Program, method, information processing device, and system

Abstract

There is a problem in that suitable patent documentation is not being created. [Solution] A program to be executed by a computer having a processor and a memory unit, the program executing a proposal acquisition step in which the processor acquires proposal information describing an invention, and a specification acquisition step in which specification information that structures the invention described in the proposal information in terms of elements and relationships based on the information output by inputting the proposal information and a first instruction that outputs the elements of the invention and relationships indicating the associations between multiple elements into a generation AI.

Description

[Technical Field]

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

[0002] Techniques for preparing patent documents are known. Patent Document 1 discloses a technology for assisting in the understanding of claims, which identifies and presents key elements in claims, enabling readers to focus on reading the explanation. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-096200 Summary of the Invention [Problem to be solved by the invention]

[0004] There is a problem in that suitable patent documentation is not being created. Therefore, the present disclosure has been made to solve the above problem, and its purpose is to provide a technique for creating suitable patent documents. The present disclosure also addresses the problem that documents such as invention proposals cannot be formatted into information (patent specifications) suitable for creating patent specifications, etc. The present disclosure has been made to solve the above problem, and its purpose is to format documents such as invention proposals into information (patent specifications) suitable for creating patent specifications, etc. In addition, the present disclosure provides inventions that address the following problems: We were unable to create prompts for creating suitable patent documents.We were unable to create prompts for formatting documents such as invention proposals into suitable information (patent specifications) when creating patent specifications, etc. [Means for solving the problem]

[0005] A program to be executed by a computer having a processor and a memory unit, the program executing a proposal acquisition step in which the processor acquires proposal information describing an invention, and a specification acquisition step in which specification information is acquired that structures the invention described in the proposal information in terms of elements and relationships, based on information output by inputting into a generation AI a first instruction for outputting elements of the invention and relationships showing the associations between multiple elements, and the proposal information. [Effects of the Invention]

[0006] According to the present disclosure, it is possible to create suitable patent documents. It is possible to format suitable information (patent specifications) when creating patent specifications, etc. It is possible to create prompts for generating AI such as large-scale language models to execute the above processes. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 2 is a block diagram showing the functional configuration of the system 1. [Figure 2] FIG. 2 is a block diagram showing the functional configuration of the server 10. [Figure 3] FIG. 2 is a block diagram showing the functional configuration of a user terminal 20. [Figure 4] FIG. 10 is a diagram showing the data structure of a user table 1012. [Figure 5] FIG. 10 is a diagram showing the data structure of a proposal table 1013. [Figure 6] FIG. 10 is a diagram showing the data structure of a specification table 1014. [Figure 7] FIG. 10 is a diagram showing the data structure of a structure table 1015. [Figure 8] FIG. 10 is a diagram showing the data structure of a viewpoint table 1016. [Figure 9] FIG. 10 is a diagram showing the data structure of a specification table 1017. [Figure 10] FIG. 10 is a diagram showing the data structure of a configuration table 1018. [Figure 11] FIG. 10 is a diagram showing the data structure of a precedent case table 1019. [Figure 12] FIG. 10 is a diagram showing the data structure of an instruction table 1031. [Figure 13] 10 is a flowchart showing the operation of a specification creation process. [Figure 14] 10 is a flowchart showing the operation of a specification preparation process. [Figure 15] 10 is a flowchart showing the operation of a precedent case analysis process. [Figure 16] FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all drawings describing the embodiments, common components are designated by the same reference numerals, and repeated description will be omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, each drawing is a schematic diagram and is not necessarily a precise illustration.

[0009] <System 1 Configuration> The system 1 in this disclosure is an information processing system that provides information services related to patents. The system 1 includes an information processing device including a server 10, a user terminal 20, and an artificial intelligence system 40, all of which are connected via a network N. FIG. 1 is a block diagram showing the functional configuration of the system 1. As shown in FIG. FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG. FIG. 3 is a block diagram showing the functional configuration of the user terminal 20. As shown in FIG.

[0010] Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the server 10, the user terminal 20, and the artificial intelligence system 40, descriptions that overlap with the basic hardware configuration and basic functional configuration of the computer will be omitted.

[0011] <Server 10 configuration> The server 10 is an information processing device that provides information services related to patents. The server 10 includes a storage unit 101 and a control unit 104 .

[0012] <Configuration of the storage unit 101 of the server 10> The memory unit 101 of the server 10 includes an application program 1011 , a user table 1012 , a proposal table 1013 , a specification table 1014 , a structure table 1015 , a viewpoint table 1016 , a description table 1017 , a configuration table 1018 , a precedent table 1019 , and an instruction table 1031 .

[0013] The application program 1011 is a program for causing the control unit 104 of the server 10 to function as each functional unit. Application programs 1011 include applications such as a web browser application.

[0014] User table 1012 is a table that stores and manages information about member users (hereinafter, "users") who use the service. When a user registers to use the service, the user's information is stored in a new record in user table 1012. This allows the user to use the service according to the present disclosure. The user table 1012 is a table having columns of user ID, user name, and user data, with the user ID as the primary key. FIG. 4 is a diagram showing the data structure of the user table 1012. As shown in FIG.

[0015] The user ID is an item that stores user identification information for identifying a user. The user identification information is an item that is set with a unique value for each user. The user name is an item for storing the name of the user. The user name may be set to any character string such as a nickname instead of a name. The user data includes information specific to the individual user and attribute information relating to the user's characteristics and background. The user's unique information includes information unique to the user, such as the user's date of birth (age), sex, and the like. The user's attribute information includes information such as the user's educational history (highest level of education, major, graduation year), occupation, work history, interests, place of residence, and language.

[0016] The proposal table 1013 is a table for storing and managing information related to proposals (proposal information). The proposal table 1013 is a table having a proposal ID as a primary key and columns of proposal ID, user ID, and proposal data. FIG. 5 is a diagram showing the data structure of the proposal table 1013.

[0017] The proposal ID is an item that stores proposal identification information for identifying a proposal. The proposal identification information is an item in which a unique value is set for each piece of proposal information. The user ID is an item for storing user identification information for identifying a user. Proposal data is an item that stores information about invention proposals. Proposal data also includes proposal data that has been converted (summarized) using predetermined rules or other artificial intelligence systems such as generation AI. Specifically, an invention proposal is a document prepared by an employee of an inventor who belongs to a company, etc., and includes information such as a claim outline that serves as the basis for the scope of the patent claims, specific explanations of embodiments, experimental data, measurement results, comparative data, examples, detailed explanations of manufacturing methods, usage methods, etc., drawings, flow charts, block diagrams, photographs, graphs, prior art documents, prior art search results, expected marketability, information on related cases, whether or not joint research or development has taken place, information on legal restrictions such as confidentiality agreements, and the results of in-house invention evaluations (rankings). The proposal data includes any documents, sentences, documents, etc. related to inventions created in-house, in addition to documents submitted to government agencies such as patent specifications and patent gazettes. The proposal data also includes notification documents, such as invention notification forms, submitted by employees of a company, etc., to their employers, etc., in accordance with invention and device regulations, etc. The proposal data also includes any documents, such as idea memos in which inventions are described. The proposal data may be an item that stores a file in any document format, such as text, Word, PowerPoint, or PDF.

[0018] The specification table 1014 is a table for storing and managing information relating to specifications (specification information). Specifically, patent specifications (hereinafter, "specifications") in this disclosure are stored in association with viewpoint information and structure information. Specification information includes viewpoint information and structure information. The specification table 1014 is an item that stores information about the invention content organized according to viewpoint and structure. This allows information such as unstructured invention proposals to be organized in a unified manner according to specific viewpoint types and structure types. Furthermore, high-quality patent specifications can be created from patent specifications. The specification table 1014 is a table having a specification ID as a primary key and columns of a specification ID, a proposal ID, and a user ID. FIG. 6 is a diagram showing the data structure of the specification table 1014.

[0019] The specification ID is an item that stores specification identification information for identifying a specification. The specification identification information is an item in which a unique value is set for each piece of specification information. The proposal ID is an item for storing proposal identification information for identifying a proposal. The user ID is an item for storing user identification information for identifying a user.

[0020] The structure table 1015 is a table for storing and managing information relating to the structure (structure information). The structure table 1015 is a table having a structure ID as a primary key and columns of a structure ID, a specification ID, a first group ID, a structure type, structure data, and novelty. FIG. 7 is a diagram showing the data structure of the structure table 1015.

[0021] The structure ID is an item that stores structure identification information for identifying a structure. The structure identification information is an item that has a unique value set for each piece of structure information. The specification ID is an item for storing specification identification information for identifying a specification. The first group ID is an item that stores group identification information for structural information. Specifically, multiple pieces of structural information stored in association with one specification identification information are stored in association with one or more related groups (clusters, segments). This allows one large piece of specification information to be regarded as a collection of multiple partial specification information. The structure type is an item for storing information about the type (type, class) of the structure. The structure type is an item for storing information (such as character strings) that indicates the type of structure when capturing an invention, such as an element, attribute, or relationship. Structure type: Element "Element" is a type of perspective when viewing an invention structurally. Specifically, the "components" that make up the subject invention are called "elements." Unlike the terms "configuration" and "component" commonly used in the patent industry, the term "element" in this disclosure does not include the connections (relationships, interactions, etc.) between elements. In the case of a method, an element is a meaningful single process (step) among the processes that make up the method. In the case of a program, an element is a function that performs a meaningful single calculation. Structure type: attribute "Attributes" are a type of perspective when structurally understanding an invention. Specifically, an "attribute" is something that "absolutely" defines the properties of an element. For example, the statement "The color of a car is red" is an "attribute" that defines the color of the element "car" as absolutely "red." Note that an "attribute" can be considered as a type of "relation" as shown below. An "attribute" can also be considered as part of an element. The structural type associated with an "attribute" can be omitted. Structure type: Relation "Relationship" is a perspective for structurally understanding an invention. Specifically, a "relationship" is something that "relatively" defines the relationship between elements. For example, the statement "An automobile is supported by wheels" defines the connection between an element called an automobile and another element called a wheel relatively by referencing each other, and is therefore a "relationship." The structure data is an item that stores information (structure information) about the structure of the invention. For example, for each structure type, information (text information, image information, etc.) about the structure of the invention extracted from the proposal data is stored as follows: In addition, structure data that has been converted (summarized) using predetermined rules or other artificial intelligence systems such as generation AI is also included in the structure data. Structure type: Element The "elements" are identified by element IDs (E1, E2, etc.), and information indicating the element (character string information, image information, etc.) is stored in association with each element ID. ·goggles Transmissive display Position sensor Head direction sensor Data Processing Unit Structure type: attribute "Attributes" are identified by attribute IDs (A1, A2, etc.), and information indicating the attribute (character string information, image information, etc.) is associated and stored for each attribute ID. In the case of attributes, the element ID of the target element (E1, E7, etc.) is associated and stored for each attribute ID. Attribute information includes attribute values ​​(type value, device, transparency type, location information, etc.) and attribute information types (kind value, features, detection target, processing, etc.). ·{Goggles, type: wearable device} ·{Transparent display, type:transparent, kind:features} {Location sensor, type: location information, kind: detection target} ·{Head direction sensor, type: direction information, kind: detection target} ·{Data Processing Unit, type:Data Processing, kind:Processing} Structure type: Relation "Relationships" are identified by relationship IDs (R1, R2, etc.), and are stored in association with information (text information, image information, etc.) that indicates the interrelationships (interactions) between multiple elements. Relationship information includes the following information: Information 1. Related elements: Related elements store information that indicates the relationship between two or more elements. Related elements store information (element IDs (e.g., [E1, E2])) that identify a group of elements that are included in the relationship. For example, the related elements store the physical relationships between elements (bonded, placed, adjacent, etc.), the input / output relationships of information, the input / output relationships of energy (electricity, electrothermal, vibration, mechanical energy, etc.), and the like. Information 2. Relationship type: The relationship type (type) stores information indicating the type of relationship. For example, the relationship type stores information indicating the relationship type such as "physical configuration," "data flow," "control relationship," and "functional cooperation." Information 3. Related content: The relationship content is an item that stores the specific content of the relationship. The relationship content stores information (character string information, image information, etc.) that explains the specific interactions and relationships between elements. { elements:[goggles, see-through display], type:physical configuration, Content: Goggles equipped with a transparent display } { elements: [goggles, position sensor, head direction sensor], type:physical configuration, content: Position sensors and head direction sensors are installed in the goggles } { elements: [position sensor, head direction sensor, data processing unit], type:dataflow, content: The congestion status acquisition, area identification, and display functions work together } Novelty is an item that stores information indicating the novelty of a structure. Specifically, novelty stores information such as 1 (novelty), 0 (no novelty), etc. For example, among the configurations, a configuration that is described in the precedent table 1019, etc. is associated and stored with "0 (no novelty)," and a configuration that is not described is associated and stored with "1 (novelty)."

[0022] The viewpoint table 1016 is a table for storing and managing information (viewpoint information) relating to viewpoints of the invention. The viewpoint table 1016 is a table having a viewpoint ID as a primary key and columns of viewpoint ID, specification ID, first group ID, viewpoint type, viewpoint data, and exclusion flag. FIG. 8 is a diagram showing the data structure of the viewpoint table 1016.

[0023] The viewpoint ID is an item for storing viewpoint identification information for identifying viewpoints of the invention. The viewpoint identification information is an item for which a unique value is set for each viewpoint information. The specification ID is an item for storing specification identification information for identifying a specification. The first group ID is an item for storing group identification information of the structure information. The viewpoint type is an item for storing information about the type (type, class) of the viewpoint. The viewpoint type is an item for storing information (such as a character string) indicating the type of viewpoint when grasping an invention, such as technical field, use, problem, solution (structure), effect, etc. The viewpoint type includes any viewpoint such as purpose, principle of operation, principle of action, industrial applicability, safety, risk assessment, application field, use case, etc. Furthermore, for example, the purpose may be subdivided and managed into technical purpose, industrial purpose, economic purpose, social purpose, etc. In this disclosure, a configuration in which the solution (configuration, structure) is stored and managed in the structure table 1015 is disclosed as an example. The structure information may also be stored in the viewpoint table 1016. The viewpoint information may also be stored in the structure table 1015. The viewpoint data is an item for storing information (viewpoint information) relating to the viewpoint of the invention. For example, for each viewpoint type, information (text information, image information, etc.) related to the viewpoint extracted from the proposal data is stored as follows: In addition, viewpoint data that has been converted (summarized) using predetermined rules or other artificial intelligence systems such as generation AI is also included in the viewpoint data. Viewpoint type: Technical field AR goggle technology Transparent display technology Wearable device technology · Viewpoint type: Usage Use as goggles at ski resorts Check the lift congestion status Check restaurant congestion status Perspective type: Issue The ski resort is so large that it is difficult to locate the facilities. -Poor visibility of lift position in bad weather - Low visibility of restaurant location in bad weather - It is difficult to grasp the congestion status of the facility - Reduced user convenience Viewpoint type: Function - Obtaining congestion status for each area - Obtaining the user's current location -Information on congestion status in the surrounding area -Detection of user's head position and direction - Identifying the area within the user's field of view Highlighting of less crowded areas Perspective type: Structure Goggles with a transparent display Location information acquisition system Head direction detection system ·Crowd status acquisition and display program Area-specific programs Perspective type: Effect - Check lift congestion status even in bad weather - Check restaurant congestion even in bad weather - Providing appropriate information according to the user's location and direction -Improved facility utilization efficiency in poor visibility environments - Disperse users by directing them to less crowded facilities The exclusion flag is an item that stores information indicating whether or not a viewpoint is to be used in the specification preparation described below. Specifically, the exclusion flag stores information such as 0 (excluded) or 1 (not excluded). An excluded viewpoint is a viewpoint that will not be used in the specification preparation.

[0024] The specification table 1017 is a table for storing and managing information related to patent specifications (specification information). While the present disclosure has disclosed an example of a configuration for storing claims, detailed descriptions of the invention, and drawings, the present disclosure is not limited to this. For example, a separate column may be provided for each of the items constituting a specification, such as an abstract, title of the invention, technical field, background art, prior art documents, patent documents, non-patent documents, summary of the invention, problem to be solved by the invention, means for solving the problem, effects of the invention, brief description of the drawings, mode for carrying out the invention, examples, industrial applicability, explanations of symbols, accession numbers, and free text for sequence listings. The specification may also include drawings. Although a patent specification will be described as an example in this disclosure, the present invention may be applied to any document other than a patent, any legal document (such as a contract), and the like. The specification table 1017 is a table having a specification ID as a primary key, and columns for specification ID, specification ID, user ID, claims, detailed description of the invention, and drawings. FIG. 9 is a diagram showing the data structure of the specification table 1017.

[0025] The specification ID is an item that stores specification identification information for identifying a patent specification. The specification identification information is an item that has a unique value set for each specification. The specification ID is an item for storing specification identification information for identifying a specification. The user ID is an item for storing user identification information for identifying a user. The claims are items that store the claims of a patent specification. The claims may contain a plurality of claims, each of which may consist of a plurality of elements. In addition, claims that have been converted (summarized) using predetermined rules or other artificial intelligence systems such as generation AI are also included in the scope of claims. The detailed description of the invention is an item that stores the item of the detailed description of the invention in the patent specification. In addition, in the present disclosure, as an example, the detailed description of the invention may be an item that stores items in a patent specification that are not included in the claims. In addition, the detailed description of the invention may also be converted (summarized) using predetermined rules or other artificial intelligence systems such as generation AI. Drawings is an item that stores the drawing items in the patent specification.

[0026] The configuration table 1018 is a table for storing and managing information (configuration information) relating to the configuration of the claims (the constituent elements of the invention content described in the claims, hereinafter referred to as configuration). In the present disclosure, each of the claims stored in the claims of the specification table 1017 is stored in a respective record of the configuration table 1018. The configuration table 1018 is a table having the configuration ID as a primary key, and columns of configuration ID, specification ID, claim number, second group ID, and configuration. FIG. 10 is a diagram showing the data structure of the configuration table 1018.

[0027] The configuration ID is an item that stores configuration identification information for identifying a configuration. The configuration identification information is an item that has a unique value set for each piece of configuration information. The statement ID is an item for storing statement identification information for identifying a statement. The claim number is an item for storing the claim number of the claim to which the configuration belongs. Specifically, the claim number stores information indicating the claim number of claim 1, claim 2, etc. The second group ID is an item for storing second group identification information for identifying the second group. A structure is an item that stores information about a structure. Specifically, a structure is an item that stores information that indicates a structure (such as a character string or an image). Structures also include those that have been converted (summarized) using predetermined rules or other artificial intelligence systems such as generation AI.

[0028] The precedent case table 1019 is a table for storing and managing information relating to precedent cases (precedent case information). The precedent case table 1019 is a table having a precedent case ID as a primary key and columns of a precedent case ID, a user ID, and precedent case data. FIG. 11 is a diagram showing the data structure of the precedent case table 1019.

[0029] The precedent case ID is an item for storing precedent case identification information for identifying a precedent case. The precedent case identification information is an item for which a unique value is set for each precedent case information. The user ID is an item for storing user identification information for identifying a user. The precedent data is an item for storing precedent information relating to prior art documents (prior art documents). The prior art data may be an item that stores files in any document format, such as text, Word, PowerPoint, PDF, etc. The prior art data may also be configured to store patent numbers, patent publication numbers, and other identification information that can be used to reference prior art. Prior art data may also include data that has been converted (summarized) using predetermined rules or other artificial intelligence systems, such as generation AI.

[0030] The instruction table 1031 is a table for storing and managing information relating to instructions (instruction information). The instruction table 1031 is a table having an instruction ID as a primary key and columns of an instruction ID, an instruction type, and an instruction statement. FIG. 12 is a diagram showing the data structure of the instruction table 1031. As shown in FIG.

[0031] The instruction ID is an item for storing instruction identification information for identifying an instruction, and a unique value is set for each instruction. The instruction type is an item for storing the type of instruction. Specifically, information (character strings, etc.) indicating the process to be used, such as a specification creation process, a description creation process, or a precedent analysis process, may be stored. Alternatively, information (character strings, etc.) specifying the process that uses the instruction may be stored. The instruction text field stores an instruction text. In the present disclosure, various processes according to the present disclosure can be executed by creating prompts using instruction texts identified according to instruction IDs or instruction types in various tasks.

[0032] <Configuration of the control unit 104 of the server 10> The control unit 104 of the server 10 includes a user registration control unit 1041, a creation unit 1042, and an analysis unit 1043. The control unit 104 executes an application program 1011 stored in the storage unit 101, thereby realizing each functional unit.

[0033] The user registration control unit 1041 performs processing to store information about users who wish to use the service according to the present disclosure in the user table 1012. The information stored in the user table 1012 is generated when a user opens a web page operated by a service provider from any information processing terminal, enters information into a predetermined input form, and transmits the information to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, completing the user registration. This allows the user stored in the user table 1012 to use the service. Before the user registration control unit 1041 registers the user information in the user table 1012, the service provider may conduct a predetermined examination to restrict whether or not the user is permitted to use the service. The user ID may be any character string or number that can identify the user, any character string or number desired by the user, or may be automatically set by the user registration control unit 1041.

[0034] The creation unit 1042 performs a process of creating a prompt.

[0035] The analysis unit 1043 performs processing to analyze documents relating to the invention.

[0036] <Configuration of User Terminal 20> The user terminal 20 is an information processing device operated by a user who uses a service. The user terminal 20 may be, for example, a mobile terminal such as a smartphone or tablet, a stationary personal computer (PC) or a laptop PC, or a wearable terminal such as a head mounted display (HMD) or a wristwatch terminal. The user terminal 20 includes a storage unit 201 , a control unit 204 , an input device 206 , and an output device 208 .

[0037] <Configuration of the storage unit 201 of the user terminal 20> The storage unit 201 of the user terminal 20 includes a user ID 2011 and an application program 2012 .

[0038] The user ID 2011 is the user's account ID. The user transmits the user ID 2011 from the user terminal 20 to the server 10. The server 10 identifies the user based on the user ID 2011 and provides the user with the service according to the present disclosure. The user ID 2011 includes information such as a session ID temporarily assigned by the server 10 to identify the user using the user terminal 20.

[0039] The application program 2012 may be stored in advance in the storage unit 201, or may be configured to be downloaded from a web server or the like operated by a service provider via a communication IF. The application programs 2012 include applications such as a web browser application. The application program 2012 includes an interpreted programming language such as JavaScript (registered trademark) that runs on a web browser application stored on the user terminal 20.

[0040] <Configuration of the control unit 204 of the user terminal 20> The control unit 204 of the user terminal 20 includes an input control unit 2041 and an output control unit 2042. The control unit 204 executes an application program 2012 stored in the storage unit 201, thereby realizing each functional unit.

[0041] <Configuration of the input device 206 of the user terminal 20> The input device 206 of the user terminal 20 includes a camera 2061 , a microphone 2062 , a position information sensor 2063 , a motion sensor 2064 , and a touch device 2065 .

[0042] <Configuration of the output device 208 of the user terminal 20> The output device 208 of the user terminal 20 includes a display 2081 and a speaker 2082 .

[0043] <Configuration of Artificial Intelligence System 40> The artificial intelligence system 40 is an information processing device that outputs a response to a prompt. For example, the artificial intelligence system 40 includes generative AIs such as ChatGPT, OpenAI GPT, Anthropic Claude3, PerplexityAsk, and BingAI, large-scale language models, and the like. These artificial intelligence systems have a dialogue (chat) function, and a user can provide any inquiry or command to the artificial intelligence system in text to receive a response to the inquiry or command. In the present disclosure, a user can obtain a text response that assists in the reading comprehension of patent documents by sending a prompt created during query processing to the artificial intelligence system 40. In addition, in this disclosure, the artificial intelligence system is not limited to a text-based dialogue system. For example, it may be an image generation AI system such as Midjourney or Stable Diffusion. For example, a user can send a prompt created in an inquiry process to such an image generation AI system to obtain an image or video as a response that assists in reading and understanding patent documents. Additionally, the present disclosure can also be applied to an artificial intelligence system that outputs answer content in the form of video, audio, etc. The artificial intelligence system 40 includes a generative AI and a large-scale language model system (LLM system).

[0044] <System 1 Operation> Each process of the system 1 will be explained below. FIG. 13 is a flowchart showing the operation of the specification creation process. FIG. 14 is a flowchart showing the operation of the specification preparation process. FIG. 15 is a flowchart showing the operation of the precedent case analysis process.

[0045] <Specification creation process> This is a process for creating documents (patent specifications) that are uniformly organized according to specific viewpoint types and structure types from proposal information such as non-standard invention proposals.

[0046] <Outline of the specification creation process> The specification creation process is a series of processes that receive a proposal, extract and store first perspective information, extract and store first structural information, compare it with prior examples, explore concepts such as higher-level concepts and intermediate-level concepts, and generate second perspective information.

[0047] <Details of the specification creation process> The specification creation process will be described in detail below.

[0048] The user operates the input device 206 of the user terminal 20 to input the URL of a page for executing the specification creation process (specification creation process page) into a web browser or the like, and opens the specification creation process page. The control unit 204 of the user terminal 20 sends a request to the server 10 to open the specification creation process page. Based on the received request, the control unit 104 of the server 10 generates a specification creation process page and sends it to the user terminal 20. The control unit 204 of the user terminal 20 displays the received specification creation process page on the display 2081 of the user terminal 20. The specification creation page includes a proposal information input field for accepting input of proposal information, and a prior example information input field for accepting input of one or more pieces of prior example information. A proposal, also called an invention proposal, is a document prepared by an employee of an inventor belonging to a company, etc., and serves as a starting point for a patent specification, etc. Details are explained in the proposal data of proposal table 1013. The prior art is a prior art document, and details are explained in the prior art data of the prior art table 1019 .

[0049] <Proposal acceptance> In step S101, the creation unit 1042 of the server 10 executes a proposal acquisition step of acquiring proposal information in which an invention is described. Specifically, the user operates the input device 206 of the user terminal 20 to input information about the invention (such as character strings, text, images, and other documents containing these) into the proposal information input field. The user may also operate the input device 206 of the user terminal 20 to upload document files such as Word and PDF to the proposal information input field. The control unit 204 of the user terminal 20 transmits the user ID 2011 and the input data entered into the proposal information input field to the server 10. The creation unit 1042 of the server 10 receives and acquires the input data received from the user terminal 20. The creation unit 1042 of the server 10 stores the user ID 2011 and the input data in the user ID and proposal data fields of a new record in the proposal table 1013. The creation unit 1042 of the server 10 creates a new record of specification information in the specification table 1014, and stores the user ID 2011 and the proposal ID of the new record in the user ID and proposal ID fields, respectively. The proposal data does not necessarily have to be uploaded by the user, but may be acquired automatically in cooperation with an external system such as another proposal management system or invention notification system.

[0050] <Precedent acceptance> The creating unit 1042 of the server 10 executes a precedent acquisition step of acquiring precedent information in which precedents are described. Specifically, the user operates the input device 206 of the user terminal 20 to input information about the prior case (such as character strings, text, images, and other documents containing these) into the prior case information input field. The user may also operate the input device 206 of the user terminal 20 to upload a document file, such as Word or PDF, to the prior case information input field. The control unit 204 of the user terminal 20 transmits the user ID 2011 and the input data entered into the prior case information input field to the server 10. The creation unit 1042 of the server 10 receives and acquires the input data received from the user terminal 20. The creation unit 1042 of the server 10 stores the user ID 2011 and the input data in the user ID and prior case data fields of a new record in the prior case table 1019. The prior case data may be configured to store a patent number, a patent publication number, or other identification information that can reference a prior case. In the present disclosure, the configuration is such that input of the prior example is accepted from a user, but this is not limited thereto. For example, the prior example may be stored in advance in the storage unit 101 of the server 10, or may be acquired by referring to an external system. Alternatively, one or more prior examples may be identified by searching a patent database (not shown) or the like based on proposal information (information based on the proposal information, such as viewpoint information, structure information, specification information, and configuration information, which is created based on the proposal information, as described below), and input of the prior example (patent number, patent publication number, or other identification information that can refer to the prior example) may be accepted.

[0051] <First structure extraction / memory> In step S102, the creation unit 1042 of the server 10 executes a specification acquisition step to acquire specification information that structures the invention described in the proposal information from the perspective of elements and relationships, based on the information output by inputting the first instruction to output the elements of the invention and relationships showing the associations between multiple elements and the proposal information into the generation AI. Specifically, the creation unit 1042 of the server 10 creates a first prompt by including the proposal data acquired in step S101 in the {proposal information} section of the first instruction. <1st instruction> #Instructions From the following proposed information describing a patented invention: Please print out each element, attribute, and relationship of the invention. {Proposal Information}

[0052] The creation unit 1042 of the server 10 inputs the created first prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs a first response content to the first prompt to the server 10. The first response content is an example of proposal information related to AR ski goggles. <First answer content> ·element ·goggles Transmissive display Position sensor Head direction sensor Data Processing Unit ·attribute ·{Goggles, type: wearable device} ·{Transparent display, type:transparent, kind:features} {Location sensor, type: location information, kind: detection target} ·{Head direction sensor, type: direction information, kind: detection target} { Data processing unit, type: Data processing, kind: Processing} ·relationship { elements:[goggles, see-through display], type:physical configuration, Content: Goggles equipped with a transparent display } { elements: [goggles, position sensor, head direction sensor], type:physical configuration, content: Position sensors and head direction sensors are installed in the goggles } { elements: [position sensor, head direction sensor, data processing unit], type:dataflow, content: The congestion status acquisition, area identification, and display functions work together }

[0053] The creation unit 1042 of the server 10 divides the first response contents into structure types (elements, attributes, relationships), etc., and stores the first response contents for each structure type in the structure type and structure data items of a new record in the structure table 1015. The specification ID stores the specification ID of the specification information created in step S101. The novelty flag stores a value of 0 (no novelty).

[0054] <First viewpoint extraction and memory> In step S103, the specification acquisition step includes a step of acquiring specification information structured from a predetermined perspective including the problem or effect of the invention based on information output by inputting a second instruction for outputting a predetermined perspective including the problem or effect of the invention and at least a part of the proposed information into the generation AI. Specifically, the creation unit 1042 of the server 10 creates a second prompt by including the proposal data acquired in step S101 in the {proposal information} section of the second instruction. <Second instruction> #Instructions From the following proposed information describing a patented invention: Please print out the technical field, application, problem, function, configuration, and effect of the invention. {Proposal Information}

[0055] The creation unit 1042 of the server 10 inputs the created second prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs a second response content to the second prompt to the server 10. The second response content is an example of proposal information related to AR ski goggles. <2nd answer content> Viewpoint type: Technical field AR goggle technology Transparent display technology Wearable device technology · Viewpoint type: Usage Use as goggles at ski resorts Check the lift congestion status Check restaurant congestion status Perspective type: Issue The ski resort is so large that it is difficult to locate the facilities. -Poor visibility of lift position in bad weather - Low visibility of restaurant location in bad weather - It is difficult to grasp the congestion status of the facility - Reduced user convenience Viewpoint type: Function - Obtaining congestion status for each area - Obtaining the user's current location -Information on congestion status in the surrounding area -Detection of user's head position and direction - Identifying the area within the user's field of view Highlighting of less crowded areas Perspective type: Structure Goggles with a transparent display Location information acquisition system Head direction detection system ·Crowd status acquisition and display program Area-specific programs Perspective type: Effect - Check lift congestion status even in bad weather - Check restaurant congestion even in bad weather - Providing appropriate information according to the user's location and direction -Improved facility utilization efficiency in poor visibility environments - Disperse users by directing them to less crowded facilities

[0056] The creation unit 1042 of the server 10 divides the second response content into perspectives (technical field, use, problem, function, configuration, effect), etc., and stores the second response content for each perspective type in the perspective type and perspective data items of a new record in the perspective table 1016. The specification ID stores the specification ID of the specification information created in step S101. The exclusion flag stores a value of 0 (exclude). The perspectives extracted from the proposal information are not used in creating the specification. Note that the perspectives extracted from the proposal information may also be used in creating the specification.

[0057] In the present disclosure, an example has been described in which the structure extraction in step S102 and the viewpoint extraction in step S103 are performed by using different instruction sentences, namely, a first instruction and a second instruction, to create the first prompt and the second prompt, respectively, but this is not limiting. For example, the structure extraction and viewpoint extraction may be performed in one step using a prompt created by including suggested information in an instruction that combines the first instruction and the second instruction (including the first instruction and the second instruction). In other words, steps S102 and S103 may be performed in a single step.

[0058] <Comparison with previous cases> In step S104, the creation unit 1042 of the server 10 executes a prior case acquisition step of acquiring one or more pieces of prior case information in which prior art is described. Specifically, the creation unit 1042 of the server 10 refers to the precedent table 1019 and acquires precedent information including precedent data. If the precedent data item stores a patent number, a patent publication number, or other identification information that can be used to reference a precedent, the creation unit 1042 refers to a patent database (not shown) or the like and acquires a file in any document format, such as text, Word, PowerPoint, or PDF, in which the precedent is described.

[0059] In step S104, the creation unit 1042 of the server 10 executes a feature acquisition step of acquiring feature specification information consisting of elements and relationships of the invention that are not described in the prior art, based on the information output by inputting into the generation AI a fifth instruction to output elements and relationships of the invention that are not described in the prior art, at least a portion of the specification information, and information based on the prior art information.

[0060] Specifically, the creation unit 1042 of the server 10 creates the fifth prompt by including the structure data acquired in step S102 in the {structure information} field of the fifth instruction, and the acquired precedent data (text, images, etc. describing the precedents) in the {precedent 1} and {precedent 2} fields, respectively. In addition, in the {structural information} section, structural information (first answer content) is added for each element, attribute, and relationship. In addition, in the places of {Prior example 1} and {Prior example 2}, instead of the prior example data, items of viewpoint data and structured data obtained by performing viewpoint extraction (step S505) and structure extraction (step S506) on the prior example data may be added. Alternatively, the fifth prompt may be created by adding the viewpoint information extracted in step S103 to the fifth instruction. <5th instruction> #Instructions From the structural information below, please output any structures that are not listed in the preceding examples. {structural information} #Precedent {Precedent 1} {Precedent 2}

[0061] The creation unit 1042 of the server 10 inputs the created fifth prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs a fifth answer to the fifth prompt to the server 10. The fifth answer is an example of proposal information related to AR ski goggles. <5th answer content> New relationships { elements: [position sensor, head direction sensor, data processing unit], type:dataflow, content: The congestion status acquisition, area identification, and display functions work together }

[0062] <Concept search> In step S105, the creation unit 1042 of the server 10 executes a concept strengthening step of expanding the elements and relationships included in the feature specification information based on the information output by inputting an eleventh instruction for outputting superordinate concepts, subordinate concepts, intermediate concepts, parallel concepts, similar concepts, etc. of the elements and relationships of the invention and at least a part of the specification information into the generation AI. The creation unit 1042 of the server 10 executes a concept strengthening step of expanding the elements and relationships included in the feature specification information based on the information output by inputting an eleventh instruction for outputting superordinate concepts, subordinate concepts, intermediate concepts, parallel concepts, similar concepts, etc. of the elements and relationships of the invention, at least a part of the specification information, and information based on the precedent information into the generation AI.

[0063] Specifically, the creation unit 1042 of the server 10 creates the 11th prompt by including the structural data related to the feature specification information acquired in step S105 in the {structural information} portion of the 11th instruction. Structural information (fifth answer content) is added to the {structural information} portion for each element, attribute, and relationship. Note that, in place of {structure information}, instead of the characteristic specification information, structure information (first response content) before the comparison with the prior example in step S104 may be added. Note that, instead of the precedent data, the {precedent example 1} and {precedent example 2} sections may be replaced with viewpoint data and structured data items obtained by performing viewpoint extraction (step S505) and structure extraction (step S506) on the precedent data. Note that the precedent data is not necessarily required and is an optional item. <11th instruction> #Instructions For the following structural information, please output superordinate concepts, subordinate concepts, intermediate concepts, parallel concepts, similar concepts, etc. for the elements, attributes, and relationships of the invention. When outputting, please refer to prior examples. {structural information} #Precedent {Precedent 1} {Precedent 2}

[0064] The creation unit 1042 of the server 10 inputs the created 11th prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs an 11th answer to the 11th prompt to the server 10. The 11th answer is an example of proposal information related to AR ski goggles. <11th answer content> superordinate concept Data Processing Systems Sensor network system Integrated information processing system Real-time data processing system middle concept Sensor linkage system -Complex sensor data integration Multi-sensor fusion Sensor data stream processing subordinate concept Integrated position and direction sensor system Location data processing Directional data processing Data synchronization processing parallel concept Sensor fusion technology - Integration of data from multiple sensors Real-time data processing -Visualized display of information

[0065] <Generating a second perspective> In step S106, the control unit 104 of the server 10 includes a step of acquiring specification information structured from a predetermined perspective including the problem or effect of the invention based on the information output by inputting a 12th instruction for outputting a predetermined perspective including the problem or effect of the invention and information based on the feature specification information into the generation AI. Specifically, the creation unit 1042 of the server 10 creates the second prompt by including the feature specification information (fifth answer content) acquired in step S104 in the {feature specification information} section of the twelfth instruction. Note that the viewpoint information (second answer content) extracted in step S103 may be added to the {viewpoint information} section. This makes it possible to extract information such as issues and effects about the feature specification information extracted by comparing it with a prior example from the specification information. Note that the {viewpoint information} is not necessarily required and is an optional item. The descriptions of the issues, effects, etc. described in the proposal information may not be in line with the feature specification information, which is the patent application point, but by executing the second viewpoint generation step, it is possible to create issues and effects in line with the feature specification information, which is the novel patent application point. <12th instruction> #Instructions From the following proposed information describing a patented invention: Please print out the technical field, application, problem, function, configuration, and effect of the invention. {Features and specifications} #Points of View {Point of View}

[0066] The creation unit 1042 of the server 10 inputs the created 12th prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs a 12th answer to the 12th prompt to the server 10. The 12th answer is an example of proposal information related to AR ski goggles. <12th answer content> Viewpoint type: Technical field Sensor technology for wearable devices Real-time situational awareness system · Viewpoint type: Usage - Understand the congestion situation within the facility · Route guidance to users Perspective type: Issue - It is difficult to provide optimal information using only simple location information - Realization of real-time situational information provision Viewpoint type: Function -Detection of user position and head direction Obtaining congestion status and identifying areas Perspective type: Structure Position and head orientation sensors Data Processing Unit Perspective type: Effect -Highly accurate situational awareness - Providing optimal information in real time

[0067] The creation unit 1042 of the server 10 divides the 12th answer contents into perspectives (technical field, use, problem, function, configuration, effect), etc., and stores the 12th answer contents for each perspective type in the perspective type and perspective data items of a new record in the perspective table 1016. The specification ID stores the specification ID of the specification information created in step S101. The exclusion flag stores a value of 1 (non-exclusion). The perspectives extracted in step S106 shall be used to create the specification. This allows the issues and effects according to the characteristic specification information to be used in the specification creation process described below.

[0068] <Specification preparation process> The specification preparation process is a process for preparing a part or all of a patent specification from a patent specification, which is a structured document.

[0069] <Outline of specification preparation process> The specification creation process is a series of processes that acquire a patent specification, create patent claims, group multiple components included in the claims, divide the patent specification into multiple partial specifications, associate one or more partial specifications with each component group, create a patent specification and drawings based on the component groups and partial specifications, and allow the user to edit and modify the created patent specification and drawings.

[0070] <Details of the specification preparation process> The specification preparation process will be described in detail below.

[0071] <Patent specification acquisition> In step S301, the creation unit 1042 of the server 10 executes a specification acquisition step of acquiring specification information in which the invention is structured in terms of elements and relationships. The user operates the input device 206 of the user terminal 20 to input the URL of a page for executing the specification creation process (specification creation processing page) into a web browser or the like, and opens the specification creation processing page. The control unit 204 of the user terminal 20 sends a request to the server 10 to open the specification creation processing page. Based on the received request, the control unit 104 of the server 10 generates a specification creation processing page and sends it to the user terminal 20. The control unit 204 of the user terminal 20 displays the received specification creation processing page on the display 2081 of the user terminal 20. The creation unit 1042 of the server 10 searches the user ID item in the specification table 1014 based on the user ID 2011, and acquires one or more pieces of specification information. The creation unit 1042 of the server 10 displays and presents the acquired one or more pieces of specification information on the specification creation processing page in a selectable manner. The user operates the input device 206 of the user terminal 20 to select a desired piece of specification information from one or more pieces of specification information presented. The control unit 204 of the user terminal 20 transmits the specification ID of the selected specification information to the server 10. The creation unit 1042 of the server 10 receives and accepts the specification ID. Based on the specification ID, the creation unit 1042 of the server 10 searches the specification ID item in the specification table 1014 and acquires the specification information related to the specification creation process. In the present disclosure, structure extraction and viewpoint extraction are performed on the proposed information in advance in the specification creation process, but this is not limited to this. For example, the specification creation process may be configured to accept the proposed information, and the specification information including structure information and viewpoint information may be acquired by executing the process related to the specification creation process.

[0072] The creation unit 1042 of the server 10 creates a new record of the specification information in the specification table 1017, and stores the user ID 2011 and the specification ID of the selected predetermined specification information in the user ID and specification ID fields, respectively.

[0073] <Claim Creation (First Embodiment)> In step S302, the creation unit 1042 of the server 10 executes the 1A patent acquisition step of acquiring the scope of the patent claim based on the information output by inputting the third instruction for outputting the scope of the patent claim based on the elements and relationships of the invention and at least a part of the feature specification information into the generation AI.

[0074] Specifically, the creation unit 1042 of the server 10 creates the third prompt by including the feature specification information acquired in step S104 in the {specification information} portion of the third instruction. Note that the {specification information} portion may include any part or all of the specification information, including viewpoint information and structure information, instead of the feature specification information. For example, the user may operate the input device 206 of the user terminal 20 to select part or all of the specification information (including viewpoint information and structural information), and the selected specification information may be added to the {specification information} section. Note that in addition to the feature specification information, the {reference information} section may include any part or all of the specification information, including proposal information, viewpoint information, and structural information other than the feature specification information. Note that although the reference information is optional, including the reference information allows for more appropriate claims to be created. <3rd instruction> #Instructions Please create your patent claims based on the structure below and by referring to the reference information. {Specification information} #Reference information {Reference information}

[0075] The creation unit 1042 of the server 10 inputs the created third prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs a third answer to the third prompt to the server 10. The third answer is an example of proposal information related to AR ski goggles. <3rd answer content> [Claim 1] An information processing device, a congestion status acquisition unit that acquires congestion data indicating a congestion status of people or things for each of a plurality of areas; a location acquisition unit that acquires a current location of a user; an area identification unit that identifies a plurality of areas existing around the user based on the location of the user; a display control unit that displays the congestion data acquired for each of the identified areas on a transmissive display; An information processing device comprising: [Claim 2] The area specifying unit Detecting a head direction of the user; identifying an area included in the user's field of view from among the plurality of areas based on the head direction; The information processing device according to claim 1. [Claim 3] The display control unit Identifying the least congested area among the plurality of areas based on the congestion data; highlighting the area on the transmissive display; 3. The information processing device according to claim 1 or 2.

[0076] The creation unit 1042 of the server 10 stores the claims (third response content) in the claims item of the new record in the specification table 1017 created in step S301. Note that the user may add or modify the content of the claims and store it.

[0077] <Claim Creation (Second Embodiment)> In step S302, the 1A patent acquisition step executes a step of obtaining the scope of the patent claims based on the information output by inputting the 5th instruction and at least a portion of the characteristic specification information excluding the problem or effect of the invention into the generation AI. Specifically, the creation unit 1042 of the server 10 may exclude information related to perspectives other than the structure, such as the problem and effect, from the information to be included in the third prompt. This makes it possible to exclude information related to perspectives other than the structure, such as the problem and effect, from the third prompt. For example, the creation unit 1042 of the server 10 adds structural information other than the proposal information and feature / specification information to the {reference information} section, and does not add perspective information, thereby creating the third prompt excluding perspectives such as the problem and effect. Note that perspectives such as the problem and effect may be excluded from the proposal information separately using the artificial intelligence system 40. This allows the creation of suitable claims based on the essential structure of the invention, which is based on novel elements and relationships compared to prior art, without considering the problem and effect. Also, including descriptions of the problem and effect can prevent the claims from becoming redundant. Although the reference information is optional, including the reference information can help draft more appropriate claims.

[0078] <Claim Creation (Third Embodiment)> In step S302, the creation unit 1042 of the server 10 executes the first B patent acquisition step of acquiring the scope of patent claims. Specifically, the claims do not need to be prepared by the specification preparation process according to the present disclosure. For example, the user may input the claims he or she has prepared himself or herself into a claim input field or the like provided on the specification preparation processing page. The control unit 204 of the user terminal 20 transmits the input claims to the server 10. The preparation unit 1042 of the server 10 receives and acquires the claims input by the user. In this case, the process from step S303 onward in the specification preparation process can be executed. In other words, the user creates the claims themselves without having them automatically prepared, and has the AI ​​system 40 prepare only the specification corresponding to the claims. Since claims are rights documents, users may create them themselves. The system 1 according to the present disclosure can flexibly accommodate such user needs.

[0079] <Creating patent claims (creating issues and effects)> In step S302, the creation unit 1042 of the server 10 executes a note acquisition step to acquire the issues or effects for each of one or more claims based on the information output by inputting the 31st instruction for outputting the issues or effects for each of one or more claims included in the scope of the claims and at least a portion of the specification information into the generation AI.

[0080] Specifically, the creation unit 1042 of the server 10 creates the 31st prompt by including the claims acquired in step S302 in the {claims} portion of the 31st instruction. In addition to the scope of the patent claim, any part or all of the specification information, including the proposal information, viewpoint information, and structure information, may be included in the {reference information} section. Although the reference information is optional, including the reference information can help create a more suitable scope of the patent claim. <31st instruction> #Instructions Please output the issues and effects for each of the claims in the patent claims below. {Claims} #Reference information {Reference information}

[0081] The creation unit 1042 of the server 10 inputs the created 31st prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs a 31st answer to the 31st prompt to the server 10. The 31st answer is an example of proposal information related to AR ski goggles. <31st answer content> Claim 1 Challenge: In the vast space of a ski resort, it is difficult to comprehensively grasp the surrounding congestion situation based on the user's current location. Effect: It is possible to display the congestion status of multiple areas around the user's current location in real time, allowing the user to efficiently grasp the situation in the entire space. Claim 2 Issue: There is a discrepancy between the direction the user is actually looking and the information displayed, making it difficult to intuitively grasp the information. Effect: By selectively presenting only the necessary information based on the user's head direction and field of view, it is possible to provide information that is highly consistent with the real world. Claim 3 Issue: It is difficult to quickly determine the best area from multiple options, making it difficult to make efficient decisions. Benefit: Automatically identifying and highlighting the least congested areas helps users make better decisions and allows for more efficient facility use.

[0082] The creation unit 1042 of the server 10 stores the claims (the 31st response content) in the claims field of the new record in the specification table 1017 created in step S301, in association with each claim. Note that the claims may also be stored in the appendix field (not shown) of the specification table 1017 in association with the claim number. This allows for the creation of information on the problems or effects of an invention that are more suited to each claim than if the scope of the patent claim and the invention proposal were entered. For example, this can be used to create a patent specification that explains the problems and effects for each claim in the scope of the patent claim.

[0083] <Element Grouping> In step S303, the creation unit 1042 of the server 10 executes a structure division step of dividing the scope of claims into a plurality of structures. Specifically, the creation unit 1042 of the server 10 divides the claims acquired in step S302 into constituent elements (hereinafter referred to as "structures"). The division into constituent elements may be performed using sentence delimiters (such as commas, dividing according to character strings such as means, step, and part), the number of characters, or any other morphological analysis technique. The creation unit 1042 of the server 10 may create a 32nd prompt by including the scope of the claim obtained in step S302 in the 32nd instruction for dividing the sentence into components, and may divide the scope of the claim into multiple components based on the information output by inputting the prompt into the artificial intelligence system 40.

[0084] As a result, the claim (claim 1) acquired in step S302 is divided into features 1A to 1F as follows: <Divided Claims> (1A) An information processing device, (1B) a congestion status acquisition unit that acquires congestion data indicating the congestion status of people or objects for each of a plurality of areas; (1C) a location acquisition unit that acquires a user's current location; (1D) an area identification unit that identifies a plurality of areas around the user based on the position of the user; (1E) a display control unit that displays the congestion data acquired for each of the identified areas on a transmissive display; (1F) An information processing device equipped with:

[0085] The creation unit 1042 of the server 10 stores the statement ID, claim number (claim 1, claim 2, etc.), and component string "An information processing device comprising," "A congestion status acquisition unit that acquires congestion data indicating the congestion status of people or objects for each of a plurality of areas," etc., contained in the statement information of the statement table 1017 created in step S301, in the statement ID, claim number, and configuration items of a new record in the configuration table 1018, respectively. As a result, each of the components (configurations) of the claims is stored in multiple records in the configuration table 1018.

[0086] In step S303, the creation unit 1042 of the server 10 executes a grouping step of grouping the plurality of configurations divided in the configuration dividing step into one or more configuration groups. Specifically, the creating unit 1042 of the server 10 groups the multiple configurations divided in step S303. The grouping method includes the following methods. · Group configurations related to the same means, steps, parts, etc. (crowding status acquisition unit, location information acquisition unit, area identification unit, display control unit) into the same group. Group similar structures into the same group. Similarity between structures can be calculated based on the text similarity of the components (the inverse of the text distance). For example, similarity can be calculated using cosine similarity, N-gram similarity, the inverse of Levenshtein distance, Jaro-Winkler distance, Hamming distance, Jaccard coefficient, or similarity of embedding vectors such as Word2Vec or BERT. Similar structures can be grouped by calculating the similarity between structures and applying any clustering method such as k-means. A prompt is created by including one or more components in an instruction to group similar configurations. The prompt is input to the artificial intelligence system 40, which can then group multiple configurations based on the information output. In addition, grouping may be performed by combining the above methods.

[0087] The creation unit 1042 of the server 10 stores group identification information (group index, group label such as A, B, etc.) for each piece of configuration information stored in the configuration table 1018 in the second group ID field of the configuration table 1018. This allows each of the multiple configurations to be stored in association with a group label.

[0088] The creation unit 1042 of the server 10 executes a configuration summarization step of creating a configuration summary for at least some of the plurality of configuration groups. Specifically, the creation unit 1042 of the server 10 creates a prompt for each group by including the text of one or more components included in the group in an instruction to create a summary. Based on the information output by inputting the prompt into the artificial intelligence system 40, a summary (composition summary) of the components included in the group can be created for each group.

[0089] <Patent specification division> In step S304, the creation unit 1042 of the server 10 executes a specification division step of dividing the plurality of elements included in the specification information into a plurality of partial specification information each consisting of a plurality of elements related to each other. The creation unit 1042 of the server 10 executes a specification division step of dividing the plurality of elements included in the specification information into a plurality of partial specification information each consisting of a plurality of elements having a common relationship to each other. Specifically, the creating unit 1042 of the server 10 divides the structural information included in the specification information into a plurality of partial specification information whose elements are related to each other. For example, let us consider a case where the structural information contains five elements A to E. Furthermore, let us assume that the structural information contains the relationships [A, C], [B, C], and [D, E]. In this case, it is possible to divide the five structural information A to E into two pieces of structural information: a first partial structural information consisting of three elements A to C and the relationships [A, C] and [B, C], and a second partial structural information consisting of two elements D and E and the relationship [D, E].

[0090] In this way, when structural information contains many elements, attributes, and relationships, it can be divided into multiple partial structural information consisting of some elements that are closely related by relationships. Note that when dividing the structural information, the multiple partial structural information may be exclusive to the differences (have no common elements), or some elements of the multiple structural information may overlap with the differences. The creation unit 1042 of the server 10 can interpret the structural information as a distance matrix (similarity matrix) in which relationships are distances between elements. The creation unit 1042 of the server 10 can divide the distance matrix (similarity matrix) into multiple pieces of substructure information by applying any clustering method to the distance matrix (similarity matrix). Note that weights are assigned to the "relationships," and the information may be divided into substructure information according to the relationships. The creation unit 1042 of the server 10 can associate each piece of viewpoint information stored in the viewpoint table 1016 with substructure information. For example, issues, effects, etc. related to a group of elements related to predetermined substructure information can be treated as subviewpoint information associated with predetermined substructure information. Identification of issues, effects, etc. related to a group of elements related to predetermined substructure information can be realized using the artificial intelligence system 40. For example, a prompt may be created by including viewpoint information and substructure information in an instruction to evaluate the association between a viewpoint such as an issue or effect and a group of elements related to the substructure information, and the prompt may be input to the artificial intelligence system 40, which may then divide the viewpoint information into substructure information associated with multiple pieces of substructure information based on the information output. Alternatively, the above methods may be combined to divide the information into partial structure information.

[0091] In this way, the creation unit 1042 of the server 10 can divide the structure information and viewpoint information into partial structure information and partial viewpoint information, respectively. This allows even a complex invention consisting of a large number of elements, attributes, and relationships to be divided into partial specification information consisting of smaller partial structure information and partial viewpoint information. The creation unit 1042 of the server 10 assigns group identification information (group index, group label such as A, B, etc.) to each piece of division specification information. The creation unit 1042 of the server 10 stores the group identification information in the first group ID item of the structure table 1015 and the viewpoint table 1016. As a result, the viewpoint information and structure information stored in the records of the structure table 1015 and the viewpoint table 1016 are grouped into specific groups.

[0092] The creating unit 1042 of the server 10 executes a partial summarization step of creating a partial summary for at least some of the plurality of partial specification information. Specifically, the creation unit 1042 of the server 10 creates a prompt for each group by including text of one or more pieces of structural information and viewpoint information contained in the group in an instruction to create a summary. Based on the information output by inputting the prompt into the artificial intelligence system 40, a summary (viewpoint summary) of the structures contained in the group can be created for each group.

[0093] <Association> In step S305, the creation unit 1042 of the server 10 executes a specification specifying step of specifying one or more predetermined partial specification information associated with a predetermined configuration from among the plurality of partial specification information divided in the specification dividing step. The specification identifying step includes a step of identifying predetermined partial specification information associated with a partial abstract that is similar to a predetermined configuration. Specifically, the creating unit 1042 of the server 10 associates the partial specification information divided in step S304 with each of the components divided in step S303. The following methods are available for associating the components. - Associating similar configurations and subspecifications. Similarity can be calculated based on the similarity (inverse of the text distance) between the text contained in the configuration and the subspecification. For example, similarity can be calculated using cosine similarity, N-gram similarity, the inverse of Levenshtein distance, Jaro-Winkler distance, Hamming distance, Jaccard coefficient, or similarity of embedding vectors such as Word2Vec and BERT. By calculating the similarity between configurations, it is possible to associate configurations and subspecifications that have a similarity above a certain value. A prompt is created by including a predetermined configuration and partial specification information in an instruction to identify a partial specification related to the configuration. The predetermined configuration and partial specification information can be associated based on the information output by inputting the prompt into the artificial intelligence system 40. In this case, the partial summary may be used instead of the text contained in the partial specification.

[0094] The creation unit 1042 of the server 10 executes a specification specifying step of specifying one or more predetermined partial specification information associated with a predetermined configuration group from among the plurality of partial specification information divided in the specification dividing step. Specifically, the creating unit 1042 of the server 10 associates the partial specification information divided in step S304 with each of the configuration groups grouped in step S303. The association method can be as follows. - Associating similar component groups and subspecifications. The calculation of similarity is the same as when calculating similarity for each component, but the similarity can be calculated by processing using the text of the component group instead of the component. A prompt is created by including the configurations included in a predetermined configuration group and the partial specification information in an instruction to identify the partial specification related to the configuration. The predetermined configuration group and the partial specification information can be associated based on the information output by inputting the prompt into the artificial intelligence system 40. In this case, instead of the text of each component included in the component group, a component summary may be used. In this case, the partial summary may be used instead of the text contained in the partial specification.

[0095] The specification identifying step includes a step of identifying predetermined partial specification information associated with a partial summary similar to a constituent summary of a predetermined constituent group. Specifically, the association between a configuration group and partial specification information may be performed using a configuration summary and partial summary that summarize each of the configurations and specification information (viewpoint information, structure information) included in the configuration group, respectively. A prompt is created by including a configuration summary and a partial summary in an instruction to identify a partial specification related to the configuration. Based on the information output by inputting the prompt to the artificial intelligence system 40, a predetermined configuration group can be associated with partial specification information. Even in cases where the size of a component group is large and it is difficult to calculate the degree of similarity with the partial specification information, or where the size of the partial specification information is large and it is difficult to calculate the degree of similarity with a predetermined component, it is possible to identify suitable partial specification information according to the predetermined component group.A more suitable patent specification according to the predetermined component group can be created.

[0096] <Description (First embodiment)> In step S306, the creation unit 1042 of the server 10 executes a second patent acquisition step of acquiring at least a portion of the patent specification based on the information output by inputting into the generation AI the fourth instruction of outputting at least a portion of the items described in the patent specification based on the elements and relationships of the invention and the scope of the claims, the specification information, and the scope of the claims acquired in the first A patent acquisition step. The creation unit 1042 of the server 10 executes a second patent acquisition step of acquiring at least a portion of the patent specification based on the information output by inputting into the generation AI the fourth instruction of outputting at least a portion of the items described in the patent specification based on the elements and relationships of the invention and the scope of the claims, and the specification information and the scope of the claims acquired in the first B patent acquisition step.

[0097] Specifically, the creation unit 1042 of the server 10 creates the 1A prompt by including the specification information (viewpoint information, structural information) and the claims obtained in step S302 in the {specification information} and {claims} sections of the 1A instruction, respectively. In addition, some or all of the proposed information may be included in the {reference information} section. Although the reference information is optional, including the reference information can help create a more suitable patent specification. <1A instruction, 4th instruction> #Instructions Please prepare a patent specification based on the following claims: #Claims {Claims} #Specifications {Specification information} #Reference information {Reference information} {Proposal Information}

[0098] The creation unit 1042 of the server 10 inputs the created 1A prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs the 1A answer content to the 1A prompt to the server 10. The 1A answer content is an example of proposal information related to AR ski goggles. <1A answer details> MODE FOR CARRYING OUT THE INVENTION An embodiment of the present invention will be described in detail with reference to the drawings. System Configuration The information processing device of this embodiment is realized as a head-mounted display (HMD) equipped with a transmissive display, and includes a congestion status acquisition unit, a position acquisition unit, an area identification unit, and a display control unit. How it works The congestion status acquisition unit acquires real-time congestion data from sensors or image analysis systems installed in each area. The location acquisition unit acquires the user's current location using GPS or other means. The area identification unit identifies multiple areas around the user based on the acquired location information. The display control unit displays the congestion data for each identified area on a transparent display in the form of color coding, numerical display, or other formats.

[0099] The creation unit 1042 of the server 10 stores all or part of the patent specification (1A response content) in the item of detailed description of the invention, etc. of the new record in the specification table 1017 created in step S301.

[0100] In addition, the information may be stored in each of the items included in the specification table 1017, such as abstract, detailed description of the invention, drawings, abstract, title of the invention, technical field, background art, prior art documents, patent documents, non-patent documents, summary of the invention, problem to be solved by the invention, means for solving the problem, effects of the invention, brief description of the drawings, form for implementing the invention, examples, industrial applicability, explanation of symbols, accession number, free text of sequence listing, etc. Furthermore, the fourth instruction has the same basic structure as the first instruction, but rather than creating the entire statement, it is an instruction to create a portion of the statement relating to each item. As with the first instruction, the creation unit 1042 of the server 10 creates a fourth prompt based on the fourth instruction, and can obtain a portion of the statement based on the information output by inputting the fourth prompt into the artificial intelligence system 40. The creation unit 1042 of the server 10 can create the entire statement by combining the obtained portions of the statement. This allows you to create a specification piece by piece even when the content of an invention is large, and obtain a large patent specification without being restricted by the number of tokens. Also, by not including unnecessary information in the prompt, hallucination can be suppressed and the output quality of the specification can be improved.

[0101] <Description (2A embodiment)> The second patent acquisition step executes a step of acquiring at least a portion of a patent specification corresponding to a specified configuration based on information output by inputting the fourth instruction, specification information, and a specified configuration among multiple configurations into the generation AI. Specifically, the creation unit 1042 of the server 10 creates the fourth prompt by including the specification information (viewpoint information, structural information) and the structure of the claims divided in step S303 in the {specification information} and {claims} sections of the fourth instruction, respectively. In addition, some or all of the proposed information may be included in the {reference information} section. Although the reference information is optional, including the reference information can help create a more suitable patent specification. The creation unit 1042 of the server 10 inputs the created fourth prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs to the server 10 the content of a fourth answer to the fourth prompt. This allows you to obtain a portion of a patent specification based on one or more features included in the scope of the patent claim. For example, you can create a patent specification that corresponds to each feature, allowing you to create a suitable patent specification that meets the support requirements for each feature.

[0102] <Description (2B embodiment)> The second patent acquisition step executes a step of acquiring at least a portion of a patent specification corresponding to a specified configuration based on information output by inputting the fourth instruction, specified partial specification information, and a specified configuration into the generation AI. Specifically, in the second embodiment, unlike the second embodiment, the creation unit 1042 of the server 10 creates the fourth prompt by including, in the {specification information} section of the fourth instruction, "partial specification information" (in step S305) associated with a predetermined configuration inserted in the {claims} section, rather than "specification information (viewpoint information, structural information)." This allows a more suitable patent specification to be created for a specified configuration by removing partial specification information that is not related to the specified configuration from the information contained in the specification information when creating a patent specification text for the specified configuration. Specifically, by eliminating unnecessary partial specification information, it is possible to suppress the occurrence of hallucination by the generation AI.In addition, by eliminating unnecessary partial specification information, it is possible to create a patent specification that is not redundant for each specified configuration.

[0103] <Description (2C embodiment)> The second patent acquisition step executes a step of acquiring at least a portion of the patent specification corresponding to the configuration group based on the information output by inputting the fourth instruction, specification information, and one or more configurations included in a specified configuration group among the configuration groups into the generation AI. Specifically, in the second embodiment C, unlike the second embodiment A, the creation unit 1042 of the server 10 creates the fourth prompt by including "one or more grouped configurations" in step S303 in the {Claims} section of the fourth instruction, rather than "predetermined configuration." This allows similar or same category configurations to be grouped into the same configuration group, and for each configuration group, overlapping descriptions can be eliminated, allowing for a more suitable patent specification to be created.

[0104] <Description (2D embodiment)> In step S306, the second patent acquisition step executes a step of acquiring at least a portion of the patent specification corresponding to the specified configuration based on the information output by inputting the fourth instruction, specified partial specification information, and one or more configurations included in the specified configuration group into the generation AI. Specifically, in the 2D embodiment, unlike the 2A embodiment, the creation unit 1042 of the server 10 creates a fourth prompt by including "one or more grouped configurations" in step S303 in the {Claims} portion of the fourth instruction, rather than "predetermined configuration." Also, unlike the 2A embodiment, the creation unit 1042 of the server 10 creates a fourth prompt by including (in step S305) "partial specification information" associated with the predetermined configuration group inserted in the {Claims} portion, rather than "specification information (viewpoint information, structure information)." This allows for the creation of a more suitable patent specification for a specified component group by removing partial specification information that is not related to the specified component group from the information contained in the specification information when creating a patent specification text for the specified component group. Specifically, by eliminating unnecessary partial specification information, it is possible to suppress the occurrence of hallucination by the generation AI.In addition, by eliminating unnecessary partial specification information, it is possible to create a patent specification that is not redundant for each specified configuration. Furthermore, if a patent specification is created separately for each of the multiple configurations included in a configuration group, duplicated descriptions will be included, but by creating them together for each configuration group, a more suitable patent specification can be created that excludes duplicated descriptions.

[0105] <Description (Third embodiment)> In step S306, the creation unit 1042 of the server 10 executes an order acquisition step to acquire the order of description of the configuration groups based on the information output by inputting the fifth instruction for outputting the order of description of the configurations, information based on one or more configuration groups, and part or all of the proposal information or part or all of the specification information into the generation AI. The creation unit 1042 of the server 10 executes a second patent acquisition step for each of the multiple constituent groups, and also executes a fifth patent acquisition step for acquiring a patent specification by combining portions of the multiple acquired patent specifications in the order in which they are written.

[0106] Specifically, the creation unit 1042 of the server 10 creates the fifth prompt by including one or more configurations included in a predetermined configuration group in the {configuration group} section of the fifth instruction. The creation unit 1042 of the server 10 creates the fifth prompt by including at least one of proposal information, specification information (viewpoint information, structure information), and partial specification information in the {reference information} section. A configuration summary may be inserted in the {configuration group} section. <5th instruction> #Instructions Please output the order of the following configuration. For each group ID, output information indicating the order. {Configuration Group}

[0107] The creation unit 1042 of the server 10 inputs the created fifth prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs the content of a fifth answer to the fifth prompt to the server 10. The fifth instruction includes an instruction to associate and output information indicating the order for each second group ID. The creation unit 1042 of the server 10 identifies the configuration group for each second group ID by referring to the second group ID in the configuration table 1018, and performs specification creation (embodiment 2C) and specification creation (embodiment 2D) for each configuration included in the configuration group. The creation unit 1042 of the server 10 creates a suitable statement by combining at least a portion of the statements output for each of the second group IDs in accordance with the order contained in the fifth reply content. By combining the parts of the patent specifications obtained for each of the predetermined constituent groups in the order in which they are written, it is possible to obtain a patent specification that follows the order in which the constituent groups are written. Note that the patent specification created by combining does not have to be the entire patent specification, and may be just a part of the patent specification.

[0108] In the specification writing (third embodiment), an example of outputting the description order for each component group has been disclosed as an example, but the present invention is not limited to this. For example, the description order may be output for each divided component in step S303. In this case, too, by combining parts of the patent specification obtained by executing specification writing (second embodiment) and specification writing (second embodiment) for each component according to the description order, it is possible to obtain a suitable patent specification according to the description order of the components.

[0109] <Drawing> In step S307, the creation unit 1042 of the server 10 may create drawings based on the viewpoint information and structural information included in the specification information. Specifically, the creation unit 1042 of the server 10 can create drawings such as a block diagram, a structural diagram, a configuration diagram, and a functional diagram based on the structural information. This allows not only the main text of the specification but also the drawings to be created automatically.

[0110] <Editing Operation (First Embodiment)> In step S308, the creation unit 1042 of the server 10 executes a specification presentation step of presenting the specification information acquired in the specification acquisition step. Specifically, the creation unit 1042 of the server 10 acquires specification information (structure information, viewpoint information) from the specification table 1014, the structure table 1015, and the viewpoint table 1016, and transmits it to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the received and acquired structure information and viewpoint information on the display 2081 of the user terminal 20. The user checks the presented structure information and viewpoint information.

[0111] The creation unit 1042 of the server 10 executes a specification editing step of accepting an editing operation for the specification information presented in the specification presenting step. Specifically, the user edits the contents of the presented structure information and viewpoint information by operating the input device 206 of the user terminal 20. Specifically, the user modifies the names (labels) of elements included in the structure information and modifies the contents of attributes and relationships by operating the input device 206 of the user terminal 20. The user also modifies the contents of viewpoints by operating the input device 206 of the user terminal 20. In this way, the user can modify and edit the specification information by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 transmits a request to modify and edit the specification information to the server 10. Upon receiving the request, the creation unit 1042 of the server 10 updates the specification information by overwriting the information of the target records in the specification table 1014, structure table 1015, and viewpoint table 1016. The user may check the contents of the specification and drawings created in steps S306 and S307, and may modify or edit the specification information.

[0112] <Editing Operation (Second Embodiment)> In step S308, the creation unit 1042 of the server 10 executes a patent presentation step of presenting at least a part of the patent specification acquired in the second patent acquisition step. Specifically, the creation unit 1042 of the server 10 transmits specification information, such as the claims and detailed description of the invention, stored in the specification table 1017, to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the received and acquired patent specification on the display 2081 of the user terminal 20. The user confirms the presented specification. The drawings created in step S307 may also be presented.

[0113] The creation unit 1042 of the server 10 executes a patent editing step of accepting editing operations for at least a part of the patent specification presented in the patent presentation step. Specifically, the user edits the content of the presented specification by operating the input device 206 of the user terminal 20. Specifically, the user may be able to edit the presented patent specification text (text, images, etc.), drawings, etc. by operating the input device 206 of the user terminal 20 by directly adding or correcting them. Furthermore, the user may operate the input device 206 of the user terminal 20 to input instructions for correcting the patent specification text, drawings, etc. into an edit instruction input field, etc. For example, "replace term X with term Y" or "describe the process of step S305 in detail." Such cases are also included in the editing operation for the patent specification, and the edit instructions become information indicating the editing operation. The control unit 204 of the user terminal 20 acquires the pre-amendment and post-amendment contents of the specification text, drawings, etc. that have been added or amended by the user. In this case, the pre-amendment and post-amendment contents become information indicating the editing operation on the patent specification. The control unit 204 of the user terminal 20 transmits information indicating the edited contents to the server 10. The creation unit 1042 of the server 10 acquires and accepts the information indicating the edited contents.

[0114] In step S308, the second patent acquisition step executes a step of acquiring at least a portion of the patent specification based on the information output by inputting the fourth instruction, the specification information for which editing operations were accepted in the specification editing step, and information indicating the editing operations accepted in the patent editing step into the generation AI. Specifically, the creation unit 1042 of the server 10 executes the processing from steps S301 to S307 of the specification creation process based on the specification information edited (modified) in the editing operation (first embodiment), and creates a new patent specification, drawings, etc. As a result, a new patent specification (first edited patent specification) is created that reflects the contents of the edited (modified) specification information.

[0115] Then, the creation unit 1042 of the server 10 executes processing on the first edited patent specification based on the "information indicating the edited content" in the editing operation (second embodiment). Specifically, the creation unit 1042 of the server 10 creates a prompt that includes an instruction to modify the patent document based on the information indicating the editing operation received in the patent editing step, the information indicating the editing operation received in the patent editing step, and the first edited patent specification. The creation unit 1042 of the server 10 inputs the created prompt to the artificial intelligence system 40, and obtains the second edited patent specification based on the information output by inputting the prompt. The second edited patent specification is the first edited patent specification that has been modified based on the "information indicating the editing content" in the editing operation (second embodiment). Note that the processing based on the "information indicating the editing content" in the editing operation (second embodiment) may directly edit the first edited patent specification using the artificial intelligence system 40, or, for example, the first edited patent specification may be modified by generating a program (such as replace(term X, term Y)) that executes the process of "replacing term X with term Y" and executing processing based on that program on the first edited patent specification. In this case, since there are no restrictions such as a limit on the number of tokens in the artificial intelligence system 40, it is possible to appropriately reflect the corrections even in lengthy patent specifications. In this way, in the present disclosure, by combining the first edit (correction) on the specification information and the second edit (correction) on the patent specification, it is possible to obtain a high-quality patent specification while minimizing the limit on the number of tokens in the artificial intelligence system 40, even for patent specifications that are large documents.

[0116] This allows the user to modify the contents of a created patent specification in two ways: by modifying the specification information, or by modifying the created patent specification itself. Users can easily make large-scale revisions to a specification by modifying the specification information. Specifically, by modifying the specification information, the revisions can be easily reflected in the entire specification. Furthermore, since the patent specification itself can be amended, minor amendments can be made without affecting the overall structure of the specification, allowing users to amend patent specifications efficiently without any hassle.

[0117] <Precedent analysis processing> The precedent analysis process is a process for creating documents in which patent documents such as cited documents and non-patent documents are uniformly organized according to specific viewpoint types and structure types.

[0118] <Outline of precedent analysis process> The precedent analysis process is a series of processes that search for precedents, present the precedents, accept selection of an appropriate precedent as prior art, analyze the precedent, extract and store third perspective information based on the precedent, and extract and store third structural information.

[0119] In the prior example analysis process, steps S505 and S506 of the analysis process differ from steps S102 and S103 of the specification creation process in that the analysis target is prior example information rather than proposal information, but other processes may be similar to steps S102 and S103. This makes it possible to obtain invention knowledge structured according to viewpoint type and structure type even for prior examples.

[0120] <Details of the precedent analysis process> The preceding example analysis process will be described in detail below.

[0121] <Precedent data search> In step S501, the analysis unit 1043 of the server 10 executes a precedent search step for searching precedent data. Specifically, the system 1 according to the present disclosure may include a patent search database for realizing a patent search system. A patent search database is a database that stores various patent publications and related documents that can serve as prior art documents, and is configured to allow users to search for prior art using predetermined criteria such as index information, keyword search, patent classification, etc. For example, searches can be narrowed down to search by application date, publication date, legal status, claim content, invention title, etc. The user operates the input device 206 of the user terminal 20 to input search keywords and search conditions (e.g., patent classification indicating a specific technical field, inventors or applicants, publication date range, etc.) and set detailed search options including logical operators. The control unit 204 of the user terminal 20 transmits the search conditions and search options to the server 10. The analysis unit 1043 of the server 10 searches the patent search database for prior art data that matches the conditions, and acquires the prior art data. Note that the server 10 may automatically construct search conditions, search options, etc. based on the proposal data stored in the proposal table 1013, without accepting input from the user terminal, and search the patent search database for prior art data that matches the conditions based on the search conditions and search options, and acquire the prior art data.

[0122] <Precedent data presentation> In step S502, the analysis unit 1043 of the server 10 executes a precedent case presentation step of presenting one or more precedent case data in a selectable manner. Specifically, the analysis unit 1043 of the server 10 converts the precedent data acquired in the search step (S501) into presentation data (for example, screen data for a precedent data list page or an individual detail page) and transmits it to the user terminal 20. The control unit 204 of the user terminal 20 outputs and presents the received display data to the output device 208 of the user terminal 20. The control unit 204 of the user terminal 20 presents the precedent data in a list format or a detailed display format. The user can refer to each presented precedent data and view detailed information, related literature links, summaries, and drawings, etc.

[0123] <Precedent data acceptance> In step S503, the analysis unit 1043 of the server 10 executes a precedent case receiving step of receiving a selection of predetermined precedent case data from one or more precedent case data. Specifically, the user operates the input device 206 of the user terminal 20 to select a predetermined prior example suitable for the specification creation process and description creation process according to the present disclosure from one or more prior example data presented on the output device 208 of the user terminal 20. Specifically, the user operates the input device 206 of the user terminal 20 to select a check box displayed in association with one or more prior example data. The control unit 204 of the user terminal 20 transmits the selected prior example data to the server 10. Specifically, the analysis unit 1043 of the server 10 receives and accepts the precedent data. The analysis unit 1043 of the server 10 stores the selected precedent data in the precedent data field of a new record in the precedent table 1019. The analysis unit 1043 of the server 10 stores the selected one or more precedent data in multiple new records in the precedent table 1019.

[0124] <Precedent data analysis> In step S504, the analysis unit 1043 of the server 10 executes a precedent analysis step of analyzing the predetermined precedent data selected in step S503. Specifically, the analysis unit 1043 of the server 10 executes the analysis process of extracting structure and viewpoints from the precedent by applying precedent information instead of proposal information in the processes of steps S102 and S103 of the specification creation process. As a result, the analysis unit 1043 of the server 10 creates viewpoint information and structure information related to the precedent. The creation unit 1042 of the server 10 creates a new specification information record in the specification table 1014, and stores the user ID 2011 and the precedent ID of the new record in the user ID and proposal ID fields, respectively. A specification information record is created for each of one or more pieces of precedent information.

[0125] <Third structure extraction / memory> In step S505, the analysis unit 1043 of the server 10 executes a prior example specification acquisition step to acquire specification information of a prior example that structures the invention described in the prior example from the perspective of elements and relationships, based on the information output by inputting the first instruction to output the elements of the invention and relationships showing the associations between multiple elements and prior example information into the generation AI. Specifically, the creation unit 1042 of the server 10 creates the 51st prompt by including the precedent data acquired in step S503 in the {suggestion information} portion of the first instruction. The creation unit 1042 of the server 10 inputs the created 51st prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs to the server 10 the content of a 51st answer to the 51st prompt. The creation unit 1042 of the server 10 divides the 51st answer contents into structure types (elements, attributes, relationships), etc., and stores the 51st answer contents for each structure type in the structure type and structure data items of a new record in the structure table 1015. The specification ID stores the specification ID of the specification information created in step S503. The novelty flag stores a value of 0 (no novelty).

[0126] <Third perspective extraction and memory> In step S506, the specification acquisition step of the prior example includes a step of acquiring specification information of the prior example structured from a specified perspective including the problem or effect of the invention based on information output by inputting a second instruction for outputting a specified perspective including the problem or effect of the invention and at least a portion of the prior example information into the generation AI. Specifically, the creation unit 1042 of the server 10 creates the 52nd prompt by including the precedent data acquired in step S503 in the {suggestion information} portion of the second instruction. The creation unit 1042 of the server 10 inputs the created 52nd prompt to the artificial intelligence system 40. The artificial intelligence system 40 outputs to the server 10 the content of a 52nd answer to the 52nd prompt. The creation unit 1042 of the server 10 divides the 52nd answer contents into perspectives (technical field, use, problem, function, configuration, effect), etc., and stores the 52nd answer contents for each perspective type in the perspective type and perspective data items of a new record in the perspective table 1016. The specification ID stores the specification ID of the specification information created in step S504. The exclusion flag stores a value of 0 (exclusion).

[0127] In the present disclosure, an example has been given in which the structure extraction in step S505 and the viewpoint extraction in step S506 are performed by using different instruction sentences, namely, a first instruction and a second instruction, to create the first prompt and the second prompt, respectively, but this is not limiting. For example, the structure extraction and viewpoint extraction may be performed in a single step using a prompt created by including precedent information in an instruction that combines the first instruction and the second instruction (including the first instruction and the second instruction). In other words, steps S505 and S506 may be performed in a single step.

[0128] <Basic computer hardware configuration> 16 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main memory device 902, an auxiliary memory device 903, and a communication IF 991 (interface), which are electrically connected to one another by a communication bus 921.

[0129] The processor 901 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

[0130] The main memory device 902 is used to temporarily store programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0131] The auxiliary storage device 903 is a storage device for saving data and programs, such as a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, or a semiconductor memory.

[0132] The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using wired or wireless communication standards. The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can connect to the Internet via a predetermined access point. In the case of a wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), and Bluetooth (registered trademark). In the case of a wired connection, the network also includes a direct connection using a USB (Universal Serial Bus) cable, etc.

[0133] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration across multiple computers 90 and interconnecting them via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

[0134] <Basic functional configuration of computer 90> The following describes the functional configuration of a computer realized by the basic hardware configuration (FIG. 16) of the computer 90. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

[0135] The functional units of the computer 90 can also be realized by distributing all or part of the functional units among multiple computers 90 interconnected via a network. The computer 90 is a concept that includes not only a single computer 90 but also a virtualized computer system.

[0136] The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903, expanding them in the main storage device 902, and executing processing in accordance with the programs. The control unit can realize functional units that perform various types of information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0137] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes programs stored in memory. In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions. If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0138] The storage unit is realized by a main storage device 902 and an auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Furthermore, the processor 901 can allocate a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 in accordance with the programs. Furthermore, the control unit can cause the processor 901 to execute processes for adding, updating, and deleting data stored in the storage unit in accordance with the various programs.

[0139] A database refers to a relational database, which manages data sets called masters and tables in a tabular format structurally defined by rows and columns, by relating them to each other. In a database, a table is called a table, a master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated. Typically, each table and each master has a column set as a primary key to uniquely identify a record, but setting a primary key to a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in specific tables and masters stored in the storage unit according to various programs. Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

[0140] Note that the databases and masters in this disclosure may include any data structure in which information is structurally defined (such as a list, dictionary, associative array, or object). The data structure also includes data that can be considered as a data structure by combining data with functions, classes, methods, etc. written in any programming language.

[0141] Furthermore, the information, data, etc. disclosed in this disclosure are intended to exemplify one concept of the information, data, etc., and are not intended to limit the concept. For example, information, data, etc. also include information, data, etc. that has been converted or summarized. For example, in the case where user data is data related to a user, such as the user's name, date of birth, occupation, etc., the user data may also include text describing an overview of the user that has been converted (summarized) using predetermined rules or other artificial intelligence systems such as generation AI.

[0142] The communication unit is realized by the communication IF 991. The communication unit realizes a function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 901 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

[0143] <About the prompt> A prompt is a query (including text, character strings, images, videos, audio, etc.) that is input to artificial intelligence systems, such as generative AI and large-scale language models. By inputting a prompt to an artificial intelligence system, a user can instruct the system on how to process information. A user can input a prompt to the AI ​​system so that the AI ​​system will output a desired result. Note that the prompt does not have to be a character string, but can be an image, video, audio, or other prompt. For example, a user's gesture, voice instruction, or other prompt can also be a prompt.

[0144] <About creating prompts> A prompt can be input by a user's input operation on a user terminal. Also, a document file, an image, a video, an audio, etc. can be uploaded and input as a prompt. A user can create a prompt by combining an instruction input by inputting on a user terminal with other instructions, data, etc. In this case, the prompt may include one or more instruction sentences, data, etc. Also, the prompt may include only one or more instruction sentences or one or more data. A prompt can be created by including part of an instruction, data, etc. with another instruction, data, etc. A prompt can be created by inserting a portion of an instruction, data, etc. into another instruction, data, etc. Prompts can be created by combining instructions, data, etc. with other instructions, data, etc. A prompt can be created by combining instructions, data, etc. with other instructions, data, etc. A prompt can be created by adding instructions, data, etc. to other instructions, data, etc. In this disclosure, expressions such as "include," "insert," "combine," "combine," and "append" used when creating prompts from directives, data, and the like are used as terms that refer to the same information processing process. In other words, these can be treated as the same information processing process in that the same prompt is created based on one or more directives, data, and the like. For example, the term "include" encompasses information processing such as "insert," "combine," "combine," and "append." Similarly, "insert," "combine," "combine," and "append" also encompass information processing such as "include," "insert," "combine," "combine," and "append," respectively.

[0145] <Additional Notes> The matters described in the above embodiments will be supplemented below.

[0146] (Appendix 1) A program to be executed by a computer having a processor and a memory unit, the program executing a proposal acquisition step (S101) in which the processor acquires proposal information describing an invention, and a specification acquisition step (S103) in which specification information is acquired that structures the invention described in the proposal information in terms of elements and relationships, based on information output by inputting a first instruction for outputting elements of the invention and relationships showing the associations between multiple elements, and the proposal information, into a generation AI. This makes it possible to create documents relating to patent specifications that are structured in terms of elements and relationships from proposal information such as unstructured invention proposals. Patent specifications can be used to create patent specifications, etc.

[0147] (Appendix 2) A program described in Appendix 1, which executes a prior art acquisition step (S104) of acquiring one or more pieces of prior art information describing prior art; a feature acquisition step (S104) of acquiring feature specification information consisting of elements and relationships of the invention that are not described in the prior art based on information output by inputting into the generation AI a fifth instruction to output elements and relationships of the invention that are not described in the prior art, at least a portion of the specification information, and information based on the prior art information; and a firstA patent acquisition step (S302) of acquiring the scope of the patent claim based on information output by inputting into the generation AI a third instruction to output the scope of the invention based on the elements and relationships, and at least a portion of the feature specification information. This allows you to create high-quality, suitable claims that are differentiated from the prior art.

[0148] (Appendix 3) The program described in Appendix 2, wherein the specification acquisition step (S102) includes a step of acquiring specification information structured from a predetermined perspective including the problem or effect of the invention based on information output by inputting a second instruction for outputting a predetermined perspective including the problem or effect of the invention and at least a portion of the proposed information into the generation AI. This makes it possible to create documents related to patent specifications that are structured from the perspective of issues and effects, from proposal information such as unstructured invention proposals. Patent specifications can be used to create patent specifications, etc.

[0149] (Appendix 4) The program described in Appendix 3, wherein the 1A patent acquisition step (S302) is a step of acquiring the scope of the patent claim based on the information output by inputting the 5th instruction and at least a portion of the characteristic specification information excluding the problem or effect of the invention into the generation AI. This allows the creation of suitable claims based purely on the essential structure of the invention, which is based on novel elements and relationships compared to prior art, without considering the problems and effects.

[0150] (Appendix 5) A program described in Appendix 1, in which a processor executes a 1B patent acquisition step (S302) of acquiring the scope of the patent claims, and an appendix acquisition step (S302) of acquiring the issues or effects for each of one or more appendixes based on information output by inputting into a generation AI a 31st instruction of outputting the issues or effects for each of one or more appendixes included in the scope of the patent claims, and at least a portion of the specification information. This makes it possible to create information on the problem or effect of the invention that is more suitable for each claim than when inputting the scope of the patent claim and the invention proposal. For example, it can be used to create patent specifications that explain the issues and effects of each claim in a patent.

[0151] (Appendix 6) A program as described in Appendix 1, in which a processor executes a first B patent acquisition step (S302) of acquiring the scope of the patent claims, a fourth instruction of outputting at least a portion of the items described in the patent specification based on the elements and relationships of the invention and the scope of the patent claims, and a second patent acquisition step (S306) of acquiring at least a portion of the patent specification based on information output by inputting specification information and the scope of the patent claims acquired in the first B patent acquisition step into a generation AI. This allows for the creation of a high-quality, suitable patent specification that is in line with the scope of the claims.

[0152] (Appendix 7) A program as described in Appendix 2, in which a processor executes a fourth instruction to output at least a portion of the items described in the patent specification based on the elements and relationships of the invention and the scope of the claims, and a second patent acquisition step (S306) to acquire at least a portion of the patent specification based on information output by inputting the specification information and the scope of the claims acquired in the first A patent acquisition step into a generation AI. This allows us to obtain a high-quality, suitable patent specification that is in line with the scope of the patent claims, which are created based on new elements and relationships in comparison with prior art.

[0153] (Appendix 8) A program as described in Appendix 6 or 7, in which a processor executes a component division step (S303) of dividing the scope of the patent claim into a plurality of components, and a second patent acquisition step (S306) is a step of acquiring at least a portion of a patent specification corresponding to a predetermined component based on information output by inputting the fourth instruction, specification information, and a predetermined component among the plurality of components into a generation AI. This allows for the acquisition of a portion of the patent specification based on each of one or more features included in the claims. For example, since it is possible to create patent specification text for each configuration, it is possible to create a suitable patent specification that meets the support requirements for each configuration.

[0154] (Appendix 9) A program as described in Appendix 8, in which a processor executes a specification division step (S304) of dividing a plurality of elements included in the specification information into a plurality of partial specification information consisting of a plurality of elements having a common relationship with each other, and a specification identification step (S305) of identifying one or more predetermined partial specification information associated with a predetermined configuration from the plurality of partial specification information divided in the specification division step, and a second patent acquisition step (S306) is a step of acquiring at least a part of a patent specification corresponding to the predetermined configuration based on information output by inputting the fourth instruction, the predetermined partial specification information, and the predetermined configuration into a generation AI. This allows a more suitable patent specification to be created for a specified configuration by removing partial specification information that is not related to the specified configuration from the information contained in the specification information when creating a patent specification text for the specified configuration. Specifically, by eliminating unnecessary partial specification information, it is possible to suppress the occurrence of hallucination by the generation AI.In addition, by eliminating unnecessary partial specification information, it is possible to create a patent specification that is not redundant for each specified configuration.

[0155] (Appendix 10) The program described in Appendix 9, wherein a processor executes a partial summarization step (S304) of creating a partial summary for at least a portion of a plurality of partial specification information, and a specification identification step (S305) of identifying a specified partial specification information associated with a partial summary similar to a specified configuration. This makes it possible to identify more suitable partial specification information according to a predetermined configuration. In particular, even when the scale of the partial specification information is large and it is difficult to calculate the similarity between the partial specification information and the predetermined configuration, it is possible to identify more suitable partial specification information according to the predetermined configuration. A more suitable patent specification can be prepared for a given configuration.

[0156] (Appendix 11) A program as described in Appendix 8, in which a processor executes a component division step (S303) of dividing the scope of the patent claim into a plurality of components, and a grouping step (S303) of grouping the plurality of components divided in the component division step into one or more component groups, and a second patent acquisition step (S306) is a step of acquiring at least a portion of the patent specification corresponding to the component group based on information output by inputting the fourth instruction, specification information, and one or more components included in a specified component group among the component groups into a generation AI. This allows similar or same category configurations to be grouped into the same configuration group, and for each configuration group, overlapping descriptions can be eliminated, allowing for a more suitable patent specification to be created.

[0157] (Appendix 12) A program as described in Appendix 11, in which a processor executes a specification division step (S304) of dividing a plurality of elements included in the specification information into a plurality of partial specification information consisting of a plurality of elements related to each other, and a specification identification step (S305) of identifying one or more predetermined partial specification information related to a predetermined configuration group from the plurality of partial specification information divided in the specification division step, and a second patent acquisition step (S306) is a step of acquiring at least a part of a patent specification corresponding to the predetermined configuration based on information output by inputting the fourth instruction, the predetermined partial specification information, and one or more configurations included in the predetermined configuration group into a generation AI. This allows for the creation of a more suitable patent specification for a specified component group by removing partial specification information that is not related to the specified component group from the information contained in the specification information when creating a patent specification text for the specified component group. Specifically, by eliminating unnecessary partial specification information, it is possible to suppress the occurrence of hallucination by the generation AI.In addition, by eliminating unnecessary partial specification information, it is possible to create a patent specification that is not redundant for each specified configuration. Furthermore, if a patent specification is created separately for each of the multiple configurations included in a configuration group, duplicated descriptions will be included, but by creating them together for each configuration group, a more suitable patent specification can be created that excludes duplicated descriptions.

[0158] (Appendix 13) The program described in Appendix 12, wherein a processor executes a configuration summarization step (S303) of creating a configuration summary for at least a portion of a plurality of configuration groups, and a partial summarization step (S304) of creating a partial summary for at least a portion of a plurality of partial specification information, and a specification identification step (S305) of identifying specified partial specification information associated with a partial summary similar to the configuration summary of a specified configuration group. This makes it possible to identify more suitable partial specification information according to a predetermined configuration group. Even in cases where the size of a configuration group is large and it is difficult to calculate the similarity with the partial specification information, or where the size of the partial specification information is large and it is difficult to calculate the similarity with a specified configuration, it is possible to identify appropriate partial specification information according to the specified configuration group. It is possible to create a more suitable patent specification for a given constituent group.

[0159] (Appendix 14) The program described in Appendix 11, in which a processor executes an order acquisition step (S306) of acquiring the order of description of the configuration groups based on information output by inputting a fifth instruction for outputting the order of description of the configurations, information based on one or more configuration groups, and part or all of the proposal information or part or all of the specification information into a generation AI, and a fifth patent acquisition step (S306) of executing a second patent acquisition step for each of the multiple configuration groups and acquiring a patent specification by combining parts of the multiple acquired patent specifications in the order of description. This makes it possible to obtain the order of description of the predetermined component groups. By combining the parts of the patent specifications obtained for each of the predetermined component groups in the order of description, it is possible to obtain a patent specification that follows the order of description of the predetermined component groups. Note that the patent specification created by combining does not have to be the entire patent specification, and may be just a part of the patent specification.

[0160] (Appendix 15) A program described in Appendix 6 or 7, which executes a specification presentation step (S308) of presenting specification information acquired in the specification acquisition step, a specification editing step (S308) of accepting editing operations on the specification information presented in the specification presentation step, a patent presentation step (S308) of presenting at least a portion of the patent specification acquired in the second patent acquisition step, and a patent editing step (S308) of accepting editing operations on at least a portion of the patent specification presented in the patent presentation step, wherein the second patent acquisition step (S308) is a step of acquiring at least a portion of the patent specification based on information output by inputting the fourth instruction, the specification information for which editing operations were accepted in the specification editing step, and information indicating the editing operations accepted in the patent editing step into a generation AI. This allows the user to modify the contents of a created patent specification in two ways: by modifying the specification information, or by modifying the created patent specification itself. Users can easily make large-scale revisions to a specification by modifying the specification information. Specifically, by modifying the specification information, the revisions can be easily reflected in the entire specification. Furthermore, since the patent specification itself can be amended, minor amendments can be made that do not affect the overall structure of the specification. Users can efficiently revise patent specifications without any hassle. [Explanation of symbols]

[0161] 1 System, 10 Server, 101 Memory Unit, 104 Control Unit, 106 Input Device, 108 Output Device, 20 User Terminal, 201 Memory Unit, 204 Control Unit, 206 Input Device, 208 Output Device, 40 Artificial Intelligence System, 401 Memory Unit, 404 Control Unit, 406 Input Device, 408 Output Device

Claims

1. A program to be executed by a computer having a processor and a storage unit, the processor: a proposal acquisition step of acquiring proposal information describing an invention; a specification acquisition step of acquiring specification information that structures the invention described in the proposal information from the viewpoint of elements and relationships based on information output by inputting a first instruction for outputting elements of the invention and relationships indicating the relationships between multiple elements and the proposal information into a generation AI; a prior art acquisition step of acquiring one or more pieces of prior art information describing prior art; a fifth instruction for outputting elements and relationships of the invention that are not described in the prior art, and a feature acquisition step for acquiring feature specification information consisting of elements and relationships of the invention that are not described in the prior art, based on information output by inputting at least a part of the specification information and information based on the prior art information into a generation AI; a first A patent acquisition step of acquiring the scope of the patent claim based on information output by inputting a third instruction for outputting the scope of the patent claim based on the elements and relationships of the invention and at least a part of the feature specification information into a generation AI; To execute program.

2. The specification acquisition step includes a step of acquiring the specification information structured from a predetermined perspective including the problem or effect of the invention based on information output by inputting a second instruction for outputting a predetermined perspective including the problem or effect of the invention and at least a part of the proposed information into a generation AI. The program according to claim 1.

3. The first A patent acquisition step is a step of acquiring the scope of the patent claim based on information output by inputting the fifth instruction and at least a part of the characteristic specification information excluding the problem or effect of the invention into a generating AI. The program according to claim 2.

4. the processor: a first B patent acquisition step of acquiring claims; A note acquisition step of acquiring the problem or effect for each of one or more claims based on information output by inputting a 31st instruction for outputting the problem or effect for each of one or more claims included in the scope of claims and at least a part of the specification information into a generation AI; To execute The program according to claim 1.

5. the processor: a first B patent acquisition step of acquiring claims; a fourth instruction for outputting at least a portion of the description items of the patent specification based on the elements and relationships of the invention and the scope of the claims; and a second patent acquisition step for acquiring at least a portion of the patent specification based on information output by inputting the specification information and the scope of the claims acquired in the first B patent acquisition step into a generation AI; To execute The program according to claim 1.

6. A program to be executed by a computer having a processor and a storage unit, the processor: a proposal acquisition step of acquiring proposal information describing an invention; a specification acquisition step of acquiring specification information that structures the invention described in the proposal information from the viewpoint of elements and relationships based on information output by inputting a first instruction for outputting elements of the invention and relationships indicating the relationships between multiple elements and the proposal information into a generation AI; a first B patent acquisition step of acquiring claims; a fourth instruction for outputting at least a portion of the description items of the patent specification based on the elements and relationships of the invention and the scope of the claims; and a second patent acquisition step for acquiring at least a portion of the patent specification based on information output by inputting the specification information and the scope of the claims acquired in the first B patent acquisition step into a generation AI; To execute program.

7. the processor: a fourth instruction for outputting at least a portion of the description items of the patent specification based on the elements and relationships of the invention and the scope of the patent claims; and a second patent acquisition step for acquiring at least a portion of the patent specification based on information output by inputting the specification information and the scope of the patent claims acquired in the first A patent acquisition step into a generation AI; To execute The program according to claim 1.

8. the processor: a component division step of dividing the scope of the claim into a plurality of components; Run The second patent acquisition step is a step of acquiring at least a part of a patent specification corresponding to a predetermined configuration based on information output by inputting the fourth instruction, the specification information, and a predetermined configuration among the plurality of configurations into a generation AI. The program according to any one of claims 5 to 7.

9. the processor: a specification dividing step of dividing the plurality of elements included in the specification information into a plurality of partial specification information each including a plurality of elements having a common relationship with each other; a specification specifying step of specifying one or more predetermined partial specification information associated with a predetermined configuration from the plurality of partial specification information divided in the specification dividing step; Run The second patent acquisition step is a step of acquiring at least a part of a patent specification corresponding to the predetermined configuration based on information output by inputting the fourth instruction, the predetermined partial specification information, and the predetermined configuration into a generation AI. The program according to claim 8.

10. the processor: a partial summarization step of creating a partial summary for at least a part of the plurality of partial specification information; Run the specification identifying step is a step of identifying the predetermined partial specification information associated with a partial summary similar to the predetermined configuration; The program according to claim 9.

11. the processor: a component division step of dividing the scope of the claim into a plurality of components; a grouping step of grouping the plurality of configurations divided in the configuration division step into one or more configuration groups; Run The second patent acquisition step is a step of acquiring at least a part of a patent specification corresponding to a specific configuration group based on information output by inputting the fourth instruction, the specification information, and one or more configurations included in a specific configuration group among the configuration groups into a generation AI. The program according to claim 8.

12. the processor: a specification dividing step of dividing the plurality of elements included in the specification information into a plurality of partial specification information each including a plurality of elements related to each other; a specification specifying step of specifying one or more predetermined partial specification information associated with a predetermined configuration group from the plurality of partial specification information divided in the specification dividing step; Run The second patent acquisition step is a step of acquiring at least a part of a patent specification corresponding to the predetermined configuration based on information output by inputting the fourth instruction, the predetermined partial specification information, and one or more configurations included in the predetermined configuration group into a generation AI. The program according to claim 11.

13. the processor: a configuration summarizing step of generating a configuration summary for at least some of the plurality of configuration groups; a partial summarization step of creating a partial summary for at least a part of the plurality of partial specification information; Run the specification identifying step is a step of identifying the predetermined partial specification information associated with a partial summary similar to a constituent summary of the predetermined constituent group; The program according to claim 12.

14. the processor: An order acquisition step of acquiring the description order of the configuration groups based on information output by inputting a fifth instruction to output the description order of the configurations, information based on the one or more configuration groups, and part or all of the proposal information or part or all of the specification information into a generation AI; a fifth patent acquisition step of executing the second patent acquisition step for each of a plurality of constituent groups and acquiring a patent specification by combining parts of the acquired plurality of patent specifications in the order of description; To execute The program according to claim 11.

15. a specification presentation step of presenting the specification information acquired in the specification acquisition step; a specification editing step of accepting an editing operation for the specification information presented in the specification presenting step; a patent presentation step of presenting at least a part of the patent specification acquired in the second patent acquisition step; a patent editing step of accepting an editing operation for at least a part of the patent specification presented in the patent presenting step; Run The second patent acquisition step is a step of acquiring at least a part of the patent specification based on information output by inputting the fourth instruction, the specification information for which the editing operation was accepted in the specification editing step, and information indicating the editing operation accepted in the patent editing step into a generation AI. The program according to any one of claims 5 to 7.

16. A method executed by an information processing device including a processor and a storage unit, wherein the processor executes all of the steps executed in the invention according to any one of claims 1 to 7.

17. 8. An information processing device comprising a processor and a storage unit, wherein the processor executes all of the steps executed in the invention according to any one of claims 1 to 7.

18. A system comprising means for executing all steps performed in the invention according to any one of claims 1 to 7.

Images