Program, method, information processing device, and system

Abstract

This program is to be executed by a computer provided with a processor and a storage unit, wherein the processor executes: a task receiving step for receiving task information pertaining to a task to be executed with respect to a patent document; a query receiving step for receiving query information to be applied to the patent document; a document acquisition step for acquiring a patent document pertaining to a patent; an extraction step for extracting a predetermined extraction place, from the patent document acquired in the document acquisition step, in accordance with the task received in the task receiving step; and a generation step for generating a prompt including the query information received in the query receiving step and the extraction place extracted in the extraction step.

Description

Program, method, information processing device, and system

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

[0002] There are known technologies to support patent work. Patent Document 1 discloses a technology for supporting the understanding of claims, which identifies and presents key elements in claims, allowing readers to focus on reading the explanations.

[0003] JP 2011-096200 A

[0004] A problem exists in that it is not easy to generate suitable prompts to be applied to patent documents. Therefore, the present disclosure has been made to solve the above problem, and its purpose is to provide a technology that easily generates suitable prompts to be applied to patent documents.

[0005] A program to be executed by a computer having a processor and a memory unit, the program executing the following steps: a task receiving step in which the processor receives task information related to a task to be performed on a patent document; a query receiving step in which query information to be applied to the patent document is received; a document acquisition step in which patent documents related to patents are acquired; an extraction step in which, from the patent documents acquired in the document acquisition step, predetermined extracted portions are extracted in accordance with the task received in the task receiving step; and a generation step in which a prompt is generated that includes the query information received in the query receiving step and the extracted portions extracted in the extraction step.

[0006] According to the present disclosure, it is possible to easily generate suitable prompts to be applied to patent documents.

[0007] 1 is a block diagram showing the functional configuration of the system 1. FIG. 1 is a block diagram showing the functional configuration of the server 10. FIG. 1 is a block diagram showing the functional configuration of the user terminal 20. FIG. 2 is a diagram showing the data structure of a user table 1012. FIG. 3 is a diagram showing the data structure of a document table 1013. FIG. 4 is a diagram showing the data structure of a term table 1014. FIG. 5 is a diagram showing the data structure of a support table 1015. FIG. 6 is a diagram showing the data structure of a task master 1016. FIG. 7 is a diagram showing the data structure of a list table 1017. FIG. 8 is a flowchart showing the operation of a document display process. FIG. 9 is a flowchart showing the operation of an inquiry process. FIG. 10 is an example screen showing the operation of a document display process and an inquiry process. FIG. 11 is a flowchart showing the operation of a list process. FIG. 11 is a block diagram showing the basic hardware configuration of a computer 90.

[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] <Configuration of System 1> System 1 in the present disclosure is an information processing system that provides a patent document reading support service. System 1 includes information processing devices, a server 10, a user terminal 20, and an artificial intelligence system 40, which are connected via a network N. Fig. 1 is a block diagram showing the functional configuration of system 1. Fig. 2 is a block diagram showing the functional configuration of the server 10. Fig. 3 is a block diagram showing the functional configuration of the user terminal 20.

[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] <Configuration of Server 10> The server 10 is an information processing device that provides a patent document reading support service. The server 10 includes a storage unit 101 and a control unit 104.

[0012] <Configuration of Storage Unit 101 of Server 10 > The storage unit 101 of the server 10 includes an application program 1011 , a user table 1012 , a document table 1013 , a term table 1014 , a support table 1015 , a task master 1016 , and a list table 1017 .

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

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

[0015] The user ID is an item that stores user identification information for identifying a user. The user identification information is an item in which a unique value is set for each user. The user name is an item that stores the user's name. The user name may not be a name, but may be any character string such as a nickname.

[0016] The document table 1013 is a table for storing and managing information (document information) related to patent documents. The document table 1013 is a table having columns for document ID, user ID, document name, and document content. Fig. 5 shows the data structure of the document table 1013.

[0017] The document ID is an item that stores document identification information for identifying a patent document. The user ID is an item that stores user identification information for identifying a user. The document name is an item that stores the name of a patent document. Any character string can be set for the document name. For example, the document name stores the publication number, registration number, application number, and other serial numbers of the patent document. The document content is an item that stores the document content of the patent document. Specifically, the text information of the patent document is stored. For example, the document content includes some or all of the "claims," ​​"abstract," "detailed description of the invention," "examples," "embodiments," etc. contained in the patent document (specification). Specifically, the publication text of the publication publication, patent gazette, etc. is stored.

[0018] The term table 1014 is a table for storing and managing information related to terms (term information). The term table 1014 is a table having columns for document ID and term text. FIG. 6 shows the data structure of the term table 1014.

[0019] The document ID is an item that stores document identification information for identifying a patent document. The term text is an item that stores a character string of a term. Specifically, the term text stores a character string of technical terms, etc., included in a patent document identified by the document identification information.

[0020] The support table 1015 is a table for storing and managing prompts related to query sentences sent to the AI ​​system and the responses (support information) from the AI ​​system. The support table 1015 has columns for document ID, prompt, and response. Figure 7 shows the data structure of the support table 1015.

[0021] The document ID is a field that stores document identification information for identifying patent documents. The prompt is a field that stores a prompt related to a query sentence to an artificial intelligence system. A prompt is primarily a query sentence (text) input to an artificial intelligence system. Specifically, a user can input a prompt to an artificial intelligence system so that the artificial intelligence system outputs a desired output result. Note that the prompt does not need to be a character string, but may be a prompt in the form of an image, video, audio, etc. For example, a user's gesture, voice instruction, etc. can also be a prompt. The answer content is a field that stores the answer content from the artificial intelligence system to the prompt. Specifically, text information related to the answer content from the artificial intelligence system is stored. Note that, although an artificial intelligence system that provides an answer in text is described as an example in this disclosure, this is not limited thereto. In an artificial intelligence system that provides an answer in the form of an image, video, audio, etc., the answer content may also be stored as image data, video data, audio data, etc.

[0022] The task master 1016 is a table for storing and managing information (task information) related to tasks executed on patent documents. The task master 1016 is a table having columns for task ID, task type, extracted item, and task data, with the task ID as the primary key. Figure 8 shows the data structure of the task master 1016.

[0023] The task ID is a field that stores task identification information for identifying a task. The task identification information is a field that is assigned a unique value for each piece of task information. The task type is a field that stores task type information related to the type of task. Specifically, the task type stores a string that identifies the content of the task according to the purpose of the processing (task) performed on the patent document. In the present disclosure, the task type stores information such as "classification," "screening," and "applicability determination" according to the content of the task. Classification task: A task that classifies multiple patent documents according to their respective contents. Screening task: A task that determines whether each of multiple patent documents is related to a target document. Specifically, tasks may be subdivided into "prior art search," "prior art search," "invalidation document search," etc. Applicability determination task: A task that determines whether each of multiple patent documents is related to a target product. For example, these are tasks performed in patent work, such as "clearance search," "FTO search," and "infringement product search." Extraction item is a field that stores information (extraction item information) indicating the extracted items of patent documents when executing a task. Specifically, the extracted items include character strings indicating extracted items of the patent document providing the task, such as "abstract," "specification," "claims," ​​and "drawings." The extracted items also include character strings indicating extracted items of the patent document providing the task, such as "title of the invention," "detailed description of the invention," "technical field," "background art," "prior art documents," "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," "embodiments," "industrial applicability," "explanation of symbols, etc.", "problem," and "solution." Specifically, the extracted items store the following extracted item information according to the task type: Classification: abstract, claims, claim 1, specification, etc. Screening: abstract, claims, claim 1, specification, etc. Applicability determination: claim 1, claims. Task data is an item that stores information (character strings) related to the task. Specifically, the task data stores the following character strings according to the task type:The <Query> field contains the query data (described below), and the <Extracted Document> field contains the extracted portions (extracted content, partial sentences) from the patent document, identified based on the extraction fields, to generate a prompt. - When the task type is "Classification Assignment": "Define the technology classification as follows. Classify the inventions described in the "Target Patents" below into Class A, B, or C. Calculate the relevance between the target patents and the classification on a scale of 0 to 100. Output the reasons for your decision. #Technology Classification: <Query> (Classification A "...", Classification B "...", Classification C "...") #Target Patents: <Extracted Documents> (Abstract and Claims section (contents) of the patent document)" - When the task type is "Screening": "Consider whether the invention described in the "Target Invention" below is also described in the invention described in the "Target Patent" below. Calculate the relevance between the target invention and the target patent on a scale of 0 to 100. Output the reasons for your decision." #Target invention: <Query> (Apparatus comprising ... means, ... means, ...) #Target patent: <Extracted document> (Abstract, claims, specification section (contents) of patent document)' - If the task type is "Applicability determination" "Please consider whether the products, services, etc. described in the "Target product" below fall within the scope of the invention described in the "Target patent" below. Calculate the relevance between the target product and the target patent between 0 and 100. Output the reason for this determination. #Target product: <Query> (Apparatus comprising ... means, ... means, ...) #Target patent: <Extracted document> (Claim 1 section (contents) of patent document)'.

[0024] The list table 1017 is a table for storing and managing a list (list information) including multiple patent documents. The list table 1017 has columns for list ID, document list, task ID, and query data, with the list ID as the primary key. Figure 9 shows the data structure of the list table 1017.

[0025] The list ID field stores list identification information for identifying a list. The list identification information is a field with a unique value assigned to each list. The document list field stores a list of document IDs for multiple patent documents. The document list may store not only document IDs but also document names, document contents, etc. associated with the document IDs. The task ID field stores task identification information indicating a task to be applied to a list containing multiple patent documents identified by the list identification information. The query data field stores a query to be applied to a list containing multiple patent documents identified by the list identification information. Specifically, the query data stores the following queries depending on the type of task: Classification task: A sentence (character string) defining the classification target and a list of multiple example sentences (character strings) expressing the classification target are stored. Example: Classification A is "...", Classification B is "...", Classification C is "...". Screening: A sentence (character string) describing the target invention is stored. Example: A device comprising ... means, ... means, and .... Applicability determination: A sentence (character string) describing the target product is stored. Example: A device comprising means for..., means for..., and...

[0026] <Configuration of control unit 104 of server 10> The control unit 104 of the server 10 includes a user registration control unit 1041, a document display unit 1042, and an inquiry unit 1043. The control unit 104 executes an application program 1011 stored in the storage unit 101, thereby realizing each functional unit.

[0027] The user registration control unit 1041 performs a process of storing information about users who wish to use the service disclosed herein in the user table 1012. Information stored in the user table 1012 is generated when a user opens a webpage operated by the service provider from an 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 user registration. This allows the user stored in the user table 1012 to use the service. Prior to the user registration control unit 1041 registering user information in the user table 1012, the service provider may conduct a predetermined screening process to restrict whether or not the user can use the service. The user ID may be any string or number that can identify the user. It may be any string or number desired by the user, or the user registration control unit 1041 may automatically set any string or number.

[0028] The document display unit 1042 executes a document display process, the details of which will be described later.

[0029] The inquiry unit 1043 executes inquiry processing, the details of which will be described later.

[0030] <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, or a stationary personal computer (PC) or laptop PC. It may also be 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.

[0031] <Configuration of Storage Unit 201 of User Terminal 20 > The storage unit 201 of the user terminal 20 includes a user ID 2011 and an application program 2012 .

[0032] 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 services 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.

[0033] The application program 2012 may be stored in advance in the storage unit 201, or may be downloaded from a web server operated by a service provider via a communication IF. The application program 2012 includes an application such as a web browser application. The application program 2012 includes an interpreter-type programming language such as JavaScript (registered trademark) that is executed on a web browser application stored in the user terminal 20.

[0034] <Configuration of control unit 204 of 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.

[0035] <Configuration of Input Device 206 of 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 .

[0036] <Configuration of Output Device 208 of User Terminal 20 > The output device 208 of the user terminal 20 includes a display 2081 and a speaker 2082 .

[0037] <Configuration of Artificial Intelligence System 40> The artificial intelligence system 40 is an information processing device that outputs responses to prompts. Examples of the artificial intelligence system 40 include ChatGPT, OpenAI GPT, PerplexityAsk, and BingAI. 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 reading a patent document by sending a prompt created in the inquiry process to the artificial intelligence system 40. Furthermore, in the present disclosure, the artificial intelligence system is not limited to a text-based dialogue system. For example, an image generation AI system such as Midjourney or Stable Diffusion may be used. For example, a user can obtain an image or video response that assists in reading a patent document by sending a prompt created in the inquiry process to such an image generation AI system. 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).

[0038] <Operation of System 1> Each process of System 1 will be described below. Fig. 10 is a flowchart showing the operation of document display processing. Fig. 11 is a flowchart showing the operation of query processing. Fig. 12 is an example screen showing the operations of document display processing and query processing. Fig. 13 is a flowchart showing the operation of list processing. Fig. 14 is an example screen showing the operation of list processing.

[0039] <Document Display Processing> The document display processing is a process of accepting a patent document and terminology, and highlighting the patent document based on the terminology (highlighting the display in a display format that adds decorations such as a different color, background color, bold, underline, etc.).

[0040] <Overview of document display processing> The document display processing is a series of processes that accept a patent document, extract key words based on the patent document, accept input of terms, perform highlighting processing on the patent document based on the terms, and display the document after the highlighting processing.

[0041] <Details of Document Display Processing> Details of the document display processing will be described below.

[0042] In step S101, the document display unit 1042 of the server 10 executes a document reception step for receiving a patent-related document. Specifically, the user operates the input device 206 of the user terminal 20 to input the URL of a page for executing document display processing (document display processing page) into a web browser or the like, and opens the document display processing page. The control unit 204 of the user terminal 20 sends a request to open the document display processing page to the server 10. Based on the received request, the control unit 104 of the server 10 generates a document display processing page and sends it to the user terminal 20. The control unit 204 of the user terminal 20 displays the received document display processing page on the display 2081 of the user terminal 20.

[0043] 12 shows an example of a document display screen in the document display process. A document display page D1 is displayed on the display 2081 of the user terminal 20. The document display page D1 includes a document display screen D10. The document display screen D10 includes a document input button D100, a document display area D101, a term input area D102, and a query / answer area D105. The term input area D102 includes term input fields D1021, D1022, D1023, etc., definition / explanation buttons D1031, D1032, D1033, etc., and a summary generation button D1041. The query / answer area D105 includes a prompt input field D1051, a prompt send button D1052, prompts D1061, D1062, etc., answer contents D1071, D1072, etc., and auxiliary buttons D1081, D1082, D1083, etc. The reply content D1071 includes paragraph numbers D1091, D1092, and so on.

[0044] The user operates the input device 206 of the user terminal 20 to press the document input button D100 displayed on the document display screen D10. The control unit 204 of the user terminal 20 generates a document input dialog screen and displays it on the display 2081 of the user terminal 20. The user inputs the document name and document content on the document input dialog screen. Specifically, the user operates the input device 206 of the user terminal 20 to input the publication number of the unexamined publication or patent publication in the document name input field. The user operates the input device 206 of the user terminal 20 to input text information of the specification of the unexamined publication or patent publication in the document content input field. Note that the control unit 204 of the user terminal 20 may acquire the document content by referencing a publication database (not shown) based on the publication number entered in the document name field and automatically enter the content. The user presses the "send button" displayed on the document input dialog screen to send the information entered in the document name and document content input fields to the server 10. The information sent to the server 10 includes the user ID 2011. The document display unit 1042 of the server 10 receives and accepts the user ID 2011, document name, and document content from the user terminal 20. The document display unit 1042 of the server 10 stores the received user ID 2011, document name, and document content in the user ID, document name, and document content items of a new record in the document table 1013, respectively.

[0045] In step S101, the document display unit 1042 of the server 10 executes a document presentation step in which the document accepted in the document acceptance step is presented to the user. The control unit 204 of the user terminal 20 displays the accepted document content in the document display area D101 and presents it to the user. The user can check the content of the patent document in the document display area D101.

[0046] In step S102, the document display unit 1042 of the server 10 executes a keyword identification step of identifying one or more keyword words obtained by analyzing the content of the document received in the document receiving step. Specifically, the document display unit 1042 of the server 10 identifies one or more keyword words by analyzing the document content received in step S101. The document display unit 1042 of the server 10 applies morphological analysis to sentences included in the document content to divide them into words. The document display unit 1042 of the server 10 calculates the importance (score) of each word using the TF-IDF method, text ranking method, n-gram method, or the like. The TF-IDF method is a method of calculating the importance of each word by combining the word frequency and inverse document frequency. The n-gram method is a method of extracting n consecutive words and calculating a score for each word based on their frequency of occurrence. The text ranking method is a method of calculating the importance of each word based on the PageRank algorithm. Other methods include LexRank and LSA (Latent Semantic Analysis). The document display unit 1042 of the server 10 extracts and identifies a predetermined number of words in order of importance, or words with an importance level equal to or higher than a predetermined value, as key words. The document display unit 1042 of the server 10 transmits the identified key words to the user terminal 20. The control unit 204 of the user terminal 20 receives and accepts the key words. Note that the control unit 204 of the user terminal 20 may also execute the key word extraction process.

[0047] In step S103, the control unit 204 of the user terminal 20 executes a term receiving step of receiving one or more terms contained in the document received in the document receiving step. Specifically, the user operates the input device 206 of the user terminal 20 to input terms contained in the document content displayed in the document display area D101 into the term input fields D1021, D1022, and D1023 by copying and pasting or performing input operations using the keyboard. The user can input any character string into the term input fields D1021, D1022, and D1023.

[0048] In step S103, a term receiving step is executed to receive one or more keyword words identified in the keyword identifying step as one or more terms. Specifically, the control unit 204 of the user terminal 20 may present to the user one or more keyword words received from the server 10 in the term input fields D1021, D1022, and D1023. The control unit 204 of the user terminal 20 may receive one or more keyword words received from the server 10 as one or more terms.

[0049] In step S103, the control unit 204 of the user terminal 20 executes a keyword presentation step of presenting one or more keyword words identified in the keyword identification step to the user. Specifically, the control unit 204 of the user terminal 20 may present one or more keyword words received from the server 10 on the display 2081 of the user terminal 20 in a selectable manner. For example, the user operates the input device 206 of the user terminal 20, whereby one or more keyword words are presented to the user in a selectable manner (for example, in a manner associated with a check box, a radio box, or the like).

[0050] In step S103, the term receiving step receives, in response to a user input operation for one or more key words presented in the key word presenting step, at least some of the key words corresponding to the input operation as one or more terms. Specifically, the user operates the input device 206 of the user terminal 20 to select one or more specific key words from one or more key words presented in a selectable manner on the display 2081 of the user terminal 20. The control unit 204 of the user terminal 20 inputs the selected one or more specific key words into the term input fields D1021, D1022, and D1023. This allows the control unit 204 of the user terminal 20 to receive the one or more specific key words selected by the user as one or more terms.

[0051] The control unit 204 of the user terminal 20 presents one or more keyword words to the user by superimposing a dialog presenting the one or more keyword words on the document display screen D10. The user may operate the input device 206 of the user terminal 20 to perform a selection operation for the one or more keyword words, thereby inputting the selected one or more keyword words into the term input fields D1021, D1022, and D1023.

[0052] In step S104, the control unit 204 of the user terminal 20 performs a highlighting process on one or more terms included in the document content displayed in the document display area D101. Specifically, the control unit 204 of the user terminal 20 highlights (highlights) one or more terms included in the document content received in step S103 by adding decorations such as a different color, background color, bold text, or underlining. For example, the control unit 204 of the user terminal 20 can highlight one or more terms included in the document content by replacing each of the one or more terms with one or more highlighted terms. Note that the document display unit 1042 of the server 10 may also perform the highlighting process.

[0053] In step S105, a document presenting step is executed in which one or more terms contained in the document are presented to the user in an identifiable manner based on one or more terms accepted in the term accepting step. Specifically, the control unit 204 of the user terminal 20 displays the highlighted document content in the document display area D101 and presents it to the user.

[0054] <Query processing> Query processing is a process in which a prompt (query sentence, question sentence, question query) regarding a query sentence is created based on the terms received in the document display process, and based on that prompt, the artificial intelligence system is queried for information that will be useful in reading and understanding the patent document.

[0055] <Overview of query processing> Query processing is a series of processes that accept a term selection, create a prompt based on the selected term, accept editing of the prompt from the user, send the prompt to the artificial intelligence system, receive the response content from the artificial intelligence system, and display the received response content.

[0056] <Details of Inquiry Processing> Details of the inquiry processing will be described below.

[0057] In step S301, the user operates the input device 206 of the user terminal 20 to select one or more term input fields D1021, D1022, and D1023 included in the term input area D102. Specifically, the user operates the input device 206 of the user terminal 20 to press one of the definition / explanation buttons D1031, D1032, and D1033. This selects one of the term input fields D1021, D1022, and D1023 corresponding to the pressed definition / explanation button D1031, D1032, or D1033. The user operates the input device 206 of the user terminal 20 to press the summary generation button D1041. This selects all of the term input fields D1021, D1022, and D1023. Note that a configuration in which only some of the term input fields D1021, D1022, and D1023 are selected may also be used. For example, a configuration may be adopted in which a predetermined one or more of the multiple term input fields D1021, D1022, and D1023 are selected by selecting a check box or the like associated with each of the term input fields D1021, D1022, and D1023. In addition, the user can select some or all of the term input fields D1021, D1022, and D1023 by operating the input device 206 of the user terminal 20 in the term input area D102.

[0058] In step S302, the control unit 204 of the user terminal 20 executes a query generation step of generating a prompt for the query sentence based on the terms received in the term reception step. Specifically, the control unit 204 of the user terminal 20 generates a prompt for the query sentence based on the terms selected in step S301.

[0059] In step S302, the query creation step executes a step of creating a prompt including a sentence requesting the definition or explanation of the meaning of one or more terms. Specifically, when the user operates the input device 206 of the user terminal 20 to press the definition / explanation button D1031, the control unit 204 of the user terminal 20 creates a prompt (character string) such as "Please explain the meaning or content of the term "Term 1" in this sentence" based on the term "Term 1" entered in the term input field D1021. In step S301, if only one term is selected, the control unit 204 of the user terminal 20 may automatically create a prompt including a sentence requesting the definition or explanation of the term.

[0060] In step S302, the query generation step executes a step of generating a prompt including a sentence requesting an explanation of the relationship between multiple terms. Specifically, when the user operates the input device 206 of the user terminal 20 to press the summary generation button D1041, the control unit 204 of the user terminal 20 generates a prompt (character string) such as "Please explain the relationship between the terms 'Term 1', 'Term 2', and 'Term 3' in this sentence" based on the terms "Term 1," "Term 2," and "Term 3" entered in the term input fields D1021, D1022, and D1023. If multiple terms are selected in step S301, the control unit 204 of the user terminal 20 may automatically generate a prompt including a sentence requesting an explanation of the relationship between the multiple terms.

[0061] In step S302, the query generation step executes a step of generating a prompt including information about the technical field identified based on the content of the document received in the document reception step. Specifically, the control unit 204 of the user terminal 20 identifies "Technical Field 1," which is the technical field mentioned in the patent document, by analyzing the content of the text. The technical field may be identified based on a character string, such as a patent classification, included in the patent document. The control unit 204 of the user terminal 20 generates a prompt (character string) such as "The following text is a text in the technical field of "Technical Field 1." This is included in the already generated prompt. For example, the control unit 204 of the user terminal 20 generates a prompt such as "The following text is a text in the technical field of "Technical Field 1." Please explain the meaning and content of the term "Term 1" in this text."

[0062] In step S302, the query creation step executes a step of creating a prompt in response to an input operation received from the user. Specifically, the control unit 204 of the user terminal 20 may be configured to create the prompt in response to an input operation of the input device 206 of the user terminal 20, such as pressing the definition / explanation button D1031, D1032, or D1033 or pressing the summary generation button D1041. Alternatively, the control unit 204 of the user terminal 20 may automatically create a prompt in response to terms and keywords entered in the term input fields D1021, D1022, or D1023, without receiving an input operation from the user.

[0063] In step S302, the control unit 204 of the user terminal 20 completes the prompt by adding the entire document content to the end of the prompt. For example, the control unit 204 of the user terminal 20 creates a prompt such as, "The following text is from the technical field of 'Technical Field 1'. Please explain the meaning and content of the term 'Term 1' in this text. [Document Content]."

[0064] In step S302, the control unit 204 of the user terminal 20 may complete the prompt by adding a portion of the document content to the end of the prompt, rather than the entire document content. For example, the control unit 204 of the user terminal 20 may create a prompt such as, "The following text is from the technical field of 'Technical Field 1'. Please explain the meaning and content of the term 'Term 1' in this text. [Partial Document 1] [Partial Document 2] [Partial Document 3]."

[0065] The query generation step executes a step of identifying a partial document that is part of the document received in the document receiving step based on the query sentence or one or more terms, and creating a prompt including the partial document. The query generation step executes a step of identifying lines or paragraphs containing words included in the query sentence or one or more terms from the document received in the document receiving step, and creating a prompt including a partial document consisting only of the line or paragraph. Specifically, the control unit 204 of the user terminal 20 divides the document content into multiple partial documents, each of which is a line or paragraph. The control unit 204 of the user terminal 20 calculates the relevance between the input values ​​in the term input fields D1021, D1022, and D1023 and the multiple partial documents. Specifically, the relevance can be determined by using cosine similarity, Euclidean distance, Jakker coefficient, or the like between each of the multiple partial documents and the input values ​​in the term input fields D1021, D1022, and D1023. The control unit 204 of the user terminal 20 extracts a predetermined number of partial documents in order of relevance, or one or more partial documents with a relevance equal to or greater than a predetermined value, and adds them to the end of the prompt. The control unit 204 of the user terminal 20 may also calculate the relevance between an already created prompt and multiple partial documents. In this case, one or more partial documents highly relevant to the already created prompt are added to the end of the prompt. Note that partial documents do not need to be lines or paragraphs, and partial documents may be obtained by dividing any document unit that makes up the patent document.

[0066] The query unit 1043 of the server 10 may also execute the prompt creation process.

[0067] The control unit 204 of the user terminal 20 inputs the created prompt into the prompt input field D1051.

[0068] In step S303, the user can edit the content of the prompt entered in the prompt input field D1051 by operating the input device 206 of the user terminal 20. Specifically, the user can modify and edit the prompt entered in the prompt input field D1051 by operating the input device 206 of the user terminal 20. The user can add any of the auxiliary character strings, such as "Please explain briefly," "Please explain in bullet points," or "Please explain in 300 characters or less," to the prompt entered in the prompt input field D1051 by operating the input device 206 of the user terminal 20 and pressing any of the auxiliary buttons D1081, D1082, and D1083. This allows the response content from the artificial intelligence system 40 to be controlled so that it matches the user's expectations.

[0069] In step S304, the query unit 1043 of the server 10 executes a query transmission step in which the query is sent by transmitting the prompt created in the query creation step to an artificial intelligence system operated by an external business. Specifically, the user presses the prompt transmission button D1052 by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 transmits the character string (prompt) entered in the prompt input field D1051 to the server 10. The query unit 1043 of the server 10 transmits the character string (prompt) received from the user terminal 20 to an API (Application Programming Interface) endpoint of the artificial intelligence service provided by the artificial intelligence system 40. Note that the control unit 204 of the user terminal 20 may also transmit the character string (prompt) entered in the prompt input field D1051 directly to the API (Application Programming Interface) endpoint of the artificial intelligence service.

[0070] In step S305, the query unit 1043 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 query unit 1043 of the server 10 transmits the received response to the user terminal 20. Note that the control unit 204 of the user terminal 20 may receive the response to the sent prompt directly from the artificial intelligence system 40.

[0071] In step S306, the query unit 1043 of the server 10 executes an answer presentation step of presenting to the user the answer content to the prompt sent in the query sending step. The answer presentation step executes a step of presenting the answer content to the user along with the document presented in the document presentation step. Specifically, upon receiving a response, the control unit 204 of the user terminal 20 displays the prompt and the answer content included in the response to the prompt in prompt D1061 and answer content D1071, respectively. Multiple prompts and multiple answer contents to the multiple prompts are displayed in prompts D1061, D1062, ..., answer contents D1071, D1072, respectively, and presented to the user. The query answer area D105 is displayed together with the document display area D101. This allows the user to check the highlighted patent document and the answer content from the artificial intelligence system together, thereby efficiently reading and understanding the patent document.

[0072] In step S306, the answer presentation step executes a step of presenting one or more terms included in the answer content to the user in an identifiable manner based on one or more terms accepted in the term acceptance step. Specifically, the control unit 204 of the user terminal 20 may also highlight the character strings displayed in the prompts D1061 and D1062 and the character strings displayed in the answer content D1071 and D1072. For example, the control unit 204 of the user terminal 20 may highlight one or more terms included in the character string of the prompt or answer content by replacing each of the terms with one or more highlighted terms. This allows the terms included in the answer content from the artificial intelligence system to also be highlighted. The user can check the highlighted patent document and the highlighted answer content together, allowing for efficient reading and understanding of the patent document.

[0073] The answer presentation step includes a partial identification step of identifying a partial document that is a part of the document received in the document receiving step and that is related to the prompt or the answer content, and a step of presenting information indicating the identified partial document together with the answer content. The answer presentation step includes a partial identification step of identifying a line or paragraph of the document received in the document receiving step that is related to the prompt or the answer content, and a step of presenting the identified line or paragraph together with the answer content. Specifically, the control unit 204 of the user terminal 20 divides the document content into multiple partial documents, each for one line or paragraph. The control unit 204 of the user terminal 20 calculates the relevance between the input values ​​in the term input fields D1021, D1022, and D1023 and the multiple partial documents. Specifically, the relevance can be determined by using cosine similarity, Euclidean distance, Jakker coefficient, or the like between each of the multiple partial documents and the input values ​​in the term input fields D1021, D1022, and D1023. The control unit 204 of the user terminal 20 displays a predetermined number of partial documents in order of relevance, or line numbers or paragraph numbers that identify one or more partial documents with a relevance equal to or greater than a predetermined value, in the paragraph numbers D1091 and D1092 of the inquiry / answer area D105. Note that partial documents do not have to be lines or paragraphs, and partial documents may be obtained by dividing any document unit that constitutes the patent document.

[0074] The document display unit 1042 of the server 10 may execute the answer content presentation process.

[0075] <List processing> List processing is a process that accepts from a user a list containing multiple patent documents and a question (query) to be applied to the list, generates a prompt by applying the query to the multiple patent documents included in the list, and makes a query to an artificial intelligence system based on the prompt.

[0076] <Overview of list processing> List processing is a series of processes that accepts query input from a user, accepts a list containing multiple patent documents, identifies the patent documents included in the list, generates a prompt based on the query and the patent documents, sends the generated prompt to an artificial intelligence system, receives a response from the artificial intelligence system, and presents the received response in association with the patent document.

[0077] <Details of List Processing> Details of list processing will be explained below.

[0078] In step S501, the list processing unit 1044 of the server 10 presents a list processing screen for executing list processing to the user. Specifically, the user operates the input device 206 of the user terminal 20 to execute a browser application or the like, and opens the list page D3 by inputting the URL or the like of a web page (list page) for executing list processing. The control unit 204 of the user terminal 20 transmits a request including the user ID 2011 for opening the list page to the server 10.

[0079] When the server 10 receives the request, it generates a list page and transmits it to the user terminal 20. The control unit 204 of the user terminal 20 displays and presents the list page on the display 2081 of the user terminal 20. Fig. 14 shows an example of a list screen in list processing. A list page D3 is displayed on the display 2081 of the user terminal 20. The list page D3 includes a task selection field D301, an extraction item selection field D311, a query input field D302, a document input field D303, a prompt display field D304, a send button D305, and an answer result D306.

[0080] In step S501, the control unit 204 of the user terminal 20 executes a task presentation step of presenting multiple pieces of task information to the user in a selectable manner. Specifically, the list processing unit 1044 of the server 10 references the task master 1016, acquires the task ID and task type items, and transmits them to the user terminal 20. The control unit 204 of the user terminal 20 displays the received multiple task types in the task selection field D301 in a selectable manner. For example, the control unit 204 of the user terminal 20 presents each of the multiple task types displayed in the task selection field D301 to the user in association with a radio button for selecting the task type.

[0081] In step S501, the list processing unit 1044 of the server 10 executes a task reception step of receiving task information related to a task to be executed on a patent document. The task reception step executes a step of receiving, from a user, input operation of predetermined task information from the plurality of task information presented in the task presentation step. Specifically, the user operates the input device 206 of the user terminal 20 to select a predetermined task type to be executed on the patent document from the plurality of task types displayed in the task selection field D301.

[0082] The task receiving step receives task information indicating at least one of a classification task for assigning a classification to a patent document, a screening task for determining the relevance of the patent document to a target document, and a correlation determination task for determining the relevance of the patent document to a target product. Specifically, the user can select a predetermined task type from task types such as a classification task, a screening task, or a correlation determination task. Note that a configuration may be adopted in which multiple task types can be selected.

[0083] The control unit 204 of the user terminal 20 transmits a task ID corresponding to the task information selected in the task selection field D301 to the server 10. The list processing unit 1044 of the server 10 receives and accepts the task ID.

[0084] Although the present disclosure has disclosed an example in which multiple pieces of task information are presented in a selectable manner and selected by the user, this is not limiting. For example, the task information may be of one type (one of a classification task, a screening task, and a relevant / unrelated task), and the task information may be predetermined as the specified task information. In this case, the processing of step S501 may be omitted. In this case, the list processing unit 1044 of the server 10 can be interpreted as having received input of the predetermined task information. Furthermore, the task information may not be received by selection, but may be identified based on the content of a query received in a query receiving step (described later). Instead of the task selection field D301, a task input field may be provided in which the user can input task information, task type, etc. The user may input information indicating task information, such as a classification task, a screening task, or a relevant / unrelated task, into the task input field, and the control unit 204 of the user terminal 20 or the list processing unit 1044 of the server 10 may then receive the task type.

[0085] In step S502, the list processing unit 1044 of the server 10 executes a query receiving step of receiving query information to be applied to the patent document. Specifically, the user operates the input device 206 of the user terminal 20 to input a character string related to the query to be applied to the patent document into the query input field D302. For example, the user operates the input device 206 of the user terminal 20 to input a query such as the following into the query input field D302 according to the task type selected in step S501:

[0086] [Query for classification task] Classification A is a classification related to information processing equipment, Classification B is a classification related to agricultural machinery, and Classification C is a classification related to food products.

[0087] [Queries for Screening Tasks] Query Example 1) An apparatus comprising ... means, ... means, and ... Query Example 2) A method comprising ... steps, ... steps, and ... Query Example 3) A program that executes ... steps, ... steps, and ...

[0088] [Queries for a task for determining whether or not something is relevant] Query example 1) An apparatus comprising ... means, ... means, and ... Query example 2) A method comprising ... steps, ... steps, and ... Query example 3) A program that executes ... steps, ... steps, and ...

[0089] The control unit 204 of the user terminal 20 transmits the character string input in the query input field D302 to the server 10. The list processing unit 1044 of the server 10 receives the character string and accepts it as query data.

[0090] In step S503, the list processing unit 1044 of the server 10 executes a document acquisition step for acquiring patent documents related to patents. Specifically, the user operates the input device 206 of the user terminal 20 to input the document ID of the patent document in the document input field D303. It should be noted that the patent document does not need to be specified by the document ID in the document table 1013; the user may input the patent number of the published patent publication or the like, the abstract of each patent document, the scope of claims, and the patent specification, etc., into the document input field D303. The user may also be configured to directly select patent document information contained in a Word, Excel, CSV file, etc. stored in the memory unit 201 of the user terminal 20 as the file to be uploaded. Any means may be used by the user as long as it allows the user to transmit a specified patent document to the server 10.

[0091] The document acquisition step executes a step of acquiring patent documents relating to multiple patents. The user may operate the input device 206 of the user terminal 20 to transmit multiple patent documents to the server 10. The user may operate the input device 206 of the user terminal 20 to input document IDs of multiple patent documents in the document input field D303. The user may also transmit an Excel file, CSV file, or the like containing information on multiple patent documents to the server 10.

[0092] The control unit 204 of the user terminal 20 transmits one or more patent documents input or selected by the user to the server 10. The list processing unit 1044 of the server 10 acquires and accepts one or more patent documents by reception.

[0093] The list processing unit 1044 of the server 10 stores the task ID, query data, and one or more patent documents received from the user terminal 20 in the task ID, query data, and document list fields of a new record in the list table 1017.

[0094] In this disclosure, as an example, the processing when one patent document is input will be described from steps S504 to S507 below. Note that when multiple patent documents are input, the processing from steps S504 to S507 may be executed for each of the multiple patent documents.

[0095] In step S504, the list processing unit 1044 of the server 10 executes an extraction step of extracting a predetermined portion from the patent document acquired in the document acquisition step in accordance with the task accepted in the task acceptance step. Specifically, the list processing unit 1044 of the server 10 searches the document ID field in the document table 1013 based on the received document ID, and acquires the document content field. Note that this process may be omitted if the user inputs the document content in the document input field D303 or uploads a file or the like containing the document content.

[0096] Alternatively, a patent database (not shown) or the like may be referenced based on the received document ID and document name to acquire patent documents including abstracts, claims, specifications, etc. In this case, patent documents may be acquired from a patent database or the like, excluding predetermined extracted items based on the acquired extracted items. For example, in the case of a pertinence determination task, patent documents may be acquired from a patent database or the like, excluding extracted items such as abstracts and specifications. This case also corresponds to extracting predetermined extracted portions from the text content.

[0097] Based on the received task ID, the list processing unit 1044 of the server 10 searches for the item of the task ID in the task master 1016 and acquires the extracted items and task data. Based on the acquired extracted items, the list processing unit 1044 of the server 10 extracts predetermined extracted parts (extracted content, partial sentences) from the document content.

[0098] The extraction step may further shorten the character string of the extracted portion in accordance with a token number limit, such as the number of characters that the artificial intelligence system 40 can accept as input, as described below. Specifically, the list processing unit 1044 of the server 10 divides the character string included in the extracted portion into sentences, such as sentences and phrases, extracts sentences and phrases with high importance calculated based on methods such as TF-IDF, LexRank, and LSA, and removes sentences and phrases with low importance, thereby shortening the character string to fit within the number of characters that the artificial intelligence system 40 can accept as input. Alternatively, the extracted portion may be a portion from the beginning of the extracted portion that is a predetermined length that the artificial intelligence system 40 can accept as input, and any character string exceeding the predetermined length may be removed. Additionally, any post-processing may be applied to the specified extracted portion. In this case, the character string after applying any post-processing may also be treated as a type of specified extracted portion.

[0099] For example, the extraction step executes a step of extracting predetermined extracted passages from at least one of the abstract, claims, claim 1, and description of the patent document if the task information is a classification task, or from at least one of the abstract, claims, claim 1, and description of the patent document if the task information is a screening task, or from at least one of claim 1 and claim 1 of the patent document if the task information is a classification task. This allows passages necessary for executing the task selected by the user to be extracted from the document content of the patent document. Note that while the present disclosure has disclosed an example of a process for extracting predetermined extracted passages from a patent document without user operation, this is not limiting. For example, depending on the task information received in the task reception step, the extraction item selection field D311 may present the availability of predetermined extraction items, and the predetermined extracted passages may be extracted from the patent document depending on the extraction items selected by the user. For example, if the task information is a classification task, an extraction item selection field D311 may be presented to the user, allowing the user to select at least one of the abstract, claims, claim 1, and description. Predetermined extraction passages may be extracted from the patent document according to the extraction item selected by the user. This allows at least one of the abstract, claims, claim 1, and description to be excluded from the predetermined extraction passages in the classification task, depending on the user's selection. The present disclosure is sufficient as long as it is possible to execute a process for extracting different extraction passages from the same patent document according to the content of the task (task information) executed by the user. For example, it is sufficient to execute a process for extracting different extraction passages for each of the screening task and the subject / non-subject determination task (e.g., the description for the screening task, and claim 1 for the subject / non-subject determination task) for a single patent document to which a screening task and a subject / non-subject determination task are applied.

[0100] In the extraction step, a plurality of predetermined extracted portions are extracted from each of the plurality of patent documents acquired in the document acquisition step in accordance with the task accepted in the task acceptance step. Specifically, when a plurality of patent documents are input, the extraction step is executed for each of the patent documents included in the plurality of patent documents. Furthermore, the extracted extracted portions are stored in association with a document ID.

[0101] In step S505, the list processing unit 1044 of the server 10 executes a generating step of generating a prompt including the query information received in the query receiving step and the extracted portion extracted in the extracting step. The generating step executes a step of generating a prompt according to the task information received in the task receiving step. The generating step executes a step of generating a prompt including instructions to output index values ​​and the basis for the index values ​​related to the patent document acquired in the document acquisition step. The generating step executes a step of generating a prompt including instructions to output index values ​​indicating the execution results of the task according to the task information received in the task receiving step.

[0102] Specifically, the list processing unit 1044 of the server 10 generates a prompt by applying the query data acquired in step S502 and the extracted portion extracted in step S504 to the task data acquired in step S504. The list processing unit 1044 of the server 10 can generate the following prompt by replacing "<query>" and "<extracted document>" in the character string of the task data with the query data and the extracted portion, respectively.

[0103] [Prompt for classification task] Define the technology classification as follows. Classify the inventions described in the "target patents" below into either classification A, B, or C. Calculate the relevance between the target patents and the classification on a scale of 0 to 100. Output the reason for your decision. #Technology classification: Classification A is a classification related to information processing equipment. Classification B is a classification related to agricultural machinery. Classification C is a classification related to food products. #Target patents: [Abstract] ... [Claims] ...

[0104] [Prompt for screening tasks] Please consider whether the invention described in the "target invention" below is described in the invention described in the "target patent" below. Calculate the relevance between the target invention and the target patent on a scale of 0 to 100. Please output the reason for your decision. #Target invention: ...means, ...means, and an apparatus comprising ... #Target patent: [Abstract] ... [Claims] ... [Specification] ...

[0105] [Prompt for applicability determination task] Please consider whether the products, services, etc. described in the "Target Product" below fall within the scope of the invention described in the "Target Patent" below. Calculate the relevance between the target product and the target patent on a scale of 0 to 100. Please output the reason for your decision. #Target Product: Apparatus comprising ... means, ... means, and ... #Target Patent: [Claim 1] ...

[0106] In step S505, the generation step executes a step of generating multiple prompts for each of the multiple patent documents acquired in the document acquisition step based on the query information accepted in the query acceptance step and each of the multiple extracted portions extracted in the extraction step. Specifically, when multiple patent documents are input, the generation step executes a step of generating prompts based on the extracted portions extracted for each patent document included in the multiple patent documents. In addition, the generated prompts are stored in association with the document ID.

[0107] In step S506, the list processing unit 1044 of the server 10 transmits the generated prompt to the user terminal 20. The control unit 204 of the user terminal 20 displays the received prompt in a prompt display field D304 of the user terminal 20. The list processing unit 1044 of the server 10 executes a transmission step of transmitting the prompt generated in the generation step to the artificial intelligence system. Specifically, the user presses the send button D305 by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 transmits a request to the server 10 to transmit the generated prompt (character string) to the artificial intelligence system 40. The list processing unit 1044 of the server 10 transmits the generated prompt (character string) to an API (Application Programming Interface) endpoint of the artificial intelligence service provided by the artificial intelligence system 40. The control unit 204 of the user terminal 20 may directly send the prompt (character string) displayed in the prompt display field D304 to the API (Application Programming Interface) endpoint of the artificial intelligence service.

[0108] In step S507, the list processing unit 1044 of the server 10 executes an answer receiving step of receiving an answer to the prompt from the artificial intelligence system 40. The list processing unit 1044 of the server 10 executes an answer receiving step of receiving an answer including an index value and a rationale for the prompt from the artificial intelligence system 40. Specifically, the list processing unit 1044 of the server 10 receives a response to the sent prompt. The response includes a character string related to the answer to the prompt. For example, the answer includes the following information. Note that in this disclosure, the following answer will be described as an example, but it is preferable to receive the answer as structured data such as JSON having fields (keys) related to the "index value" and "rationale." 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.

[0109] [Answer for classification task] #Classification: A #Relevance: 80 #Reason: The target patent has the structure..., structure.... On the other hand, the target patent does not have the structure..., structure.... It matches the classification definition of Classification A, but does not match the classification definitions of Classification B and Classification C. The relevance with Classification A is about 80.

[0110] [Answer for screening task] #Relevance: 40 #Reason: The target invention matches the target patent in terms of..., but differs in terms of.... The differences are large, and the relevance to the target patent is about 40.

[0111] [Answer for the applicability determination task] #Relevance: 20 #Reason: The target product matches the target patent in terms of ..., but differs in terms of .... The target product is not included in the scope of rights of the target patent. The relevance with the target patent is about 20.

[0112] In this case, the index value (relevance) is an index value indicating the accuracy of the assigned classification if the task information is a classification assignment task, an index value indicating the relevance with the target invention if the task information is a screening task, and an index value indicating the relevance with the target product if the task information is a pertinence determination task.

[0113] The list processing unit 1044 of the server 10 stores the document ID received in step S503, the prompt generated in step S505, and the answer in the document ID, prompt, and answer items of a new record in the support table 1015.

[0114] In step S508, the list processing unit 1044 of the server 10 executes an answer presentation step in which the index values ​​and the rationale received in the answer reception step are presented to the user. Specifically, the list processing unit 1044 of the server 10 transmits the received answer content to the user terminal 20. The control unit 204 of the user terminal 20 displays the received answer content in the answer result D306. Note that the user may be configured to be able to download information related to the answer result in a file format such as Word, Excel, or CSV file by operating the input device 206 of the user terminal 20. The list processing unit 1044 of the server 10 may present the user with extracted portions of the patent document in addition to the index values ​​and rationale. This allows the user to confirm which portions of the patent document were used to calculate the index values ​​and on what basis.

[0115] When multiple patent documents are input, the list processing unit 1044 of the server 10 transmits to the user terminal 20 response contents corresponding to the prompts generated for each of the multiple patent documents. The control unit 204 of the user terminal 20 may display and present the received response contents in the response result D306. Specifically, document identification information such as the document ID, publication number, and document name of each of the multiple patent documents may be associated with the prompts generated for each document and the response contents received from the artificial intelligence system 40 in response to the prompts, and presented accordingly. In addition to the index values ​​and rationale, extracted portions of the patent documents may also be presented to the user. Furthermore, the user may operate the input device 206 of the user terminal 20 to download a file, such as a Word, Excel, or CSV file, that stores document identification information such as the document ID, publication number, and document name of each of the multiple patent documents, the prompts generated for each document, and the response contents received from the artificial intelligence system 40 in response to the prompts.

[0116] 15 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main storage device 902, an auxiliary storage device 903, and a communication IF 991 (interface), which are electrically connected to one another by a communication bus 921.

[0117] The processor 901 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, a register, a peripheral circuit, and the like.

[0118] The main storage device 902 is for temporarily storing programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0119] 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.

[0120] The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using a wired or wireless communication standard. The network is composed of the Internet, a LAN, various mobile communication systems constructed using 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 network that is directly connected using a USB (Universal Serial Bus) cable, etc.

[0121] 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 concept of the computer 90 includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

[0122] <Basic Functional Configuration of Computer 90> A description will be given of the functional configuration of the computer realized by the basic hardware configuration (FIG. 15) of the computer 90. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

[0123] 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.

[0124] The control unit is realized by the processor 901 reading various programs stored in the auxiliary storage device 903, loading them into 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.

[0125] 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. 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. The control unit can cause the processor 901 to add, update, and delete data stored in the storage unit in accordance with the various programs.

[0126] The term "database" refers to a relational database, which manages data sets called tables and masters in a tabular format structurally defined by rows and columns, by associating them with 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 established and associated. Typically, each table and each master is assigned a column that serves as a primary key to uniquely identify a record, but assigning a primary key to a column is not required. 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, the information processing device and information processing system according to the present disclosure can be considered to have been manufactured.

[0127] 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.

[0128] The communication unit is realized by the communication IF 991. The communication unit realizes the 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. Furthermore, the communication unit can transmit information output from the control unit to other computers 90.

[0129] <Additional Notes> The matters described in the above embodiments will be added below.

[0130] (Supplementary Note 1) A program to be executed by a computer including a processor and a storage unit, the program executing: a task receiving step (S501) in which the processor receives task information related to a task to be performed on a patent document; a query receiving step (S502) in which query information to be applied to the patent document is received; a document acquisition step (S503) in which patent documents related to patents are acquired; an extraction step (S504) in which, from the patent documents acquired in the document acquisition step, a predetermined extraction portion is extracted in accordance with the task received in the task receiving step; and a generation step (S505) in which a prompt is generated that includes the query information received in the query receiving step and the extraction portion extracted in the extraction step. This allows a user to easily generate a suitable prompt in accordance with a task to be applied to a patent document.

[0131] (Supplementary Note 2) The task receiving step (S501) is a step of receiving task information indicating at least one of a classification task for assigning a classification to a patent document, a screening task for determining the relevance of the patent document to a target document, and a suitability determination task for determining the relevance of the patent document to a target product, and the extraction step (S504) is a step of extracting different predetermined extraction portions according to the task information received in the task receiving step from at least one of the abstract, claims, Appendix 1, and description of the patent document if the task information is a classification task, or at least one of the abstract, claims, Appendix 1, and description of the patent document if the task information is a screening task, or at least one of Appendix 1 and claims of the patent document if the task information is a suitability determination task. This allows a user to easily generate a suitable prompt according to a desired task from among classification, screening, and suitability determination tasks to be applied to the patent document.

[0132] (Supplementary Note 3) The program according to Supplementary Note 1, wherein the generating step (S505) is a step of generating a prompt including an instruction to output index values ​​and the basis of the index values ​​for the patent document acquired in the document acquisition step, thereby enabling a user to perform a task on the patent document and generate a prompt for obtaining the index values ​​and the basis of the index values.

[0133] (Supplementary Note 4) The generating step (S505) is a step of generating a prompt including an instruction for outputting an index value indicating the execution result of the task corresponding to the task information received in the task receiving step, and the index value is an index value indicating the accuracy of the assigned classification if the task information is a classification task, an index value indicating the relevance to the target invention if the task information is a screening task, and an index value indicating the relevance to the target product if the task information is a pertinence determination task, in the program described in Supplementary Note 3. This allows a user to generate a prompt for outputting an index value indicating the execution result when performing tasks such as classification, screening, and pertinence determination on a patent document.

[0134] (Supplementary Note 5) The program according to Supplementary Note 3, wherein the processor executes a sending step (S506) of sending the prompt generated in the generating step to an artificial intelligence system, an answer receiving step (S507) of receiving an answer content including an index value and a basis for the prompt from the artificial intelligence system, and an answer presenting step (S508) of presenting the index value and the basis received in the answer receiving step to a user. This allows the user to perform a task on a patent document and to check the answer content including an index value indicating the result of the task when it is executed and the basis for the index value.

[0135] (Supplementary Note 6) The generating step (S505) is a step of generating a prompt in accordance with the task information received in the task receiving step, in the program according to Supplementary Note 1. This allows a user to easily generate a suitable prompt in accordance with a task to be applied to a patent document.

[0136] (Supplementary Note 7) The program according to Supplementary Note 1, wherein the document acquisition step (S503) is a step of acquiring patent documents relating to multiple patents, the extraction step (S504) is an extraction step of extracting multiple predetermined extraction points from each of the multiple patent documents acquired in the document acquisition step in accordance with the task accepted in the task acceptance step, and the generation step (S505) is a step of generating multiple prompts for each of the multiple patent documents acquired in the document acquisition step based on the query information accepted in the query acceptance step and each of the multiple extraction points extracted in the extraction step. This allows the user to collectively create prompts for applying predetermined tasks and predetermined queries to multiple patent documents. This reduces the man-hours required for creating prompts.

[0137] (Supplementary Note 8) The program according to Supplementary Note 1, wherein the processor executes a task presentation step (S501) of presenting a plurality of pieces of task information to a user in a selectable manner, and a task reception step (S501) of receiving, from the user, an input operation for predetermined task information from the plurality of pieces of task information presented in the task presentation step. This allows the user to easily create a suitable prompt according to the task by selecting the desired task information to be executed from the presented plurality of pieces of task information.

[0138] (Supplementary Note 9) The program according to Supplementary Note 1, wherein the processor executes a sending step (S506) of sending the prompt generated in the generating step to an AI system, and a response receiving step (S507) of receiving a response to the prompt from the AI ​​system, thereby enabling a user to obtain a response to the prompt that is suitable for a task applied to a patent document.

[0139] (Supplementary Note 10) The program according to Supplementary Note 1, wherein the processor executes an extraction presentation step of presenting a plurality of selectable extraction items to the user in accordance with the task received in the task reception step, and an item selection step of receiving a selection operation from the user for one or more predetermined extraction items from the plurality of extraction items presented in the extraction presentation step, and the extraction step is a step of extracting predetermined extraction portions from the patent document based on the one or more predetermined extraction items selected in the item selection step. This allows the user to edit the extraction portions according to the task applied to the patent document. A prompt corresponding to a suitable extraction portion can be created depending on the content of the task the user wants to perform.

[0140] (Supplementary Note 11) A method executed by a computer having a processor and a memory, wherein the processor executes all of the steps performed in the invention according to any one of Supplementary Note 1 to Supplementary Note 10. This allows a user to easily generate suitable prompts depending on the task to be applied to a patent document.

[0141] (Supplementary Note 12) An information processing device comprising a control unit and a storage unit, wherein the control unit executes all steps executed in the invention according to any one of Supplementary Note 1 to Supplementary Note 10. This allows a user to easily generate a suitable prompt according to a task applied to a patent document.

[0142] (Supplementary Note 13) A system comprising means for executing all steps performed in the invention according to any one of Supplementary Note 1 to Supplementary Note 10. This allows a user to easily generate suitable prompts according to the task to be applied to a patent document.

[0143] 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 memory unit, wherein the processor executes the following steps: a task receiving step for receiving task information related to a task to be performed on a patent document; a query receiving step for receiving query information to be applied to the patent document; a document acquisition step for acquiring patent documents related to patents; an extraction step for extracting a predetermined extraction portion from the patent document acquired in the document acquisition step in accordance with the task received in the task receiving step; and a generation step for generating a prompt including the query information received in the query receiving step and the extraction portion extracted in the extraction step.

2. The program of claim 1, wherein the task receiving step is a step of receiving the task information indicating at least one of the following tasks: a classification task for assigning a classification to a patent document; a screening task for determining the relevance of the patent document to a target document; and a relevance determination task for determining the relevance of the patent document to a target product; and the extraction step is a step of extracting the different predetermined extraction parts according to the task information received in the task receiving step: at least one of the abstract, claims, claim 1, and specification of the patent document when the task information is a classification task; at least one of the abstract, claims, claim 1, and specification of the patent document when the task information is a screening task; and at least one of the claim 1 and specification of the patent document when the task information is a relevance determination task.

3. The program according to claim 1, wherein said generating step is a step of generating said prompt including an instruction to output an index value related to said patent document acquired in said document acquisition step and a reason for said index value.

4. The program of claim 3, wherein the generating step is a step of generating the prompt including an instruction for outputting an index value indicating the result of executing a task corresponding to the task information received in the task receiving step, and the index value is an index value indicating the accuracy of the assigned classification if the task information is a classification assignment task, an index value indicating the degree of relevance to the target invention if the task information is a screening task, and an index value indicating the degree of relevance to the target product if the task information is a non-classification task.

5. The program described in claim 3, wherein the processor executes the following steps: a sending step for sending the prompt generated in the generating step to an artificial intelligence system; an answer receiving step for receiving an answer content including the index value and the rationale for the prompt from the artificial intelligence system; and an answer presenting step for presenting the index value and the rationale received in the answer receiving step to a user.

6. The program according to claim 1, wherein said generating step is a step of generating said prompt in response to said task information accepted in said task accepting step.

7. The program of claim 1, wherein the document acquisition step is a step of acquiring patent documents relating to a plurality of patents, the extraction step is a step of extracting a plurality of specified extraction points for each of the plurality of patent documents acquired in the document acquisition step in accordance with the task accepted in the task acceptance step, and the generation step is a step of generating a plurality of prompts for each of the plurality of patent documents acquired in the document acquisition step based on the query information accepted in the query acceptance step and each of the plurality of extraction points extracted in the extraction step.

8. The program of claim 1, wherein the processor executes a task presentation step of presenting a plurality of pieces of task information to a user in a selectable manner, and the task acceptance step is a step of accepting, from the user, an input operation of a predetermined piece of task information from the plurality of pieces of task information presented in the task presentation step.

9. The program of claim 1, wherein the processor executes a sending step of sending the prompt generated in the generating step to an artificial intelligence system, and an answer receiving step of receiving an answer to the prompt from the artificial intelligence system.

10. The program of claim 1, wherein the processor executes an extraction presentation step of presenting a plurality of extraction items to the user in a selectable manner in accordance with the task accepted in the task acceptance step, and an item selection step of accepting a selection operation from the user for a predetermined one or more extraction items from the plurality of extraction items presented in the extraction presentation step, wherein the extraction step is a step of extracting the predetermined extraction portion from the patent document based on the predetermined one or more extraction items selected in the item selection step.

11. A method implemented on a computer having a processor and a memory, the processor performing all of the steps performed in any one of claims 1 to 10.

12. An information processing device comprising a control unit and a storage unit, the control unit executing all of the steps executed in any one of the inventions according to claims 1 to 10.

13. A system comprising means for executing all the steps performed in any one of claims 1 to 10.

Images