Program, method, information processing apparatus, and system

Abstract

To provide a program, a method, an information processing device, and a system for causing an artificial intelligence system to output a suitable answer.SOLUTION: A program to be executed by a computer including a processor and a storage unit, the program causing the processor to: acquire a document related to a patent; divide the acquired document into one or a plurality of blocks; The program causes the computer to execute a block dividing step of specifying one or a plurality of block tags associated with each of the blocks, a sub-block dividing step of dividing at least a part of the one or plurality of blocks divided in the block dividing step into one or a plurality of sub-blocks, and a tag expanding step of assigning, to at least a part of the one or plurality of sub-blocks divided in the sub-block dividing step, a tag corresponding to a block tag of a block from which the sub-block is divided.SELECTED DRAWING: Figure 9

Description

[Technical Field]

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

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

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

[0004] There is a problem in that users cannot get the artificial intelligence system to output a suitable answer. Therefore, the present disclosure has been made to solve the above problem, and its purpose is to provide a technology that allows an artificial intelligence system to output a suitable answer. [Means for solving the problem]

[0005] A program to be executed by a computer having a processor and a memory unit, wherein the processor executes the following steps: a document acquisition step of acquiring a document related to a patent; a block division step of dividing the document acquired in the document acquisition step into one or more blocks and identifying one or more block tags associated with each of the blocks; a sub-block division step of dividing at least a portion of the one or more blocks divided in the block division step into one or more sub-blocks; and a tag expansion step of assigning a tag to at least a portion of the one or more sub-blocks divided in the sub-block division step according to the block tag of the block from which the sub-block was divided. [Effects of the Invention]

[0006] According to the present disclosure, an artificial intelligence system can be made to output a suitable answer. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 2 is a block diagram showing the functional configuration of the system 1. [Figure 2] FIG. 2 is a block diagram showing the functional configuration of the server 10. [Figure 3] FIG. 2 is a block diagram showing the functional configuration of a user terminal 20. [Figure 4] FIG. 10 is a diagram showing the data structure of a user table 1012. [Figure 5] FIG. 10 is a diagram showing the data structure of a document table 1013. [Figure 6] FIG. 10 is a diagram showing the data structure of an instruction table 1014. [Figure 7] FIG. 10 is a diagram showing the data structure of a support table 1015. [Figure 8] 10 is a flowchart showing the operation of a tag expansion process. [Figure 9] 10 is a flowchart showing the operation of an inquiry process. [Figure 10]FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90. DETAILED DESCRIPTION OF THE INVENTION

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

[0009] <System 1 Configuration> The system 1 in this disclosure is an information processing system that provides a patent document analysis service. Note that this disclosure can be applied to legal documents, contracts, and any other documents other than patent documents. The system 1 includes an information processing device including a server 10, a user terminal 20, and an artificial intelligence system 40, all of which are connected via a network N. FIG. 1 is a block diagram showing the functional configuration of the system 1. As shown in FIG. FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG. FIG. 3 is a block diagram showing the functional configuration of the user terminal 20. As shown in FIG.

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

[0011] <Server 10 configuration> The server 10 is an information processing device that provides a patent document analysis service. The server 10 includes a storage unit 101 and a control unit 104 .

[0012] <Configuration of the storage unit 101 of the server 10> The storage unit 101 of the server 10 includes an application program 1011 , a user table 1012 , a document table 1013 , an instruction table 1014 , and a support table 1015 .

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

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

[0015] The user ID is an item that stores user identification information for identifying a user. The user identification information is an item that is set with a unique value for each user. The user name is an item for storing the name of the user. The user name may be set to any character string such as a nickname instead of a name.

[0016] The document table 1013 is a table for storing and managing information (document information) relating to patent documents. The document table 1013 is a table having columns for document ID, user ID, document name, document content, and processed document. FIG. 5 is a diagram showing 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 for storing user identification information for identifying a user. The document name is an item that stores the name of the patent document. Any character string can be set as the document name. For example, the document name stores the publication number, registration number, application number, or other reference number of the patent document. The document content is an item that stores the document content of a patent document. Specifically, the text information of the patent document is stored. For example, the document content may include 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 unexamined patent publication, patent gazette, etc. is stored. In this disclosure, the patent document stored in the document content includes paragraph numbers (0001, 0002, 0003..., claim 1, claim 2...) and character strings related to headings (heading text). In this disclosure, claims are included in the paragraph numbers, but they may also be included in the heading text. In this disclosure, paragraph numbers and heading text are collectively referred to as block tags. Block tags are written in association with each document block (a block of a document consisting of multiple sentences or sentences is usually called a document block) identified by a paragraph or heading. The heading strings are strings such as the name of the invention, technical field, background art, prior art documents, patent documents, non-patent documents, summary of the invention, problem to be solved by the invention, means for solving the problem, effects of the invention, brief description of the drawings, form for implementing the invention, Example 1, Example 2..., industrial applicability, explanation of symbols, accession number, free text of sequence listing, number 1, number 2..., chemical 1, chemical 2..., table 1, table 2..., etc. A paragraph number is a sequential number that uniquely identifies each paragraph within a patent document, and in Japan it is represented by four-digit Arabic numerals. A heading text is a string of characters used as a heading to indicate a specific section or content of a patent document. In Japanese patent documents, paragraph numbers and heading text are enclosed in square brackets to indicate that they are paragraph numbers and heading text, respectively. Note that while this disclosure will be described using Japanese patent documents as an example, it is not limited to this and can be applied to paragraph numbers and heading text in U.S. patents, European patents, and other patent documents of any country. The processed document is an item for storing text information obtained by processing the document contents of a patent document. Specifically, the text information is stored by performing tag expansion processing, which will be described later, on the document contents.

[0018] The instruction table 1014 is a table that stores instruction sentences (instruction information) for creating query sentences for the artificial intelligence system. The instruction table 1014 is a table having an instruction ID as a primary key and columns of instruction ID and instruction data. FIG. 6 is a diagram showing the data structure of the instruction table 1014.

[0019] The instruction ID is an item for storing instruction identification information for identifying instruction information. The instruction data is an item for storing text information including query sentences (instructions) for the artificial intelligence system. Specifically, in the present disclosure, instruction sentences (including questions regarding the document contents) for the document contents stored in the document table 1013 are stored. The instruction sentences may be input by the user operating an input device of the user's own information processing terminal. The instruction sentence may be selected by the user's selection operation from one or more instruction sentence candidates stored in advance in a table (not shown) or the like. In the present disclosure, a prompt, which is a query sentence for an artificial intelligence system, is generated by combining instruction data with part or all of a processed document.

[0020] The support table 1015 is a table for storing and managing prompts related to query sentences sent to the AI ​​system and response contents (support information) from the AI ​​system. The support table 1015 is a table having columns for document ID, prompt, and answer content. FIG. 7 is a diagram showing the data structure of the support table 1015.

[0021] The document ID is an item that stores document identification information for identifying a patent document. A prompt is an item that stores a prompt related to a query sentence to an artificial intelligence system. A prompt is mainly a query sentence (text) that is 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 a prompt does not have to be a character string, but can also be a prompt in the form of an image, video, audio, etc. For example, a gesture or audio instruction by the user can also be a prompt. The answer content is an item that stores the answer content from the artificial intelligence system in response 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 answers using text will be described as an example in this disclosure, the present invention is not limited to this. In an artificial intelligence system that provides answers using images, videos, audio, etc., the answer content may also store image data, video data, audio data, etc.

[0022] <Configuration of the control unit 104 of the server 10> The control unit 104 of the server 10 includes a user registration control unit 1041, 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.

[0023] The user registration control unit 1041 performs processing to store information about users who wish to use the service according to the present disclosure in the user table 1012. The information stored in the user table 1012 is generated when a user opens a web page operated by a service provider from any information processing terminal, enters information into a predetermined input form, and transmits the information to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, completing the user registration. This allows the user stored in the user table 1012 to use the service. Before the user registration control unit 1041 registers the user information in the user table 1012, the service provider may conduct a predetermined examination to restrict whether or not the user is permitted to use the service. The user ID may be any character string or number that can identify the user, any character string or number desired by the user, or may be automatically set by the user registration control unit 1041.

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

[0025] The inquiry unit 1043 executes inquiry processing, the details of which will be described later.

[0026] <Configuration of User Terminal 20> The user terminal 20 is an information processing device operated by a user who uses a service. The user terminal 20 may be, for example, a mobile terminal such as a smartphone or tablet, a stationary personal computer (PC) or a laptop PC, or a wearable terminal such as a head mounted display (HMD) or a wristwatch terminal. The user terminal 20 includes a storage unit 201 , a control unit 204 , an input device 206 , and an output device 208 .

[0027] <Configuration of the storage unit 201 of the user terminal 20> The storage unit 201 of the user terminal 20 includes a user ID 2011 and an application program 2012 .

[0028] The user ID 2011 is the user's account ID. The user transmits the user ID 2011 from the user terminal 20 to the server 10. The server 10 identifies the user based on the user ID 2011 and provides the user with the service according to the present disclosure. The user ID 2011 includes information such as a session ID temporarily assigned by the server 10 to identify the user using the user terminal 20.

[0029] The application program 2012 may be stored in advance in the storage unit 201, or may be configured to be downloaded from a web server or the like operated by a service provider via a communication IF. The application programs 2012 include applications such as a web browser application. The application program 2012 includes an interpreted programming language such as JavaScript (registered trademark) that runs on a web browser application stored on the user terminal 20.

[0030] <Configuration of the control unit 204 of the user terminal 20> The control unit 204 of the user terminal 20 includes an input control unit 2041 and an output control unit 2042. The control unit 204 executes an application program 2012 stored in the storage unit 201, thereby realizing each functional unit.

[0031] <Configuration of the input device 206 of the user terminal 20> The input device 206 of the user terminal 20 includes a camera 2061 , a microphone 2062 , a position information sensor 2063 , a motion sensor 2064 , and a touch device 2065 .

[0032] <Configuration of the output device 208 of the user terminal 20> The output device 208 of the user terminal 20 includes a display 2081 and a speaker 2082 .

[0033] <Configuration of Artificial Intelligence System 40> The artificial intelligence system 40 is an information processing device that outputs a response to a prompt. Examples of the artificial intelligence system 40 include ChatGPT, OpenAI GPT, PerplexityAsk, 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 the reading comprehension of a patent document by sending a prompt created in the query processing to the artificial intelligence system 40. In addition, in this disclosure, the artificial intelligence system is not limited to a text-based dialogue system. For example, it may be an image generation AI system such as Midjourney or Stable Diffusion. For example, a user can send a prompt created in an inquiry process to such an image generation AI system to obtain an image or video as a response that assists in reading and understanding patent documents. In addition, the present disclosure can also be applied to an artificial intelligence system that outputs answers in the form of video, audio, etc.

[0034] <System 1 Operation> Each process of the system 1 will be explained below. FIG. 8 is a flowchart showing the operation of the tag expansion process. FIG. 9 is a flowchart showing the operation of the inquiry process.

[0035] <Tag expansion processing> The tag expansion process is a process of assigning block tags to sub-blocks (sentences, paragraphs) contained in document blocks such as paragraphs and sections contained in the acquired patent document. In other words, it is a process of expanding the block tags (paragraph numbers, headings) assigned to document blocks into sub-blocks. Specifically, it is a process of inheriting the block tags (paragraph numbers, headings) of the multiple document blocks that make up the patent document to the sub-blocks into which the document block is divided. The tag expansion process may be executed asynchronously with the query process, or may be executed as part of the query process. For example, it may be executed in advance when the patent document is stored, or may be executed during the query process (e.g., step S302). Also, the tag expansion process may be executed in advance for some blocks of the patent document (blocks related to paragraphs) when the patent document is stored, and executed during the query process for other blocks (blocks related to headings). In other words, the tag expansion process may be executed once or multiple times for part or all of a single patent document.

[0036] <Overview of tag expansion process> The tag expansion process is a series of processes that acquire a patent document, divide the acquired patent document into one or more document blocks such as paragraphs or sections, identify block tags (paragraph numbers, heading text) associated with the one or more document blocks, add the identified block tags to one or more sub-blocks (texts, sentences) contained in the document block, and create and store a processed document in which the block tags have been added to the sub-blocks.

[0037] <Details of tag expansion process> The tag expansion process will be described in detail below.

[0038] In step S101, the control unit 104 of the server 10 executes a document acquisition step for acquiring documents related to patents. Specifically, the control unit 104 of the server 10 refers to the document table 1013 and acquires document information including the document contents. Note that the control unit 104 of the server 10 may start executing the tag expansion process, for example, when the patent document is stored in the document table 1013.

[0039] An example of the document contents of a patent document in this disclosure is shown below. Note that for convenience of description in the specification, corner brackets are written in square brackets. The following patent document consists of a document block corresponding to eight paragraph numbers, paragraphs 0008 to 0016. The patent document may be a part of a patent specification or the entirety of the patent specification. The following patent document can be considered to consist of text blocks related to the headings of the problem to be solved by the invention (paragraphs 0008 and 0009), the means for solving the problem (paragraphs 0010 and 0011), the effects of the invention (paragraphs 0012 and 0013), and the mode for carrying out the invention (paragraphs 0014 and 0015). Note that a text block related to a heading may include text blocks related to one or more paragraphs. In the tag expansion process, a document block may be specified for either or both of a paragraph number unit and a heading sentence unit.

[0040] [Patent Document] [Problem to be solved by the invention]

[0008] The problem to be solved is the inability to visually confirm the input position, which is an obstacle when manually scanning high-resolution drawings. This problem is particularly noticeable when inputting detailed drawings or complex illustrations, and it significantly reduces the user's work efficiency.

[0009] With conventional hand scanners, the housing structure makes it difficult to confirm the exact position while scanning, forcing users to guess the input position as they go along, resulting in repeated scanning of incorrect areas or overlooking important parts. [Means for solving the problem]

[0010] The most important feature of this invention is that the light is received along an optical path that is inclined relative to the direction perpendicular to the document, so that the scanning position on the document or the position immediately before (or after) it can always be seen. By adopting this oblique optical path, the user can perform operations while directly checking the scanning position.

[0011] Specifically, the optical system installed inside the housing is tilted to capture light at an angle that is not parallel to the scan plane, allowing the user to directly view the scan position through openings on the side and top of the housing. [Effects of the invention]

[0012] The hand scanner of the present invention scans with a one-dimensional image sensor through an oblique optical axis from the top of the housing, so the field of view of the sensor, i.e., the input position, can be constantly observed or confirmed directly or nearby, which has the advantage that the left or right side edge can be used depending on the binding conditions of the input object and the operation method. This feature allows the user to perform scanning work accurately and efficiently.

[0013] Furthermore, this structure can accommodate documents of various shapes, allowing for smooth scanning of bound sections of books and thick documents. Furthermore, regardless of whether you are left-handed or right-handed, you can select the edge that is most convenient for you to operate, making it highly versatile and able to meet the needs of a wide range of users. [Mode for Carrying Out the Invention]

[0014] The objective of inputting an image from outside the housing or as close to the edge of the housing as possible was achieved with a minimum number of parts and without compromising the thickness of the optical components. This design concept simultaneously achieved a compact overall device and reduced manufacturing costs.

[0015] Furthermore, by optimizing the optical system layout, the company has succeeded in improving user visibility while maintaining high image quality, thereby achieving both precise scanning and improved operability, effectively resolving the issues faced by conventional hand scanners.

[0041] In step S102, the control unit 104 of the server 10 executes a block division step of dividing the document acquired in the document acquisition step into one or more blocks and identifying one or more block tags associated with each of the blocks. The block division step executes a step of dividing the patent document into one or more blocks beginning with a paragraph number or a heading and identifying one or more paragraph numbers or headings associated with each of the blocks. Specifically, the control unit 104 of the server 10 divides the document content acquired in step S101 into paragraph numbers or headings to acquire multiple document blocks. The control unit 104 also identifies the paragraph numbers or headings associated with each document block as block tags. While the present disclosure uses paragraph numbers and headings as examples of units for dividing the document content into blocks, the present disclosure is not limited to these. For example, the blocks may be divided into any document units, such as embodiments (first embodiment, second embodiment, etc.), examples (first example, second example, etc.), and variations (first variation, second variation, etc.). In this case, the block tags are embodiments, examples, variations, etc. In addition, character strings that are related to block tags such as unnecessary paragraph numbers and headings may be removed from the divided blocks. For example, when dividing blocks into paragraph numbers, headings may be removed. When dividing blocks into headings, paragraph numbers may be removed. This allows the artificial intelligence system 40 to output answers that more appropriately refer to block tags. As a result, the document content acquired in step S101 is divided into blocks each consisting of a paragraph. Similarly, the document content is divided into blocks each consisting of a heading (volume, part, chapter, section, paragraph, subsection, chapter, sub-subsection, part, chapter, section, subsection, sub-subsection).

[0042] For example, document content A is divided into block A and block B as follows.

[0043] [Block A (Block division by paragraph number)] Block 1: Block Tag: 0008 Block contents: The problem to be solved is the inability to visually confirm the input position, which is an obstacle when manually scanning high-resolution drawings. This problem is particularly noticeable when inputting detailed drawings or complex illustrations, and it significantly reduces the user's work efficiency. Block 2: Block Tag: 0009 Block contents: With conventional hand scanners, the housing structure makes it difficult to confirm the exact position while scanning, forcing users to guess the input position as they go along, resulting in repeated scanning of incorrect areas or overlooking important parts. Block 3: Block Tag: 0010 Block contents: The most important feature of this invention is that the light is received along an optical path that is inclined relative to the direction perpendicular to the document, so that the scanning position on the document or the position immediately before (or after) it can always be seen. By adopting this oblique optical path, the user can perform operations while directly checking the scanning position. Block 4: Block Tag: 0011 Block contents: Specifically, the optical system installed inside the housing is tilted to capture light at an angle that is not parallel to the scan plane, allowing the user to directly view the scan position through openings on the side and top of the housing. Block 5: Block Tag: 0012 Block contents: The hand scanner of the present invention scans with a one-dimensional image sensor through an oblique optical axis from the top of the housing, so the field of view of the sensor, i.e., the input position, can be constantly observed or confirmed directly or nearby, which has the advantage that the left or right side edge can be used depending on the binding conditions of the input object and the operation method. This feature allows the user to perform scanning work accurately and efficiently. Block 6: Block Tag: 0013 Block contents: Furthermore, this structure can accommodate documents of various shapes, allowing for smooth scanning of bound sections of books and thick documents. Furthermore, regardless of whether you are left-handed or right-handed, you can select the edge that is most convenient for you to operate, making it highly versatile and able to meet the needs of a wide range of users. Block 7: Block Tag: 0014 Block contents: The objective of inputting an image from outside the housing or as close to the edge of the housing as possible was achieved with a minimum number of parts and without compromising the thickness of the optical components. This design concept simultaneously achieved a compact overall device and reduced manufacturing costs. Block 8: Block Tag: 0015 Block contents: Furthermore, by optimizing the optical system layout, the company has succeeded in improving user visibility while maintaining high image quality, thereby achieving both precise scanning and improved operability, effectively resolving the issues faced by conventional hand scanners.

[0044] [Block B (Block division by heading sentence)] Block 1: Block Tags: The Problem the Invention is Trying to Solve Block contents: The problem to be solved is the inability to visually confirm the input position, which is an obstacle when manually scanning high-resolution drawings. This problem is particularly noticeable when inputting detailed drawings or complex illustrations, and it significantly reduces the user's work efficiency. With conventional hand scanners, the housing structure makes it difficult to confirm the exact position while scanning, forcing users to guess the input position as they go along, resulting in repeated scanning of incorrect areas or overlooking important parts. Block 2: Block Tags: A Solution to the Problem Block contents: The most important feature of this invention is that the light is received along an optical path that is inclined relative to the direction perpendicular to the document, so that the scanning position on the document or the position immediately before (or after) it can always be seen. By adopting this oblique optical path, the user can perform operations while directly checking the scanning position. Specifically, the optical system installed inside the housing is tilted to capture light at an angle that is not parallel to the scan plane, allowing the user to directly view the scan position through openings on the side and top of the housing. Block 3: Block Tags: Inventive Effects Block contents: The hand scanner of the present invention scans with a one-dimensional image sensor through an oblique optical axis from the top of the housing, so the field of view of the sensor, i.e., the input position, can be constantly observed or confirmed directly or nearby, which has the advantage that the left or right side edge can be used depending on the binding conditions of the input object and the operation method. This feature allows the user to perform scanning work accurately and efficiently. Furthermore, this structure can accommodate documents of various shapes, allowing for smooth scanning of bound sections of books and thick documents. Furthermore, regardless of whether you are left-handed or right-handed, you can select the edge that is most convenient for you to operate, making it highly versatile and able to meet the needs of a wide range of users. Block 4: Block Tags: Detailed Description Block contents: The objective of inputting an image from outside the housing or as close to the edge of the housing as possible was achieved with a minimum number of parts and without compromising the thickness of the optical components. This design concept simultaneously achieved a compact overall device and reduced manufacturing costs. Furthermore, by optimizing the optical system layout, the company has succeeded in improving user visibility while maintaining high image quality, thereby achieving both precise scanning and improved operability, effectively resolving the issues faced by conventional hand scanners.

[0045] In step S103, the control unit 104 of the server 10 executes a sub-block expansion step of dividing at least a part of one or more blocks divided in the block division step into one or more sub-blocks. The sub-block expansion step executes a step of dividing a block of a patent document beginning with a paragraph number or a heading sentence into sub-blocks spanning one or more sentences. Specifically, the control unit 104 of the server 10 divides the block divided in step S102 into sentences to obtain multiple document blocks (sub-blocks). Also, the control unit 104 identifies the block tags of the blocks from which the sub-blocks were divided. As a result, the document content acquired in step S101 is divided into sub-blocks in units of sentences. Note that in the present disclosure, an example of dividing a block into sub-blocks consisting of sentences has been disclosed as an example, but this is not limiting. For example, a section block may be divided into sub-blocks of smaller granularity, such as sub-sections and sub-sub-sections, or may be divided into sub-blocks consisting of multiple characters that are even smaller than a sentence. A block is a part that makes up a document, and a sub-block may be any part that makes up a block.

[0046] For example, blocks 1 and 2 of block A are divided into sub-blocks A as follows:

[0047] [Sub-block A (block division by paragraph number)] Sub-block 1: Block Tag: 0008 Sub-block contents: The problem to be solved is the inability to visually confirm the input position, which is an obstacle when manually scanning and inputting a high-resolution image. Sub-block 2: Block Tag: 0008 Sub-block contents: This problem is particularly noticeable when inputting detailed drawings or complex illustrations, and it significantly reduces the user's work efficiency. Sub-block 3: Block Tag: 0009 Sub-block contents: With conventional hand scanners, the structure of the housing makes it difficult to confirm the exact position during scanning. Sub-block 4: Block Tag: 0009 Sub-block contents: As a result, users were forced to guess where to input data as they went along, resulting in many cases of repeatedly scanning the wrong part or overlooking the necessary part.

[0048] In step S104, the control unit 104 of the server 10 executes a tag expansion step of assigning tags to at least some of the one or more sub-blocks divided in the sub-block expansion step, in accordance with the block tags of the blocks from which the sub-blocks were divided. The tag expansion step executes a step of assigning tags to at least some of the one or more sentences divided in the sub-block expansion step, in accordance with paragraph numbers or heading sentences. Specifically, the control unit 104 of the server 10 assigns tags corresponding to the block tags to the sub-blocks divided in step S103. The control unit 104 of the server 10 may add the block tag directly to the sub-block. The control unit 104 of the server 10 may add a sub-block index (numbers, letters, etc. for distinguishing sub-blocks within a block) to the block tag, and add the index to the sub-block. The control unit 104 of the server 10 may issue an arbitrary unique key (such as a UUID) to each sub-block, and associate them with block tags using a database (not shown) or the like. Sub-block tags can be tags that inherit block tags in any way. By having each sub-block tag inherit the block tag of the original block, the relationship with the original block can be maintained. This makes it easy to restore the original document structure even after processing at the sub-block level.

[0049] For example, the following subblock A1 is obtained by adding a subblock tag (a block tag with a subblock index added) to subblock A. The original block tags 0008 and 0009 may be added as subblock tags instead of 0008-1, 0008-2, 0009-1, 0009-2, etc. Alternatively, any unique key associated with the original block tags 0008 and 0009 via a database (not shown) may be added. In this case, too, the artificial intelligence system 40 can obtain a response that appropriately references the unique key. By identifying the block tag from the unique key, the position of the subblock in the original document can be identified from the response content.

[0050] [Sub-block A1 (block division by paragraph number)] Sub-block 1: (0008-1) The problem to be solved is that the input position cannot be visually confirmed, which is an obstacle when manually scanning and inputting a high-resolution image. Sub-block 2: (0008-2) This problem becomes particularly noticeable when inputting detailed drawings or complex illustrations, and causes a significant decrease in the user's work efficiency. (0009-1) In conventional hand scanners, the structure of the housing makes it difficult to confirm the exact position during scanning. (0009-2) As a result, users were forced to guess the input position as they worked, resulting in many cases of repeatedly scanning the wrong part or overlooking the necessary part.

[0051] In step S104, a tag development step is executed to assign a tag including tag identification information to the sub-block. Specifically, a tag added to a sub-block may include a character string (tag identification information) for identifying it as a tag. For example, a sub-block tag may include character strings such as P_, S_, P:, and S:. Note that any character string can be used as tag identification information, as long as it is not a character string that is frequently used in document content.

[0052] For example, the sub-block A2 below is a sub-block A2 that includes tag identification information (P_) in its sub-block tag.

[0053] [Sub-block A2 (block division by paragraph number)] Sub-block 1: (P_0008-1) The problem to be solved is the inability to visually confirm the input position, which is an obstacle when manually scanning and inputting high-resolution images. Sub-block 2: (P_0008-2) This problem is particularly noticeable when inputting detailed drawings or complex illustrations, and it significantly reduces the user's work efficiency. (P_0009-1) With conventional hand scanners, it was difficult to confirm the exact position during scanning due to the structure of the housing. (P_0009-2) As a result, users were forced to guess the input position as they worked, resulting in many cases of repeatedly scanning the wrong part or overlooking the necessary part.

[0054] In step S104, a tag development step is executed in which a tag corresponding to the block tag of the block from which the subblocks are divided is assigned to one or all of the subblocks. Specifically, the control unit 104 of the server 10 may assign sub-block tags to only some of the sub-blocks divided in step S103, or may assign sub-block tags to all of the sub-blocks.

[0055] Blocks 1 and 2 of block A are divided into sub-block A3 as shown below. In this case, the tag identification information is "S_". Also, in this example, the sub-block tag is assigned the original block tag (without using the sub-block index).

[0056] [Sub-block A3 (block division by paragraph number)] Sub-block 1: (S_0008) The problem to be solved is that the input position cannot be visually confirmed, which is an obstacle when manually scanning and inputting a high-resolution image. Sub-block 2: (S_0008) This problem is particularly noticeable when inputting detailed drawings or complex illustrations, and it significantly reduces the user's work efficiency. Sub-block 3: (S_0009) With conventional hand scanners, it was difficult to confirm the exact position during scanning due to the structure of the housing. Sub-block 4: (S_0009) As a result, users were forced to guess the input position as they went along, resulting in many cases of repeatedly scanning the wrong part or overlooking the necessary part.

[0057] For example, block 1 of block B is divided into the following sub-block B1. In this case, the tag identification information is "S_". Also, this example shows that the sub-block tag is assigned HASH1 (a unique key such as a hash string or random string) associated with the block tag from which it was divided, "Problem to be Solved by the Invention". Also, this example shows that the sub-block index is not used.

[0058] [Sub-block B1 (block division by heading sentence)] Sub-block 1: (S_HASH1) The problem to be solved is the inability to visually confirm the input position, which is an obstacle when manually scanning and inputting high-resolution images. Sub-block 2: (S_HASH1) This problem is particularly noticeable when inputting detailed drawings or complex illustrations, and it significantly reduces the user's work efficiency. Sub-block 3: (S_HASH1) With conventional hand scanners, it was difficult to confirm the exact position during scanning due to the structure of the housing. Sub-block 4: (S_HASH1) As a result, users were forced to guess the input position as they went along, resulting in many cases of repeatedly scanning the wrong part or overlooking the necessary part.

[0059] In step S104, a tag expansion step is executed to insert a block tag at the beginning, end, or between the beginning and end of the sub-block. Specifically, the sub-block tag does not need to be added to the beginning of the sub-block, but may be added to the end of the sub-block or included at any position within the sub-block. By adding (inserting) the sub-block tag to the beginning of the sub-block, the artificial intelligence system 40 can more effectively recognize the sub-block tag and improve the quality of processing.

[0060] [Example of inserting at the end of a sub-block] Sub-block 1: The problem to be solved is the inability to visually confirm the input position, which is an obstacle when manually scanning and inputting high-resolution images. (S_0008) Sub-block 2: This problem is particularly noticeable when inputting detailed drawings or complex illustrations, significantly reducing the user's work efficiency. (S_0008)

[0061] [Example of inserting between sub-blocks] Sub-block 1: The problem to be solved (S_0008) is that the input position cannot be visually confirmed, which is an obstacle when manually scanning and inputting a high-resolution image. Sub-block 2: This problem is particularly noticeable when inputting detailed drawings or complex illustrations (S_0008), significantly reducing the user's work efficiency.

[0062] In step S105, the control unit 104 of the server 10 stores the tagged sub-block in the document table 1013 of the server 10 in the processed document item of the patent document that is the target of the tag expansion process.

[0063] <Inquiry processing> The inquiry process is a process of creating a prompt (inquiry text, question text, question query) regarding an inquiry text based on the received instructions and patent document, and making an inquiry to the artificial intelligence system 40 using the prompt.

[0064] <Inquiry processing overview> Query processing is a series of processes that accept input of an instruction sentence, acquire document information, create a prompt based on the instruction sentence and the document information, send the prompt to the artificial intelligence system 40, receive the answer content output from the artificial intelligence system 40, and present the received answer content.

[0065] <Inquiry processing details> The inquiry process will be described in detail below.

[0066] In step S301, the control unit 104 of the server 10 executes an instruction statement receiving step of receiving an instruction statement. Specifically, the user operates the input device 206 of the user terminal 20 to input the URL of a page for executing inquiry processing (inquiry processing page) into a web browser or the like, and opens the inquiry processing page. The control unit 204 of the user terminal 20 sends a request to open the inquiry processing page to the server 10. The control unit 104 of the server 10 generates an inquiry processing page based on the received request and sends it to the user terminal 20. The control unit 204 of the user terminal 20 displays the received inquiry processing page on the display 2081 of the user terminal 20. The inquiry processing page includes an instruction input field for inputting an instruction statement, and an input field for a publication number for specifying a document (patent document) such as a patent gazette. The inquiry processing page may also include an input field into which a patent document such as a patent gazette can be directly input. By operating the input device 206 of the user terminal 20, the user can input instructions into the instruction input field to instruct the artificial intelligence system 40 to process the patent document specified on the inquiry processing page. The instructions are used to instruct the generating AI to perform tasks such as: Instructions for abstracting patent documents Instructions for classifying patent documents according to predetermined classification criteria - Instructions for comparing patent documents with product specifications, etc. - Instructions to output the matching and differences between patent documents and specific viewpoints Instructions for assessing the value of patent documents In this disclosure, an instruction sentence for classification according to a predetermined classification criterion is disclosed as an example. The control unit 104 of the server 10 generates a prompt for input to the artificial intelligence system 40 by inserting the patent document specified on the inquiry processing page or a processed document created by tag expansion processing for the patent document into the {patent document} portion of the instruction sentence. In this disclosure, an example of inserting a processed document into the {patent document} portion will be described. Furthermore, the directives of the present disclosure include directives that refer to block tags (paragraph numbers, headings), etc. For example, in the following directive A, the part "Please also output the paragraph numbers or headings of the patent document" corresponds to a directive that refers to block tags (paragraph numbers, headings), etc.

[0067] [Instruction A] Classify patent documents into either Class A, Class B, or Class C. Please also print the paragraph numbers or headings of the patent documents referenced in the classification. #Patent documents {Patent Document}

[0068] In step S301, the control unit 104 of the server 10 executes an instruction statement receiving step of receiving an instruction statement including an instruction to refer to the tag assigned in the tag expanding step. The control unit 104 of the server 10 executes an instruction statement receiving step of receiving an instruction statement including an instruction to refer to tag identification information. For example, the directive may include the directive "Paragraph numbers or headings start with 'P_'" which includes strings (P_, S_, P:, S:) that refer to tag identification information as follows: [Instruction B] Classify patent documents into either Class A, Class B, or Class C. Please also output the paragraph numbers or headings of the patent documents referenced in the classification. The paragraph numbers or headings will begin with "P_". #Patent documents {Patent Document}

[0069] The user operates the input device 206 of the user terminal 20 to select a send button included in the inquiry processing page. The control unit 204 of the user terminal 20 transmits a request to the server 10, including the instruction text input on the inquiry processing page and a publication number for specifying the patent document (the present disclosure discloses an example of transmitting a document ID). Note that if a patent document has been input on the inquiry processing page, the patent document that is the subject of the inquiry processing may be transmitted to the server 10. The control unit 104 of the server 10 receives and accepts the request including the instruction statement and the document ID.

[0070] In step S302, the control unit 104 of the server 10 executes a document information acquisition step of acquiring document information including the processed document. The control unit 104 of the server 10 searches the document ID item in the document table 1013 based on the acquired document ID, and acquires document information including the document content and the processed document. In the present disclosure, the document information stored in the document table 1013 is configured to create a processed document by previously performing tag expansion processing, but this is not limiting. For example, a processed document may be created by first applying tag expansion processing to the document content included in the acquired document information in step S302 without previously applying tag expansion processing to the document content. Furthermore, the document content to which the tag expansion process is applied does not necessarily have to be obtained from the document table 1013; the processed document may be obtained by applying the tag expansion process to the patent document entered in the input field on the inquiry processing page (included in the request sent from the user terminal 20) as the document content. In the present disclosure, any method and timing may be used as long as the processed document created by the tag expansion process is acquired.

[0071] In step S303, the control unit 104 of the server 10 executes a prompt creation step in which a prompt is created by including one or more sub-blocks to which tags have been added in the tag expansion step in the instruction statement received in the instruction statement reception step. The control unit 104 of the server 10 generates a prompt for input to the artificial intelligence system 40 by inserting the patent document specified on the inquiry processing page or a processed document created by tag expansion processing for the patent document into the {patent document} portion of instruction A and instruction B. In this disclosure, an example of inserting a processed document into the {patent document} portion will mainly be described.

[0072] The processed document is a document obtained by combining the sub-blocks described in sub-block A, sub-block B, sub-block A1, sub-block A2, sub-block A3, and sub-block B1. The processed document includes a sub-block tag. For example, the processed document for blocks 1 and 2 of block A is as follows: The processed document may be a document formed by combining some or all of the blocks contained in the document content.

[0073] [Processed documents] (0008-1) The problem to be solved is that the input position cannot be visually confirmed, which is an obstacle when manually scanning and inputting a high-resolution image. Sub-block 2: (0008-2) This problem becomes particularly noticeable when inputting detailed drawings or complex illustrations, and causes a significant decrease in the user's work efficiency. (0009-1) In conventional hand scanners, the structure of the housing makes it difficult to confirm the exact position during scanning. (0009-2) As a result, users were forced to guess the input position as they worked, resulting in many cases of repeatedly scanning the wrong part or overlooking the necessary part.

[0074] In step S303, the control unit 104 of the server 10 executes a prompt creation step in which a prompt is created by including one or more sub-blocks to which a tag containing tag identification information has been assigned in the tag expansion step in the instruction statement received in the instruction statement reception step. Specifically, the control unit 104 of the server 10 generates a prompt for input to the artificial intelligence system 40 by inserting the patent document specified on the inquiry processing page or the processed document created by tag expansion processing for the patent document into the {patent document} part of the instruction statement B. In this disclosure, an example of inserting the processed document into the {patent document} part will mainly be described. The control unit 104 of the server 10 stores the generated prompt in the prompt field of the new record in the support table 1015.

[0075] In step S304, the control unit 104 of the server 10 executes a query sending step of sending the prompt created in the query creating step to the artificial intelligence system 40 operated by an external business operator to make a query. Specifically, the control unit 104 of the server 10 transmits the prompt (character string) generated in step S303 to the server 10. The control unit 104 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. Alternatively, the control unit 204 of the user terminal 20 may generate a prompt and send the character string (prompt) directly to an API (Application Programming Interface) endpoint of the artificial intelligence service.

[0076] In step S305, the control unit 104 of the server 10 executes an answer acquisition step of acquiring an answer to be output by inputting the prompt created in the prompt creation step into the artificial intelligence system 40. Specifically, the control unit 104 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 control unit 104 of the server 10 transmits the received response to the user terminal 20. Alternatively, the control unit 204 of the user terminal 20 may directly receive and acquire the response to the sent prompt from the artificial intelligence system 40 .

[0077] The response from the artificial intelligence system 40 includes a response that references a block tag. For example, the following response content examples are P_0028 and P_0042. As an example, a case where tag identification information is included (instruction statement B) has been described, but tag identification information does not necessarily have to be included. If the instruction statement does not include a character string that references tag identification information, the response statement from the artificial intelligence system also does not include tag identification information.

[0078] [Answer content] Classification: Classification A Reason: The patent document contains the words "···(P_0028)" and "···(P_0042)". Reference paragraph: P_0028, P_0042

[0079] The control unit 104 of the server 10 stores the received answer content in the answer content field of the record created in step S303 in the support table 1015. As a result, the prompt created in step S303 and the answer content from the artificial intelligence system 40 in response to it are stored in association with each other.

[0080] In step S306, the control unit 104 of the server 10 executes an answer presenting step of presenting to the user the content of an answer to the prompt transmitted in the inquiry transmitting step. Specifically, when the control unit 204 of the user terminal 20 receives the response, it displays and presents the prompt and the answer content included in the response to the prompt on the display 2081 of the user terminal 20. This allows the user to visually confirm the answer from the artificial intelligence system 40 to the instruction statement for the patent document on the display 2081 of the user terminal 20.

[0081] In step S306, the control unit 104 of the server 10 executes an identification / exclusion step of excluding tag identification information from the answer acquired in the answer acquisition step. Furthermore, the control unit 104 of the server 10 or the control unit 204 of the user terminal 20 may execute a process to remove tag identification information (the character string "P_" in the example answer content) from the received answer content. For example, tag identification information can be removed from the answer content by replacing it with a regular expression or the like. The answer content from which tag identification information has been removed is shown below. [Answer content] Classification: Classification A Reason: The patent document contains the words "···(0028)" and "···(0042)". Reference paragraph: 0028, 0042 In this way, by excluding tag identification information from the answer output from the artificial intelligence system 40, it is possible to output an answer that is more readable to the user.

[0082] In step S104, if the control unit 104 of the server 10 assigns a unique key, a hash string, a random string, etc. to the sub-block, it restores the string to a paragraph number or a heading by referring to a database, etc. (not shown). For example, "HASH1" in the case of sub-block B1 is replaced with "Problem that the invention aims to solve" and the heading sentence is restored.

[0083] Additionally, the control unit 104 of the server 10 may remove redundant information about the sub-block index (numbers, letters, etc. for distinguishing sub-blocks within a block) from the response content.

[0084] The effect of the present invention will now be described: By executing tag expansion step S104 in the tag expansion process of the present invention, sub-block tags that inherit the block tag are assigned to each of the sub-blocks included in a block. Although artificial intelligence systems have advanced language analysis capabilities, when a single paragraph or block such as a section contained in document content contains many sentences, they may not be able to properly extract paragraph numbers or headings (for example, the extraction of paragraph numbers and headings may be ignored).Even in such cases, by applying the tag expansion process according to the present disclosure to the document content, the artificial intelligence system can obtain more appropriate answers that refer to paragraph numbers and headings.

[0085] <Basic computer hardware configuration> 10 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main memory device 902, an auxiliary memory device 903, and a communication IF 991 (interface), which are electrically connected to one another by a communication bus 921.

[0086] The processor 901 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

[0087] The main memory device 902 is used to temporarily store programs, data to be processed by the programs, etc. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0088] 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.

[0089] The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using wired or wireless communication standards. The network is composed of the Internet, a LAN, various mobile communication systems constructed by wireless base stations, etc. For example, the network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can connect to the Internet via a predetermined access point. In the case of a wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), and Bluetooth (registered trademark). In the case of a wired connection, the network also includes a direct connection using a USB (Universal Serial Bus) cable, etc.

[0090] It should be noted that the computer 90 can be virtually realized by distributing all or part of each hardware configuration across multiple computers 90 and interconnecting them via a network. In this way, the computer 90 is a concept that includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

[0091] <Basic functional configuration of computer 90> The following describes the functional configuration of a computer realized by the basic hardware configuration (FIG. 10) of the computer 90. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

[0092] 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.

[0093] The control unit is realized by the processor 901 reading out various programs stored in the auxiliary storage device 903, expanding them in the main storage device 902, and executing processing in accordance with the programs. The control unit can realize functional units that perform various types of information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0094] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes programs stored in memory. In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions. If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0095] The storage unit is realized by a main storage device 902 and an auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Furthermore, the processor 901 can allocate a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 in accordance with the programs. Furthermore, the control unit can cause the processor 901 to execute processes for adding, updating, and deleting data stored in the storage unit in accordance with the various programs.

[0096] A database refers to a relational database, which manages data sets called masters and tables in a tabular format structurally defined by rows and columns, by relating them to each other. In a database, a table is called a table, a master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated. Typically, each table and each master has a column set as a primary key to uniquely identify a record, but setting a primary key to a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in specific tables and masters stored in the storage unit according to various programs. Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

[0097] 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.

[0098] The communication unit is realized by the communication IF 991. The communication unit realizes a function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 901 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

[0099] <Additional Notes> The matters described in the above embodiments will be supplemented below.

[0100] (Appendix 1) A program to be executed by a computer having a processor and a memory unit, wherein the processor executes the following steps: a document acquisition step (S101) of acquiring a document related to a patent; a block division step (S102) of dividing the document acquired in the document acquisition step into one or more blocks and identifying one or more block tags associated with each of the blocks; a sub-block division step (S103) of dividing at least a portion of the one or more blocks divided in the block division step into one or more sub-blocks; and a tag expansion step (S104) of assigning a tag to at least a portion of the one or more sub-blocks divided in the sub-block division step according to the block tag of the block from which the sub-block was divided. This allows the creation of a document (processed document) for creating a prompt that will yield a more suitable answer. Furthermore, by inputting a prompt that includes the processed document into an AI system, the AI ​​system can be made to output a more suitable answer.

[0101] (Appendix 2) The block division step (S102) is a step of dividing a patent document into one or more blocks beginning with a paragraph number or a heading, and identifying one or more paragraph numbers or headings associated with each of the blocks, and is a program as described in Appendix 1. This allows the creation of patent documents (processed documents) for creating prompts that will yield more appropriate answers. Furthermore, by inputting a prompt that includes the processed documents into an AI system, the AI ​​system can be made to output more appropriate answers.

[0102] (Appendix 3) The program described in Appendix 2, wherein the sub-block expansion step (S103) is a step of dividing a block of a patent document beginning with a paragraph number or a heading sentence into sub-blocks covering one or more sentences, and the tag expansion step (S104) is a step of assigning tags corresponding to the paragraph number or heading sentence to at least a portion of the one or more sentences divided in the sub-block division step. This allows the creation of patent documents (processed documents) for creating prompts that output more appropriate answers. Furthermore, by inputting a prompt that includes the processed documents into an AI system, the AI ​​system can be made to output more appropriate answers.

[0103] (Appendix 4) A program described in any one of Appendices 1 to 3, in which a processor executes an instruction statement receiving step (S301) in which an instruction statement including an instruction referencing a tag assigned in the tag expansion step, and a prompt creation step (S303) in which a prompt is created by including one or more sub-blocks assigned tags in the tag expansion step in the instruction statement receiving step. This allows the artificial intelligence system to output an answer that references the tag by inputting a prompt including an instruction to reference the tag from the artificial intelligence system to the artificial intelligence system. For example, if the instructions include instructions to extract terms or words from a patent document, the artificial intelligence system can be made to output a response that includes tags to identify the location where the terms or words were extracted. In the present disclosure, by assigning tags to sub-blocks as well, it is possible to have the artificial intelligence system output answers that refer to the tags more accurately.

[0104] (Appendix 5) 5. The program according to any one of appendices 1 to 4, wherein the tag expanding step (S104) is a step of assigning a tag including tag identification information to the sub-block. This allows the AI ​​system to input a document (processed document) in a format that makes it easier for the AI ​​system to identify (recognize) the tags, and allows the AI ​​system to output a more appropriate answer by referring to the tags. In the present disclosure, by including tag identification information in the tag, it is possible to have the artificial intelligence system output answers that refer to the tag more accurately.

[0105] (Appendix 6) A program as described in Appendix 5, in which a processor executes an instruction statement receiving step (S301) in which an instruction statement including an instruction to reference tag identification information is received, and a prompt creation step (S303) in which a prompt is created by including one or more sub-blocks to which a tag including tag identification information has been assigned in a tag expansion step in the instruction statement receiving step. This allows the AI ​​system to input a document (processed document) in a format that makes it easier for the AI ​​system to identify (recognize) the tags, and allows the AI ​​system to output a more appropriate answer by referring to the tags. In the present disclosure, by including tag identification information in the tag, it is possible to have the artificial intelligence system output answers that refer to the tag more accurately.

[0106] (Appendix 7) A program as described in Appendix 6, in which a processor executes an answer acquisition step (S305) in which the processor acquires an answer to be output by inputting the prompt created in the prompt creation step into an artificial intelligence system, and an identification exclusion step (S306) in which tag identification information is excluded from the answer acquired in the answer acquisition step. This allows the tag identification information to be excluded from the answer output from the artificial intelligence system, thereby making it possible to output an answer that is more readable to the user.

[0107] (Appendix 8) The program according to any one of appendices 1 to 7, wherein the tag expanding step (S104) is a step of assigning tags to one or all of the sub-blocks according to the block tag of the block from which the sub-blocks were divided. This makes it possible to create a document (processed document) for creating a prompt that will yield a more suitable answer.

[0108] (Appendix 9) 9. The program according to any one of appendices 1 to 8, wherein the tag expansion step (S104) is a step of inserting a block tag at the beginning, end, or between the beginning and end of the sub-block. This makes it possible to create a document (processed document) for creating a prompt that will yield a more suitable answer.

[0109] (Appendix 10) A computer-implemented method comprising a processor and a memory, wherein the processor performs all of the steps performed in the invention according to any one of appendices 1 to 9. This makes it possible to create a document (processed document) for creating a prompt that will yield a more suitable answer.

[0110] (Appendix 11) An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps executed in the invention according to any one of Supplementary Note 1 to Supplementary Note 9. This makes it possible to create a document (processed document) for creating a prompt that will yield a more suitable answer.

[0111] (Appendix 12) A system comprising means for performing all steps performed in any of the inventions according to any one of appendixes 1 to 9. This makes it possible to create a document (processed document) for creating a prompt that will yield a more suitable answer. [Explanation of symbols]

[0112] 1 System, 10 Server, 101 Memory Unit, 104 Control Unit, 106 Input Device, 108 Output Device, 20 User Terminal, 201 Memory Unit, 204 Control Unit, 206 Input Device, 208 Output Device, 40 Artificial Intelligence System, 401 Memory Unit, 404 Control Unit, 406 Input Device, 408 Output Device

Claims

1. A program to be executed by a computer having a processor and a storage unit, the processor: a document acquisition step of acquiring documents relating to the patent; a block division step of dividing the document acquired in the document acquisition step into one or more blocks and identifying one or more block tags associated with each of the blocks; a sub-block dividing step of dividing at least a part of the one or more blocks divided in the block dividing step into one or more sub-blocks; a tag development step of assigning a tag to at least a part of the one or more sub-blocks divided in the sub-block division step, the tag corresponding to the block tag of the block from which the sub-block was divided; A program that executes.

2. The block division step is a step of dividing the patent document into one or more blocks beginning with a paragraph number or a heading, and identifying one or more paragraph numbers or headings associated with each of the blocks; The program according to claim 1.

3. The sub-block development step is a step of dividing a block of a patent document starting with a paragraph number or a heading sentence into sub-blocks each spanning one or more sentences; The tag development step is a step of assigning tags corresponding to paragraph numbers or headings to at least a part of one or more sentences divided in the subblock division step. The program according to claim 2.

4. the processor: an instruction statement receiving step of receiving an instruction statement including an instruction to refer to the tag added in the tag expanding step; a prompt creating step of creating a prompt by including one or more sub-blocks to which the tag is added in the tag expanding step in the instruction statement received in the instruction statement receiving step; To execute The program according to claim 1.

5. The tag expanding step is a step of assigning a tag including tag identification information to the sub-block. The program according to claim 1.

6. the processor: an instruction statement receiving step of receiving an instruction statement including an instruction to refer to the tag identification information; a prompt creating step of creating a prompt by including one or more sub-blocks to which the tag including the tag identification information is added in the tag expanding step in the instruction statement received in the instruction statement receiving step; To execute The program according to claim 5.

7. the processor: an answer acquisition step of inputting the prompt created in the prompt creation step into an artificial intelligence system and acquiring an answer to be output; an identification / exclusion step of excluding tag identification information from the answer acquired in the answer acquisition step; To execute The program according to claim 6.

8. the tag expansion step is a step of assigning tags to all of the one or more sub-blocks according to the block tags of the blocks from which the sub-blocks were divided; The program according to claim 1.

9. The tag expansion step is a step of inserting the block tag at the beginning, end, or between the beginning and end of the sub-block. The program according to claim 1.

10. A method implemented on a computer having a processor and a memory, wherein the processor performs all of the steps performed in the invention according to any one of claims 1 to 9.

11. 10. An information processing device comprising a control unit and a storage unit, wherein the control unit executes all of the steps executed in the invention according to any one of claims 1 to 9.

12. A system comprising means for executing all steps performed in any one of the inventions according to claims 1 to 9.

Images