Information processing method and information processing device

Abstract

An information processing method according to an embodiment of the present invention comprises: extracting, from a first database that has a plurality of items of alert information for calling attention of a user on the basis of a first reference to contents of document units constituting a document, at least one item of the alert information on the basis of an assistance target document; extracting, from a second database that has registered therein items of playbook information for calling attention of the user on the basis of a second reference to the contents of the document units constituting the document and that causes the playbook information to be editable, at least one item of the playbook information on the basis of the assistance target document; and generating review information including the playbook information.

Description

Information processing method and information processing device

[0001] An embodiment of the present disclosure relates to an information processing method and an information processing device.

[0002] Systems for supporting document review have been proposed. For example, a legal text evaluation method implemented by a computer for evaluating legal text has been proposed, which includes an input step for accepting input of legal text, a read step for reading evaluation range information regarding the evaluation range of the legal text and evaluation rules for the legal text, an evaluation step for evaluating at least a range of the legal text corresponding to the evaluation range information based on the evaluation rules, and an output step for outputting an evaluation. In such systems, an automatic review process may be performed using highly versatile standards registered in advance by the system provider.

[0003] In such review processing, it would be beneficial if the review processing could be performed using not only pre-registered, highly versatile criteria, but also individual criteria that take into account the organization to which the user belongs, position, and the like.

[0004] Japanese Patent Application Laid-Open No. 2019-212315

[0005] The problem to be solved by the present disclosure is to provide a support technology that enables flexible document review.

[0006] An information processing method according to an embodiment includes extracting at least one piece of alert information based on a support target document from a first database having a plurality of pieces of alert information that alert a user to the contents of document units that constitute a document based on a first criterion; extracting at least one piece of playbook information based on the support target document from a second database in which playbook information that alerts a user to the contents of document units that constitute a document based on a second criterion is registered and the playbook information is editable; and generating review information including the playbook information.

[0007] FIG. 1 is a schematic diagram illustrating an overview of a document browsing support system according to an embodiment. FIG. 2 is a block diagram illustrating an example of the hardware configuration of an information processing device according to an embodiment. FIG. 3 is a diagram illustrating an example of functional blocks in a processor of the information processing device according to this embodiment. FIG. 4A is a diagram illustrating an example of an alert display of review information provided to a user on a terminal device. FIG. 4B is a diagram illustrating an example of an alert display of review information, in which alert information created by a first review process and alert information created by a second review process are displayed. FIG. 5A is a diagram illustrating an example of a GUI (registration GUI) for registering playbook information in a second database for each document unit type by a registration unit. FIG. 5B is a diagram illustrating an example of a GUI (registration GUI) for registering playbook information in a second database for each document unit type by a registration unit. FIG. 5C is a diagram illustrating an example of a GUI for searching for and displaying playbook information for each document unit type. FIG. 6 is a diagram illustrating an example of playbook information registered in the second database. FIG. 7 is a block diagram illustrating an example of the hardware configuration of a terminal device. FIG. 8 is a diagram illustrating an example of functional blocks in a processor of the terminal device. FIG. 9 is a flowchart showing an example of the flow of a playbook information registration process. FIG. 10 is a flowchart showing the flow of a document viewing support process including a second review process according to the first example. FIG. 11 is a flowchart showing the flow of the second review process according to the first example. FIG. 12 is a flowchart showing the flow of the second review process according to the second example. FIG. 13 is a flowchart showing the flow of the second review process according to the third example. FIG. 14 is a diagram showing an example of a GUI provided to a user on a terminal device when registering playbook information. FIG. 15 is a flowchart showing an example of the flow of a playbook information registration process according to the second embodiment.

[0008] Hereinafter, the embodiments will be described in detail with reference to the drawings. In the following description, components having substantially the same functions and configurations are designated by the same reference numerals and will be described only when necessary. In addition, the embodiments can be combined with other embodiments, modifications, and conventional techniques.

[0009] FIG. 1 is a schematic diagram illustrating an overview of a document browsing assistance system S according to this embodiment. As shown in FIG. 1, the document browsing assistance system S according to this embodiment functions as a support system for users when browsing documents, and includes, for example, an information processing device 10 according to this embodiment, and at least one terminal device T1 to TN that can communicate with the information processing device 10 via a network N. The terminal devices T1 to TN are operated, for example, by users P1 to PN, respectively. Note that the configuration of the terminal devices T1 to TN will be described as an example.

[0010] Here, the document viewing support system S according to this embodiment is, for example, a system that supports viewing (displaying) documents on a browser. In this specification, a document refers to a document in any language that is created in accordance with certain rules or standards, such as a regulation, law, or custom. Document data refers to document data, regardless of data format. Document data is typically text data, but can also include image data, tabular data, and other data. Furthermore, documents or document data can include meta-information (version, creation date, update date, creator, updater, etc.) created by word processing software, format information (decorations such as underlines and highlights, fonts, indents, etc.), change history information, comment information, and the like.

[0011] For the sake of concreteness, the following description will be given by way of example of a case in which the documents handled by the document browsing support system S are legal documents (e.g., contracts) written in Japanese. However, the documents handled by the document browsing support system S are not limited to contracts and may be, for example, internal organizational regulations, or may be, for example, company rules written in English. Furthermore, the legal documents handled by the document browsing support system S may be written in any language.

[0012] Furthermore, the document browsing support system S according to this embodiment can be provided with a document creation support function in addition to the document browsing support function. Here, the document creation support function refers to a function for editing (correcting, adding, deleting, etc.) the contents of the document to be supported, and providing information to support editing. In the following, for the sake of concrete explanation, an example will be taken in which the document browsing support system S is provided with the document creation support function.

[0013] The services (document viewing assistance services) provided by the document viewing assistance system S of this embodiment may include, for example, at least one of the following: performing a document review process on a document to be supported on a web browser and providing the results to the user; performing document editing in response to instructions from the user; saving the edited document or providing it to the user; editing additional information associated with the document to be supported (e.g., meta information, comment information, chat information, format information, etc.); creating a new document (including copies); comparing multiple documents (e.g., clearly indicating difference information); automatically proofreading the document to be supported; and performing various processes using a translation display function.

[0014] In this specification, a document review process refers to, for example, a process of analyzing or evaluating information contained in a document to be supported based on certain criteria and outputting the results. For example, a document review process includes checking and examining whether the information contained in a document to be supported is appropriate based on certain criteria. Specifically, the process includes, for example, comparing the wording in the document with a pre-prepared checklist and outputting the results of the comparison or the indications contained in the checklist. Furthermore, editing refers to, for example, adding, deleting, or changing information contained in the document to be edited.

[0015] In particular, the document browsing support system S according to this embodiment can execute a first review process and a second review process as document review processes. The first review process and the second review process will be described in detail later.

[0016] The meta information associated with the document to be supported includes, for example, at least one of the following: document ID, document type (e.g., basic transaction agreement, non-disclosure agreement, outsourcing contract, etc.), version, creation date and time, update date and time, upload date and time, creator, updater, deadline, and document ID of related document.

[0017] In this embodiment, the comment information associated with a document to be supported is additional information created by at least one user involved in the creation of the document, and is associated and managed for each version of the document to be supported. The comment information associated with a document to be supported may be comments created by word processing software.

[0018] In this embodiment, chat information refers to additional information generated by using a chat function for a document to be supported between multiple users involved in the creation of the document, and is managed in association with multiple versions of the document to be supported. This additional information is typically text data, but can also include other data formats such as images and audio.

[0019] The document to be supported in this embodiment may be a document file uploaded from a terminal device, a file newly created on an information processing device using an online editor, or a file that has already been uploaded and saved and / or edited.

[0020] The terminal device T1 in this embodiment is a client device managed by a user P1 who uses the document browsing assistance service. The terminal device T1 displays a document on the screen of a display device, for example, based on information from the information processing device 10. In this embodiment, the user can use the document review results, editing screen, etc. displayed on the screen of the display device of the terminal device T1 to perform operations such as indent replacement processing for the assistance target document, document review reference, comment input, comment reference, chat information input, chat information reference, document editing processing, translation display of the assistance target document, display of document review information, display of difference information, display of suggested drafts, display of pointed out items, and document saving.

[0021] Next, the specific configurations of the information processing device 10 and the terminal device T1 of this embodiment will be described.

[0022] (Information Processing Device 10) The information processing device 10 of this embodiment is a device that is connected to a client device via communication and performs various processes in response to requests from the client device. For example, it is a server device managed by a provider of a document browsing assistance service. For example, the information processing device 10 provides a document browsing assistance service to a terminal device T1 in response to a document browsing assistance request received from a terminal device T1 as a client device via a network N. In particular, the information processing device 10 of this embodiment executes a second review process, a document editing process, etc. in the document browsing assistance service.

[0023] 2 is a block diagram showing an example of the hardware configuration of the information processing device 10 according to the embodiment. As shown in Fig. 2, the information processing device 10 according to the embodiment is a computer, and includes, for example, a processor 11, a main storage device (memory) 13, an auxiliary storage device (memory) 15, a network interface 17, a device interface 18, and a bus 19 connecting the respective components.

[0024] The information processing device 10 of this embodiment shown in Figure 2 includes one of each component, but may also include multiple of the same component. Also, while Figure 2 shows one information processing device 10, the software may be installed on multiple computers, with each of the multiple computers executing the same or different parts of the software. In this case, a form of distributed computing may be used in which each computer communicates with the other computers via a network interface 17 or the like to execute the processing. In other words, the information processing device 10 of this embodiment may be configured as a system that realizes various functions described below by having one or more computers execute instructions stored in one or more storage devices.

[0025] The various calculations of the information processing device 10 of this embodiment may be executed in parallel using one or more processors, or using multiple computers via a network. Furthermore, the various calculations may be distributed to multiple processing cores within a processor and executed in parallel. Furthermore, some or all of the processes, means, etc. disclosed herein 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 device 10 via a network. Thus, the processes of the document browsing assistance system S of this embodiment may be executed in the form of parallel computing using one or more computers.

[0026] The processor 11 may be an electronic circuit (such as a processing circuit, processing circuitry, CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), or ASIC (Application Specific Integrated Circuit)) including a control device and an arithmetic device of the information processing device 10. The processor 11 may also be a semiconductor device including a dedicated processing circuit. 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. The processor 11 may also include an arithmetic function based on quantum computing.

[0027] The processor 11 performs arithmetic processing based on data and software (programs) input from each device, etc., configured internally of the information processing device 10, and can output arithmetic results and control signals to each device, etc. The processor 11 may control each component constituting the information processing device 10 by executing an OS (Operating System), applications, etc. of the information processing device 10.

[0028] The information processing device 10 in this embodiment may be realized by one or more processors 11. Here, the processor 11 may refer to one or more electronic circuits arranged on one chip, or may refer to one or more electronic circuits arranged on two or more chips or two or more devices. When multiple electronic circuits are used, the electronic circuits may communicate with each other via wire or wirelessly.

[0029] The main memory device 13 in this embodiment is a memory device that stores instructions executed by the processor 11, various data, etc., and information stored in the main memory device 13 is read by the processor 11. The auxiliary memory device 15 is a memory device other than the main memory device 13. Note that these memory devices refer to any electronic component capable of storing electronic information, and may be semiconductor memory. The semiconductor memory may be either volatile memory or non-volatile memory. The memory device for saving various data used in the information processing device 10 according to this embodiment may be realized by the main memory device 13 or the auxiliary memory device 15, or may be realized by an internal memory built into the processor 11. For example, the memory unit in this embodiment may be realized by the main memory device 13 or the auxiliary memory device 15.

[0030] Multiple processors may be connected (coupled) to one storage device (memory), or a single processor 11 may be connected. Multiple storage devices (memories) may be connected (coupled) to one processor. When the information processing device 10 in this embodiment is configured with at least one storage device (memory) and multiple processors connected (coupled) to this at least one storage device (memory), it may include a configuration in which at least one of the multiple processors is connected (coupled) to at least one storage device (memory). This configuration may also be realized by storage devices (memories) and processors 11 included in multiple computers. Furthermore, it may include a configuration in which the storage device (memory) is integrated with the processor 11 (for example, a cache memory including an L1 cache and an L2 cache).

[0031] The network interface 17 of this embodiment is an interface for connecting to the network N wirelessly or via a wire. The network interface 17 may be an appropriate interface, such as one conforming to an existing communication standard. Information may be exchanged with an external device connected via the network N through the network interface 17. The network N may be a wide area network (WAN), a local area network (LAN), a personal area network (PAN), or a combination thereof, as long as information is exchanged between the information processing device 10 and the external device. An example of a WAN is the Internet, an example of a LAN is IEEE 802.11 or Ethernet (registered trademark), and an example of a PAN is Bluetooth (registered trademark) or NFC (Near Field Communication), etc.

[0032] The device interface 18 in this embodiment is an interface such as a USB (Universal Serial Bus) that directly connects to an output device such as a display device, an input device, or an external device. The external device may also be a storage device (memory), network storage, HDD, or other storage. The external device may also be a device that has some of the functions of the components of the information processing device 10 in this embodiment. In other words, the information processing device 10 may transmit or receive some or all of the processing results of the external device.

[0033] 3 is a diagram showing an example of functional blocks in the processor 11 according to this embodiment. The processor 11 includes, for example, an acquisition unit 111, an analysis unit 113, a registration unit 114, an edit processing unit 115, a first control unit 117, and a first storage unit 119 as functions realized by the processor 11. The functions realized by the acquisition unit 111, the analysis unit 113, the registration unit 114, the edit processing unit 115, the first control unit 117, and the first storage unit 119 are each stored as a program in, for example, the main storage device 13 or the auxiliary storage device 15. The processor 11 can realize the functions related to the analysis unit 113, the registration unit 114, the edit processing unit 115, the first control unit 117, and the first storage unit 119 by reading and executing the program stored in the main storage device 13 or the auxiliary storage device 15.

[0034] The acquisition unit 111 of this embodiment acquires, for example, document data in DOCX format as the support target document via the network N. The acquisition unit 111 also acquires, for example, document data in DOCX format stored in the first storage unit 119 as the support target document. The acquisition unit 111 also acquires, for example, document data in DOCX format stored in a storage unit of another device as the support target document via the network N.

[0035] The analysis unit 113 of this embodiment performs a document review process using, for example, the document data of the support target document received from the acquisition unit 111. That is, the analysis unit 113 of this embodiment performs a first review process and a second review process to generate document review information related to the document data. Note that the document review information is an example of analysis information.

[0036] Furthermore, the document review information generated by the document review process executed by the analysis unit 113 of this embodiment is based on information obtained by analyzing the document based on rules or standards applicable to the document (e.g., certain regulations, laws, or customs). For example, contract review information as used in this embodiment may include: (1) indication of whether clauses contained in the document (in this embodiment, the contract) are advantageous or disadvantageous to the user (the parties); (2) advice on modifying or deleting clauses contained in the contract; (3) indication of omission of items that should normally be included in the contract and suggestions for items to be added; and (4) information on the importance or recommended level of each review result item. The (document) review information exemplified above in (1) to (4) may be referred to as contract review information if the document to be supported is a contract. Using this information, users can easily identify legal risks contained in the contract and review the contract, including suggesting modifications. Formatting information, such as whether the text conforms to standards, and whether specified terminology is used may also be included.

[0037] The document review process performed by the analysis unit 113 may also include a process for extracting risks contained in the support target document (risk check process). Here, the risk check process involves, for example, determining the risk (remaining risk) remaining in the risk management document for one of the contracting parties (hereinafter referred to as the "risk management subject document"), using data on a contract document (hereinafter referred to as the "reference document") that is the support target and for which a contract agreement has been reached between multiple contracting parties (Company A and Company B in this embodiment), and presenting the results to the user. The risk information data including the results of the risk check is an example of document review information.

[0038] The risks targeted by the risk check process may include, for example, risks assumed from clauses, expressions, and wording that are included in the reference document but not in the risk management document, risks assumed from clauses, expressions, and wording that are not included in the reference document but are included in the risk management document (hereinafter also referred to as ``unconfirmed risks''), risks assumed from clauses, expressions, and wording that are included in both the reference document and the risk management document, and risks assumed due to the existence of clauses, expressions, and wording that are not included in the reference document and the risk management document.

[0039] The analysis unit 113 extracts, for example, information contained in a document (document data) and necessary for generating review information. A variety of techniques can be employed to extract information from document data. For example, a keyword search of the document data may be performed to extract characters, numbers, and the like contained near the keywords. Information may also be extracted using morphological analysis, syntactic analysis, semantic analysis, and contextual analysis. Information may also be extracted using natural language processing using machine learning. Prior to these processes, information necessary for document review, such as text data, may be extracted from the received document data, or text data may be extracted from image data using OCR or other processing. Document review processing may also be performed on the received document without extracting information necessary for generating document review information, as described above.

[0040] The analysis unit 113 may employ various techniques for generating document review information. For example, the extracted information may be used to generate document review information based on a rule base. Alternatively, a trained model may be used that receives the extracted information as input and outputs corresponding document review information. Furthermore, a combination of a rule-based approach and a trained model may be employed. Furthermore, before generating the document review information, the document may be divided into units such as articles, paragraphs, and subsections. The units of division may correspond to document units.

[0041] The analysis unit 113 can also generate document review information according to the perspective of the user (the party) by using meta information associated with the support target document. Furthermore, the analysis unit 113 can also generate document review information by referencing the contents of other documents (other versions of the support target document, other contracts related to the support target document, etc.). Meta information includes information added to the document file itself, such as information about the document creator, and information added by the user, etc., by inputting it separately from the file.

[0042] The review information generated by the analysis unit 113 is displayed in a display format called an alert display on the display unit of the terminal device T1, for example.

[0043] 4A is a diagram showing an example of a review information alert display provided to a user on terminal device T1. In FIG. 4A, a support target document 400 is displayed on the left, and alert information 401 for alerting the user to the review information is displayed on the right, associated with a clause type such as "Obligation of Receiving Party" and positioned in a corresponding manner. Each piece of alert information 401 can include the importance of the content it points out. In this embodiment, a document unit is a clause.

[0044] Here, we will explain the first review process and the second review process executed by the analysis unit 113. The first review process is a review process executed based on highly versatile standards (first standards) prepared, for example, by a party that provides a document browsing assistance service. The first review process is executed using, for example, a database (first database) or a trained model created by the provider of the document browsing assistance service.

[0045] On the other hand, the second review process is performed based on, for example, unique (individual) criteria (second criteria) of the party receiving the document browsing assistance service. The unique criteria of the party receiving the document browsing assistance service are specified, for example, by a playbook. Here, a playbook is a document containing information that an organization or individual receiving the document browsing assistance service considers when reviewing, for example, a document to be supported. It includes reference information such as the meaning and purpose of each provision, response policies, and response examples. In this embodiment, various information contained in the playbook is also referred to as "playbook information." The second review process is performed, for example, using a database (second database) or a trained model created by the party receiving the document browsing assistance service using the playbook. In this specification, the criteria include a determination criterion that determines whether review information (alert information) is to be output and the review information that is to be output when it is determined that the review information should be output based on the determination criterion.

[0046] In the review process based on the second criterion of this embodiment, whether to output alert information is based on the same determination criterion as the first criterion. That is, the first review process based on the first criterion and the second review process based on the second criterion are both performed based on the type of document unit generated from the document to be supported, and the review information extracted as a result is output as alert information. The alert information may also include reference information for the second criterion. Note that the determination criterion for the second criterion may be different from that of the first criterion. For example, the first criterion may be based on something other than the type of document unit (e.g., words), and the second criterion may be based on the document unit.

[0047] The second criteria are preferably set based on the same judgment criteria as the first criteria, i.e., so that if the first criteria issues an alert, the second criteria also display alert information. Because the first criteria are provided by the system provider, the judgment criteria are often already tuned. Therefore, by setting the second criteria in accordance with the first criteria, it is possible to easily set the second criteria to display the necessary review information with high accuracy. When the first review information is displayed simultaneously with the reference information, the content of the reference information can supplement, replace, or cancel the information displayed by the first criteria. Furthermore, whether or not to output alert information through the review process based on the second criteria can be determined, for example, based on criteria different from those for outputting alert information through the review process based on the first criteria. For example, if the first review process determines whether or not to output a review result based on both the classification (hereinafter sometimes referred to as the clause type) assigned to a certain document unit that indicates the meaning of that document unit and the alert occurrence condition, the second review process can always display a playbook if the clause type matches, regardless of the alert occurrence condition. Furthermore, whether or not to output alert information through the review process based on the second criteria can also be determined, for example, based on the corresponding clause type. It is even more preferable to set the criterion as a clause type corresponding to the document type. By setting a criterion for each clause type that is relatively easy to detect using a machine learning model trained by the system provider, it becomes possible to display the necessary review information with high accuracy. Furthermore, even if alert information is not set for a certain clause type based on the first criterion and alert information is not output, second review information can be set for that clause type, and the second alert information can be output when a document unit classified as that clause type is included / not included in the support target document.

[0048] The second criterion may be unrelated to the first criterion, which can be achieved by creating a machine learning model or a unique rule (e.g., whether a certain term is included or not) that can be determined based on the second criterion set by the user.

[0049] When the first review process is executed, the alert information 401 shown in Fig. 4A is generated based on the first database or the like created by the provider of the document viewing assistance service. By checking the alert information 401 created by the first review process, the user can properly understand the general risks and the like contained in the support target document 400.

[0050] Furthermore, when the first review process and the second review process are performed, the alert information 401 shown in FIG. 4A is generated based on a first database or the like created by the provider of the document browsing assistance service and a second database or the like created by the recipient of the document browsing assistance service, including the user, using a playbook. At this time, each piece of alert information 401 shown in FIG. 4A can be provided with information that identifies whether the alert information is based on the first criteria or the second criteria. By checking the alert information 401 created by the second review process, the user can understand the risks, etc. contained in the support target document 400 based on the individual content of the user, etc.

[0051] The registration unit 114 registers playbook information in the second database of the first storage unit 119 based on the information acquired by the acquisition unit 111. Specifically, the registration unit 114 associates playbook information input by a user or classified by a trained model with a document unit type, registers the playbook information in the second database of the first storage unit 119, and edits the second database. Here, the document unit type indicates the content of each document unit (document unit) when the document is divided into items, paragraphs, sentences, etc. For example, if the document is a contract, the document units are articles, clauses, and items, and the document unit type (e.g., article type) indicates a title (content of the article) such as "Definition of Terms." Registration in the registration unit may be performed by inputting data from a screen described below or by uploading data containing the necessary information (e.g., a table-format file). This allows multiple playbook information to be registered at once, improving user convenience. Furthermore, if the playbook information used by the user is saved in a table format, convenience is further improved.

[0052] FIG. 4B is a diagram showing an example of a review information alert display in which alert information 401a created by the first review process and alert information 401b and 401c created by the second review process are displayed. As shown in FIG. 4B , alert information 401a created by the first review process of this embodiment and alert information 401b and 401c created by the second review process are both displayed in association with the target clause. That is, in the example of FIG. 4B , alert information 401a created by the first review process and alert information 401b created by the second review process are displayed side by side for one clause 400, "Confidentiality." Furthermore, alert information 401c created by the second review process is displayed in association with "Compensation for Damages," a clause different from "Confidentiality." Furthermore, an icon is displayed on the clause of the support target document 410 indicating that alert information is displayed for that clause. The alert information created by the second review process of this example includes a preferred position, a preferred language clause, a fallback position, a fallback language clause, and the like, regarding the contents of the document unit.

[0053] Furthermore, in this embodiment, the alert information 401a is provided with "Addition," which is information indicating that the alert information was created by the first review process, and the alert information 401b and 401c are provided with "Playbook," which is information indicating that the alert information was created by the second review process. The user can quickly understand which provision the displayed alert information corresponds to and whether the alert information was created by the first review process or the second review process.

[0054] 4B shows a case where both the alert information created by the first review process and the alert information created by the second review process are displayed. However, depending on the settings, it is also possible to display only the alert information created by the first review process or only the alert information created by the second review process.

[0055] 5A and 5B are diagrams showing an example of a GUI (registration GUI) for registering playbook information by document unit type in the second database by the registration unit 114. This is an example of entering playbook information using an alert information setting screen (Playbook alert). The registration GUI shown in FIGS. 5A and 5B can be used to register, for example, by document unit type that constitutes the target clause. This allows playbook information to be entered or registered with less operational burden on the user. In this embodiment, moving the scroll bar 520 downward from the state of the registration GUI shown in FIG. 5A changes to the state of the registration GUI shown in FIG. 5B.

[0056] As shown in Figures 5A and 5B, the registration GUI displays items such as an importance setting area (Importance) 500, a position (Position) 501, guidance (Guidance) 502, a preferred position (Preferred position) 503, a preferred language clause (Preferred sample language) 504, a fallback position (Fallback position) 505, and a fallback language clause (Fallback sample language) 506.

[0057] The importance setting area 500 is an item for setting the importance of each piece of playbook information added for each document unit type. In the example of FIG. 5A, the importance is set to three levels: "Low," "Medium," and "High." However, the present invention is not limited to this example and may be set using a slider bar or by directly entering numbers.

[0058] The position 501 indicates, for example, the position of the user when reviewing the document, and is an item for specifying the position of the disclosing party, the disclosed party, etc., when the contract type is, for example, a "confidentiality agreement." By setting this item, it is possible to display appropriate alert information for risks, etc., contained in the document that change depending on the user's position.

[0059] The guidance 502 is an item for entering, for example, the standards, purpose, interpretation method, and points to note of the clause. Tables and images can also be input into the guidance 502 as needed.

[0060] The preferred position 503 is an item for entering, for example, a preferred course of action in contract negotiations.

[0061] The preferred language clause 504 is an item for entering recommended wording for the corresponding clause, regulation, etc., for example.

[0062] The fallback position 505 is an item for entering, for example, a fallback course of action in contract negotiations.

[0063] The fallback language clause 506 is an item for entering wording that is recommended when fallback is performed on the corresponding clause or provision, for example.

[0064] The user can register each item constituting the playbook information via the registration GUI shown in Figures 5A and 5B. Registration via the registration GUI may involve inputting or editing text, or selecting from prepared options. For items included in the first criteria (e.g., "position" described below), it is preferable to display predetermined options such as radio buttons or pull-down menus so that the user can select from them, as this allows for appropriate display of alert information.

[0065] FIG. 5C is a diagram showing an example of a search screen (search GUI) for searching playbook information registered in the second database for each document unit type.

[0066] As shown in Figure 5C, the GUI for searching playbook information displays, for example, an alert information list 402, a document type (contact type) 404, the user's position (Your position) 405 related to the document, such as the document disclosing party, an add playbook button 406, an importance setting area 407, a first information area 408, and a second information area 409.

[0067] In the alert information list 402 of this embodiment, alert information categorized by document unit type (by article type in this embodiment) into which document units are categorized is displayed in a list. The user can check all of the alert information registered for each article type using the alert information list 402.

[0068] The document type (contact type) 404 in this embodiment is an item for specifying the type of document to which the playbook information is applied. In this embodiment, the document to which the playbook information is applied is a contract, and an example is taken in which "Non-Disclosure Agreement" is selected as the document type (contact type) 404.

[0069] In this embodiment, the user's position (Your position) 405 indicates the position of the user when reviewing the document, and is an item for specifying the position of the disclosing party, the disclosed party, etc., when the contract type 404 is "confidentiality agreement." By setting this item, it is possible to display appropriate alert information for risks, etc., contained in the document that change depending on the user's position.

[0070] The add playbook button 406 in this embodiment is a button for instructing the addition (registration) of new playbook information for each document unit type. As shown in FIG. 5C , for example, the add playbook button 406 is provided for each document unit type (each clause type), such as "Confidential Information" and "Use of Confidential Information only for the Purpose." By pressing the add playbook button 406 provided corresponding to, for example, "Confidential Information," the user can transition to a registration screen displaying the registration GUI shown in FIGS. 5A and 5B.

[0071] The importance display area 407 in this embodiment is an item that displays the importance of each playbook information searched and selected by the user. In the example of Figure 5C, the setting is made in a radio button-like display with three levels: "Low," "Medium," and "High." However, this is not limited to this example, and the format may be, for example, a slider bar or numbers.

[0072] In this embodiment, the first information area 408 is an area for displaying the language clause of the searched playbook information. The user can input any information as text information in the first information area 408.

[0073] The second information area 409 in this embodiment is an area where guidance on the searched playbook information is displayed.

[0074] In the playbook information of this embodiment, for example, information indicating the update date and time and the user who updated each piece of playbook information may be automatically recorded. The document type (Contact type) 404, the position of the user involved in the document (such as the document disclosing party) 405, and the update date and time are meta information (playbook meta information) indicating the attributes of the playbook information. The playbook meta information may also include a disclosure scope such as "Legal organization only," a "filtering setting" for gradually selecting the information to be displayed, a "recommended clause" indicating clauses related to the playbook information that are advantageous to the user's position, "other clauses" indicating clauses related to the playbook information that are advantageous to the other party's position, "disclosure status," and "comment information" that allows free comments to be entered as text information.

[0075] A user can search for desired playbook information by inputting at least one item into the search GUI.

[0076] The registration unit 114 registers playbook information in the second database of the first storage unit 119, for example, based on information input via the GUI shown in Figures 5A and 5B.

[0077] 6 is a diagram showing an example of playbook information registered in the second database of the first storage unit 119. In FIG. 6, the item "Article ID" is an "Article Type (Document Unit Type)" and is an ID corresponding to the document unit type "Confidential Information" shown in FIG. 5C.

[0078] The item "Playbook ID" in this embodiment is a unique ID for identifying each playbook information.

[0079] In the item "Playbook" of this embodiment, the information entered in the first information area 504 and the second information area 502 shown in FIG. 5A, for example, is registered as the contents of the playbook information.

[0080] In the item "position" of this embodiment, for example, information selected in the user's position (Your position) 501 shown in FIG. 5A is registered.

[0081] In the "Contract Type" field of this embodiment, a document type (in this embodiment, a contract type, which is an example of a document type) such as the "Non-Disclosure Agreement" shown in FIG. 5C is registered. When the document type (contract type) is registered from the screen of FIG. 5C, for example, the information selected in the contract type display field 404 in FIG. 5C is registered. When the document type (contract type) is registered from the screen of FIG. 5A or 5B, for example, a document type may be selected and registered from predetermined document types, or the document type to which the support target document displayed or selected on the screen before transitioning to the screen of FIG. 5A or 5B belongs may be registered. Note that the document type is an example of playbook meta information.

[0082] In the item "importance" of this embodiment, for example, the importance set in the importance setting area 407 shown in Fig. 5A is registered. Note that the importance is an example of playbook meta information.

[0083] The analysis unit 113 of this embodiment executes the second review process by referring to the second database shown in Fig. 6. That is, for example, when the article ID "1" (i.e., the document unit type) is set to "Confidential Information," the analysis unit 113 generates review information including playbook information associated with the article ID "1" according to the second database shown in Fig. 6 for the document unit type "Confidential Information," and displays it as alert information.

[0084] The editing processing unit 115 of this embodiment generates data for editing by converting the data format of the support target document (document data) received via the first control unit 117. For example, the editing processing unit 115 converts document data in a "DOCX" format file, which is the support target document received via the acquisition unit 111, from XML format to "JSON" format, and generates data for editing.

[0085] Furthermore, the editing processing unit 115 of this embodiment executes editing processing on the data to be edited in response to an editing instruction received from the terminal device T1 via the acquisition unit 111. Here, the editing processing executed by the editing processing unit 115 includes adding, deleting, and changing information included in the data to be edited. More specifically, this includes adding, modifying, and deleting words, sentences, and character decorations (e.g., font, character color, character size, character thickness, underlining, strikethrough, etc.) to the data to be edited.

[0086] The editing process executed by the editing processing unit 115 can include format editing process, word input assistance process, sentence suggestion process, pointed out matter extraction process, and difference information extraction process.

[0087] Here, the format editing process refers to, for example, a process of correcting the format of the data to be edited as a document. For example, the format editing process corrects indentation, line head of bullet points, right / left justification, misalignment of clause numbers, etc., preferably automatically by the system. The editing processing unit 115, for example, references format information of the support target document corresponding to the data to be edited, and executes the format editing process on the data to be edited based on this information.

[0088] It is preferable that document format settings be stored in advance in the information processing device 10 or a terminal based on the type of document to be supported, such as a contract. For example, in the case of legal documents such as contracts or company regulations, the order may be article, paragraph, and subparagraph, with the clause numbers arranged in ascending order and the indentation increasing from article to paragraph and subparagraph. The editing processing unit 115 may also execute format editing processing according to the type based on meta information of the document to be supported. This format setting may be created by the user, provided as part of the document viewing support service, or customized by the user. Alternatively, the format setting of the document to be supported may be interpreted and created based on that.

[0089] The word input assistance process of this embodiment is a process that assists input, for example, by presenting candidate words or phrases to be input next when editing document data. This supports the user's input operation during editing and reduces the workload. For example, frequently occurring words or phrases according to the type of the support target document can be presented as input candidates. Furthermore, support target documents stored by the user or the organization to which the user belongs can be analyzed to present frequently used words or phrases. The user can also set words or phrases. The editing processing unit 115 can determine candidate words according to the type based on meta information of the support target document. The words or phrases presented in this input assistance process are displayed, for example, in a predetermined window on the screen (within the document editing window).

[0090] The proposal suggestion process of this embodiment is, for example, a process of displaying input candidate proposals during editing. For example, if the document is a contract, an example of amendment based on at least some of the amendments to the contract may be read from a database that stores example clause proposals and presented as a proposal candidate. This supports the input operation of the user during editing and reduces the workload.

[0091] As a suggestion process, the editing processing unit 115 may present predetermined suggestion candidates, suggestion candidates determined by the user or the document browsing assistance service provider, suggestion candidates generated by a text generation service within or outside the system using a large-scale language model (LLM), or suggestion candidates that frequently appear depending on the type of document to be supported. Furthermore, the editing processing unit 115 may present as suggestion candidates those that are more frequently used than other suggestions or highly rated by the user or users, etc., among suggestions contained in documents stored by the user or the organization to which the user belongs. When there are multiple example candidates, the editing processing unit 115 may further select at least one suggestion candidate based on the adoption rate (the percentage of suggested suggestions selected by users) or adoption frequency of the clauses in past document browsing assistance services, and present the candidates with the highest adoption rate to the user first. The suggested suggestion candidates may also be presented, for example, as document review information or other information.

[0092] The editing processor 115 can also edit the data for editing in response to the editing instruction based on the presented candidate sentences, for example, an instruction by a drag-and-drop operation. The proposed sentences may be displayed in a positional correspondence with the corresponding portions of the document. For example, the candidate sentences are displayed in close proximity to the corresponding portions of the document. This display allows the user to compare the candidate sentences with the corresponding portions of the document with minimal eye movement, thereby reducing the burden on the user. Furthermore, a portion of the data for editing may be replaced with the presented candidate sentences, either automatically or in accordance with a user instruction. In this case, it is preferable to keep a revision history of the data for editing so that the type of editing that was performed can be clearly identified.

[0093] The indication display process of this embodiment involves, for example, presenting to the user indications related to the document to be supported (e.g., document review information, comment information, chat information, revision history of the editing data, comments on the document data created by the functions of the word processing software, etc.). The editing processing unit 115 of this embodiment presents, for example, the extracted indications to the user in a predetermined display format. It is preferable that the indications are displayed in a list in an area that does not overlap with the portion of the document to which the indications refer, such as a document review area displayed alongside the editing area, or in an independent (separate) window such as a pop-up window.

[0094] Furthermore, a combination of the processing for displaying pointed out items and the processing for suggesting sentences may be used to propose pointed out items and candidate sentences that can resolve the pointed out items. In this case, it is preferable that the pointed out items and candidate sentences are displayed in a positional correspondence with the pointed out portions of the document. For example, it is preferable that the pointed out items and candidate sentences are displayed in close proximity to the corresponding pointed out items. This type of display allows the user to compare the pointed out items, candidate sentences, and the corresponding portions of the document with minimal eye movement, thereby reducing the burden on the user.

[0095] Additionally, the document review area and pop-up windows displaying the issues and draft candidates can be collapsed, minimized, or resized. This allows the user to easily view the limited size of the document display screen, for example, by aligning it with the parts of the document that are being pointed out. Furthermore, the spacing between each clause in the editing area may be increased based on the height of the issues or draft candidates. This type of display makes it possible to more clearly and easily show the correspondence between the issues, draft candidates, and the parts of the document that are being pointed out.

[0096] The difference information extraction process of this embodiment involves presenting to the user difference information between two pieces of document data, for example, the support target document data before correction and the document data after correction. The editing processing unit 115 of this embodiment may, for example, extract difference information from the support target document data before correction and the document data after correction, and present the information to the user in a predetermined display format, for example, by displaying the differences differently from the remaining parts (i.e., the same parts) in an emphasized manner or by highlighting them.

[0097] The editing processing unit 115 of this embodiment executes the various editing processes described above in response to an editing instruction received from the terminal device T1. Furthermore, the editing processing unit 115 of this embodiment may convert the data format of the support target document data or translation data in response to a save instruction received from the terminal device T1, and generate document data that will be the next version of the support target document. For example, in response to a download instruction or save instruction received from the terminal device T1, the editing processing unit 115 can use support target document data in the "JSON" format to generate document data in the "DOCX" format that will be the next version of the support target document.

[0098] The first control unit 117 of this embodiment communicates information with the terminal device T1 via a network. Specifically, for example, the first control unit 117 receives various instructions, such as document data, document review instructions, editing instructions, translation instructions, save instructions, and output instructions (e.g., download instructions), transmitted from the terminal device T1. The first control unit 117 also transmits editing screen information (including information for executing editing processing on the terminal device T1 side) to the terminal device T1. The first control unit 117 receives information including document data after editing processing from the terminal device T1.

[0099] The first control unit 117 of this embodiment generates layout information in a document editing process. The layout information in the document editing process is, for example, information for displaying editing data in a predetermined format on a browser screen of the terminal device T1. The first control unit 117 of this embodiment may also generate layout information in a document review process. The layout information in the document review process is, for example, information for displaying the document review information generated by the document review process and the support target document in a predetermined format on a browser screen of the terminal device T1.

[0100] The layout information may positionally correspond the document review information (including translated information) generated by the document review process to the document to be supported. Positional correspondence refers to, for example, associating display positions to facilitate user browsing, specifically, associating positions on the screen, for example, clause-by-clause, paragraph-by-paragraph, or sentence-by-sentence. Positional correspondence includes, for example, displaying corresponding portions closer to each other in the height or width direction than other portions on the screen, more preferably, displaying them side by side. Furthermore, when additional information is also displayed, the layout information may include information for positionally corresponding the additional information to the document review information and editing data.

[0101] Any method may be used to generate the layout information. For example, the layout information may be generated by using a search function to score the degree of match for each position in the editing data (e.g., each clause or each paragraph), for words and phrases included in the document review information, and displaying the document review information at the position with the highest score. Furthermore, for example, by assigning coordinates to each clause or paragraph in the editing data and associating the coordinates with the corresponding document review information, the display positions of the clauses and paragraphs and the document review information may be associated.

[0102] In this embodiment, the first control unit 117 transmits various information such as document review information generated in the analysis unit 113, editing data generated in the editing processing unit 115, translation data generated by the translation processing unit 116, and layout information generated in the first control unit 117 in response to a request from the terminal device T1.

[0103] The first storage unit 119 stores, for example, document data uploaded from the terminal device T1, new versions of document data generated from editing data by document editing processing, documents to be supported in DOCX format, and additional information associated with each document data.

[0104] The first storage unit 119 also stores a first database and a second database. Here, the first database is a database in which multiple pieces of alert information that alert the user to the content of document units that make up a document are registered based on a first criterion. The multiple pieces of alert information registered in the first database may be configured to be uneditable. The second database is a database in which playbook information that alerts the user to the content of document units that make up a document are registered based on a second criterion. The playbook information registered in the second database is editable by an editing process.

[0105] (Terminal Device T1) The terminal device T1 of this embodiment transmits and receives information relating to document display and document editing to and from the information processing device 10 in, for example, a document browsing support service (document browsing support system).

[0106] 7 is a block diagram showing an example of the hardware configuration of a terminal device T1 according to an embodiment. As shown in FIG. 7, the terminal device T1 is a computer, and includes, for example, a processor 21, a main storage device (memory) 23, an auxiliary storage device (memory) 25, a network interface 27, a device interface 28, a bus 29 connecting the respective components, 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 similar to those of the processor 11, the main storage device 13, the auxiliary storage device 15, the network interface 17, the device interface 18, and the bus 19, respectively, and therefore description thereof will be omitted.

[0107] 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), an organic EL (Electro Luminescence) panel, etc. Based on instructions from the processor 21, the display device 30 displays, for example, a document review screen and a document editing screen (described later).

[0108] The input device 31 is a device such as a keyboard, a mouse, or a touch panel. A user can use the input device 31 to input various editing instructions, for example, in document editing processing. The instructions input from the input device 31 are sent to the processor 21.

[0109] The terminal device T1 may also 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 manipulate and edit document data.

[0110] 8 is a diagram showing an example of functional blocks in the processor 21. The processor 21 includes, for example, a second control unit 40, a browser unit 42, and a second storage unit 44 as functions realized by the processor 21. The functions realized by the second control unit 40, the browser unit 42, and the second storage unit 44 are each stored as a program in, for example, the main storage unit 23 or the auxiliary storage unit 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 program stored in the main storage unit 23 or the auxiliary storage unit 25.

[0111] The second control unit 40 starts up the browser unit 42 in response to, for example, an instruction from the user.

[0112] The browser unit 42 is, for example, a general web browser, and executes processing in accordance with HTML (Hyper Text Markup Language) data, scripts (for example, JavaScript (registered trademark)), etc. When started, the browser unit 42 transmits an initial access URL to the information processing device 10 and accesses it.

[0113] The browser unit 42 of this embodiment displays data including text data and image data received from the information processing device 10 in a predetermined format on the display device 30 of the terminal device T1. More specifically, in a document review process, the browser unit 42 displays document review information, document data, additional information, etc. received from the information processing device 10 in a predetermined format based on layout information on the display device 30 of the terminal device T1. In addition, in a document editing process, the browser unit 42 of this embodiment displays, for example, document review information, editing data, additional information, etc. received from the information processing device 10 in a predetermined format based on layout information on the display device 30 of the terminal device T1.

[0114] Furthermore, the browser unit 42 transmits, for example, a start instruction from the user to the information processing device 10. For example, the browser unit 42 receives playbook information registration screen information (including information for executing the registration process) from the first control unit 117 of the information processing device 10 and executes the registration process, etc. The browser unit 42 receives, for example, the support target document for which the registration process has been executed, and stores it in the second storage unit 44.

[0115] The second storage unit 44 stores, for example, support target document data before editing processing and support target document data in DOCX format after editing processing acquired by the browser unit 42. The second storage unit 44 also stores, for example, a playbook owned by the party receiving the document browsing support service.

[0116] [Playbook Information Registration Processing] Next, the playbook information registration processing realized by the document browsing support system S will be described.

[0117] 9 is a flowchart showing an example of the flow of the playbook information registration process. As shown in FIG. 9, first, the second control unit 40 of the terminal device T1 of this embodiment launches the browser unit 42 in response to, for example, a user instruction. The browser unit 42 of the terminal device T1 transmits login information such as an initial access URL and a registration ID to the information processing device 10 (step S1).

[0118] The first control unit 117 of the information processing device 10 of this embodiment executes authentication processing in response to login information from the terminal device T1, for example. The first control unit 117 also transmits document browsing support screen information generated by the first control unit 117 (step S2).

[0119] The browser unit 42 of the terminal device T1 of this embodiment displays the document browsing assistance screen on the display device 30 based on the document browsing assistance screen information received from the information processing device 10, for example (step S3).

[0120] In response to an instruction from the user, the browser unit 42 of the terminal device T1 of this embodiment causes the display device 30 to display an alert list display screen (step S4).

[0121] The browser unit 42 of the terminal device T1 of this embodiment accepts, for example, on an alert list display screen, a selection of a clause type to which playbook information is to be added from the user (step S5). For example, in the example of the alert list display screen shown in FIG. 5C, the browser unit 42 accepts, from the user, a selection of a clause type to which playbook information is to be added in response to an operation of the "Add Playbook button" displayed corresponding to the clause type "Confidential Information." This step allows information to be input and edited, for example, on the screens shown in FIGS. 5A and 5B as new alert information using a playbook.

[0122] In response to an instruction from the user, the browser unit 42 of the terminal device T1 of this embodiment accepts the addition of playbook information and playbook meta information (i.e., writing to the first information area 408, etc.) (step S6). The browser unit 42 of the terminal device T1 of this embodiment transmits the added playbook information and playbook meta information to the information processing device 10.

[0123] The first control unit 117 of the information processing device 10 of this embodiment receives the playbook information and playbook meta information transmitted from the terminal device T1 (step S7).

[0124] The registration unit 114 of the information processing device 10 of this embodiment registers the received playbook information and playbook meta information in the second database of the first storage unit 119 (step S8).

[0125] According to this embodiment, a user can add playbook information corresponding to a desired clause type, along with playbook meta information, to a database used during review processing on the alert list display screen. Therefore, a user can easily customize the database for review processing that better suits their own criteria.

[0126] [First Example of Second Review Process] Next, a first example of the second review process realized by the document browsing support system S will be described. The second review process according to the first example executes the review process based on the second criteria. In this embodiment, playbook information associated with the clause type exists, and the review process is executed using the associated playbook information.

[0127] 10 is a flowchart showing the flow of the document browsing assistance process including the second review process according to the first example. As shown in FIG. 10, first, the second control unit 40 of the terminal device T1 activates the browser unit 42 in response to, for example, a user instruction. The browser unit 42 of the terminal device T1 transmits login information, such as an initial access URL and a registration ID, to the information processing device 10 (step S11).

[0128] The first control unit 117 of the information processing device 10 executes authentication processing in response to login information from the terminal device T1, for example. The first control unit 117 also transmits document browsing support screen information generated by the first control unit 117 (step S12).

[0129] The browser unit 42 of the terminal device T1 displays a document browsing assistance screen on the display device 30 based on the document browsing assistance screen information received from the information processing device 10, for example (step S13).

[0130] The browser unit 42 of the terminal device T1 transmits the support target document data to the information processing device 10 in response to, for example, a document upload instruction from the user (step S14). The acquisition unit 111 of the information processing device 10 stores, for example, the document data acquired (received) from the terminal device T1 in the first storage unit 119. The first control unit 117 of the information processing device 10 generates, for example, document preview screen information based on the document data acquired by the acquisition unit 111. The first control unit 117 of the information processing device 10 transmits, for example, the generated document preview screen information to the terminal device T1 (step S15). Note that the document upload instruction and the storage of the document data in the first storage unit 119 may be performed, for example, by another user and / or another terminal in another department who requests the legal department to review the contract prior to the editing process. The document data may also be subjected to a document type determination of the support target document and document unit analysis.

[0131] The browser unit 42 of the terminal device T1 displays a document preview screen based on, for example, the document preview screen information received from the information processing device 10 (step S16). At this stage, since the document review process has not yet been performed, for example, only the document to be supported is displayed on the document preview screen. By executing step S6, the document viewing support system S of this embodiment can be used not only for document review and editing, but also for document viewing. The display of the document preview screen can be omitted by accepting a document review instruction or performing the document review process (described later) before displaying the document preview screen.

[0132] The browser unit 42 of the terminal device T1 transmits, for example, a document review instruction input by the user to the information processing device 10 (step S17). At this time, for example, information regarding the user's position regarding the document to be supported (for example, the position of "information disclosure party") is also included in the document review instruction and transmitted.

[0133] The analysis unit 103 of the information processing device 10 executes a second review process in response to the document review instruction from the terminal device T1, and generates second review information (step S18). In this embodiment, the second review information does not include the first review information.

[0134] FIG. 11 is a flowchart showing the flow of the second review process according to the first example. As shown in FIG. 11, the analysis unit 103 of the information processing device 10 executes a first review process (i.e., a review process executed based on highly versatile standards prepared, for example, by a party providing a document browsing assistance service) using, for example, a first database (step S180a) to generate first review information about the support target document (step S181a). Note that analysis of the clause types included in the support target document is performed simultaneously with or prior to the generation of the first review information. The first review process is performed, for example, based on the clause types and / or other information (e.g., wording) included in the support target document.

[0135] Next, the analysis unit 103 of the information processing device 10 refers to the second database and determines whether or not playbook information associated with the clause type exists (step S182a).

[0136] If it is determined that playbook information associated with the clause type exists (Yes in step S182a), the analysis unit 103 of the information processing device 10 extracts the associated playbook information and its meta information (playbook meta information), and generates second review information together with the first review information generated in step S181a (step S183a).

[0137] On the other hand, if it is determined that there is no playbook information associated with the clause type (No in step S182a), the analysis unit 103 of the information processing device 10 proceeds to step S184a.

[0138] The analysis unit 103 of the information processing device 10 determines whether the next article exists (step S184a). If it is determined that the next article exists (Yes in step S184a), the analysis unit 103 of the information processing device 10 repeatedly executes the processes of steps S182a to S184a to update the second review information. On the other hand, if it is determined that the next article does not exist (No in step S184a), the analysis unit 103 of the information processing device 10 determines the content of the second review information (step S185a). Note that the generation of the first review information and the second review information does not necessarily have to be performed in this order. For example, the generation of the first review information and the second review information may be performed simultaneously, or review information for multiple article types may be generated in a single step.

[0139] 10 , the first control unit 107 of the information processing device 10 generates layout information for displaying the first review information and the second review information in association with the support target document. The first control unit 107 of the information processing device 10 transmits the support target document data, the first review information, the second review information, and the layout information generated by the first control unit 107 to the terminal device T1 (step S19).

[0140] The browser unit 42 of the terminal device T1 displays a document review screen (step S20) based on the support target document data, the first review information, the second review information, and the layout information received from the information processing device 10. That is, the alert information according to the first standard and the alert information according to the second standard (i.e., the playbook) are displayed on the document review screen together with information that allows them to be distinguished from each other, in a form aligned with the corresponding clauses, for example, as shown in FIG. 4A .

[0141] The display order of the playbook information included in the second review information on the document review screen can be controlled based on, for example, the importance and update date and time included in the playbook meta information. Also, the playbook information included in the second review information can be switched to be displayed or hidden based on at least one of the type of the document to be supported, the importance of the clause, and the user's position.

[0142] The second review information may also include status information indicating whether the alert information in each playbook has been addressed in the support target document. The status may be changed in response to a user input on the document review screen.

[0143] [Second Example of Second Review Processing] Next, we will explain a second example of the second review processing realized by the document browsing support system S. The second review processing according to the second example is to execute the second review processing using playbook meta information indicating the attributes of the playbook information when playbook information associated with the article type exists.

[0144] In the following, for the sake of concrete explanation, an example will be given in which the second review process is performed using "user position" as playbook meta information. "User position" is merely an example, and it is also possible to perform the second review process using playbook meta information such as "language" and "update date and time." Furthermore, it is also possible to perform the second review process using a combination of multiple playbook meta information.

[0145] When comparing the second review process according to the first example with the second review process according to the second example, only the content of the second review process shown in step S18 in FIG. 11 is different.

[0146] Fig. 12 is a flowchart showing the flow of the second review process according to the second example, which is executed in step S18 of Fig. 11. As shown in Fig. 12, the analysis unit 103 of the information processing device 10 executes the first review process (i.e., review process executed based on highly versatile standards prepared, for example, by the document browsing assistance service provider) using, for example, a first database (step S180b), and generates first review information about the support target document (step S181b).

[0147] Next, the analysis unit 103 of the information processing device 10 refers to the second database and determines whether or not playbook information associated with the clause type exists (step S182b).

[0148] If it is determined that playbook information associated with the clause type exists (Yes in step S182b), the analysis unit 103 of the information processing device 10 determines whether the user's position regarding the document to be supported (for example, the position of the ``information disclosing party'' for the document type ``confidentiality agreement'') exists in the meta information (playbook meta information) of the playbook information associated with the clause type (step S183b).

[0149] If it is determined that the user's position related to the document to be supported is present in the playbook meta information (Yes in step S183b), the analysis unit 103 of the information processing device 10 extracts the associated playbook information and playbook meta information, and generates second review information by combining it with the first review information generated in step S181b (step S184b).

[0150] On the other hand, if it is determined that there is no playbook information associated with the article type (No in step S182a), or if it is determined that the user's position related to the document to be supported does not exist in the playbook meta information (No in step S183b), the analysis unit 103 of the information processing device 10 transitions the processing to step S185b.

[0151] The analysis unit 103 of the information processing device 10 determines whether the next article exists (step S185b). If it is determined that the next article exists (Yes in step S185b), the analysis unit 103 of the information processing device 10 repeats the processes of steps S182b to S185b to update the second review information. On the other hand, if it is determined that the next article does not exist (No in step S185b), the analysis unit 103 of the information processing device 10 determines the content of the second review information (step S186b).

[0152] According to the second review process of this second example, it is possible to provide the user with second review information in which only playbook information that matches the position related to the document to be supported is extracted, thereby supporting a highly accurate and efficient review process.

[0153] [Third Example of the Second Review Process] Next, a third example of the second review process implemented by the document browsing support system S will be described. The second review process according to the third example generates second review information including all playbook information associated with each provision type when multiple provision types exist in one provision (for example, when two or more provision types, such as "Effect of Rights" and "Restriction of Effect of Rights," are registered in one provision). Note that when comparing the second review process according to the first example with the second review process according to the third example, only the content of the second review process shown in step S18 in FIG. 11 is different.

[0154] Fig. 13 is a flowchart showing the flow of the second review process according to the third example, which is executed in step S18 of Fig. 11. As shown in Fig. 13, the analysis unit 103 of the information processing device 10 executes the first review process (i.e., review process executed based on highly versatile standards prepared by, for example, a party providing the document browsing assistance service) using, for example, a first database (step S180c), and generates first review information about the document to be supported (step S181c).

[0155] Next, the analysis unit 103 of the information processing device 10 refers to, for example, the second database and extracts the article type associated with the target article (step S182c).

[0156] The analysis unit 103 of the information processing device 10 refers to the second database and determines whether or not playbook information associated with the extracted clause type exists (step S183c).

[0157] If it is determined that playbook information associated with the clause type exists (Yes in step S183c), the analysis unit 103 of the information processing device 10 stores the playbook information associated with the clause type and its meta information (playbook meta information) as display targets in the first storage unit 119 (step S184c). On the other hand, if it is determined that playbook information associated with the clause type does not exist (No in step S183c), the analysis unit 103 of the information processing device 10 transitions the processing to step S185c.

[0158] The analysis unit 103 of the information processing device 10 refers to the second database and determines whether or not there remains any article type associated with the target article (step S185c).

[0159] If it is determined that there are any article types associated with the target article (Yes in step S185c), the analysis unit 103 of the information processing device 10 repeatedly executes the processes of steps S182c to S185c and stores playbook information for each article type. On the other hand, if it is determined that there are no article types associated with the target article (No in step S185c), the analysis unit 103 of the information processing device 10 generates second review information by combining the playbook information and playbook meta information stored in step S184c with the first review information generated in step S181c (step S186c).

[0160] The analysis unit 103 of the information processing device 10 determines whether the next article exists (step S187c). If it is determined that the next article exists (Yes in step S187c), the analysis unit 103 of the information processing device 10 repeats the processes of steps S182c to S187c to update the second review information. On the other hand, if it is determined that the next article does not exist (No in step S187c), the analysis unit 103 of the information processing device 10 determines the content of the second review information (step S188c).

[0161] According to the second review process of the third example, even when one article has multiple article types, it is possible to generate second review information that includes all of the playbook information associated with each article type, thereby supporting highly accurate and efficient review processes.

[0162] The information processing device 10 according to this embodiment includes a first database, a second database, an acquisition unit 111, an analysis unit 113, and a first control unit 117. The first database is, for example, an alert information database in which multiple pieces of alert information that alert the user to the content of document units constituting a document are registered by document unit type based on a first criterion (e.g., a highly versatile criterion prepared by the party providing the document browsing support service). The second database is, for example, a playbook information database in which multiple pieces of playbook information that alert the user to the content of document units constituting a document are registered by document unit type based on a second criterion (e.g., a unique (individual) criterion of the party receiving the document browsing support service). The acquisition unit 111 acquires the support target document. The analysis unit 113 extracts at least one piece of alert information from the alert information database based on the type of support target document unit that constitutes the support target document, extracts at least one piece of playbook information from the playbook information database based on the type of support target document unit that constitutes the support target document, and performs a second review process on the support target document to generate second review information that includes the extracted alert information and the extracted playbook information. The first control unit 117 displays the second review information and the corresponding support target document unit on the display device 30 of the terminal device T1.

[0163] Therefore, the user can execute a review process and check the results using not only the highly versatile criteria prepared by the document viewing support service provider, but also their own (individual) criteria registered as playbook information. As a result, a support technology can be provided that realizes automatic review processing of documents using individual criteria.

[0164] Furthermore, according to the information processing device 10 of the embodiment, playbook information can be registered in the second database at any time for each document unit type (article type). Therefore, the user can freely customize the playbook information and execute a second review process using unique (individual) criteria. As a result, a support technology that realizes a highly flexible automatic review process can be provided.

[0165] Furthermore, according to the information processing device 10 of the embodiment, when registering playbook information, the playbook information can be registered in association with related alert information from an alert information list display screen on which multiple pieces of alert information are displayed by document unit type. Furthermore, when registering playbook information, the playbook information can also be registered in association with related alert information from a review information display screen that is displayed after executing a review process on the support target document. Therefore, the user can register playbook information while checking the associated document unit type (article type) and the content of the alert information based on the related first criteria.

[0166] Furthermore, according to the information processing device 10 of the embodiment, playbook information can be registered in association with at least one attribute of the type of document to be supported, the importance of each document, the user's position, and the update date and time.

[0167] The display order of the playbook information included in the second review information on the document review screen can be controlled based on, for example, the importance and update date and time included in the playbook meta information. Also, the playbook information included in the second review information can be filtered and displayed based on at least one of the type of document to be supported, the importance of the clause, and the user's position.

[0168] Therefore, the user can display only the playbook information narrowed down by the desired conditions (playbook meta information). As a result, it is possible to provide a support technology that realizes a review process with high flexibility and accuracy.

[0169] The second review information may also include status information indicating whether each playbook information item has been addressed or not. The status may be changed in response to an input from the user on the document review screen.

[0170] Therefore, the user can manage the status of each playbook information, which makes it possible to provide a user-friendly review process based on their own criteria.

[0171] Second Embodiment Next, a document browsing support system S according to a second embodiment will be described. The document browsing support system S according to the second embodiment registers playbook information for a document to be supported, for example, by using a document before correction and a document after correction.

[0172] Here, in this embodiment, a document before revision of a support target document (hereinafter simply referred to as a "pre-revision document") is a document (e.g., a first-version document) in which an administrator or a responsible person has not yet made any content modifications, additions, deletions, or comments to the support target document. Furthermore, a document after revision of a support target document (hereinafter simply referred to as a "post-revision document") is a document (e.g., a final version document) in which an administrator or a responsible person has made content modifications, additions, deletions, or comments to the support target document. Note that the pre-revision document and the post-revision document are not limited to those described above. When a document is designated as a post-revision document, any document in an earlier version may be designated as the pre-revision document. Furthermore, when a document is designated as a post-revision document, a template for that document may be designated as the pre-revision document. In other words, the pre-revision document and the post-revision document may be different enough to generate playbook information, and the post-revision document does not necessarily have to be created based on the pre-revision document. The final version of the document is generally one for which the document review has been completed and which is often considered desirable from the user's perspective, so by using the final version of the document as the revised document, appropriate playbook information can be generated.

[0173] 15 is a flowchart showing an example of the flow of the playbook information registration process according to the second embodiment. As shown in FIG. 15, first, the second control unit 40 of the terminal device T1 of this embodiment launches the browser unit 42 in response to, for example, an instruction from a user. The browser unit 42 of the terminal device T1 transmits login information such as an initial access URL and a registration ID to the information processing device 10 (step S21).

[0174] The first control unit 117 of the information processing device 10 of this embodiment executes authentication processing in response to login information from the terminal device T1, for example. The first control unit 117 also transmits document browsing support screen information generated by the first control unit 117 (step S22).

[0175] The browser unit 42 of the terminal device T1 of this embodiment displays the document browsing assistance screen on the display device 30 based on the document browsing assistance screen information received from the information processing device 10, for example (step S23).

[0176] The second control unit 40 of the terminal device T1 transmits the pre-edited document and the post-edited document to the information processing device 10 in response to, for example, an upload instruction from the user (step S24).

[0177] The acquisition unit 111 of the information processing device 10 stores the pre-edited document and the post-edited document received from, for example, the terminal device T1 in the first storage unit 119. The registration unit 114 of the information processing device 10 executes a difference information detection process using the pre-edited document and the post-edited document (step S25).

[0178] Here, the difference information detection process is a process of detecting differences in content between a post-editing document and a pre-editing document and generating difference information indicating the differences. Therefore, the difference information may include information such as what information has been modified, added, or deleted from the pre-editing document, and what comments have been added. The difference information detection process is performed, for example, by dividing the pre-editing document and the post-editing document into document units such as paragraphs, articles, clauses, and subsections, comparing the document units based on the article type, and generating difference information for each document unit if differences exist. The difference information may also include differences in meta-information such as document type and language added to the pre-editing document and the post-editing document.

[0179] The first control unit 117 of the information processing device 10 transmits the generated difference information to the terminal device T1 (step S26).

[0180] The browser unit 42 of the terminal device T1 displays on the display device 30 a registration necessity selection screen including the received difference information and a selection check box for instructing whether or not to register playbook information using the difference information (step S27).

[0181] When the browser unit 42 of the terminal device T1 receives a selection instruction via a selection checkbox to "not register playbook information using difference information" (No in step S28), it terminates the playbook information registration process. On the other hand, when the browser unit 42 of the terminal device T1 receives a selection instruction via a selection checkbox to "register playbook information using difference information" (Yes in step S28), it transmits the selection instruction to the information processing device 10.

[0182] The first control unit 117 of the information processing device 10 receives a selection instruction from the terminal device T1 to "register playbook information using difference information" (step S30), and classifies the difference information for each document unit into article types and registers them as playbook information in the second database (step S31).

[0183] According to the second embodiment, a user can automatically register new playbook information in the second database by uploading the pre-edited and post-edited documents of the support target document. Therefore, the user's workload can be reduced compared to when the user selects desired information from the alert information list and registers playbook information via the GUI shown in FIG. 5C . Note that the difference information may be edited or otherwise modified by the user or the system to become playbook information. In this case, the change may be possible on the registration necessity screen. Furthermore, when registering playbook information, other information (e.g., playbook meta information) may also be registered.

[0184] (Variation 1) In the first embodiment, as shown in Fig. 5C, a GUI was exemplified in which an "Add Playbook button" was provided for each provision type on the alert information list display screen. In contrast to this, on the review information display screen shown in Fig. 4A, as shown in Fig. 14, an "Add Playbook button" may be provided for each piece of alert information, and playbook information and playbook meta information may be edited and registered by operating the "Add Playbook button."

[0185] (Variation 2) In the first embodiment, an example was given in which a GUI for a user to register playbook information is displayed on the screen, and the playbook information is registered in the second database from the GUI. In contrast, for example, in registering playbook information, a trained model may be used to determine the document unit type (article type) to which each playbook information should be associated, and the playbook information may be associated with at least one determined document unit type and registered in the second database. Note that if the determined document unit type is inappropriate, the playbook information may be associated with another document unit type selected by the user.

[0186] (Variation 3) Some or all of the devices in the above-described embodiments may be configured with hardware, or may be configured with information processing software (programs) executed by a CPU, a GPU, etc. Furthermore, in the above-described embodiments, when multiple storage devices store data, each of the multiple storage devices may store only a portion of the data, or may store the entire data.

[0187] An information processing method according to an embodiment uses a first database in which a plurality of pieces of alert information that alert a user to the contents of document units that constitute a document based on a first criterion is registered by document unit type, and a second database in which a plurality of pieces of playbook information that alert a user to the contents of document units that constitute a document based on a second criterion is registered by document unit type, and includes the steps of: acquiring a support target document; extracting at least one piece of alert information from the first database based on the type of support target document unit that constitutes the support target document; extracting at least one piece of playbook information from the second database based on the type of support target document unit that constitutes the support target document; performing a review process on the support target document; generating review information that includes the extracted alert information and the extracted playbook information; and displaying the review information and the corresponding support target document unit on a display device.

[0188] An information processing method according to an embodiment is an information processing method that uses a first database in which a plurality of pieces of alert information that alert a user to the contents of document units that constitute a document based on a first criterion are registered by type of document unit, and that generates a second database by registering a plurality of pieces of playbook information that alert a user to the contents of document units that constitute a document based on a second criterion by type of document unit, acquires a support target document, extracts at least one piece of alert information from the first database based on the type of support target document unit that constitutes the support target document, extracts at least one piece of playbook information from the second database based on the type of support target document unit that constitutes the support target document, performs a review process on the support target document, generates review information that includes the extracted alert information and the extracted playbook information, and displays the review information and the corresponding support target document unit on a display device.

[0189] An information processing program according to an embodiment uses a first database in which a plurality of pieces of alert information that alert the user to the contents of document units that make up a document based on a first criterion is registered by document unit type, and a second database in which a plurality of pieces of playbook information that alert the user to the contents of document units that make up a document based on a second criterion is registered by document unit type to acquire a support target document, extract at least one piece of alert information from the first database based on the type of support target document unit that makes up the support target document, extract at least one piece of playbook information from the second database based on the type of support target document unit that makes up the support target document, perform a review process on the support target document, generate review information that includes the extracted alert information and the extracted playbook information, and display the review information and the corresponding support target document unit on a display device.

[0190] An information processing program according to an embodiment uses a first database in which a plurality of pieces of alert information that alert the user to the contents of document units that make up a document based on a first criterion are registered by type of document unit, and generates a second database by registering a plurality of pieces of playbook information that alert the user to the contents of document units that make up a document based on a second criterion by type of document unit, acquires a support target document, extracts at least one piece of alert information from the first database based on the type of support target document unit that makes up the support target document, extracts at least one piece of playbook information from the second database based on the type of support target document unit that makes up the support target document, performs a review process on the support target document, generates review information including the extracted alert information and the extracted playbook information, and displays the review information and the corresponding support target document unit on a display device.

[0191] Although the embodiments of the present disclosure have been described in detail above, these embodiments are presented as examples and are not intended to be limiting. Each embodiment can be modified by various additions, changes, substitutions, partial deletions, combinations, etc., without departing from the technical spirit of the present invention. These embodiments and their modifications are included within the scope of the invention described in the claims and their equivalents.

Claims

1. An information processing method comprising: extracting at least one piece of alert information based on a support target document from a first database having a plurality of pieces of alert information that alert a user to the contents of document units that constitute the document based on a first criterion; extracting at least one piece of playbook information based on the support target document from a second database in which playbook information that alerts a user to the contents of document units that constitute the document based on a second criterion is registered and the playbook information is editable; and generating review information including the playbook information.

2. An information processing method using a first database in which multiple alert information that draws a user's attention based on a first criterion about the contents of document units that make up a document is registered by type of the document unit, comprising: editing a second database by registering multiple playbook information that draws a user's attention based on a second criterion about the contents of document units that make up a document by type of the document unit; acquiring a support target document; extracting at least one of the alert information from the first database based on the type of the support target document unit that makes up the support target document; extracting at least one of the playbook information from the second database based on the type of the support target document unit that makes up the support target document; performing a review process on the support target document to generate review information including the extracted alert information and the extracted playbook information; and displaying the review information and the corresponding support target document unit on a display device.

3. The information processing method of claim 2, further comprising the step of: in registering the playbook information, registering the playbook information in association with the related alert information from a display screen on which the multiple alert information are displayed by the type of the document unit.

4. The information processing method of claim 2, further comprising the step of: registering the playbook information in association with the related alert information from a display screen of review information displayed by executing a review process on the support target document.

5. The information processing method of claim 2, further comprising the steps of: inputting the acquired playbook information into a learned model to determine the type of at least one of the document units to be registered; and registering the acquired playbook information in a second database by associating it with the determined type of the at least one of the document units.

6. The information processing method according to claim 2, wherein in registering the playbook information, the playbook information is generated based on difference information between a pre-modification document and a post-modification document.

7. The information processing method according to claim 1 or 2, wherein the document to be supported is a legal document, and the document unit is a clause unit.

8. The information processing method according to claim 2, wherein the playbook information is registered in association with at least one attribute selected from the type of the document to be supported, the importance of the document unit to be supported, the user's position, and the update date and time, and the review process is performed based on the attribute.

9. The information processing method according to claim 8, further comprising: determining a display order of the playbook information included in the review information based on the importance.

10. The information processing method according to claim 8, further comprising determining a display order of the playbook information included in the review information based on the update date and time.

11. The information processing method according to claim 8, further comprising filtering the playbook information included in the review information based on at least one of the type of the support target document, the importance of the support target document unit, and the user's position.

12. An information processing method as described in claim 1 or 2, further comprising: the review information including status information indicating completion or incompletion of the playbook information; and changing the status information in response to input from a user.

13. The information processing method according to claim 2, further comprising: dividing the acquired support target document into a plurality of support target document units; and determining the type for each of the plurality of support target document units.

14. The information processing method according to claim 1 or 2, wherein the review information includes information that distinguishes between the alert information and the playbook information.

15. An information processing device comprising: a first database in which multiple alert information that draws a user's attention based on a first criterion regarding the contents of document units that make up a document is registered; a second database in which playbook information that draws a user's attention based on a second criterion regarding the contents of document units that make up a document is registered; an analysis unit that extracts at least one of the alert information from the first database based on a support target document, extracts at least one of the playbook information from the second database based on the support target document, and generates review information including the playbook information; and a control unit that outputs the review information and the support target document unit corresponding to the support target document to an output device.

Images