests for correction sent together with the correction request in step S410. In this embodiment, the draft received in step S405, the background information received in step S407, and the evaluation information generated by the evaluation unit 13 in step S408 are stored in the storage unit, and the acquisition unit 11 acquires the draft information, the evaluation information, and the background information based on them. Note that when the draft is created and evaluated by an external device, the acquisition unit 11 may acquire the draft information and the evaluation information from the user terminal device 2 or the external device.

[0104] In addition, when the correction request instructs to correct only a part of the draft, not the entire range of the draft, the draft information does not need to include the contents of the entire draft, and only the part related to the subject of the correction may be included in the draft information. However, for example, when there is a group of multiple clauses that define a set of regulations, and corrections are made to the pointed out matters regarding the clauses included in the group, it is preferable that the draft information includes the contents of the entire multiple clauses of the group, not only the single clause that corresponds to the pointed out matters.

[0105] Next, in step S411, the command generating unit 12 generates a revision command for causing the writing generation model to generate a proposed revision of the draft, based on the draft information, evaluation information, background information, and information on requests from the parties regarding revisions acquired by the acquiring unit 11. Since the writing generation model of this embodiment is a conversational model that receives a sentence in a natural language as input and generates a sentence as a response, the revision command is generated as a sentence in a natural language.

[0106] The command generation unit 12 of this embodiment generates, as a correction command, a sentence in which instructions regarding corrections are described for each clause corresponding to the pointed out matter. In particular, when there are multiple pointed out matters in one clause or a group of clauses that defines a set of regulations, if a correction command is generated for each pointed out matter, there is a possibility that multiple contradictory correction proposals will be generated. Therefore, the command generation unit 12 of this embodiment generates a sentence of a correction command for each clause or group of clauses corresponding to the multiple pointed out matters as a correction command for a clause or group of clauses in which multiple pointed out matters exist.

[0107] The generation of the correction command will be specifically described below. First, for background information, when background information is input by selection, a word corresponding to the selected background information is identified. For example, by setting a corresponding word in advance for each option of background information, it is possible to identify a word corresponding to the selected background information.

[0108] Similarly, when request information is input by selection, first, a word corresponding to the selected request is identified. For example, by setting in advance corresponding words for each combination of the target pointed out matter and the request option, it is possible to identify a word corresponding to the selected request for each pointed out matter.

[0109] Then, the command generating unit 12 generates a correction command based on those words, the draft information, and a command statement separately registered in advance in the storage unit of the document correction device 1. On the other hand, when the background information and the request are input as free text, the correction command may be generated using the input background information and a command statement prepared in advance.

[0110] Here, as in the case of generating a creation command in draft creation, it is preferable to store a character string describing a rule for document creation according to the background information as a word corresponding to the background information. For example, in a legal document, the legal meaning may differ between describing an exception in a sentence of a provision and describing a disclaimer separately after the sentence. By combining words that specify rules for such a description method according to the background information, an appropriate legal document can be created. Note that, among a plurality of rules corresponding to each background information, the document correction device 1 may determine a rule to be included in the correction command based on the background information, or a configuration may be adopted in which a plurality of rules are included in the correction command and a statement to use an appropriate rule from the plurality of rules based on the background information is included in the correction command, thereby determining a rule to be used by the text generation model.

[0111] As an instruction sentence, for example, "As a result of reviewing the above draft, the following points were made. Please prepare a revision proposal based on the following conditions, taking into account the points made," or "As a result of reviewing the above draft, the following points were made. Please prepare an appropriate contract document based on the following rules, taking into account the points made," etc., can be stored in advance in the storage unit of the document correction device 1. Then, a sentence that combines the contents of the draft, the instruction sentence, and words based on the background information and the request can be generated as a creation command for instructing the text generation model to create a draft.

[0112] When the revision command is generated, the process proceeds to step S412, where the command generation unit 12 transmits the generated revision command to the sentence generation device 3. The transmission of the revision command to the sentence generation device 3 in step S412 corresponds to the transmission of the revision command to the sentence generation model. The revision commands generated as described above for each clause or for each group of clauses may be transmitted in multiple batches. For example, the revision command may be configured to transmit the instruction portion first, followed by words corresponding to the points raised or requests. Alternatively, the revision command may be configured to determine whether to transmit the command all at once or in multiple batches depending on the number of characters in the revision command.

[0113] When the writing generation device 3 receives the revision command, it inputs the revision command to the writing generation model. As a result, the writing generation model outputs a revision proposal for the draft (step S413). In this embodiment, the evaluation unit 13 (re-evaluation unit) acquires a revision proposal for each pointed out item. Note that the instruction generation unit 12 may generate a revision command instructing to propose multiple revision proposals for one pointed out item in step S411, and the evaluation unit 13 (re-evaluation unit) may acquire multiple revision proposals for some or all of the pointed out items in step S413.

[0114] Furthermore, a revision command may be sent to the sentence generation model to generate revision reasons based on the evaluation information, and the revision reasons may be obtained in addition to the revision proposal. Furthermore, revision reasons for one's own company (or for one's own client) and revision reasons for the other party may be generated and obtained. In contract negotiations, one's own company and the other party make repeated revisions to each other, and at this time, at least one of revision reasons for explanation within the company and revision reasons for explanation outside the company is often written down. Writing down revision reasons requires a high level of expertise, but the above configuration can support even users without specialized knowledge to write down revision reasons.

[0115] (4) Reevaluation process In step S414, the sentence generation device 3 transmits the proposed revision, which is the output of the sentence generation model, to the document correction device 1. In the document correction device 1, reevaluation is performed by the evaluation unit 13 (reevaluation unit) in step S415. The evaluation unit 13 (reevaluation unit) acquires the proposed revision, and reevaluates the proposed revision in a procedure similar to that of the evaluation process described above. Then, reevaluation information indicating the evaluation of the proposed revision is generated in the same manner as the evaluation information described above. In other words, the reevaluation information is information indicating the evaluation of the proposed revision, and the information included in the reevaluation information is the same items as those in the evaluation information described above.

[0116] In this case, the reevaluation may be performed not on the entire draft, but only on the parts related to the points raised earlier. Specifically, the clause or group of clauses indicated in the proposed amendments may be reevaluated, and the reevaluation of the other parts may be omitted. This is expected to have the effect of improving the processing speed.

[0117] The evaluation unit 13 (reevaluation unit) then judges whether the evaluation satisfies a preset criterion based on the reevaluation information. Specifically, the evaluation unit 13 checks the risk levels of the identified items in the reevaluation information, and judges that the evaluation satisfies the criterion if the risk levels of all the identified items are equal to or lower than a predetermined risk level.

[0118] If the reevaluation of the revision proposal does not satisfy the criteria, i.e., if there is an issue with a risk level exceeding a predetermined risk level, the process returns to step S411 and the processes from generation of the revision command to reevaluation in step S415 are performed again. In this case, in the second and subsequent revision command generation processes, revision proposal information is used instead of draft information, and reevaluation information is used instead of evaluation information, and revision commands related to the revision proposal are generated in the same procedure as the generation of the revision commands described above.

[0119] As a general rule, loop processing is performed until a preset criterion is met, but if the number of repetitions becomes extremely high or it becomes impossible to exit the loop, there is a concern that the processing load will increase. Therefore, in this embodiment, an upper limit on the number of times the loop process is performed is set as the termination condition, and even if the reevaluation does not satisfy the criteria, if the termination condition is satisfied, the repetition of the reevaluation is terminated, the loop process is terminated, and the process proceeds to step S417. In addition, other termination conditions may be set, for example, when the number of changed characters is equal to or less than a certain number when comparing the draft before and after the revision. This makes it possible to prevent the repetition of a situation in which only minor revisions are made.

[0120] On the other hand, if the evaluation of the modification proposal satisfies the preset criterion, the process enters into a loop break process (break process) in the sequence diagram of Fig. 4. In step S416, the proposing unit 14 generates modification proposal information and ends the loop process (Loop process).

[0121] In the interruption process, the suggestion unit 14 generates revision proposal information. The revision proposal information includes, for each of the issues raised in the reevaluation, a clause in the draft corresponding to the issue, the details of the issues, a risk level, and the revision proposal created in the most recent step S413.

[0122] Then, in step S417, the suggestion unit 14 transmits the revision proposal information generated in step S416 to the user terminal device 2. The user terminal device 2 displays the display processing result of the revision proposal information on the display. This allows the user to receive a proposal for revising the draft.

[0123] The above-mentioned procedure of the reevaluation process will be further explained with reference to the flowchart in Fig. 6, particularly with regard to the conditions for repetition. When the document correction device 1 receives the proposed revision, which is the output of the sentence generation model, in step S414 in Fig. 4, the evaluation unit 13 (reevaluation unit) acquires this proposed revision in step S501.

[0124] Then, in step S502, a reevaluation is performed (corresponding to step S415 in FIG. 4), and in step S503, it is determined whether the evaluation of the revision proposal satisfies a preset criterion. As described above, in this embodiment, the risk levels of the pointed out items in the reevaluation information are confirmed, and it is determined that the criterion is met if the risk levels of all the pointed out items are equal to or lower than a predetermined risk level.

[0125] If the criteria are not met, the process proceeds to step S505, where it is confirmed whether the number of loops (number of revisions) has reached the upper limit. If the upper limit has not been reached ("Y" in step S505), the process proceeds to step S506, where the evaluation unit 13 (re-evaluation unit) causes the instruction generation unit 12 to generate and transmit a revision instruction again, increments the loop count counter, and the process returns to step S501.

[0126] If the criteria are met in step S503, or if the number of revisions reaches the upper limit in step S505, the process proceeds to step S504, where the evaluation unit 13 (re-evaluation unit) causes the proposal unit 14 to generate revision proposal information (corresponding to step S416 in FIG. 4). The proposal unit 14 then transmits the revision proposal information to the user terminal device 2 (corresponding to step S417 in FIG. 4), and the process ends. Note that the above processing procedure is an example, and may be arbitrarily changed, for example, by switching the judgment order of step S503 and step S505.

[0127] (5) Correction proposal screen Next, a correction proposal screen displayed on the user terminal device 2 as a result of the display process of the correction proposal information will be described with reference to Fig. 7. Fig. 7 is a display example of the correction proposal screen in this embodiment. The correction proposal screen W7 in this embodiment is displayed in a similar configuration to the evaluation screen W5 shown above, and the pointing out mark W71 and the risk filter operation section W72 are similar to the pointing out mark W51 and the risk filter operation section W52 in the evaluation screen W5, so their description will be omitted.

[0128] The difference from the evaluation screen W5 is mainly in the display content on the right side of the screen, especially the part related to "revision proposals." The revision proposal screen W7 includes revision proposals W73 for each pointed out item as a display based on the revision proposals included in the revision proposal information. The revision proposals W73 display the above-mentioned revision proposals and display the text so that it can be copied. It is also preferable to highlight the changes from the draft so that the user can easily recognize them. This allows the user to obtain the contents and revision proposals for each pointed out item, and even users who are not familiar with legal knowledge can make revisions to legal documents on their own.

[0129] In addition, when multiple suggested revisions are obtained for a problem, the suggested revision information contains multiple suggested revisions for the problem, so it is preferable to display multiple suggested revisions W73 for the problem on the suggested revision screen W7 as well so that the user can select from them.

[0130] Note that the method of outputting the revision proposal information is not limited to displaying the revision proposal screen W7 described above, and for example, the suggestion unit 14 may transmit a document-format file of the entire draft to which revision proposals have been applied to at least some of the pointed out items to the user terminal device 2. In addition, the user may be prompted to select whether or not to reflect the revision proposals displayed on the revision proposal screen W7, or which revision proposals to reflect, and the suggestion unit 14 may further transmit a document-format file in which the entire draft has been revised based on the result to the user terminal device 2.

[0131] As described above, the document revision system of this embodiment can support users who do not have specialized knowledge to make revisions to draft legal documents such as contracts. Furthermore, the quality of the draft revision can be improved by reevaluating the revision proposal and issuing a command to create another revision proposal based on the result of the reevaluation.

[0132] In addition, by generating commands in natural language text, it is possible to create revision proposals using a conversational text generation model that takes text as input and generates answer text. This makes it possible to have the model generate revision proposals that take into account various conditions such as the background and requests of the contract, and to provide revision proposals for drafts that are more in line with the user's situation and wishes.

[0133] Furthermore, a revision command may be sent to the sentence generation model to generate revision reasons based on the evaluation information, and the revision reasons may be included in the revision proposal information. Furthermore, revision reasons may be generated as revision reasons for one's own company (or for one's own client) and revision reasons for the other party. In contract negotiations, one's own company and the other party make repeated revisions to each other, and at this time, at least one of revision reasons for explanation within the company and revision reasons for explanation outside the company is often written down. Writing down revision reasons requires a high level of expertise, but the above configuration can support even users without specialized knowledge to write down revision reasons. [Explanation of symbols]

[0134] 0: Document correction system 1: Document editing device 2: User terminal device 3: Sentence generation device 11: Acquisition part 12: Instruction generation section 13: Evaluation section 14: Proposal Department 90: Terminal equipment 101: Control unit 102: Storage section 103: Communications Department 901: Control unit 902: Storage section 903: Communications Department 904: Input section 905: Output section NW: Communication network W5: Evaluation screen W51: Pointing out mark W52: Risk filter operation section W53: Bulk edit button W54: Individual edit button W7: Correction Suggestion Screen W71: Pointing out mark W72: Risk filter operation section W73: Correction proposal

Claims

1. A computer, This involves making suggestions for amendments to a legal document by evaluating each of several prescribed units contained within the legal document, Sending a command to the document generation model to generate a revised document based on at least some of the predetermined units of the plurality of predetermined units and the content of the proposed revisions relating to at least some of the predetermined units, Receiving the aforementioned revised document from the aforementioned document generation model, A method for correcting a document, including outputting the corrected document that was received.

2. The computer further includes receiving a selection from the user for one of the plurality of predetermined units, The document modification method according to claim 1, wherein the command causes the document generation model to generate the modified document based on a predetermined unit selected by the user and the content of the modification proposal relating to the predetermined unit selected by the user.

3. The computer further includes receiving input from the user of a modification request relating to a predetermined unit selected by the user, The document modification method according to claim 2, wherein the instruction causes the document generation model to generate the modified document based on the modification request.

4. Multiple modification suggestions are made with respect to a predetermined unit selected by the user, The method for modifying a document according to claim 3, wherein the input of the modification request is performed by the user selecting one of the modification proposals from among the plurality of modification proposals.

5. The method for correcting a document according to claim 3, wherein the input of the correction request is performed by the user's text input.

6. The computer The system accepts instructions for batch modification of at least some of the predetermined units of the aforementioned plurality of predetermined units, The further includes accepting a selection from the user for one of the aforementioned plurality of predetermined units, When the instruction for batch correction is received, the command causes the generation of a corrected document based on the predetermined unit subject to the batch correction and the content of the proposed corrections relating to the predetermined unit subject to the batch correction, The document modification method according to claim 1, wherein, when the selection is made by the user, the command causes the document generation model to generate the modified document based on the predetermined unit selected by the user and the content of the modification proposal relating to the predetermined unit selected by the user.

7. The computer The aforementioned revised document will be re-evaluated, A method for correcting a document according to any one of claims 1 to 6, further comprising generating the corrected document and re-evaluating the corrected document until the result of the re-evaluation meets a predetermined standard.

8. The document generation method according to any one of claims 1 to 6, wherein the legal document is generated by the document generation model.

9. The document generation method according to any one of claims 1 to 6, wherein the instruction causes the document generation model to further generate the reasons for the revision in the revised document.

10. The document generation method according to claim 9, wherein the reason for revision includes a reason for revision for internal use and a reason for revision for external use.

11. Proposing revisions to a legal document by performing an evaluation with respect to each of a plurality of predetermined units contained in the legal document, Sending a command to the document generation model to generate a revised document based on at least some of the predetermined units of the plurality of predetermined units and the content of the proposed revisions relating to at least some of the predetermined units, Receiving the aforementioned revised document from the aforementioned document generation model, A program that causes a computer to output the received revised document.

12. A proposal unit that makes a proposal for amendment to a legal document by performing an evaluation with respect to each of a plurality of predetermined units contained in the legal document, A transmission unit that sends a command to a document generation model to generate a revised document based on the content of the proposed revisions for at least some of the plurality of predetermined units and for at least some of the predetermined units, A receiving unit that receives the aforementioned revised document from the document generation model, A document correction device comprising an output unit that outputs the received corrected document.

Images