Program, method, information processing apparatus, and system

Abstract

To solve the problem that information supplementing a first document cannot be acquired.SOLUTION: A program is to be executed by a computer comprising a processor and a storage unit. When the program is executed, the processor performs a first document input step of receiving input of a first document including a description in which one or more second documents are referenced, a reference contents acquisition step of acquiring one or more reference contents being at least a part of the one or more second documents, on the basis of the description in the first document of which the input is received in the first document input step and in which one or more second documents are referenced, and an information acquisition step of acquiring supplementary information for supplementing the first document, which is outputted in response to input of a prompt including the one or more reference contents acquired in the reference contents acquisition step to a large-scale language model.SELECTED DRAWING: Figure 1

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 supporting patent work 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 an issue in that information supplementing the first document cannot be obtained. Therefore, the present disclosure has been made to solve the above problem, and its purpose is to provide a technology for acquiring information that supplements a first document. [Means for solving the problem]

[0005] A program to be executed by a computer having a processor and a memory unit, the program executing the following steps: a first document input step in which the processor accepts input of a first document including a description that references one or more other second documents; a reference content acquisition step in which, based on a description that references one or more second documents included in the first document accepted in the first document input step, the reference content acquisition step acquires one or more reference contents that are at least a part of one or more second documents; and an information acquisition step in which, in response to inputting a prompt including the one or more reference contents acquired in the reference content acquisition step into a large-scale language model, the supplementary information that supplements the first document that is output. [Effects of the Invention]

[0006] According to the present disclosure, information that supplements the first document can be obtained. [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 first document table 1013. [Figure 6] FIG. 10 is a diagram showing the data structure of a location table 1014. [Figure 7] FIG. 10 is a diagram showing the data structure of a second document table 1015. [Figure 8] 10 is a flowchart showing the operation of document assistance processing. [Figure 9] 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 the present disclosure is an information processing system that provides a document processing support service. 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 a document processing support service. 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 storage unit 101 of the server 10 includes an application program 1011 , a user table 1012 , a first document table 1013 , a location table 1014 , and a second document table 1015 .

[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 IDs and user names, 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.

[0016] The first document table 1013 is a table for storing and managing information related to the first document (first document information). Specifically, the first document includes notification documents such as a notice of reasons for refusal, a decision of refusal, an international search report, and an international search written opinion that are sent to an applicant such as an applicant by an administrative agency such as the Japan Patent Office in a patent application. Furthermore, the notification documents do not necessarily have to be notifications from administrative agencies, and include any documents sent from the other party, such as a warning letter. The first document may also include any document prepared or submitted by the applicant, such as a notice of grounds for revocation, a request for invalidation trial, various replies, and other opinions. In addition, the first document may include any document related to a trial, such as a complaint or judgment. The first document table 1013 is a table having the first document ID as a primary key and columns of the first document ID, user ID, and first document content. FIG. 5 is a diagram showing the data structure of the first document table 1013. As shown in FIG.

[0017] The primary document ID is an item that stores primary document identification information for identifying a primary document. The primary document identification information is an item in which a unique value is set for each piece of primary document information. The user ID is an item for storing user identification information for identifying a user. The first document content is an item for storing first document data relating to the content of the first document. For example, if the first document is a notice of reasons for refusal, character string information (text data) relating to the contents of the notice of reasons for refusal is stored. Note that the contents of the first document may be stored as document data in any format, such as Word format (doc, docx format), PDF format, etc.

[0018] The location table 1014 is a table for storing and managing information (location information) relating to one or more locations included in the first document. The location table 1014 is a table having a location ID as a primary key and columns of location ID, first document ID, location content, and commentary data. FIG. 6 is a diagram showing the data structure of the location table 1014.

[0019] The location ID is an item for storing location identification information for identifying location information. The location identification information is an item for which a unique value is set for each piece of location information. The first document ID is an item for storing first document identification information. The part content is an item that stores the content of each independent description item (part) such as a chapter, a section, or a paragraph contained in the first document content. For example, if the first document is a notice of reasons for refusal, the part content stores part of the first document content for each article and reason for refusal contained in the notice of reasons for refusal. The commentary data is an item that stores commentary information related to location information identified based on location identification information. The commentary data includes the following information: In addition, the commentary data does not necessarily have to be text data, and may include tabular data. - Statement of opinion regarding the validity of the content described in the section. -Explanatory text explaining the content described in the section. - An explanatory statement that explains the relationship between multiple secondary documents according to the content described in the section content. For example, the explanatory statement may include a statement such as "'Configuration A' in Secondary Document A corresponds to 'Configuration B' in Secondary Document B."

[0020] The secondary document table 1015 is a table for storing and managing information relating to secondary documents (secondary document information). The second document table 1015 is a table having the second document ID as a primary key and having columns of the second document ID, location ID, second document content, reference range, and reference content. FIG. 7 is a diagram showing the data structure of the second document table 1015. As shown in FIG.

[0021] The secondary document ID is an item that stores secondary document identification information for identifying a secondary document. The secondary document identification information is an item in which a unique value is set for each piece of secondary document information. The location ID is an item for storing location identification information for identifying a location. The second document content is an item for storing second document data relating to the content of the second document. For example, if the second document is a patent specification, character string information (text data) related to the patent specification is stored, and if the second document is a patent publication, character string information (text data) related to the patent publication is stored. The second document content may be configured to store document data in any format, such as Word format (doc, docx format), PDF format, or the like. The reference range is an item that stores information indicating the reference range of the second document (the range of a part of the second document) in the passage content identified by the passage identification information. Specifically, the reference range stores information indicating the range of a part of the second document, such as the "reference paragraph," "reference claim," or "page" of the second document mentioned in the passage content, for identifying the part of the second document. The reference content is an item that stores a portion (location) of the second document content that is specified based on the reference range. Specifically, it is an item that stores document content that is extracted from the second document content and is specified by "reference paragraph," "reference claim," "page," etc.

[0022] <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 and a document support unit 1042. The control unit 104 executes an application program 1011 stored in the storage unit 101, thereby realizing each functional unit.

[0023] 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.

[0024] The document support unit 1042 executes document support processing, the details of which will be described later.

[0025] <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 .

[0026] <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 .

[0027] 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.

[0028] 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.

[0029] <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.

[0030] <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 .

[0031] <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 .

[0032] <Configuration of Artificial Intelligence System 40> The artificial intelligence system 40 is an information processing device that outputs a response to a prompt. Examples of the artificial intelligence system 40 include ChatGPT, OpenAI GPT, PerplexityAsk, BingAI, 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 response in text that assists in the reading comprehension of patent documents by sending a prompt created in the 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 large-scale language model system (LLM system).

[0033] <System 1 Operation> Each process of the system 1 will be explained below. FIG. 8 is a flowchart showing the operation of the document support process.

[0034] <Document Support Processing> The document support process is a process that supports the reading and comprehension of a document.

[0035] <Document Support Processing Overview> The document assistance process is a series of processes that accepts input of a first document from a user, extracts one or more passages from the first document, extracts a second document and a reference range in the second document for each passage, extracts reference content based on the second document content and reference range in the second document, generates a prompt based on the passage and reference content, sends the prompt to a large-scale language model, and obtains and stores explanatory content related to the passage.

[0036] <Details of document support processing> The document support process will be described in detail below.

[0037] <First document input reception step> In step S101, the document support unit 1042 of the server 10 executes a first document input step of accepting input of a first document that includes a description that references one or more other second documents. The first document input step executes a step of accepting input of a first document, which is a notification document notified by an administrative agency, including a description that references one patent application and one or more second documents that are one or more cited documents. The notification documents include at least one of a notice of reasons for refusal, a written refusal, an international search report, and an international search written opinion.

[0038] Specifically, the user operates the input device 206 of the user terminal 20 to execute a browser application or the like, and opens the first document input page D1 by inputting the URL of a web page (first document input page) for executing the first document input process. The control unit 204 of the user terminal 20 transmits a request including the user ID 2011 for opening the first document input page to the server 10.

[0039] Upon receiving the request, the server 10 generates a first document input page and transmits it to the user terminal 20. The control unit 204 of the user terminal 20 displays the first document input page on the display 2081 of the user terminal 20 and presents it. The user inputs the document content (text data) of the first document into an input field provided on the first document input page. Note that the user may be able to upload a text file, PDF file, Word file, or the like that stores the document content of the first document using an upload button or the like provided on the first document input page. The control unit 204 of the user terminal 20 transmits the input first document to the server 10. The document support unit 1042 of the server 10 receives and accepts the first document. The document support unit 1042 of the server 10 stores the received first document and user ID 2011 in the first document content and user ID fields of a new record in the first document table 1013. The document support unit 1042 of the server 10 assigns a new number (target first document ID) to the first document ID and stores it.

[0040] For example, in this disclosure, a case where a user inputs a notice of reasons for refusal in a patent application as the first document is disclosed as an example. The first document, which is a notice of reasons for refusal, includes a statement referencing a second document, such as the application number of the patent application (the present application) that is the subject of the notice of reasons for refusal, and if the subject of the notice of reasons for refusal is a reason for refusal related to novelty, inventive step, etc., the publication number of the cited document (citation) related to the prior art. The statement referencing the second document includes the name of the second document (second document identification information for identifying the second document), such as the publication number (publication number, patent number) of the cited document, the number of the paper, etc., the URL in the case of an internet article, or the book title in the case of a book. In addition, a notice of reasons for refusal generally includes, in addition to the name of the second document that is the cited document (second document identification information), information indicating the scope of reference (reference location) when referring to the cited document in the notice of reasons for refusal (paragraph number, page number, line number, claim number, etc.).

[0041] For example, the first document, a notice of reasons for refusal, may include a statement such as "...Paragraphs 0042, 0048, etc. of Japanese Patent Application Laid-Open No. YYYY-XXXXXX (Document 1) disclose that..." In this case, "Japanese Patent Application Laid-Open No. YYYY-XXXXXX" is the second document identification information, and the paragraphs "0042" and "0048" correspond to information indicating the reference range (reference range information). The document contents described in paragraph 0042 of Japanese Patent Application Laid-Open No. XXXX-XXXXXX, "

[0042] This invention is..." and paragraph 0048, "

[0048] Thereby,..." are considered to be information indicating the reference content (reference content information). Second document identification information: Patent Publication No. YYYY-XXXXXX Reference range information: Paragraphs 0042 and 0048 ·Reference content information:

[0042] This invention is...

[0048] This results in...

[0042] <Part extraction step> In step S102, the document support unit 1042 of the server 10 extracts the contents of each independent description item (place) such as a chapter, a paragraph, or a section included in the first document content from the first document input received in step S101. Specifically, the document support unit 1042 of the server 10 divides the notice of reasons for refusal received in step S101 into sections for each reason for refusal notified, and extracts the contents of each divided section (location). For example, a notice of reasons for refusal may consist of multiple reasons for refusal, such as "Reason 1 (novelty)..., Reason 2 (inventive step),...Reason 3 (clarity)...", etc. In such cases, the notice of reasons for refusal is divided into three different documents (section contents) for each different reason, such as section content A "Reason 1 (novelty)...", section content B "Reason 2 (inventive step)...", and section content C "Reason 3 (clarity)...". The document support unit 1042 of the server 10 stores the target first document ID and the location content A in the first document ID and location content items of the new record in the location table 1014. Similarly, the document support unit 1042 of the server 10 stores the location content B and the location content C in the location content item of the new record in the location table 1014, associating them with the target first document ID and the degree of association.

[0043] In the present disclosure, an example has been described in which the first document content received in step S101 is divided into section contents and stored in section table 1014, but step S102 is not necessarily required. The document support unit 1042 of server 10 may store the entire first document content in the section content item of section table 1014. In this case, section table 1014 may be omitted, and first document table 1013 may be used instead of section table 1014. In this case, it is sufficient to provide an item in the first document table that relates to the commentary data in section table 1014.

[0044] Furthermore, although a configuration in which the content of a section in a notice of reasons for refusal is divided by reason and stored as a separate section has been disclosed as an example, it is also possible to store a configuration in which the content of the reasons for refusal for each claim is divided by reason. For example, in a case such as "Reason 1 (novelty) Claim 1..., Claim 4..., Reason 2 (inventive step) Claim 3...Claims 6-12..., Reason 3 (clarity) Claim 8..., Claim 10...", the notice of reasons for refusal is divided into six different documents (section contents) for each claim for which a different reason and reason for refusal was pointed out, such as section content A1 "Reason 1 (novelty) Claim 1...", section content A2 "Reason 1 (novelty) Claim 4...", section content B1 "Reason 2 (inventive step) Claim 3...", section content B2 "Reason 2 (inventive step) Claims 6-12...", section content C1 "Reason 3 (clarity) Claim 8...", section content C2 "Reason 3 (clarity) Claim 10...", and stored in section table 1014.

[0045] <Second Document Extraction Step (First Embodiment)> In step S103, the document support unit 1042 of the server 10 executes an identification information extraction step to extract one or more pieces of second document identification information that identify one or more second documents from the first document accepted as input in the first document input step, and one or more pieces of reference range information that indicate the reference range of each of the one or more second documents in the first document. Specifically, the document support unit 1042 of the server 10 analyzes the document content (text data of the section content) of the first document and extracts the second document identification information contained in the first document and information indicating the reference range for each second document (reference range information). For example, when the first document is a notice of reasons for refusal, the document support unit 1042 of the server 10 searches for and identifies character strings that start with a specific character string, such as "JP Patent Publication YYYY," "Patent NN," etc. Specifically, it may be possible to extract character strings that match the rules of unexamined patent publications and patent publications, such as "JP Patent Publication YYYY-XXXXXXX," "Patent NNNNNN," using regular expressions, etc. Also, for example, if the first document is written in a structured format such as HTML or XML, an HTML tag (e.g., <doc> Patent YYYY-XXXXXXX< / doc> <ref> 0042,0048< / ref> ) and extracts the second document identification information "JP Patent Publication YYYY-XXXXXXX" and reference range information (0042,0048) contained in the HTML tag. In addition, the document support unit 1042 of the server 10 may extract the second document identification information and the reference range information by using a machine learning model, a deep learning model, any other artificial intelligence model, a large-scale language model, etc. Alternatively, the second document identification information and the reference range information may be extracted in response to an input operation by the user. For example, the first document may be presented to the user, and the user may select the second document identification information and the reference range information contained in the presented first document.

[0046] The identification information extraction step includes a step of extracting one or more pieces of reference range information indicating the reference range for each of the one or more second documents, which is output in response to inputting a prompt including the first document and one or more second document identification information extracted from the first document into a large-scale language model. Specifically, the document support unit 1042 of the server 10 may first extract second document identification information from the first document, and then use the second document identification information to execute a process of extracting reference range information indicating the reference range of the second document from the first document by using a large-scale language model. This is because, while second document identification information can be extracted relatively easily from the content described in the first document, extracting reference range information is difficult even when using a machine learning model, a deep learning model, or any other artificial intelligence model, large-scale language model, etc.

[0047] For example, the document support unit 1042 of the server 10 can obtain an output including reference range information by inputting the following prompt to the artificial intelligence system 40 based on the extracted second document identification information as follows: Note that the document content of the first document or the section content is input in the [first document] section.

[0048] 〔prompt〕 In the first document, please extract the descriptions that identify the scope of reference regarding "Patent Publication No. YYYY-XXXXX1" (Reference 1) and "Patent Publication No. YYYY-XXXXX2" (Reference 2). #Document 1 [Document 1]

[0049] In response to the above prompt input, the artificial intelligence system 40 outputs, for example, the following output result: The document support unit 1042 of the server 10 acquires the reference range information of the second document related to document 1 and document 2 based on the contents of "paragraphs 0042, 0048" and "paragraphs 0028, 0024."

[0050] [Output result] JP 2006-022666 A: Paragraphs 0042 and 0048 JP 2002-00284: Paragraphs 0028 and 0024

[0051] <Second Document Extraction Step (Second Embodiment)> In step S103, the document support unit 1042 of the server 10 executes a second identification presentation step of presenting to the user one or more pieces of second document identification information extracted in the identification information extraction step. Specifically, the document support unit 1042 of the server 10 transmits the second document identification information extracted in step S102 to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the received second document identification information on the display 2081 of the user terminal 20.

[0052] In step S103, the document support unit 1042 of the server 10 executes a second document receiving step of receiving from the user input of one or more second documents corresponding to one or more pieces of second document identification information presented in the second identification presentation step. Specifically, the user inputs the document content of the second document into an upload button or input field associated with each of the presented second document identification information by operating the input device 206 of the user terminal 20. Multiple upload buttons or input fields may be provided in accordance with multiple pieces of second document identification information. For example, the user is presented with the second document identification information relating to "Japanese Patent Application Laid-Open No. YYYY-XXXXXX" via the display 2081 of the user terminal 20. The user operates the input device 206 of the user terminal 20 to input the document content of the second document (patent publication) relating to Japanese Patent Application Laid-Open No. YYYY-XXXXXX (preferably the entire specification including the abstract, claims, detailed description of the invention, etc., but only a portion will do). The control unit 204 of the user terminal 20 transmits the document content of the input second document to the server 10. The document support unit 1042 of the server 10 receives and accepts the document content of the received second document. This allows the user to reliably transmit to the server 10 the document content of the second document corresponding to the second document identification information extracted in step S102.

[0053] <Second Document Extraction Step (Third Embodiment)> In step S103, the document support unit 1042 of the server 10 acquires one or more second documents based on one or more second document identification information extracted in the identification information extraction step, and executes a second document presentation step to present the acquired one or more second documents to the user. Specifically, the document support unit 1042 of the server 10 searches a document database (not shown) or the like based on the second document identification information extracted in step S102 to acquire the document content of the second document. The document content of multiple second documents may be acquired according to multiple pieces of second document identification information. For example, the document support unit 1042 of the server 10 searches a patent document database (not shown) based on the second document identification information relating to "Patent Publication YYYY-XXXXXX" and obtains the document content of the second document (patent gazette) relating to Patent Publication YYYY-XXXXXXX (preferably the entire specification including the abstract, claims, detailed description of the invention, etc., but only a portion is acceptable). The document support unit 1042 of the server 10 transmits the acquired second document to the user terminal 20. The control unit 204 of the user terminal 20 displays the received second document on the display 2081 of the input device 206 of the user terminal 20, and presents it.

[0054] In step S103, the document support unit 1042 of the server 10 executes a second document correction step of accepting, from the user, corrections to at least a part of the one or more second documents presented in the second document presentation step. Specifically, the user can check the content of the presented second document, and if there is an error, can correct or replace the content of the second document by operating the input device 206 of the user terminal 20. Specifically, as in the second document extraction step (second embodiment), the configuration may be such that the user can input or upload the content of the second document again. For example, the document support unit 1042 of the server 10 may search the patent document database based on the second document identification information related to "JP Patent Publication No. YYYY-XXXXXX," but may identify the document content of an incorrect patent document as the document content of the second document related to the second document identification information. Even in such a case, the user can check the document content of the presented second document, and if the incorrect document has been identified as the second document, correct the document content of the second document. As a result, even if the second document cannot be extracted appropriately, the user can appropriately modify the second document to obtain supplemental information of higher quality than that which supplements the first document.

[0055] The document support unit 1042 of the server 10 stores the extracted second document identification information, reference range, the original first document (the location content identified based on the location ID), and the document content of the acquired second document in the second document table 1015 in the fields of second document ID, reference range, location ID, and second document content of a new record.

[0056] <Reference Content Extraction Step (First Embodiment)> In step S104, the document support unit 1042 of the server 10 executes a reference content acquisition step to acquire one or more reference contents that are at least a part of one or more second documents based on a description that references one or more second documents contained in the first document accepted as input in the first document input step. The reference content acquisition step executes a step of acquiring one or more reference contents that are at least a part of the patent application and the cited document based on the description that refers to the patent application and the cited document included in the notification document. For example, "Japanese Patent Application Laid-Open No. YYYY-XXXXXX" is the second document identification information, and paragraphs "0042" and "0048" are the reference range information. In this case, paragraph 0042 of Japanese Patent Application Laid-Open No. XXXX-XXXXXX, which is the second document accepted in step S103, contains the statement "

[0042] This invention is...," and paragraph 0048 contains the statement "

[0048] Thereby...." In this case, the document support unit 1042 of the server 10 extracts the following information as the reference content information: ·Reference content information:

[0042] This invention is...

[0048] This results in...

[0057] The document support unit 1042 of the server 10 executes a reference content extraction step in which, based on the one or more second document identification information and one or more reference range information extracted in the identification information extraction step, one or more reference contents identified by one or more reference ranges are extracted from the text content of one or more second documents identified by the one or more second document identification information. The reference content extraction step includes a step of extracting one or more reference contents specified by one or more reference ranges from one or more second documents received in the second document receiving step.

[0058] In step S104, the reference content extraction step includes a step of extracting reference content specified by the reference range from one or more second documents corrected in the second document correction step. Specifically, when the second document corrected by the user is accepted in the second document extraction step (third embodiment), the reference content specified by the reference range information of the second document corrected by the user is extracted.

[0059] In step S104, a reference content acquisition step executes a step of acquiring one or more reference contents extracted in the reference content extraction step. Specifically, the document support unit 1042 of the server 10 acquires and identifies the reference content of the extracted second document.

[0060] <Reference Content Extraction Step (Second Embodiment)> In step S104, the document support unit 1042 of the server 10 executes a reference content presenting step of presenting to the user one or more reference contents extracted in the reference content extracting step. Specifically, the document support unit 1042 of the server 10 transmits the extracted reference content to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the received reference content on the input device 206 of the user terminal 20 in operation 081.

[0061] In step S104, the document support unit 1042 of the server 10 executes a reference content correction step of accepting, from the user, corrections to one or more reference contents presented in the reference content presentation step. A reference content acquisition step executes a step of acquiring one or more reference contents corrected in the reference content correction step. Specifically, the user may be able to edit the presented reference content by adding or revising it by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 transmits the revised reference content to the server 10. The document support unit 1042 of the server 10 receives and accepts the revised reference content. As a result, even if the reference content cannot be extracted properly, the user can obtain supplementary information of higher quality than that of the first document by appropriately correcting the reference content.

[0062] The document support unit 1042 of the server 10 stores the extracted reference content in the reference content field of the target record in the second document table 1015. As a result, the second document table 1015 stores the second document information in which the second document identification information, the reference range, and the reference content of the second document referenced in the first document related to the location ID are associated. That is, for each section of the first document, the second document identification information, the second document, the reference range of the second document, and the reference content are stored in association with each other.

[0063] <Prompt Generation Step (First Embodiment)> In step S105, the document support unit 1042 of the server 10 executes a prompt generation step of generating a prompt to cause the large-scale language model to output supplementary information that includes one or more reference contents acquired in the reference content acquisition step and that supplements the first document. Specifically, the document support unit 1042 of the server 10 searches for the section ID item of the second document table based on the target section ID for the section content (target section ID) of a specific first document, and obtains one or more reference contents stored in association with the target section ID. The document support unit 1042 of the server 10 generates a prompt to cause the large-scale language model to output supplemental information that supplements the content of the passage in the first document, based on the passage content and one or more reference contents.

[0064] [Prompt to output additional information that supplements the content of the first document] The first document below is the Notice of Refusal issued by the Japan Patent Office. Please output supplementary information to supplement the Notice of Refusal based on the contents of the first and second documents below. #Document 1 [Contents of section] #Document 2 #Document A: Patent Publication No. YYYY-XXXXX1 (Second document identification information A) #Reference A: [Claim 1]... #Document B: Patent Publication No. YYYY-XXXXX2 (Second document identification information B) #Reference content B

[0065] [Prompt to output explanatory information explaining the issues raised in the notification document] The first document below is the Notice of Rejection issued by the Japan Patent Office. Please provide a clear explanation of the points raised in the Notice of Rejection based on the contents of the first and second documents below. #Document 1 [Contents of section] #Document 2 #Document A: Patent Publication No. YYYY-XXXXX1 (Second document identification information A) #Reference content A [Claim 1]... #Document B: Patent Publication No. YYYY-XXXXX2 (Second document identification information B) #Reference content B

[0066] The prompt generation step includes a step of generating a prompt to cause the large-scale language model to output supplementary information including at least one of opinion information regarding the validity of the points raised in the notification document, explanatory information explaining the points raised in the notification document, and correspondence information indicating the correspondence between the components described in the patent application and the components described in the cited documents. For example, the document support unit 1042 of the server 10 generates the following prompt based on the passage content and one or more reference contents: The passage content of the passage information identified based on the target passage ID is input in the [Place Content] field. Furthermore, the second document identification information and reference contents of different second documents identified by different second document identification information (second document identification information A, second document identification information B) are input as document A, document B, reference content A, and reference content B, respectively. In addition, when the first document is a notice of reasons for refusal, one of the second documents is usually the present application, so the reference content is entered as the claims (contents of claim 1, etc.) for which reasons for refusal have been notified in the present application. In addition, other second documents are other cited documents (citations) notified in the notice of reasons for refusal, so the reference content is entered as the text content of the patent gazette related to the reference content of the cited document.

[0067] [Prompt to output opinion information regarding the validity of the points raised in the notification] The first document below is the Notice of Rejection issued by the Japan Patent Office. Please output your opinion on the validity of the contents of the Notice of Rejection based on the contents of the first and second documents below. #Document 1 [Contents of section] #Document 2 #Document A: Patent Publication No. YYYY-XXXXX1 (Second document identification information A) #Reference A: [Claim 1]... #Document B: Patent Publication No. YYYY-XXXXX2 (Second document identification information B) #Reference content B

[0068] [Prompt to output explanatory information explaining the issues raised in the notification document] The first document below is the Notice of Rejection issued by the Japan Patent Office. Please provide a clear explanation of the points raised in the Notice of Rejection based on the contents of the first and second documents below. #Document 1 [Contents of section] #Document 2 #Document A: Patent Publication No. YYYY-XXXXX1 (Second document identification information A) #Reference content A [Claim 1]... #Document B: Patent Publication No. YYYY-XXXXX2 (Second document identification information B) #Reference content B

[0069] [Prompt to output correspondence information showing the correspondence between the elements described in the patent application and the elements described in the cited document] The first document below is a notice of reasons for refusal issued by the Japan Patent Office. Based on the contents of the first and second documents below, please output information showing the correspondence between the component terms described in the first document and the component terms described in the second document. #Document 1 [Contents of section] #Document 2 #Document A: Patent Publication No. YYYY-XXXXX1 (Second document identification information A) #Reference content A [Claim 1]... #Document B: Patent Publication No. YYYY-XXXXX2 (Second document identification information B) #Reference content B

[0070] <Prompt Generation Step (Second Embodiment)> In step S105, the prompt generating step includes generating a prompt for causing the large-scale language model to output assistance information for assisting in reading comprehension of the first document. Specifically, the document support unit 1042 of the server 10 searches for the section ID item of the second document table based on the target section ID for the section content (target section ID) of a specific first document, and obtains one or more reference contents stored in association with the target section ID. The document assistance unit 1042 of the server 10 generates a prompt to cause the large-scale language model to output assistance information for assisting in reading comprehension of the first document based on the passage content and the one or more reference contents.

[0071] [Prompt to output supporting information to assist in reading the first document] The first document below is the Notice of Rejection issued by the Japan Patent Office. Based on the contents of the first and second documents below, please print out supporting information to assist in reading and understanding the Notice of Rejection. #Document 1 [Contents of section] #Document 2 #Document A: Patent Publication No. YYYY-XXXXX1 (Second document identification information A) #Reference A: [Claim 1]... #Document B: Patent Publication No. YYYY-XXXXX2 (Second document identification information B) #Reference content B

[0072] <Prompt Generation Step (Third Embodiment)> In step S105, the prompt generating step includes generating a prompt including at least a portion of the specification of the patent application, for outputting amendment information related to an amendment to the claims of the patent application to the large-scale language model. In step S105, the prompt generation step includes a step of generating a prompt for outputting amendment information regarding an amendment to the claims of the patent application to the large-scale language model, the amendment including at least a portion of the specification that is not included in the scope of reference in the first document. Specifically, the document support unit 1042 of the server 10 may generate the following prompt, which includes part or all of the document content of the patent document of the present application included in the second document, in addition to the section content and one or more reference contents: Note that the document support unit 1042 of the server 10 may generate a prompt, which includes part of the document content of the patent document of the present application, that is not included in the reference scope information of the present application in the notice of reasons for refusal (first document). For example, while a notice of reasons for refusal typically includes only the claims and scope of claims as reference information for the present application, a prompt may be generated that includes references other than the claims and scope of claims, since the description for amending the claims and scope of claims is provided elsewhere in the specification.

[0073] [Prompt to output amendment information regarding amendment of claims] The first document below is a notice of reasons for refusal issued by the Japan Patent Office. Based on the contents of the first and second documents below and with reference to "other contents of document A," please propose an amendment that will differentiate the content of the claims in reference A from the invention in reference B. #Document 1 [Contents of section] #Document 2 #Document A: Patent Publication No. YYYY-XXXXX1 (Second document identification information A) #Reference content A [Claim 1]... #Other contents of Document A ... #Document B: Patent Publication No. YYYY-XXXXX2 (Second document identification information B) #Reference content B

[0074] <Prompt sending step> In step S106, the document support unit 1042 of the server 10 executes a prompt input step of inputting the prompt generated in the prompt generation step into the large-scale language model. Specifically, the document assistance unit 1042 of the server 10 sends a request including the generated prompt (character string) to an API endpoint provided by the artificial intelligence system 40 as input data for the artificial intelligence system 40. The artificial intelligence system 40 sends a response including an answer to the prompt to the server 10.

[0075] <Information acquisition steps> In step S107, the document support unit 1042 of the server 10 receives a response to the sent prompt. The response includes a character string related to the answer to the prompt. The document support unit 1042 of the server 10 stores the answer in the commentary data field of the target record in the section table 1014. This allows supplemental information (commentary data) that supplements the section content of the first document output by the artificial intelligence system 40 to be stored in association with the section content of the first document stored in the section table 1014. For example, the answer content includes the following information: Note that in this disclosure, the following answer content will be described as an example, but it is preferable to configure the answer content to be received as structured data such as JSON having a field (key) related to the "classification name." For example, in a large-scale language model (LLM) called ChatGPT, the answer result can be structured (typed) data by using a function called Function Calling.

[0076] <Information Acquisition Step (First Embodiment)> In step S107, the document support unit 1042 of the server 10 executes an information acquisition step of acquiring supplementary information that supplements the first document output in response to inputting a prompt including one or more reference contents acquired in the reference content acquisition step into a large-scale language model.

[0077] The information acquisition step includes a step of acquiring supplementary information including at least one of opinion information regarding the validity of the points raised in the notification document, explanatory information explaining the points raised in the notification document, and correspondence information indicating the correspondence between the components described in the patent application and the components described in the cited documents. Specifically, the following answers are obtained in response to the "prompt to output opinion information regarding the validity of the points raised in the notification document," "prompt to output explanatory information explaining the points raised in the notification document," and "prompt to output correspondence information showing the correspondence between the components described in the patent application and the components described in the cited documents," all of which were generated in step S105.

[0078] [Response to the opinion regarding the validity of the points raised in the notification] In the first document, it is pointed out that... It is thought that... in the first document corresponds to... in the second document, and while the... points are the same, the... points are different. However, the point that... is considered to be valid.

[0079] [Responses to the explanatory information explaining the points raised in the notification document] To explain the points made in Document 1 in more detail, it points out that "..." in Document 1 corresponds to "..." in Document 2. If we look closely at Document 2, we can see that there is a statement "...", which corresponds to "..." in Document 1.

[0080] [Response content of correspondence information showing the correspondence between the components described in the patent application and the components described in the cited document] Structure A1 in the first document corresponds to structure A2 in the second document. Specifically, in the second document, structure A2 contains the statement: Structure B1 in the first document corresponds to structure B2 in the second document. Specifically, in the second document, structure B2 contains the statement:

[0081] <Information Acquisition Step (Second Embodiment)> In step S107, the information obtaining step includes a step of obtaining supplemental information including support information for assisting in reading the first document. Specifically, the following answer content is obtained in response to the "prompt for outputting support information for supporting the reading comprehension of the first document" generated in step S105.

[0082] [Responses to support information to assist in reading comprehension of Document 1] The following support information is output to assist in the comprehension of the first document. In the first document, it is pointed out that ... corresponds to ... in the second document. A closer look at the second document reveals the statement ..., which corresponds to ... in the first document.

[0083] <Information Acquisition Step (Third Embodiment)> In step S107, the information obtaining step includes a step of obtaining amendment information regarding an amendment to the claims of the patent application based on at least a part of the specification of the patent application. The information obtaining step includes a step of obtaining amendment information regarding an amendment to the claims of the patent application based on at least a part of the specification not included in the scope of reference in the first document in the patent application. Specifically, the following answer is obtained in response to the "prompt for outputting correction information related to the amendment of claims" generated in step S105.

[0084] [Response regarding amendment of claims] To differentiate Second Document A from Second Document B, it is possible to amend Structure A1 of Second Document A with the following structure. Specifically, Second Document B contains the disclosure "...", and it is possible to amend Structure A1 of Second Document A with Structure A2. To differentiate Second Document A from Second Document C, it is possible to amend Structure A3 of Second Document A with the following structure. Specifically, Second Document C contains the disclosure "...", and it is possible to amend Structure A3 of Second Document A with Structure A4.

[0085] <Information Acquisition Step (Fourth Embodiment)> In step S107, the document support unit 1042 of the server 10 executes a configuration presentation step of presenting to the user one or more components described in the patent application acquired in the information acquisition step. Specifically, when the first document is a notice of rejection, one of the second documents is usually the application, and therefore the reference content is entered as the claim for which the rejection was notified in the application (the content of claim 1, etc., hereinafter referred to as the target claim). The document support unit 1042 of the server 10 extracts one or more components (such as means, part, or step) from the text of the target claim. The document support unit 1042 of the server 10 may use the artificial intelligence system 40 to extract one or more components from the text of the target claim. The document support unit 1042 of the server 10 transmits the extracted one or more components to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the received one or more components on the display 2081 of the user terminal 20.

[0086] In step S107, the document support unit 1042 of the server 10 executes a configuration selection step of accepting, from the user, a selection of at least a part of one or more configuration elements presented in the configuration presentation step. Specifically, the user operates the input device 206 of the user terminal 20 to select a predetermined component from one or more components displayed on the display 2081 of the user terminal 20. The control unit 204 of the user terminal 20 transmits information identifying the selected component to the server 10.

[0087] In step S107, the information acquisition step includes a step of acquiring amendment information regarding a narrowing amendment to the claims of the patent application based on the components selected in the configuration selection step and at least a part of the specification of the patent application. Specifically, the document support unit 1042 of the server 10 extracts portions of the document content of the present specification contained in the second document that are related to the received component, based on the received information identifying the component (which may be component names such as "means...", "part...", or "step..."). For example, morphological analysis may be performed to extract lines or paragraphs that include the component as portions related to the component. Alternatively, the artificial intelligence system 40 may be used to extract portions of the document content of the present specification that are related to the component. Specifically, the document support unit 1042 of the server 10 may generate a prompt such as the following, which includes the passage content, one or more reference contents, and a portion of the document content of the present application that is related to the element: In this case, "the portion of the document content of the present application that is related to the element" is inserted in place of "other contents of document A."

[0088] [Prompt to output amendment information regarding amendment of claims] The first document below is a notice of reasons for refusal issued by the Japan Patent Office. Based on the contents of the first and second documents below and with reference to "other contents of document A," please propose a suitable restrictive amendment that differentiates the content of the claims in reference A from the invention in reference B. #Document 1 [Contents of section] #Document 2 #Document A: Patent Publication No. YYYY-XXXXX1 (Second document identification information A) #Reference content A [Claim 1]... #Other contents of Document A ... #Document B: Patent Publication No. YYYY-XXXXX2 (Second document identification information B) #Reference content B

[0089] The document assistance unit 1042 of the server 10 executes a prompt input step of inputting the generated prompt into a large-scale language model. Specifically, the document assistance unit 1042 of the server 10 sends a request including the generated prompt (character string) to an API endpoint provided by the artificial intelligence system 40 as input data for the artificial intelligence system 40. The artificial intelligence system 40 sends a response including an answer to the prompt to the server 10. The document support unit 1042 of the server 10 receives a response to the sent prompt. The response includes a character string related to the answer to the prompt. The document support unit 1042 of the server 10 stores the answer in the commentary data field of the target record in the section table 1014. This allows supplemental information (commentary data) that supplements the section content related to the first document output by the artificial intelligence system 40 to be stored in association with the section content of the first document stored in the section table 1014.

[0090] The document support unit 1042 of the server 10 may transmit the commentary data to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the received commentary data on the display 2081 of the user terminal 20. The control unit 204 of the user terminal 20 also displays and presents the commentary data on the display 2081 of the user terminal 20 together with at least one of the first document and the second document. This allows the user to refer to the commentary data when reading the first document. The user can refer to suitable supplementary information that supplements the first document to read the first document.

[0091] <Basic computer hardware configuration> 9 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.

[0092] 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.

[0093] 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).

[0094] 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.

[0095] 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.

[0096] 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.

[0097] <Basic functional configuration of computer 90> The following describes the functional configuration of a computer realized by the basic hardware configuration (FIG. 9) of the computer 90. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] <Additional Notes> The matters described in the above embodiments will be supplemented below.

[0105] (Appendix 1) A program to be executed by a computer having a processor and a memory unit, the program executing: a first document input step (S101) in which the processor accepts input of a first document including a description that references one or more other second documents; a reference content acquisition step (S104) in which, based on a description that references one or more second documents included in the first document accepted in the first document input step, the reference content acquisition step acquires one or more reference contents that are at least a part of one or more second documents; and an information acquisition step (S107) in which supplemental information that supplements the first document is output in response to inputting a prompt including the one or more reference contents acquired in the reference content acquisition step into a large-scale language model. This makes it possible to obtain suitable supplementary information that supplements the first document.

[0106] (Appendix 2) The program described in Appendix 1, wherein the first document input step (S101) is a step of accepting input of a first document, which is a notification document notified by an administrative agency, including a description that references one patent application and one or more second documents that are one or more cited documents, and the reference content acquisition step (S104) is a step of acquiring one or more reference contents that are at least a part of the patent application and the cited documents based on the description that references the patent application and the cited documents included in the notification document. This makes it possible to obtain suitable supplementary information for a notification document sent from an administrative agency by referring to patent applications and cited documents.

[0107] (Appendix 3) The program described in Appendix 2, wherein the information acquisition step (S107) includes a step of acquiring supplementary information including at least one of opinion information regarding the validity of the points raised in the notification document, explanatory information explaining the points raised in the notification document, and correspondence information showing the correspondence between the components described in the patent application and the components described in the cited documents. This allows the user to refer to the patent application and cited documents when receiving a notification from an administrative agency to obtain suitable supplementary information, such as an opinion on the validity of the points raised in the notification, an explanation of the points raised, and the correspondence between the elements described in the patent application and the elements described in the cited documents.

[0108] (Appendix 4) The notification documents are the program described in Appendix 2, which includes at least one of a notice of reasons for refusal, a written decision of refusal, an international search report, and an international search written opinion. This makes it possible to obtain suitable supplementary information to supplement notification documents such as notices of reasons for refusal, decisions of refusal, international search reports, and international search written opinions issued by administrative agencies.

[0109] (Appendix 5) The program described in Appendix 4, wherein the information acquisition step (S107) by the processor includes a step of acquiring amendment information regarding amendments to the claims of the patent application based on at least a portion of the specification of the patent application. This makes it possible to obtain suitable amendment strategies and suggestions for amendment contents for the scope of claims in response to notification documents such as notices of reasons for refusal, decisions of refusal, international search reports, and international search written opinions issued by administrative agencies.

[0110] (Appendix 6) The program described in Appendix 5, wherein the information acquisition step (S107) includes a step of acquiring, in a patent application, amendment information regarding amendments to the claims of the patent application based on at least a portion of the specification that is not included in the reference scope in the first document. This makes it possible to obtain suitable amendment strategies and suggestions for amendment contents for the scope of claims in response to notification documents such as notices of reasons for refusal, decisions of refusal, international search reports, and international search written opinions issued by administrative agencies.

[0111] (Appendix 7) A program as described in Appendix 5, in which a processor executes a configuration presentation step (S107) in which one or more components described in the patent application acquired in the information acquisition step are presented to a user, and a configuration selection step (S107) in which the processor accepts from the user a selection of at least a portion of the one or more components presented in the configuration presentation step, wherein the information acquisition step (S107) includes a step of acquiring amendment information regarding a narrowing amendment to the claims of the patent application based on the components selected in the configuration selection step and at least a portion of the specification of the patent application. This allows the user to obtain a proposal of suitable candidates for a restriction amendment to the claims relating to the component selected by the user.

[0112] (Appendix 8) A program as described in Appendix 1, wherein the processor executes an identification information extraction step (S103) in which the processor extracts one or more pieces of second document identification information that identify one or more second documents from the first document accepted as input in the first document input step, and one or more pieces of reference range information that indicate the reference range of each of the one or more second documents in the first document, and a reference content extraction step (S104) in which the processor extracts one or more reference contents identified by one or more reference ranges from the text content of one or more second documents identified by the one or more pieces of second document identification information based on the one or more pieces of second document identification information and the one or more pieces of reference range information extracted in the identification information extraction step, and the reference content acquisition step (S104) is a step in which the one or more reference contents extracted in the reference content extraction step are acquired. This makes it possible to obtain supplementary information of higher quality than that for supplementing the first document.

[0113] (Appendix 9) A program as described in Appendix 8, wherein a processor executes a second document presentation step (S103) of acquiring one or more second documents based on one or more second document identification information extracted in the identification information extraction step, and presenting the acquired one or more second documents to a user, and a second document correction step (S103) of accepting from the user corrections to at least a portion of the one or more second documents presented in the second document presentation step, and wherein a reference content extraction step (S104) includes a step of extracting reference content identified by a reference range from the one or more second documents corrected in the second document correction step. As a result, even if the second document cannot be extracted appropriately, the user can appropriately modify the second document to obtain supplemental information of higher quality than that which supplements the first document.

[0114] (Appendix 10) A program as described in Appendix 8, in which a processor executes a reference content presentation step (S104) of presenting to a user one or more reference contents extracted in the reference content extraction step, and a reference content correction step (S104) of accepting from the user corrections to one or more reference contents presented in the reference content presentation step, and a reference content acquisition step (S104) of acquiring one or more reference contents corrected in the reference content correction step. This means that even if the reference content of the second document cannot be properly extracted, the user can obtain supplementary information of higher quality than that of the first document by appropriately correcting the reference content of the second document.

[0115] (Appendix 11) A program as described in Appendix 8, wherein a processor executes a second identification presentation step (S103) of presenting to a user one or more second document identification information extracted in the identification information extraction step, and a second document reception step (S103) of receiving from the user input of one or more second documents corresponding to the one or more second document identification information presented in the second identification presentation step, and wherein a reference content extraction step (S104) includes a step of extracting one or more reference contents identified by one or more reference ranges from the one or more second documents received in the second document reception step. This allows the user to input an appropriate second document according to the second document identification information, thereby making it possible to obtain supplemental information of higher quality than that for supplementing the first document.

[0116] (Appendix 12) The program described in Appendix 8, wherein the identification information extraction step (S103) includes a step of extracting one or more pieces of reference range information indicating the reference range for each of one or more second documents, which is output in response to inputting a prompt including the first document and one or more pieces of second document identification information extracted from the first document into a large-scale language model. This allows appropriate extraction of the reference range of one or more second documents from the first document.

[0117] (Appendix 13) 2. The program according to claim 1, wherein the information acquisition step (S107) includes a step of acquiring supplementary information including support information for assisting in reading comprehension of the first document. This allows the user to refer to the support information and reduce the burden of reading the first document.

[0118] (Appendix 14) A computer-implemented method comprising a processor and a memory, wherein the processor performs all of the steps performed in the invention according to any one of appendices 1 to 13. This makes it possible to obtain suitable supplementary information that supplements the first document.

[0119] (Appendix 15) An information processing device comprising a control unit and a memory unit, wherein the control unit executes all of the steps executed in the invention according to any one of Supplementary Note 1 to Supplementary Note 13. This makes it possible to obtain suitable supplementary information that supplements the first document.

[0120] (Appendix 16) A system comprising means for performing all steps performed in any of the inventions according to any one of appendixes 1 to 13. This makes it possible to obtain suitable supplementary information that supplements the first document. [Explanation of symbols]

[0121] 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 first document input step of receiving input of a first document including a description that references one or more other second documents; a reference content acquisition step of acquiring one or more reference contents that are at least a part of the one or more second documents based on a description that refers to the one or more second documents included in the first document received in the first document input step; an information acquisition step of acquiring supplemental information that supplements the first document and is output in response to inputting a prompt including the one or more reference contents acquired in the reference content acquisition step into a large-scale language model; A program that executes.

2. the first document input step is a step of receiving input of the first document, which is a notification document notified by an administrative agency, including a description that references one patent application and one or more second documents that are cited documents; the reference content acquisition step is a step of acquiring the one or more reference contents, which are at least a part of the patent application and the cited document, based on a description that refers to the patent application and the cited document included in the notification document; The program according to claim 1.

3. The information acquisition step includes: Opinion information regarding the validity of the points pointed out in the notification document; and explanatory information explaining the contents of the notice; Correspondence information indicating the correspondence between the components described in the patent application and the components described in the cited document; obtaining the supplemental information including at least one of The program according to claim 2.

4. The notification document includes at least one of a notice of reasons for refusal, a written refusal, an international search report, and an international search written opinion. The program according to claim 2.

5. the processor: the information acquisition step includes a step of acquiring amendment information regarding an amendment to the claims of the patent application based on at least a part of the specification of the patent application; The program according to claim 4.

6. the information obtaining step includes a step of obtaining amendment information regarding an amendment to the claims of the patent application based on at least a part of the specification not included in the scope of reference in the first document in the patent application; The program according to claim 5.

7. the processor: a configuration presentation step of presenting to a user one or more components described in the patent application acquired in the information acquisition step; a configuration selection step of accepting, from the user, a selection of at least a part of the one or more configuration elements presented in the configuration presentation step; Run the information acquisition step includes a step of acquiring amendment information regarding a restriction amendment to the claims of the patent application based on the components selected in the configuration selection step and at least a part of the specification of the patent application; The program according to claim 5.

8. the processor: an identification information extraction step of extracting, from the first document accepted in the first document input step, one or more pieces of second document identification information that identify the one or more second documents, and one or more pieces of reference range information that indicate reference ranges in the first document to each of the one or more second documents; a reference content extraction step of extracting one or more reference contents specified by the one or more reference ranges from text content of the one or more second documents specified by the one or more second document identification information based on the one or more second document identification information and the one or more reference range information extracted in the identification information extraction step; Run the reference content acquisition step is a step of acquiring the one or more reference contents extracted in the reference content extraction step; The program according to claim 1.

9. the processor: a second document presenting step of acquiring the one or more second documents based on the one or more second document identification information extracted in the identification information extracting step, and presenting the acquired one or more second documents to a user; a second document correction step of accepting, from the user, corrections to at least a part of the one or more second documents presented in the second document presentation step; Run the reference content extraction step includes a step of extracting the reference content identified by the reference range from the one or more second documents corrected in the second document correction step; The program according to claim 8.

10. the processor: a reference content presenting step of presenting the one or more reference contents extracted in the reference content extracting step to a user; a reference content correction step of accepting, from the user, corrections to the one or more reference contents presented in the reference content presentation step; Run the reference content acquisition step is a step of acquiring the one or more reference contents corrected in the reference content correction step; The program according to claim 8.

11. the processor: a second identification presentation step of presenting to a user the one or more pieces of second document identification information extracted in the identification information extraction step; a second document receiving step of receiving, from the user, input of the one or more second documents corresponding to the one or more second document identification information presented in the second identification presenting step; Run the reference content extraction step includes a step of extracting the one or more reference contents identified by the one or more reference ranges from the one or more second documents received in the second document receiving step, The program according to claim 8.

12. the identification information extraction step includes a step of extracting one or more pieces of reference range information indicating a reference range for each of the one or more second documents, the reference range information being output in response to inputting a prompt including the first document and the one or more second document identification information extracted from the first document into a large-scale language model; The program according to claim 8.

13. the information acquisition step includes a step of acquiring the supplemental information including support information for assisting in reading comprehension of the first document; The program according to claim 1.

14. A method implemented on a computer having a processor and a memory, wherein the processor performs all of the steps performed in the invention according to any one of claims 1 to 13.

15. 14. An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps executed in the invention according to any one of claims 1 to 13.

16. A system comprising means for executing all steps performed in any one of the inventions according to claims 1 to 13.

Images