Information processing method

Abstract

An information processing method according to an embodiment of the present invention comprises: acquiring a correction policy for each of at least one input unit of a first legal document; acquiring at least one corrected input unit that has been corrected, by using a natural language processing model and at least one prompt generated on the basis of at least an input unit and the correction policy for the input unit; and outputting the at least one corrected input unit.

Description

Technical Field

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

Background Art

[0002] Conventionally, for example, there is a system that supports a user in reviewing a document. The user reviews the document while referring to the results of the document review output by the system. Therefore, the user's workload is large. There is room for further improvement in reducing the user's workload.

Summary of the Invention

Problems to be Solved by the Invention

[0003] One embodiment of the present invention has been made in view of the above circumstances, and is to reduce the workload of a user in a system that supports the user in reviewing a document.

Means for Solving the Problems

[0004] The information processing method according to the embodiment acquires a correction policy for each of at least one input unit of a first legal document, and uses at least one prompt generated based on at least the input unit and the correction policy for the input unit and a natural language processing model to acquire at least one corrected input unit, and outputs the at least one corrected input unit.

Brief Description of the Drawings

[0005]

Figure 1

Figure 2

Figure 3

Figure 4A

Figure 4B

Figure 5

Figure 6

Mode for Carrying Out the Invention

[0006] An embodiment will be described below with reference to the drawings.

[0007] In this specification, the "part" does not simply mean a physical means, but also includes the case where the function of the "part" is realized by software. Also, even if the function of one "part" or device is realized by two or more physical means, devices, or software, or the functions of two or more "parts" or devices are realized by one physical means, device, or software, it is also acceptable.

[0008] FIG. 1 is a diagram showing an outline of an example of processing in a modification proposal system 100 according to an embodiment.

[0009] The modification proposal system 100 of the present embodiment is an information processing system realized by a modification proposal program, and is an information processing system that proposes modifications to the contents of target items of a contract document, which is a document to be supported.

[0010] For example, when a contract is concluded, an agreement is reached between the contracting parties. When reaching an agreement between the contracting parties, one or both of the contracting parties may inspect and modify the contract document. As an example, in the case of a contract between enterprises, for example, the legal department in charge of contract inspection inspects the contents of the contract document and modifies it as necessary. Note that the inspection of the contract document may also be referred to as confirmation, review, or review.

[0011] The legal documents to be processed by the amendment proposal system 100 of this embodiment are, for example, documents containing legal content that generates a predetermined legal effect within the document, and include criteria from a predetermined perspective such as being preferable or not preferable in terms of legal content or form. For example, it includes contract documents, application forms, memorandums, internal regulations, policies, etc. In this embodiment, a contract document will be used as an example for explanation. Also, legal documents may be referred to as supported documents as appropriate.

[0012] The legal documents for which amendment proposals are made by the amendment proposal system 100 of this embodiment are processable by a computer and are, for example, documents in electronic media (electronic documents). They are electronic documents created by a predetermined electronic document creation software or electronic documents obtained by digitizing a contract document in paper media using a predetermined image analysis technology (for example, OCR (Optical Character Recognition) technology).

[0013] The amendment proposal system 100 of this embodiment provides a document creation support service. The document creation support service includes, for example, performing a document review process on a supported document on a web browser and providing the result to the user, automatically correcting the document using the result of the document review process and presenting the result as a correction candidate (amendment proposal process), executing document editing in response to an instruction from the user, saving or providing the edited document to the user, editing additional information (for example, meta information, comment information, chat information, format information, etc.) associated with the supported document, creating a new document (including copies), and is a service including at least any one of these.

[0014] In particular, the amendment proposal process by the amendment proposal system 100 of this embodiment is executed using an artificial intelligence model that uses natural language. Here, the artificial intelligence model that uses natural language is, for example, a natural language processing model represented by GPT (Generative Pre-trained Transformer), etc. This natural language processing model takes a natural language text called a prompt as input and outputs a natural language text automatically generated according to the prompt.

[0015] As the natural language processing model used in the amendment proposal system 100 according to this embodiment, for example, the natural language processing models disclosed in https: / / arxiv.org / abs / 2203.02155, https: / / openai.com / blog / chatgpt / can be used.

[0016] In addition, the amendment proposal system 100 of this embodiment automatically generates a prompt (a natural language character string for querying the natural language processing model) input to the natural language processing model in the amendment proposal process, based on at least one input unit generated from the document to be supported and the amendment policy for the input unit. Here, the input unit is, for example, a sentence in units of articles, paragraphs, and items, and can be generated by dividing the document to be supported according to a predetermined standard. The amendment policy is information indicating how to amend the input unit, and is composed of natural language such as "Delete the phrase '○○'.", "Always include the phrase '××'.", "Make it a mandatory provision.", "Make it an instructive clause.", etc.

[0017] The correction policy can be obtained by referring to rules that define combinations of, for example, the type of text (e.g., the type of each text such as a text defining the purpose, a text defining the source of rights, a text defining the period, etc.) and the correction policy in a plurality of patterns. Also, these rules are created by, for example, lawyers who are experts and are managed by a database. The combinations of the text type and the correction policy managed by the database can be added or modified at any timing as necessary. Note that the correction policy can also be obtained by, for example, a learned model that takes an input unit as input and outputs a correction policy. Also, it can be obtained by a combination of processing using a learned model and rule-based processing using a database. Also, for example, the database includes information in which a plurality of sample texts and a plurality of correction policies are associated. The correction proposal system 100 may obtain a correction policy for each of at least one input unit based on the similarity between the at least one input unit and the plurality of sample texts. Note that the sample text can include the text before correction and the text after correction.

[0018] In FIG. 1, as an example of the correction proposal process, an example including an input unit generation process, a classification process, a prompt creation process as a preprocess, a natural language process, and a corrected text presentation process is shown. In the input unit generation process, for example, a clause splitting process using a clause classifier is executed. In the classification process, for example, the type of the clause obtained by the splitting process is classified by a classifier. In the prompt creation process, for example, a prompt including an input unit and a correction policy is created by referring to a database. In the natural language process, for example, a corrected text is obtained using a prompt including an input unit and a correction policy and a natural language processing model. In the corrected text presentation process, for example, the corrected text obtained in the natural language process is presented to the user as a correction candidate. That is, in the natural language process, a plurality of correction candidates that are candidates for at least one corrected input unit are generated using at least one prompt and a natural language processing model. In the corrected text presentation process, the plurality of generated correction candidates are output (presented). It is also possible to save the plurality of correction candidates and output the saved plurality of correction candidates in response to an instruction from the user.

[0019] In natural language processing, the natural language processing model used may be stored in an external information processing device 200 that is connected to the correction proposal system 100 via a network and includes at least one processor and a memory, as shown in FIG. 1. Further, the natural language processing model may be provided in the form of an API or the like from the model vendor. Note that the external information processing device 200 has, for example, the same configuration as the information processing device shown in FIG. 4A.

[0020] In this specification, the document review process is, for example, a process of analyzing whether the information included in the document to be supported is appropriate based on a certain criterion and outputting the result. For example, the document review process is a process including checking and reviewing whether the information included in the document to be supported is appropriate based on a certain criterion. Specifically, it includes matching the words in the document with a pre-prepared checklist and outputting the result of the matching or the points included in the checklist.

[0021] In the correction proposal process, for example, the input unit included in the prompt of the natural language processing model may be generated by dividing the entire text of the document to be supported into units such as articles. Further, for example, the input unit included in the prompt of the natural language processing model can also be generated for the sentences in units of articles, paragraphs, and items that are determined to be inappropriate or in need of correction by, for example, the document review process.

[0022] The correction proposal system 100 according to the present embodiment obtains at least one corrected input unit using at least one prompt generated based on at least the input unit and the correction policy for the input unit and the natural language processing model in the correction proposal process.

[0023] Therefore, according to this embodiment, constraints according to the correction policy can be imposed on the natural language processing model, and a correction input unit conforming to the correction policy can be obtained. As a result, a more specific and accurate corrected text can be obtained compared to natural language processing that uses a prompt not including the correction policy as input. On the other hand, in the case of natural language processing that uses a prompt not including the correction policy as input, the resulting corrected text often strongly depends on the training data of the natural language processing model used.

[0024] A user who receives the document creation support service of this embodiment can check and consider a corrected document as a candidate for the amendment automatically generated in the amendment proposal process on the browser screen. Further, the user can revise the document to be supported based on the review result only by determining the displayed amendment or selecting a desired amendment. In particular, even for the amendment of legal documents such as contract documents that require specialized knowledge, candidates for highly accurate corrected texts conforming to the correction policy can be obtained, and the document to be supported can be revised by a selection operation. As a result, the work burden of the user in amending the document to be supported can be significantly reduced.

[0025] FIG. 2 is a diagram showing the configuration of a correction proposal system 100 according to an embodiment. The correction proposal system 100 is an information processing system communicably connected via a network such as the Internet and a terminal device T1, for example. Details of the correction proposal system 100 will be described later.

[0026] The terminal device T1 is, for example, a computer used by a user of the correction proposal system 100, such as a smartphone, a tablet terminal, or a personal computer.

[0027] For example, a user accesses the amendment proposal system 100 through the terminal device T1 and uploads a contract, which is an example of a legal document, to the amendment proposal system 100. Then, the user receives, through the terminal device T1, the provision of amendment proposal information for the target items in the contract. In this specification, the contract can be read as a legal document as appropriate.

[0028] In FIG. 2, only one terminal device T1 is shown, but the number of terminal devices T1 is not limited to this.

[0029] Subsequently, the details of the amendment proposal system 100 will be described. The amendment proposal system 100 of the present 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 proposal input information (prompt) generation unit 160, and a modification proposal unit 170. Each unit shown in FIG. 2 can be realized, for example, by using a storage area or by the processor executing a program stored in the storage area.

[0030] The storage unit 110 of the present embodiment stores the information processed in the amendment proposal system 100. The storage unit 110 can store, for example, contract information, input unit information, and policy information, which will be described later. The storage unit 110 may be, for example, a memory.

[0031] 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 the electronic data of the contract.

[0032] Here, the contract information is information related to the contract and includes, for example, status information, position information, contract type information (collectively referred to as meta-information above), and contract content information.

[0033] The status information of this embodiment is information indicating the status of a contract document, for example, information indicating the modification status of a contract document. As the status information, for example, "other party's draft" indicating that it is a draft of the counterparty of the contract (for example, the first draft), "other party's amendment" indicating that it is a contract document modified by the counterparty of the contract, or "review completed" indicating that it is a contract document for which the confirmation by the company itself (the business operator to which the user belongs) has been completed, etc. can be cited.

[0034] The position information of this embodiment is information indicating the position of a contract document, for example, information indicating the position of the company itself (the business operator to which the user belongs). The position information may be, for example, "entrusting side" indicating that it is the entrusting side in a commissioned business contract, or "disclosing side" indicating the side disclosing confidential information in a confidentiality contract.

[0035] The contract type information of this embodiment is information indicating the type of a contract document, and may be, for example, "commissioned business contract", "confidentiality contract".

[0036] The contract document content information of this embodiment is information (for example, character data) indicating the content of a contract document.

[0037] The contract document acquisition unit 120 of this embodiment may acquire contract document information from, for example, the terminal device T1. That is, the user may provide (upload) a contract document to the contract document modification proposal system 100 through the terminal device T1, and the contract document acquisition unit 120 may acquire the contract document information of the uploaded contract document.

[0038] At this time, the contract document acquisition unit 120 may acquire contract document information from the user through, for example, the operation of the terminal device T1. In this case, when the contract document acquisition unit 120 receives the upload of a contract document from the terminal device T1, it may receive the input (for example, input by keyboard or selection of items preset by the system) of at least a part of the contract document information (for example, status information, position information, contract type information) from the user, and acquire the contract document information.

[0039] In addition, the contract acquisition unit 120 may obtain contract information from, for example, another information processing system. In this case, for example, the user may provide the contract information to the other information processing system through the terminal device T1, and the contract acquisition unit 120 may obtain the contract information provided from the other information processing system. Examples of the other information processing system include a contract management system, a document management system, and a storage on the cloud.

[0040] In addition, the contract acquisition unit 120 may analyze the content information of the contract to obtain at least some contract information (for example, status information, position information, contract type information).

[0041] 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.

[0042] The contract ID in the present embodiment is information for identifying the contract processed in the amendment proposal system 100. The contract ID is identification information that can uniquely identify each of the contracts before and after amendment in the same contract. That is, the contract ID is information that uniquely identifies the contract (i.e., the electronic document) acquired by the contract acquisition unit 120.

[0043] The sequence ID in the present embodiment is information for identifying the contract indicated by the contract processed in the amendment proposal system 100. That is, the sequence ID is, for example, a unit for managing a series of contracts (i.e., a plurality of contracts such as a contract document at the draft stage, a contract document during amendment, and an agreed contract document for the purpose of contract conclusion).

[0044] The contract acquisition unit 120 of this embodiment may generate a sequence ID, for example, in response to an operation of the terminal device T1 by the user. Specifically, when the user uploads the contract before modification, for example, when the contract before modification is uploaded to an area for managing contracts (for example, a virtual folder managed on the modification proposal system 100), a specific sequence ID (for example, a sequence ID corresponding to the virtual folder or the same sequence ID as the sequence ID of the first contract before modification) may be generated.

[0045] The sequence ID of this embodiment can be used, for example, as follows. In the negotiation of the content of the contract, there may be a case where the other party wants to further modify the content proposed for modification of the user's contract draft. The contract or contract draft is sent from the other party, for example, by email. However, although it may be advantageous as the content of the contract to directly delete the modification content of the other party, it may not be preferable from the perspective of negotiation in some cases. In such a case, with reference to the content of the contract (that is, the previous version) having the same sequence ID, the input modification policy can be made more compromising than the policy applied to the previous version, the expression of the contract can be softened, or the comment generated for presentation together with the modification proposal can be made more detailed. Also, by having the information of the previous version of the contract under review, for example, the risk of repeating the points of compromise made previously and causing difficulties in negotiation can be reduced.

[0046] Also, when a contract related to the contract under review is set, for example, the previously concluded contract before update of the contract under review, or the basic contract when the contract under review is an individual contract, or when two or more contracts such as a joint research and development contract and a joint patent application contract define the same or related content, and there is a contract with the same other party, their contract content and negotiation situation may be considered.

[0047] These may be considered at the stage of generating the correction guidelines or may be considered at the stage of generating the prompt described later, but it is preferable that they be generated as a prompt because the processing becomes simpler.

[0048] The contract document acquisition unit 120 of the present embodiment may extract information based on, for example, the contract parties in the contract document, the creation date of the contract document, and the contract document information in the contract document (for example, status information, position information, contract type information, contract document content information).

[0049] The input unit generation unit 130 of the present embodiment divides the content of the contract document into items included in the contract document based on the contract document information and stores the input units in the storage unit 110.

[0050] Here, the input unit may be, for example, the entire contract document, or may be a unit obtained by dividing the contract document into constituent units such as a title, a preface, a main text, and a signature, or may correspond to an article included in the contract document. That is, the input unit generation unit 130 can divide the content of the contract document, for example, for each "article" or "clause".

[0051] The input unit generation unit 130 can, for example, analyze the content of the contract and divide the content of the contract item by item based on the positions of characters corresponding to the input units (for example, the characters of "article" or "clause"). Note that the input unit generation unit 130 does not necessarily have to divide all contracts into input units, nor does it have to divide all items of the contract item by item. That is, the input unit generation process by the input unit generation unit 130 may be performed on only some contracts, or may be performed on only a part of a contract. Further, the input unit generation unit may, if necessary, integrate a plurality of divided units or a part of the plurality of divided units into one. For example, there may be a case where one legal argument is defined over a plurality of articles. In this case, if the division is performed with the article as a unit as described above and the acquisition of the correction policy and the correction proposal are performed for each article, it may be difficult to obtain an appropriate correction policy and correction proposal. In such a case, it is preferable to integrate parts having similar legal arguments so that an appropriate correction policy can be obtained using rules or a learned model.

[0052] Also, prior to these processes, information necessary for document review such as text data may be extracted from the received document data, or a process of extracting text data from image data may be performed by a process such as OCR.

[0053] When the contract acquisition unit 120 acquires the contract information of the contract, the input unit generation unit 130 can divide the contract before correction item by item and generate it as input unit information indicating the content before correction for each input unit.

[0054] The input unit information stored in the storage unit 110 includes, for example, an input unit ID, a contract ID, and input unit information.

[0055] The input unit ID of the present embodiment is information for identifying item information processed in the correction proposal system 100. The input unit information of the present embodiment is information indicating the content corresponding to the input unit, and is, for example, information indicating the content of each article or clause.

[0056] The amendment policy information generation unit 150 of the present embodiment generates information regarding the policy on how to preferably amend the 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 based on rules or criteria applied to the document (for example, certain rules, laws, customs). For example, as the review information of a contract such as in the present embodiment, (1) an indication of whether the terms included in the document (the contract in the present embodiment) are advantageous or disadvantageous to the user (the parties), (2) advice regarding the amendment or deletion of the terms included in the contract, (3) an indication that an item that should normally be included in the contract is missing, and a proposal for an item to be added, (4) information such as the importance of the items in each review result and the degree of recommendation, etc. can be cited. Also, format information such as whether the style of the text conforms to the standard, and whether defined terms are used may also be included.

[0057] The amendment policy information generation unit 150 of the present embodiment executes a document review process using the contract data (an example of the data of the first legal document) received from the terminal device T1. That is, the analysis unit 151 generates document review information described later regarding the document data as the document review process. Note that the document review information is an example of analysis information.

[0058] The analysis unit 151 of the present embodiment is included in the amendment policy information generation unit 150 and extracts, for example, information included in the document (document data) that is necessary for the generation of the amendment policy information. Various techniques can be adopted as the method for extracting information from the document data. For example, it may be a method of performing a keyword search on the document data and extracting alphanumeric characters, etc. included near the keyword. Also, information can be extracted by morphological analysis, syntactic analysis, semantic analysis, and context analysis. Furthermore, it may be a method of extracting information by natural language processing using machine learning. Note that, for the received document, the amendment policy information generation process may be performed without performing extraction, etc. of the information necessary for the generation of the policy information as described above.

[0059] Note that various techniques can be adopted for generating the document review information executed by the correction policy information generation unit 150. For example, it is preferable to generate the document review information based on a rule base based on rules designed by humans, especially lawyers who are experts, using the extracted information. Also, a learned model that takes the extracted information as input and outputs the corresponding document review information can be used. Furthermore, a combination of a rule-based method and a learned model can also be adopted.

[0060] In addition, the correction policy information generation unit 150 can also generate document review information according to the position of the user (the parties) by using the meta information associated with the contract. Furthermore, the analysis unit 103 can also generate document review information by referring to the contents of other documents (other versions of the support target document, other contracts related to the contract, etc.). The meta information includes both information attached to the document file itself such as the document creator and information given by the user etc. separately input from the file.

[0061] The meta information of this embodiment includes at least one of, for example, document ID, document type (such as types of basic transaction contracts, confidentiality contracts, business entrustment contracts, etc.), version, creation date and time, update date and time, upload date and time, creator, updater, deadline, and document IDs of related documents.

[0062] The correction 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 correction policy instruction based on the document review information for the input unit. Specifically, the correction policy information generation unit 150 generates a prompt described in natural language such as "This input is (the clause divided as the input unit)", "Instruction is (the correction policy)".

[0063] The prompt obtained in this way is input into the natural language processing model to obtain a corrected input unit with the input unit corrected.

[0064] Note that the natural language processing model may be stored in an information processing device connected to a system and a network. Also, the natural language processing model may be provided in the form of an API or the like from the model vendor.

[0065] FIG. 4A is a block diagram showing an example of the hardware configuration of the information processing apparatus 10 according to the embodiment. As shown in FIG. 4A, the information processing apparatus 10 is a computer, and as an example, includes 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 that connects each component.

[0066] The information processing apparatus 10 shown in FIG. 4A includes one of each component, but may include a plurality of the same components. Also, in FIG. 4A, one information processing apparatus 10 is shown, but software may be installed on a plurality of computers, and each of the plurality of computers may execute the same or different parts of the software. In this case, it may be in the form of distributed computing in which each computer communicates via a network interface 17 or the like to execute processing. That is, the information processing apparatus 10 in the present embodiment may be configured as a system in which one or a plurality of computers execute instructions stored in one or a plurality of storage devices to realize various functions described later.

[0067] Various operations of the information processing apparatus 10 may be executed in parallel using one or a plurality of processors, or using a plurality of computers via a network. Also, various operations may be distributed to a plurality of arithmetic cores in the processor and executed in parallel. Also, part or all of the processing, means, etc. of the present disclosure may be executed by at least one of a processor and a storage device provided on a cloud that can communicate with the information processing apparatus 10 via a network. Thus, the processing of the document creation support system S in the present embodiment may be in the form of parallel computing by one or a plurality of computers.

[0068] The processor 11 may be, for example, an electronic circuit (processing circuit, Processing circuit, Processing circuitry, CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), or ASIC (Application Specific Integrated Circuit), etc.) including a control device and an arithmetic device of the information processing apparatus 10. Further, the processor 11 may be a semiconductor device including a dedicated processing circuit, etc. The processor 11 is not limited to an electronic circuit using electronic logic elements, and may be realized by an optical circuit using optical logic elements. Further, the processor 11 may include an arithmetic function based on quantum computing.

[0069] The processor 11 can perform arithmetic processing based on data and software (programs) input from each device, etc. of the internal configuration of the information processing apparatus 10, and output arithmetic results and control signals to each device, etc. The processor 11 may control each component constituting the information processing apparatus 10 by executing the OS (Operating System) of the information processing apparatus 10, applications, etc.

[0070] The information processing apparatus 10 in the present embodiment may be realized by one or a plurality of processors 11. Here, the processor 11 may refer to one or a plurality of electronic circuits arranged on one chip, or may refer to one or a plurality of electronic circuits arranged on two or more chips or two or more devices. When using a plurality of electronic circuits, each electronic circuit may communicate wired or wirelessly.

[0071] The main memory device 13 is, for example, a storage device that stores instructions executed by the processor 11, various data, etc., and the information stored in the main memory device 13 is read by the processor 11. The auxiliary storage device 15 is a storage device other than the main memory device 13. Note that these storage devices mean any electronic components capable of storing electronic information, and may be semiconductor memories. The semiconductor memory may be either a volatile memory or a non-volatile memory. The storage device for storing various data used in the information processing apparatus 10 according to the present embodiment may be realized by the main memory device 13 or the auxiliary storage device 15, or may be realized by a built-in memory built into the processor 11. For example, the storage unit in the present embodiment may be realized by the main memory device 13 or the auxiliary storage device 15.

[0072] A plurality of processors may be connected (coupled) to one storage device (memory), or a single processor 11 may be connected. A plurality of storage devices (memories) may be connected (coupled) to one processor. When the information processing apparatus 10 in the present embodiment is composed of at least one storage device (memory) and a plurality of processors connected (coupled) to this at least one storage device (memory), the configuration may include that at least one of the plurality of processors is connected (coupled) to at least one storage device (memory). Further, this configuration may be realized by the storage devices (memories) and the processor 11 included in a plurality of computers. Furthermore, the configuration in which the storage device (memory) is integrated with the processor 11 (for example, a cache memory including L1 cache and L2 cache) may be included.

[0073] The network interface 17 is an interface for connecting to the network N, for example, wirelessly or by wire. The network interface 17 may use an appropriate interface such as one that conforms to an existing communication standard. Information exchange may be performed with an external device connected via the network N by the network interface 17. Note that the network N may be any one of a WAN (Wide Area Network), a LAN (Local Area Network), a PAN (Personal Area Network), or a combination thereof, as long as information exchange is performed between the information processing device 10 and the external device. An example of a WAN is the Internet, etc., an example of a LAN is IEEE802.11, Ethernet (registered trademark), etc., and an example of a PAN is Bluetooth (registered trademark), NFC (Near Field Communication), etc.

[0074] The device interface 18 is an interface such as an output device like a display device, an input device, and a USB (Universal Serial Bus) for directly connecting to an external device. Also, the external device may be a storage device (memory), a network storage, a storage such as an HDD. Further, the external device may be a device having some functions of the components of the information processing device 10 in the present embodiment. That is, the information processing device 10 may transmit or receive part or all of the processing results of the external device.

[0075] FIG. 4B is a block diagram showing an example of the hardware configuration of the terminal device T1 according to the embodiment. As shown in FIG. 4B, the terminal device T1 is a computer, and as an example, it 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 for connecting each component, a display device 30 connected to the device interface 28, and an input device 31 connected to the device interface 28. Note that 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 thus the description thereof is omitted.

[0076] 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 (Electro Luminescence) panel. The display device 30 displays, for example, a document review screen and a document editing screen described later based on an instruction from the processor 21.

[0077] The input device 31 is a device such as a keyboard, a mouse, or a touch panel. The user can input various editing instructions using the input device 31, for example, in the document editing process described later. The instruction input from the input device 31 is sent to the processor 21.

[0078] Note that the terminal device T1 may include other external devices (for example, 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.

[0079] FIG. 5 is a diagram showing an example of functional blocks in the processor 21. The processor 21 includes, as functions realized by the processor 21, for example, a second control unit 40 and a browser unit 42. The functions realized 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 realize 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 or the like.

[0080] The second control unit 40 activates the browser unit 42, for example, in response to an instruction from the user.

[0081] The browser unit 42 is, for example, a general web browser and executes processing according to HTML (Hyper Text Markup Language) data, scripts (e.g., JavaScript (registered trademark)), etc. When activated, the browser unit 42 transmits and accesses an initial access URL to the information processing apparatus 10.

[0082] The browser unit 42 of the present embodiment displays data including text data and image data received from the information processing apparatus 10 on the display device 30 of the terminal device T1 in a predetermined form. More specifically, in the document review process, the browser unit 42 displays document review information, document data, additional information, etc. received from the information processing apparatus 10 on the display device 30 of the terminal device T1 in a predetermined form based on the layout information. Also, in the document editing process, the browser unit 42 of the present embodiment displays document review information, editing data, additional information, etc. received from the information processing apparatus 10 on the display device 30 of the terminal device T1 in a predetermined form based on the layout information.

[0083] 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 in the document review process. As shown in FIG. 6, in the document review screen 60 of the present embodiment, the document to be supported 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 the document review information is displayed in the document review area 62, respectively.

[0084] For example, an edit button 68 for instructing the start of document editing processing is displayed in the document display area 61. A scroll bar 64 for scrolling the document to be supported displayed in the document display area 61 and the additional information displayed in the additional information area 67 in the vertical direction is displayed next to the additional information area 67 where the additional information is displayed.

[0085] The user clicks a button for starting the document review process displayed on the screen to instruct the start of the document review process. The system accesses the database, performs the document review process, and acquires the correction policy for each input unit. FIG. 3 is an example of a database related to the correction policy.

[0086] At this time, all the correction policies set for the type of input unit (for example, the type of clause) may be acquired, or a part of the correction policies related to the input units of the document to be supported may be acquired. However, from the viewpoint of the convenience of review, it is preferable to display a part of the correction policies.

[0087] Next, a prompt for acquiring the corrected input unit is generated based on the input unit of the document to be supported and the correction policy for it. The prompt is, for example, a natural language such as "Correct clause A according to the content of indication A." The prompt is input to the natural language processing model, and the corrected input unit generated based on the prompt is acquired as the output. When the natural language processing model is outside the system, the system transmits and receives data to and from an information processing device having the natural language processing model using a network such as the Internet.

[0088] The generation of the prompt for the natural language processing model may be performed before the acquisition instruction of the user's corrected input unit, such as clicking the button 69 that instructs to generate the corrected input unit after the review process, or may be generated after the user's instruction. Note that the "correction policy" within the frame such as 623 in FIG. 6 corresponds to the correction policy in this specification, and the "correction example" within the 623 frame corresponds to the "sample sentence" of this specification. Also, the prompt can be further generated based on the optional correction policy. The optional policy can include any of the following: making the text surface of the correction unit as close as possible to the text surface of the input unit, making the correction unit more advantageous for the user than the correction policy, or making the correction unit omit a part of the correction policy. This optional policy can be displayed. The user can select the desired policy from the displayed optional policies. Enter Making the text surface of the correction unit as close as possible to the text surface of the input unit, correction Enter Making the correction unit more advantageous for the user than the correction policy, correction Enter Making the correction unit omit a part of the correction policy, can include any of these. This optional policy can be displayed. The user can select the desired policy from the displayed optional policies.

[0089] Also, there may be provided a button 69 indicating to generate a corrected input unit for each of a plurality of input units or correction policies. Thereby, the user can acquire the corrected input unit information regarding the input unit considered necessary. For example, it is advantageous when it is desired to adjust the number of generations, such as when the generation of the corrected input unit is based on metered billing.

[0090] Next, the system sends information including the above-mentioned modified input unit to the user. The system applies the input unit or the contract document to the modified input unit according to the user's instructions, such as clicking a button 70 indicating that the amended text is applied to the contract draft, or automatically. For example, the input unit in the support target document displayed on the browser is replaced with the modified input unit. Before or after the replacement, the user can edit the modified input unit or instruct to generate the modified input unit again. Further, the obtained modified input unit and the desired instruction may be input into the natural language processing model to obtain a more preferable modified input unit. Also, at least one modified input unit can be generated for each natural language processing model using at least one prompt and a plurality of different natural language processing models, and at least one modified input unit can be output for each natural language processing model. Furthermore, at least one modified input unit generated for each natural language processing model can be saved, and in response to an instruction from the user, the saved at least one modified input unit can be output.

[0091] Note that a button 70 indicating whether to apply to each of the plurality of modified input units may be provided. Thereby, the modified input information can be confirmed, and the user can apply the modified input unit information to the input unit considered necessary. Also, before outputting at least one modified input unit, it may be checked whether the obtained at least one modified Enter force unit includes a modification Enter force standard and meets the requirements.

[0092] Note that the following comment information and chat information may be associated with the support target document of this embodiment.

[0093] The comment information associated with the document of this embodiment is additional information created by at least one user involved in the creation of the document, and is, for example, associated and managed for each version of the document. The comment information associated with the document is typically information different from the comments created by document creation software, but may also include comments created by document creation software as needed.

[0094] The chat information of this embodiment is additional information generated by using the chat function for the document among a plurality of users involved in the creation of the document, and is, for example, associated and managed with respect to a plurality of versions of the document. These additional information are typically text data, but may also include other data formats such as images and voices.

[0095] For example, the user saves the contract document that has been edited. The saved contract document can be utilized by being output as a file such as Word or PDF, downloaded, sent from the system, or a URL sent.

[0096] As described above in detail, the embodiments of the present disclosure have been presented as examples, and are not intended to be limited to individual embodiments. Each embodiment can be modified by various additions, changes, replacements, partial deletions, combinations, etc. These embodiments and their modifications are included in the invention described in the claims and the scope of equivalents thereof.

Claims

1. obtaining a correction policy for each of the at least one input unit of the first legal document; obtaining at least one corrected input unit using at least one prompt generated based on at least the input unit and the correction policy for the input unit and a natural language processing model; outputting said at least one modified input unit; An information processing method comprising:

2. The correction policy is acquired by referring to a database. The information processing method according to claim 1 .

3. The acquisition of the modification policy is determining a type for each of the at least one input unit with a classifier; the database includes information in which a plurality of types are associated with a plurality of modification policies; using the determined type and the database; The information processing method according to claim 2 , further comprising:

4. Refer to the database to obtain the correction policy and a sample sentence for each of the at least one input unit; generating the prompt based on the obtained sample sentence; The information processing method according to claim 2 , further comprising:

5. The database includes information in which a plurality of sample sentences are associated with a plurality of revision policies; obtaining the correction policy for each of the at least one input unit based on a similarity between the at least one input unit and a plurality of the sample sentences; The information processing method according to claim 4 , further comprising:

6. The sample sentences include sentences before and after correction. The information processing method according to claim 5.

7. generating a plurality of candidate corrections for the at least one corrected input unit using the at least one prompt and the natural language processing model; outputting a plurality of said correction candidates; The information processing method according to claim 1 , further comprising:

8. storing a plurality of said correction suggestions; outputting the stored plurality of correction candidates in response to a user instruction; The information processing method according to claim 7, further comprising:

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

10. storing the at least one modified input unit generated for each of the natural language processing models; outputting the stored modified at least one input unit in response to a user instruction; The information processing method according to claim 9 , comprising:

11. the first legal document is a contract; The information processing method according to claim 1 .

12. The contract was sent by the other party to the contract. The information processing method according to claim 11.

13. The at least one input unit is any one of an article, a paragraph, and a number. The information processing method according to claim 1 .

14. before outputting the at least one modified input unit, checking whether the obtained at least one modified input unit satisfies a modified output criterion including the modified policy; The information processing method according to claim 1 .

15. transmitting information for displaying a button for replacing the input unit of the first legal document with the outputted one corrected input unit; The information processing method according to claim 1 .

16. The prompts are further generated based on the option policy of the modification. The information processing method according to claim 1 .

17. The option policy includes any one of the following: making the text of the corrected input unit as close as possible to the text of the input unit; making the corrected input unit have content that is more advantageous to the user than the correction policy; and making the corrected input unit omit part of the correction policy. The information processing method according to claim 16.

18. The option policy is displayed so that the user can select it. The information processing method according to claim 16.

Images