Program, method, information processing apparatus, system

Abstract

The user has a problem that they cannot output a suitable answer to the artificial intelligence system. 【Solution means】A program for causing a computer including a processor and a storage unit to execute. The processor executes 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 specifying one or more block tags associated with each of the blocks, a sub-block division step of dividing at least a part 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 corresponding to the block tag of the block from which the sub-block is divided to at least a part of the one or more sub-blocks divided in the sub-block division step.

Description

Technical Field

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

Background Art

[0002] Techniques for assisting the reader's understanding when reading patent documents are known. Patent Document 1 discloses a technique related to assisting the understanding of claims, which specifies and presents the constituent elements that are key points in the claims so that the description thereof can be read with emphasis.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The user has a problem that it is impossible to output a suitable answer to the artificial intelligence system. Therefore, the present disclosure has been made to solve the above problems, and an object thereof is to provide a technique for outputting a suitable answer to the artificial intelligence system.

Means for Solving the Problems

[0005] A program for causing a computer including a processor and a memory unit to execute, the processor performing 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 specifying one or more block tags associated with each of the blocks, a sub-block division step of dividing at least a part 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 corresponding to the block tag of the block from which the sub-block is divided to at least a part of the one or more sub-blocks divided in the sub-block division step.

Advantages of the Invention

[0006] According to the present disclosure, it is possible to output an answer suitable for an artificial intelligence system.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiments for Carrying Out the Invention

[0008] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all the drawings for describing the embodiments, the same reference numerals are given to common components, and repeated descriptions are omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. Also, not all of the components shown in the embodiments are essential components of the present disclosure. Further, each figure is a schematic diagram and is not necessarily drawn precisely.

[0009] <Configuration of System 1> System 1 in the present disclosure is an information processing system that provides an analysis service for patent documents. Note that the present disclosure is applicable to legal documents, contracts, and other arbitrary documents other than patent documents. System 1 includes information processing devices of server 10, user terminal 20, and artificial intelligence system 40 connected via 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 server 10. FIG. 3 is a block diagram showing the functional configuration of user terminal 20.

[0010] Each information processing device is composed of a computer having an arithmetic device 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 server 10, user terminal 20, and artificial intelligence system 40, descriptions overlapping with the basic hardware configuration of the computer and the basic functional configuration of the computer described later are omitted.

[0011] <Configuration of Server 10> Server 10 is an information processing device that provides an analysis service for patent documents. Server 10 includes a storage unit 101 and a control unit 104.

[0012] <Configuration of the storage unit 101 of server 10> The storage unit 101 of 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 server 10 to function as each functional unit. The application program 1011 includes applications such as a web browser application.

[0014] The user table 1012 is a table for storing and managing information of member users (hereinafter referred to as users) who use the service. By registering for use of the service, the information of the user is stored in a new record of the user table 1012. Thereby, the user can use the service according to the present disclosure. The user table 1012 is a table having columns of 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 for storing user identification information for identifying a user. The user identification information is an item for which a unique value is set for each user. The user name is an item for storing the name of the user. The user name may be set to any string such as a nickname instead of the real name.

[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 of 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 for storing document identification information for identifying patent documents. The user ID is an item for storing user identification information for identifying users. The document name is an item for storing the name of the patent document. Any string can be set as the document name. For example, the document name stores the publication number, registration number, application number, and other sorting numbers of the patent document. The document content is an item for storing 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 "claims", "abstract", "detailed description of the invention", "examples", "embodiments", etc. included in the patent document (specification). Specifically, the text of gazettes such as published gazettes and patent gazettes is stored. In the present disclosure, the patent document stored in the document content includes paragraph numbers (0001, 0002, 0003···, claim 1, claim 2,···) and the string related to the heading (heading text). In the present disclosure, claims are included in the paragraph numbers, but may also be included in the heading text. In the present disclosure, paragraph numbers and heading text are collectively referred to as block tags. The block tags are described in association with each document block (usually a block of a document consisting of multiple sentences and paragraphs is referred to as a document block) specified by a paragraph or a 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, problems to be solved by the invention, means for solving the problems, effects of the invention, brief description of the drawings, forms for carrying out the invention, Example 1, Example 2···, industrial applicability, description of reference signs, deposit number, free text of the sequence listing, number 1, number 2···, Chemical formula 1, Chemical formula 2···, Table 1, Table 2···. The paragraph number is a consecutive number for uniquely identifying each paragraph in the patent document, and is represented by four-digit Arabic numerals in Japan. The heading text is a string used as a heading for indicating a specific section or content of the patent document. In Japanese patent documents, both paragraph numbers and heading texts are expressed as being enclosed by corner brackets to indicate that they are paragraph numbers and heading texts, respectively. Note that in this disclosure, although Japanese patent documents are used as an example for explanation, it is not limited to this, and it is applicable to paragraph numbers and heading texts in US patents, European patents, and patent documents of any other country. The processed document is an item that stores text information obtained by processing the content of a patent document. Specifically, it stores text information obtained by performing the tag expansion process described later on the document content.

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

[0019] The instruction ID is an item that stores instruction identification information for identifying instruction information. The instruction data is an item that stores text information including an inquiry sentence (instruction sentence) for an artificial intelligence system. Specifically, in this disclosure, it stores an instruction sentence (including a question sentence for the document content, etc.) for the document content stored in the document table 1013. The instruction sentence may be input by the user operating the input device of their information processing terminal. The instruction sentence may also be configured to be selected by the user from one or more stored instruction sentence candidates in a table (not shown) in advance. In this disclosure, a prompt, which is an inquiry sentence for the artificial intelligence system, is generated by combining part or all of the instruction data and the processed document.

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

[0021] The document ID is an item for storing document identification information for identifying patent documents. The prompt is an item for storing a prompt regarding an inquiry sentence for the artificial intelligence system. A prompt is mainly an inquiry sentence (text) input to the artificial intelligence system. Specifically, the user can input a prompt to the artificial intelligence system so that the artificial intelligence system outputs a desired output result. Note that the prompt does not necessarily have to be a character string, and a prompt by an image, video, voice, etc. may also be used. For example, gestures, voice instructions, etc. by the user can also be a prompt. The response content is an item for storing the response content from the artificial intelligence system to the prompt. Specifically, text information regarding the response content from the artificial intelligence system is stored. In the present disclosure, an artificial intelligence system that gives a response by text is described as an example, but it is not limited thereto. In the case of an artificial intelligence system that gives a response by an image, video, voice, etc., image data, video data, voice data, etc. may be stored as the response content.

[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 realizes each functional unit by executing the application program 1011 stored in the storage unit 101.

[0023] The user registration control unit 1041 performs a process of storing information of a user who wishes to use the service according to the present disclosure in the user table 1012. The information stored in the user table 1012 is such that the user opens a web page or the like operated by the service provider from an arbitrary information processing terminal, enters information in a predetermined input form, and transmits it to the server 10. The user registration control unit 1041 stores the received information in a new record of the user table 1012, and the user registration is completed. As a result, the user stored in the user table 1012 can use the service. Prior to the registration of user information by the user registration control unit 1041 in the user table 1012, the service provider may perform a predetermined review to restrict the user's access to 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 the user registration control unit 1041 may automatically set any character string or number.

[0024] The document display unit 1042 executes document display processing. Details will be described later.

[0025] The inquiry unit 1043 executes inquiry processing. Details will be described later.

[0026] <Configuration of the user terminal 20> The user terminal 20 is an information processing device operated by a user who uses the service. The user terminal 20 may be, for example, a mobile terminal such as a smartphone or a tablet, or a stationary PC (Personal Computer) or a laptop PC. It may also be a wearable terminal such as an HMD (Head Mount Display) or a wristwatch-type 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] User ID 2011 is the user's account ID. The user sends User ID 2011 from the user terminal 20 to the server 10. The server 10 identifies the user based on User ID 2011 and provides the services according to the present disclosure to the user. Note that User ID 2011 includes information such as a session ID temporarily assigned by the server 10 when identifying the user using the user terminal 20.

[0029] The application program 2012 may be pre-stored 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 program 2012 includes applications 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.

[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 realizes each functional unit by executing the application program 2012 stored in the storage unit 201.

[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 the artificial intelligence system 40> The artificial intelligence system 40 is an information processing device that outputs the response content for a prompt. For example, the artificial intelligence system 40 includes ChatGPT, OpenAI GPT, PerplexityAsk, BingAI, etc. These artificial intelligence systems have the function of interactive response (chat), and the user can give any inquiry or instruction to the artificial intelligence system in text, and obtain the response to the inquiry or the response to the instruction. In the present disclosure, the user can obtain a text that supports the reading of the patent document as the response content by sending the prompt created in the inquiry process to the artificial intelligence system 40. Also in the present disclosure, the artificial intelligence system is not limited to text-based interactive response. For example, it may be an image generation AI system such as Midjourney or Stable Diffusion. For example, the user can obtain an image or video that supports the reading of the patent document as the response content by sending the prompt created in the inquiry process to such an image generation AI system. In addition, the present disclosure is also applicable to artificial intelligence systems that output response content by video, voice, etc.

[0034] <Operation of System 1> Hereinafter, each process of System 1 will be described. 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 Process> The tag expansion process is a process of attaching block tags to sub-blocks (sentences, paragraphs) included in document blocks such as paragraphs and sections included in the acquired patent document. That is, it is a process of expanding the block tags (paragraph numbers, headings) attached to the document blocks to the sub-blocks. Specifically, it is a process of inheriting the block tags (paragraph numbers, headings) of a plurality of document blocks constituting the patent document to the sub-blocks obtained by dividing the document blocks. The tag expansion process may be executed asynchronously with respect to the inquiry process, or may be executed as part of the inquiry process. For example, it may be executed in advance when storing a patent document, or may be executed during the inquiry process (for example, step S302). Also, for some blocks of a patent document (blocks related to paragraphs), the tag expansion process may be executed in advance when storing the patent document, and for some other blocks (blocks related to headings), it may be configured to be executed during the inquiry process. That is, the tag expansion process may be executed once or divided into multiple times for a part or the whole of one 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 and sections, identify block tags (paragraph numbers, heading texts) associated with the one or more document blocks, append the identified block tags to one or more sub-blocks (sentences, clauses) included in the document block, and create and store a processed document with block tags appended to the sub-blocks.

[0037] <Details of Tag Expansion Process> The details of the tag expansion process will be described below.

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

[0039] An example of the document content of the patent document in this disclosure is shown below. For convenience of description in the specification, the parts in corner brackets are described in square brackets. The following patent document consists of document blocks corresponding to 8 paragraph numbers from paragraph 0008 to 0016. The patent document may be part or the whole of the patent specification. The following patent document can also be regarded as consisting of document blocks corresponding to the headings of the problems to be solved by the invention (paragraphs 0008, 0009), the means for solving the problems (paragraphs 0010, 0011), the effects of the invention (paragraphs 0012, 0013), and the forms for implementing the invention (paragraphs 0014, 0015). Note that the document block corresponding to the heading may include document blocks corresponding to one or more paragraphs. In the tag expansion process, the document block may be specified for either the unit of the paragraph number, the unit of the heading sentence, or both.

[0040] [Patent Document] [Problems to be Solved by the Invention]

[0008] The problem to be solved is that it is impossible to visually confirm the input position that becomes an obstacle in the operation of manually scanning and inputting a high-definition drawing. This problem becomes particularly prominent when inputting fine drawings or complex illustrations, etc., and is the cause of a significant reduction in the work efficiency of the user.

[0009] In the conventional hand scanner, due to the structure of the housing, it was difficult to confirm the exact position during scanning. Therefore, the user had to proceed with the work while guessing the input position, and as a result, there were many cases where incorrect parts were repeatedly scanned or necessary parts were overlooked. [Means for Solving the Problems]

[0010] The main feature of the present invention is to receive light with an optical path inclined with respect to the direction perpendicular to the document so that the scanning position of the document or immediately before (after) it is always visible. By adopting this oblique optical path, the user can perform the operation while directly confirming the position during scanning.

[0011] Specifically, by tilting the optical system installed inside the housing, light is captured at an angle that is not parallel to the scan plane. This realizes a structure in which the user can directly view the scan position from the openings provided on the side surface or the upper part of the housing. [Advantages of the Invention]

[0012] Since the hand scanner of the present invention scans with a one-dimensional image sensor through an oblique optical axis from the upper part of the housing, the field of view of the sensor, that is, the input position, can always be observed and confirmed directly or in the vicinity. Therefore, there is an advantage that the left and right side ends can be used appropriately according to the binding conditions and operation methods of the input object. Due to this feature, the user can perform the scanning operation accurately and efficiently.

[0013] Furthermore, this structure can handle manuscripts of various shapes, and can smoothly scan the bound parts of books and thick materials. Also, regardless of whether the user is left-handed or right-handed, the user can select and operate the end on the easier-to-use side, so it has high versatility and can meet the needs of a variety of users. [Embodiments for Carrying Out the Invention]

[0014] The purpose of inputting an image from outside the housing or from a position as close as possible to the side end of the housing was achieved with the minimum number of components without sacrificing the thickness of the optical system components. This design concept simultaneously achieves the compactification of the entire device and the reduction of manufacturing costs.

[0015] Furthermore, by optimizing the arrangement of the optical system, it has been successful in improving the visibility of the user while maintaining high image quality. This achieves both precise scanning operations and improved operability, effectively solving the problems of conventional hand scanners.

[0041] In step S102, the control unit 104 of the server 10 executes a block division step of dividing the document obtained in the document acquisition step into one or more blocks and specifying one or more block tags associated with each of the blocks. The block division step divides a document related to a patent into one or more blocks starting from a paragraph number or a heading sentence, and executes a step of specifying one or more paragraph numbers or heading sentences associated with each of the blocks. Specifically, the control unit 104 of the server 10 obtains a plurality of document blocks by dividing the document content obtained in step S101 in units of paragraph numbers or heading sentences. Also, the paragraph number or heading sentence related to each document block is specified as a block tag. In the present disclosure, as an example, paragraph numbers and headings are used as units when dividing the document content into blocks, but it is not limited thereto. For example, embodiments (first embodiment, second embodiment,...), examples (first example, second example,...), modification examples (first modification example, second modification example,...), etc. In addition, the blocks may be divided in any document unit. In this case, the block tags are embodiments, examples, modification examples, etc., respectively. Also, strings related to block tags such as unnecessary paragraph numbers and headings may be removed from the divided blocks. For example, when dividing blocks in units of paragraph numbers, the heading sentence may be removed. When dividing blocks in units of heading sentences, the paragraph number may be removed. Thereby, an answer referring to the block tag can be more appropriately output to the artificial intelligence system 40. Thereby, the document content obtained in step S101 is divided into blocks composed of documents in units of paragraphs. Similarly, the document content is divided into blocks composed of documents in units of headings (editing, part, chapter, section, item, subsection, subsubsection, part, chapter, section, subsection, subsubsection).

[0042] For example, the document content A is divided into the following blocks A and B.

[0043] [Block A (block division by paragraph number)] Block 1: Block tag: 0008 Block content: The problem to be solved is that the input position that hinders the operation of manually scanning and inputting a high-definition image cannot be visually confirmed. This problem becomes particularly prominent when inputting fine drawings or complex illustrations, etc., and is the cause of a significant reduction in the work efficiency of users. Block 2: Block tag: 0009 Block content: In a conventional hand scanner, due to the structure of the housing, it was difficult to confirm the exact position during scanning. Therefore, the user had to proceed with the work while guessing the input position, and as a result, there were many cases where incorrect parts were repeatedly scanned or necessary parts were overlooked. Block 3: Block tag: 0010 Block content: The main feature of the present invention is to receive light with an optical path inclined with respect to the direction perpendicular to the document so that the scanning position of the document or immediately before (after) it is always visible. By adopting this oblique optical path, the user can perform the operation while directly confirming the position during scanning. Block 4: Block tag: 0011 Block content: Specifically, by inclining the optical system installed inside the housing, light is captured at an angle that is not parallel to the scanning surface. As a result, a structure is realized in which the user can directly visually recognize the scanning position through the openings provided on the side surface or the upper part of the housing. Block 5: Block tag: 0012 Block content: The hand scanner of the present invention scans with a one-dimensional image sensor through an oblique optical axis from the upper part of the housing. Therefore, the field of view of the sensor, that is, the input position, can always be observed and confirmed directly or in the vicinity. There is an advantage that the left and right side ends can be used properly according to the binding conditions and operation methods of the input target. Due to this feature, the user can perform the scanning operation accurately and efficiently. Block 6: Block tag: 0013 Block content: Furthermore, this structure can accommodate manuscripts of various shapes, and can smoothly scan the bound parts of books and thick materials. Also, regardless of whether the user is left-handed or right-handed, the user can select and operate the end that is easier to use, so it has high versatility and can meet the needs of a variety of users. Block 7: Block tag: 0014 Block content: The purpose of inputting an image from outside the housing or from a position as close as possible to the side end of the housing is realized with the minimum number of parts without sacrificing the thickness of the optical system components. This design concept simultaneously achieves the compactification of the entire device and the reduction of manufacturing costs. Block 8: Block tag: 0015 Block content: Furthermore, by optimizing the arrangement of the optical system, it has been successful in improving the visibility of the user while maintaining high image quality. As a result, both precise scanning operations and improved operability are achieved, effectively solving the problems of conventional hand scanners.

[0044] 〔Block B (block division by heading sentence unit)〕 Block 1: Block tag: Problems to be solved by the invention Block content: The problem to be solved is that in the operation of manually scanning and inputting a high-definition drawing, the input position that hinders the operation cannot be visually confirmed. This problem becomes particularly prominent when inputting fine drawings or complex illustrations, etc., and is the cause of a significant reduction in the work efficiency of the user. In a conventional hand scanner, due to the structure of the housing, it was difficult to confirm the exact position during scanning. Therefore, the user had to proceed with the work while guessing the input position, and as a result, there were many cases where incorrect parts were repeatedly scanned or necessary parts were overlooked. Block 2: Block tag: Means for solving the problem Block content: The main feature of the present invention is to receive light with an optical path inclined with respect to the direction perpendicular to the document, so that the scanning position of the document or immediately before (after) it is always visible. By adopting this oblique optical path, the user can perform the operation while directly confirming the position during scanning. Specifically, by inclining the optical system installed inside the housing, light is captured at an angle not parallel to the scanning surface. As a result, a structure is realized in which the user can directly visually recognize the scanning position from the openings provided on the side surface or the upper part of the housing. Block 3: Block tag: Effects of the invention Block content: The hand scanner of the present invention scans with a one-dimensional image sensor through an oblique optical axis from the upper part of the housing. Therefore, the field of view of the sensor, that is, the input position, can always be observed and confirmed directly or in the vicinity. There is an advantage that the left and right side ends can be used appropriately according to the binding conditions and operation methods of the input object. Due to this feature, the user can perform the scanning work accurately and efficiently. Furthermore, this structure can be applied to manuscripts of various shapes, and can smoothly scan the bound parts of books and thick materials, etc. Also, regardless of whether the user is left-handed or right-handed, the user can select and operate the easier-to-use end, so it has high versatility and can meet the needs of a variety of users. Block 4: Block tag: Mode for Carrying Out the Invention Block content: The object of inputting an image from outside the housing or from a position as close as possible to the side end of the housing is achieved with a minimum number of components without impairing the thickness of the optical system components. This design concept simultaneously achieves the compactification of the entire device and the reduction of manufacturing costs. Furthermore, by optimizing the arrangement of the optical system, it has been successful in improving the visibility of the user while maintaining high image quality. This enables both precise scanning operations and improved operability, effectively solving the problems of 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 a plurality of blocks divided in the block division step into one or a plurality of sub-blocks. The sub-block expansion step executes a step of dividing a block starting from a paragraph number or a heading sentence in a document related to a patent into sub-blocks corresponding to one or a plurality of sentences. Specifically, the control unit 104 of the server 10 obtains a plurality of document blocks (sub-blocks) by dividing the blocks divided in step S102 in units of sentences (sentences). Also, the block tag of the block that is the source of the sub-block division is specified. Thereby, the document content obtained in step S101 is divided into sub-blocks in units of sentences (sentences). In the present disclosure, an example of dividing a block into sub-blocks consisting of sentences (sentences) is disclosed as an example, but it is not limited thereto. For example, a block of a section may be divided into sub-blocks with a smaller granularity such as sub-sections and sub-sub-sections, or may be configured to be divided into sub-blocks consisting of a plurality of characters smaller than a sentence. A block is a part constituting a document, and a sub-block only needs to be a part constituting a block.

[0046] For example, Blocks 1 and 2 of Block A are divided into the following sub-blocks A.

[0047] 〔Sub-block A (block division by paragraph number)〕 Sub-block 1: Block tag: 0008 Sub-block content: The problem to be solved is that the input position that hinders the operation of manually scanning and inputting a high-definition drawing cannot be visually confirmed. Sub-block 2: Block tag: 0008 Sub-block content: This problem becomes particularly prominent when inputting particularly detailed drawings or complex illustrations, etc., and has become a cause of greatly reducing the work efficiency of users. Sub-block 3: Block tag: 0009 Sub-block content: In a conventional hand scanner, due to the structure of the housing, it was difficult to confirm the exact position during scanning. Sub-block 4: Block tag: 0009 Sub-block content: Therefore, the user has to proceed with the work while guessing the input position, and as a result, there have been many cases where incorrect parts are repeatedly scanned or necessary parts are overlooked.

[0048] In step S104, the control unit 104 of the server 10 executes a tag expansion step of assigning a tag corresponding to the block tag of the block from which the sub-block is divided to at least a part of one or more sub-blocks divided in the sub-block expansion step. The tag expansion step executes a step of assigning a tag corresponding to a paragraph number or a heading sentence to at least a part of one or more sentences divided in the sub-block expansion step. Specifically, the control unit 104 of the server 10 assigns a tag corresponding to the block tag to the sub-blocks divided in step S103. · The control unit 104 of the server 10 may directly add the block tag to the sub-block. · The control unit 104 of the server 10 may add to the sub-block a block tag with a sub-block index (a number, alphabet, etc. for distinguishing sub-blocks within a block) added thereto. · The control unit 104 of the server 10 may issue an arbitrary unique key (such as a UUID) for each sub-block and associate them with the block tag by means of a database (not shown). As the sub-block tag, a tag obtained by inheriting the block tag by any method can be used. In this way, by making each sub-block tag inherit the block tag of the original block, the relevance to the original block can be maintained. Thereby, even after processing at the sub-block level, the original document structure can be easily restored.

[0049] For example, what is added to sub-block A as a sub-block tag (a block tag with a sub-block index added thereto) is the following sub-block A1. The sub-block tag may be the original block tags 0008 and 0009 directly, instead of 0008-1, 0008-2, 0009-1, 0009-2, etc. Also, it may be configured to add an arbitrary unique key associated with the original block tags 0008 and 0009 by means of a database (not shown). Also in this case, the artificial intelligence system 40 can obtain an answer with appropriate reference to the unique key, and by specifying the block tag from the unique key, the position of the sub-block in the original document can be specified from the answer content.

[0050] 〔Sub-block A1 (block division by paragraph number)〕 Sub-block 1: (0008-1) The problem to be solved is that in the operation of manually scanning and inputting a high-definition drawing, the input position that becomes an obstacle cannot be visually confirmed. Sub-block 2: (0008-2) This problem becomes particularly prominent when inputting detailed drawings or complex illustrations, etc., and is the cause of a significant reduction in the user's work efficiency. (0009-1) In conventional hand scanners, due to the structure of the housing, it was difficult to confirm the exact position during scanning. (0009-2) Therefore, the user has to proceed with the work while guessing the input position, and as a result, there have been many cases where incorrect parts are repeatedly scanned or necessary parts are overlooked.

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

[0052] For example, the following is sub-block A2 in which the sub-block tag of sub-block A includes tag identification information (P_).

[0053] [Sub-block A2 (block division by paragraph number)] Sub-block 1: (P_0008-1) The problem to be solved is that in the operation of scanning and inputting a high-definition drawing by hand feeding, the input position that becomes an obstacle cannot be visually confirmed. Sub-block 2: (P_0008-2) This problem becomes particularly prominent when inputting detailed drawings or complex illustrations, etc., and is the cause of a significant reduction in the user's work efficiency. (P_0009-1) In conventional hand scanners, due to the structure of the housing, it was difficult to confirm the exact position during scanning. (P_0009-2)Therefore, the user has to proceed with the work while guessing the input position, and as a result, there have been many cases where the user repeatedly scans incorrect parts or overlooks necessary parts.

[0054] In step S104, the tag expansion step executes a step of assigning a tag according to the block tag of the block from which the sub-block is divided to all of one or more sub-blocks. Specifically, the control unit 104 of the server 10 may assign a sub-block tag to only some of the plurality of sub-blocks divided in step S103, or may assign a sub-block tag to all of the sub-blocks.

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

[0056] 〔Sub-block A3 (block division by paragraph number)〕 Sub-block 1: (S_0008)The problem to be solved is that the input position that hinders the operation of manually scanning and inputting a high-definition drawing cannot be visually confirmed. Sub-block 2: (S_0008)This problem becomes particularly prominent when inputting particularly detailed drawings or complex illustrations, etc., and has been the cause of a significant reduction in the work efficiency of the user. Sub-block 3: (S_0009)In a conventional hand scanner, due to the structure of the housing, it has been difficult to confirm the exact position during scanning. Sub-block 4: (S_0009)Therefore, the user has to proceed with the work while guessing the input position, and as a result, there have been many cases where the user repeatedly scans incorrect parts or overlooks necessary parts.

[0057] For example, block 1 of block B is divided into sub-block B1 as follows. In this case, the tag identification information is "S_". Also, an example is shown where the sub-block tag is given a HASH1 (a unique key such as a hash character string, a random character string, etc.) associated with the block tag of the original block "Problems to be Solved by the Invention". Also, an example is shown where the index of the sub-block is not used in this case either.

[0058] 〔Sub-block B1 (block division by heading sentence)〕 Sub-block 1: (S_HASH1) The problem to be solved is that in the operation of manually scanning and inputting a high-definition drawing, the input position that becomes an obstacle cannot be visually confirmed. Sub-block 2: (S_HASH1) This problem becomes particularly prominent when inputting particularly detailed drawings or complex illustrations, etc., and is the cause of a significant reduction in the work efficiency of the user. Sub-block 3: (S_HASH1) In a conventional hand scanner, due to the structure of the housing, it was difficult to confirm the exact position during scanning. Sub-block 4: (S_HASH1) Therefore, the user has to proceed with the work while guessing the input position, and as a result, there have been many cases where incorrect parts are repeatedly scanned or necessary parts are overlooked.

[0059] In step S104, the tag expansion step executes a step of inserting a block tag at the head, tail, or between the head and the tail of the sub-block. Specifically, the sub-block tag does not need to be given at the head of the sub-block, and may be included at the tail of the sub-block or at any position of the sub-block. By giving (inserting) the sub-block tag at the head of the sub-block, the artificial intelligence system 40 can more preferably recognize the sub-block tag and improve the quality of processing.

[0060] [Example of Insertion at the End of Sub-Block] Sub-block 1: The problem to be solved is that the input position that hinders the operation of manually scanning and inputting a high-definition drawing cannot be visually confirmed. (S_0008) Sub-block 2: This problem becomes particularly prominent when inputting particularly detailed drawings or complex illustrations, etc., and is the cause of a significant reduction in the work efficiency of the user. (S_0008)

[0061] [Example of Insertion between Sub-Blocks] Sub-block 1: The problem to be solved (S_0008) is that the input position that hinders the operation of manually scanning and inputting a high-definition drawing cannot be visually confirmed. Sub-block 2: This problem becomes particularly prominent when inputting particularly detailed drawings or complex illustrations (S_0008), etc., and is the cause of a significant reduction in the work efficiency of the user.

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

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

[0064] [Overview of Inquiry Process] The inquiry process is a series of processes that receive the input of an instruction sentence, obtain 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] [Details of Inquiry Process] The details of the inquiry process will be described below.

[0066] In step S301, the control unit 104 of the server 10 executes an instruction receiving step for receiving an instruction sentence. Specifically, the user operates the input device 206 of the user terminal 20 to input the URL of a page (inquiry processing page) for executing an inquiry process in a web browser or the like, and opens the inquiry processing page. The control unit 204 of the user terminal 20 transmits a request for opening 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 transmits 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 sentence and an input field for a publication number for designating a document (patent document) such as a patent gazette. Note that the inquiry processing page may be provided with an input field in which a patent document such as a patent gazette can be directly input. The user can operate the input device 206 of the user terminal 20 to input an instruction sentence for instructing the processing by the artificial intelligence system 40 for the patent document specified in the inquiry processing page in the instruction input field. The instruction sentence is an instruction sentence for instructing the following tasks to the generation AI. · An instruction sentence for instructing the summary of a patent document · An instruction sentence for classifying a patent document according to a predetermined classification criterion · An instruction sentence for comparing a patent document with a product specification or the like · An instruction sentence for outputting the points of agreement and difference between a patent document and a specific perspective · An instruction sentence for evaluating the value of a patent document In the present disclosure, as an example, an instruction for classification according to a predetermined classification criterion is disclosed. The control unit 104 of the server 10 generates a prompt for input to the artificial intelligence system 40 by inserting, into the {patent document} portion of the instruction, the patent document specified on the inquiry processing page or a processed document created by tag expansion processing for the patent document. In the present disclosure, an example of inserting a processed document into the {patent document} portion will be described. In addition, the instruction of the present disclosure includes an instruction for referring to block tags (paragraph numbers, headings), etc. For example, in the following Instruction A, the portion "Please also output the paragraph number or heading of the location of the patent document referred to when classifying" corresponds to an instruction for referring to block tags (paragraph numbers, headings), etc.

[0067] 〔Instruction A〕 Classify the patent document into any one of Classification A, Classification B, and Classification C. Please also output the paragraph number or heading of the location of the patent document referred to when classifying. #Patent document {Patent document}

[0068] In step S301, the control unit 104 of the server 10 executes an instruction reception step of receiving an instruction including an instruction for referring to the tag given in the tag expansion step. The control unit 104 of the server 10 executes an instruction reception step of receiving an instruction including an instruction for referring to tag identification information. For example, the instruction may include an instruction "The paragraph number or heading starts with 'P_' " including a character string (P_, S_, P:, S:) for referring to tag identification information as follows. 〔Instruction B〕 Classify the patent document into any one of Classification A, Classification B, and Classification C. Please also output the paragraph number or heading of the location of the patent document referred to when classifying. Note that the paragraph number or heading starts with 'P_'. #Patent document {Patent document}

[0069] The user selects the send button included in the inquiry processing page by operating the input device 206 of the user terminal 20. The control unit 204 of the user terminal 20 transmits a request including the instruction text input on the inquiry processing page and the gazette number etc. (in this disclosure, an example of transmitting a document ID is disclosed as an example) for designating the patent document to the server 10. In addition, when a patent document is input on the inquiry processing page, the patent document to be the subject of the inquiry processing may be transmitted to the server 10. The control unit 104 of the server 10 acquires and accepts a request including the instruction text and the document ID by receiving it.

[0070] In step S302, the control unit 104 of the server 10 executes a document information acquisition step of acquiring document information including a processed document. The control unit 104 of the server 10 searches the document ID item of the document table 1013 based on the acquired document ID, and acquires document information including the document content and the processed document. In this disclosure, the document information stored in the document table 1013 is taken as an example of a configuration for creating a processed document by tag expansion processing in advance, but it is not limited to this. For example, it may be configured to create a processed document by applying tag expansion processing for the first time in step S302 without applying tag expansion processing in advance to the document content included in the acquired document information. In addition, the document content to which the tag expansion processing is applied does not necessarily have to be acquired from the document table 1013, and a processed document may be acquired by applying tag expansion processing to the patent document (included in the request transmitted from the user terminal 20) input in the input field of the inquiry processing page as the document content. In this disclosure, any method and any timing may be used as long as the configuration is to acquire the processed document created by the tag expansion processing.

[0071] In step S303, the control unit 104 of the server 10 executes a prompt creation step of creating a prompt by including one or a plurality of sub-blocks to which tags are assigned in the tag expansion step in the instruction text received in the instruction text reception step. The control unit 104 of the server 10 generates a prompt for input to the artificial intelligence system 40 by inserting, into the locations of the patent documents of instruction A and instruction B, the patent document specified on the inquiry processing page or a processed document created by performing tag expansion processing on the patent document. In the present disclosure, an example of inserting a processed document into the location of the patent document will be mainly described.

[0072] Note that 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 sub-block tags. For example, the processed documents at the locations of block 1 and block 2 of block A are as follows. The processed document may also be a document formed by combining some or all of the blocks included in the document content.

[0073] 〔Processed Document〕 (0008-1) The problem to be solved is that in the operation of manually scanning and inputting a high-definition drawing, the input position that hinders the operation cannot be visually confirmed. Sub-block 2: (0008-2) This problem becomes particularly prominent when inputting particularly detailed drawings or complex illustrations, etc., and is the cause of a significant reduction in the work efficiency of the user. (0009-1) In a conventional hand scanner, due to the structure of the housing, it was difficult to confirm the exact position during scanning. (0009-2) Therefore, the user has to proceed with the work while guessing the input position, and as a result, there have been many cases where incorrect parts are repeatedly scanned or necessary parts are overlooked.

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

[0075] In step S304, the control unit 104 of the server 10 executes an inquiry transmission step of making an inquiry by sending the prompt created in the inquiry creation step to the artificial intelligence system 40 operated by an external operator. Specifically, the control unit 104 of the server 10 sends the prompt (character string) generated in step S303 to the server 10. The control unit 104 of the server 10 sends the character string (prompt) received from the user terminal 20 to the 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 generate a prompt and directly send the character string (prompt) to the 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 output by inputting the prompt created in the prompt creation step to 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 regarding the answer content for the prompt. The control unit 104 of the server 10 sends the received response to the user terminal 20. Note that the control unit 204 of the user terminal 20 may obtain the response to the transmitted prompt by directly receiving it from the artificial intelligence system 40.

[0077] The answer from the artificial intelligence system 40 includes answers that refer to block tags. For example, in the following example of answer content, they are P_0028 and P_0042. As an example, the case where tag identification information is included (instruction B) has been described, but it is not always necessary to include tag identification information. When the instruction does not include a string referring to the tag identification information, the answer sentence from the artificial intelligence system also does not include the tag identification information.

[0078] 〔Answer content〕 Classification: Classification A Reason: The patent document has descriptions of "···(P_0028)" and "···(P_0042)". Reference paragraphs: P_0028, P_0042

[0079] The control unit 104 of the server 10 stores the received answer content in the answer content item of the record created in step S303 of the support table 1015. Thereby, the prompt created in step S303 and the answer content from the artificial intelligence system 40 for it are stored in association.

[0080] In step S306, the control unit 104 of the server 10 executes an answer presentation step of presenting the answer content to the user for the prompt transmitted in the inquiry transmission step. Specifically, when the control unit 204 of the user terminal 20 receives the response, it displays and presents each of the prompt and the answer content included in the response to the prompt on the display 2081 of the user terminal 20. Thereby, the user can visually confirm the answer from the artificial intelligence system 40 for the instruction 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 obtained in the answer acquisition step. Further, the control unit 104 of the server 10 or the control unit 204 of the user terminal 20 may execute a process of excluding tag identification information (the character string "P_" in the example of the answer content) from the received answer content. For example, the tag identification information can be excluded from the answer content by replacement using a regular expression or the like. The answer content with the tag identification information excluded is shown below. [Answer Content] Classification: Classification A Reason: The patent document has descriptions such as "···(0028)" and "···(0042)". Reference Paragraphs: 0028, 0042 By excluding the tag identification information from the answer output from the artificial intelligence system 40, an answer with higher readability for the user can be output.

[0082] In step S104, when the control unit 104 of the server 10 assigns a unique key, hash character string, random character string, etc. to the sub-block, it refers to a database (not shown) or the like to restore the character string to a paragraph number or a heading sentence. For example, "HASH1" in the case of sub-block B1 is replaced with "Problems to be Solved by the Invention", and the heading sentence is restored.

[0083] In addition, the control unit 104 of the server 10 may exclude redundant information of the sub-block index (numbers, alphabets, etc. for distinguishing sub-blocks in the block) from the answer content.

[0084] The effects of the present invention will be described. By executing the tag expansion step S104 in the tag expansion process of the present invention, sub-block tags inheriting the block tags are assigned to each sub-block included in the block. Although the artificial intelligence system has advanced language analysis capabilities, when a document contains a large number of sentences in a single paragraph or block such as a section, it may not be able to appropriately extract paragraph numbers or headings (for example, the extraction of paragraph numbers or headings may be ignored). Even in such cases, by applying the tag expansion process according to the present disclosure to the document content, more suitable answer content that refers to paragraph numbers or headings can be obtained from the artificial intelligence system.

[0085] <Basic Hardware Configuration of Computer> FIG. 10 is a block diagram showing the basic hardware configuration of computer 90. Computer 90 includes at least a processor 901, a main memory device 902, an auxiliary storage device 903, and a communication IF 991 (interface). These are electrically connected to each other by a communication bus 921.

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

[0087] The main memory device 902 is for temporarily storing a program and data processed by the program, etc. For example, it is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0088] The auxiliary storage device 903 is a storage device for storing data and programs. For example, it is a flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, semiconductor memory, etc.

[0089] 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 various mobile communication systems such as the Internet, LAN, wireless base stations, etc. For example, the network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks (e.g., Wi-Fi (registered trademark)) that can be connected to the Internet by a predetermined access point. When connecting wirelessly, communication protocols such as Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), etc. are included. When connecting by wire, the network also includes those directly connected by a USB (Universal Serial Bus) cable, etc.

[0090] Note that all or part of each hardware configuration can be distributed and provided to a plurality of computers 90, and the computers 90 can be virtually realized by connecting them to each other via a network. In this way, the computer 90 is a concept that includes not only a single housing or a computer 90 housed in a case, but also a virtualized computer system.

[0091] <Basic Functional Configuration of Computer 90> The functional configuration of the computer realized by the basic hardware configuration (Figure 10) of the computer 90 will be described. The computer includes at least functional units of a control unit, a storage unit, and a communication unit.

[0092] Note that the functional units included in the computer 90 can also be realized by distributing all or part of each functional unit to a plurality of computers 90 interconnected by 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 and expanding them in the main storage device 902, and executing processing according to the programs. The control unit can realize functional units that perform various information processes according to the type of program. Thereby, the computer is realized as an information processing device that performs information processing.

[0094] The functions realized by the components described in this specification may be implemented in circuitry or processing circuitry including a general-purpose processor, a specific-purpose processor, an integrated circuit, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), a conventional circuit, and / or a combination thereof, which are programmed to realize the described functions. A processor includes transistors and other circuits and is regarded as circuitry or processing circuitry. The processor may be a programmed processor that executes a program stored in a memory. In this specification, circuitry, unit, and means are hardware programmed to realize the described functions or hardware that executes them. The hardware may be any hardware disclosed in this specification or any hardware known to be programmed or execute to realize the described functions. When the hardware is a processor regarded as the circuitry type, the circuitry, means, or unit is a combination of hardware and software used to configure the hardware and / or the processor.

[0095] The storage unit is realized by the main storage device 902 and the auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Also, the processor 901 can secure a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 according to a program. Further, the control unit can cause the processor 901 to execute addition, update, and deletion processing of the data stored in the storage unit according to various programs.

[0096] The database refers to a relational database and is for managing by associating with each other a table in a tabular form structurally defined by rows and columns, and a data set called a master. In a database, a table is called a table, a master, a column of a table is called a column, and a row of a table is called a record. In a relational database, the relationship between tables and masters can be set and associated. Normally, a column serving as a primary key for uniquely identifying a record is set for each table and each master, but setting a primary key for a column is not essential. The control unit can cause the processor 901 to execute addition, deletion, and update of records in a specific table and master stored in the storage unit according to various programs. Also, by storing data, various programs, and various databases in the storage unit, the information processing apparatus and the information processing system according to the present disclosure can be regarded as being manufactured.

[0097] Note that the database and the master in the present disclosure may include any data structure (such as a list, a dictionary, an associative array, an object, etc.) in which information is structurally defined. The data structure shall also include data that can be regarded as a data structure by combining data with functions, classes, methods, etc. described in any programming language.

[0098] The communication unit is realized by the communication IF991. 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 it to the control unit. The control unit can cause the processor 901 to execute information processing on the received information according to various programs. Also, the communication unit can transmit the information output from the control unit to other computers 90.

[0099] <Supplementary Note> The matters described in each of the above embodiments are appended below.

[0100] (Supplementary Note 1) A program for causing a computer including a processor and a storage unit to execute, the processor performing a document acquisition step (S101) of acquiring a document related to a patent, dividing the document acquired in the document acquisition step into one or more blocks, and specifying one or more block tags associated with each of the blocks, a block division step (S102), dividing at least a part of the one or more blocks divided in the block division step into one or more sub-blocks, a sub-block division step (S103), and a tag expansion step (S104) of assigning a tag corresponding to the block tag of the block from which the sub-block is divided to at least a part of the one or more sub-blocks divided in the sub-block division step. Thereby, a document (processed document) for creating a prompt that can obtain a more suitable answer can be created. Also, by inputting a prompt including the processed document into an artificial intelligence system, a more suitable answer can be output to the artificial intelligence system.

[0101] (Supplementary Note 2) The block division step (S102) is a step of dividing a patent-related document into one or more blocks starting from a paragraph number or a heading sentence, and specifying one or more paragraph numbers or heading sentences associated with each of the blocks, which is the program described in Appendix 1. Thereby, a patent document (processed document) for creating a prompt for obtaining a more suitable answer can be created. Further, by inputting a prompt including the processed document into an artificial intelligence system, a more suitable answer can be output from the artificial intelligence system.

[0102] (Appendix 3) The sub-block expansion step (S103) is a step of dividing a block starting from a paragraph number or a heading sentence in a patent-related document into sub-blocks related to one or more sentences, and the tag expansion step (S104) is a step of assigning tags corresponding to the paragraph number or the heading sentence to at least a part of the one or more sentences divided in the sub-block division step, which is the program described in Appendix 2. Thereby, a patent document (processed document) for creating a prompt for outputting a more suitable answer can be created. Further, by inputting a prompt including the processed document into an artificial intelligence system, a more suitable answer can be output from the artificial intelligence system.

[0103] (Appendix 4) An instruction receiving step (S301) in which a processor receives an instruction sentence including an instruction to refer to the 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 to which the tag was assigned in the tag expansion step in the instruction sentence received in the instruction receiving step, which is the program described in any one of Appendices 1 to 3. Thereby, by inputting a prompt including an instruction to refer to a tag from an artificial intelligence system into the artificial intelligence system, an answer referring to the tag can be output from the artificial intelligence system. For example, when the instruction includes an instruction to extract terms or words from a patent document, the artificial intelligence system can be made to output an answer including tags for identifying the locations where the terms or words are extracted. In the present disclosure, by also assigning tags to sub-blocks, it is possible to more accurately output an answer referring to the tags to the artificial intelligence system.

[0104] (Appendix 5) The tag expansion step (S104) is a program described in any one of Appendices 1 to 4, which is a step of assigning tags including tag identification information to sub-blocks. Thereby, the artificial intelligence system can input a document (processed document) in a manner that makes it easier to identify (recognize) the tags. It is possible to output a more suitable answer referring to the tags to the artificial intelligence system. In the present disclosure, by including tag identification information in the tags, it is possible to more accurately output an answer referring to the tags to the artificial intelligence system.

[0105] (Appendix 6) The program described in Appendix 5, in which the processor executes an instruction receiving step (S301) of receiving an instruction statement including an instruction to refer to tag identification information, and a prompt creating step (S303) of creating a prompt by including one or more sub-blocks to which tags including tag identification information are assigned in the instruction statement received in the instruction receiving step. Thereby, the artificial intelligence system can input a document (processed document) in a manner that makes it easier to identify (recognize) the tags. It is possible to output a more suitable answer referring to the tags to the artificial intelligence system. In the present disclosure, by including tag identification information in the tags, it is possible to more accurately output an answer referring to the tags to the artificial intelligence system.

[0106] (Appendix 7) The program according to Supplementary Note 6, wherein the processor executes an answer acquisition step (S305) of acquiring an answer output by inputting the prompt created in the prompt creation step to the artificial intelligence system, and an identification exclusion step (S306) of excluding tag identification information from the answer acquired in the answer acquisition step. By excluding the tag identification information from the answer output from the artificial intelligence system, it is possible to output an answer with higher readability for the user.

[0107] (Supplementary Note 8) The tag expansion step (S104) is a step of assigning a tag corresponding to the block tag of the block from which the sub-block is divided to all of one or more sub-blocks, and is a program according to any one of Supplementary Notes 1 to 7. Thereby, it is possible to create a document (processed document) for creating a prompt from which a more suitable answer can be obtained.

[0108] (Supplementary Note 9) The tag expansion step (S104) is a step of inserting a block tag at the head, the tail, or between the head and the tail of the sub-block, and is a program according to any one of Supplementary Notes 1 to 8. Thereby, it is possible to create a document (processed document) for creating a prompt from which a more suitable answer can be obtained.

[0109] (Supplementary Note 10) A method executed by a computer including a processor and a memory, wherein the processor executes all steps executed in the invention according to any one of Supplementary Notes 1 to 9. Thereby, it is possible to create a document (processed document) for creating a prompt from which a more suitable answer can be obtained.

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

[0111] (Appendix 12) A system comprising means for performing all the steps executed 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 can obtain a more suitable answer.

Description of Signs

[0112] 1 System, 10 Server, 101 Storage Unit, 104 Control Unit, 106 Input Device, 108 Output Device, 20 User Terminal, 201 Storage Unit, 204 Control Unit, 206 Input Device, 208 Output Device, 40 Artificial Intelligence System, 401 Storage 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 program comprising: A document acquisition step of acquiring documents 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 block tags corresponding to one or more paragraph numbers or headings 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 expansion step of assigning a tag identical to a block tag of an original block from which the subblock was divided to at least a part of the one or more subblocks divided in the subblock division step; an instruction statement receiving step of receiving an instruction statement including an instruction for referencing 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; A program that executes the following.

2. The sub-block dividing step is a step of dividing a block beginning with a paragraph number or a heading sentence into sub-blocks spanning one or more sentences. The program according to claim 1.

3. A program to be executed by a computer having a processor and a storage unit, the program comprising: A document acquisition step of acquiring documents 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 block tags corresponding to one or more paragraph numbers or headings associated with each of the blocks; a removing step of removing character strings related to paragraph numbers or headings from the one or more divided blocks; an assignment step of assigning the one or more identified block tags to each of the one or more divided 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; an instruction statement receiving step of receiving an instruction statement including an instruction for referencing a block tag; a prompt creating step of creating a prompt by including the one or more blocks divided in the block dividing step in the instruction statement received in the instruction statement receiving step; A program that executes the following.

4. The block division step includes a step of dividing the patent document into one or more blocks beginning with a paragraph number or a heading sentence, and identifying a block tag corresponding to one or more paragraph numbers or heading sentences associated with each of the blocks; the sub-block dividing step is a step of dividing a block beginning with a paragraph number or a heading sentence into sub-blocks each spanning one or more sentences; The tag expansion step is a step of assigning a tag to at least a part of one or more sentences divided in the subblock division step, the tag corresponding to a paragraph number or a heading sentence associated with the block from which the subblock was divided. The program according to claim 3.

5. 4. The program according to claim 1, wherein the tag development step is a step of adding a tag including tag identification information to the subblock.

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

7. 4. The program according to claim 3, wherein the assigning step is a step of assigning a block tag including tag identification information.

8. the instruction statement receiving step is a step of receiving an instruction statement including an instruction to refer to the tag identification information, the prompt creating step is a step of creating a prompt by including, in the instruction statement received in the instruction statement receiving step, one or more blocks to which the block tag including the tag identification information is added in the adding step; The program according to claim 7.

9. The processor, an answer acquisition step of acquiring an answer to be output by inputting the prompt created in the prompt creation step to an artificial intelligence system; an identification / exclusion step of excluding tag identification information from the answer acquired in the answer acquisition step; Execute the The program according to claim 6.

10. The processor, an answer acquisition step of acquiring an answer to be output by inputting the prompt created in the prompt creation step to an artificial intelligence system; an identification / exclusion step of excluding tag identification information from the answer acquired in the answer acquisition step; Execute the The program according to claim 8.

11. 2. The program according to claim 1, wherein the tag expansion step is a step of inserting the tag at the beginning, end, or between the beginning and end of a subblock.

12. A computer implemented method comprising a processor and a memory, the method causing the processor to carry out all of the steps performed in the invention according to claim 1 or 2.

13. 3. An information processing apparatus comprising a control unit and a storage unit, the control unit executing all steps executed in the invention according to claim 1 or 2.

14. A system comprising means for executing all the steps performed in the invention according to claim 1 or 2.

15. A computer implemented method comprising a processor and a memory, the processor performing all of the steps performed in the invention according to claim 3.

16. 4. An information processing apparatus comprising a control unit and a storage unit, the control unit executing all the steps executed in the invention according to claim 3.

17. A system comprising means for executing all the steps performed in the invention according to claim 3.

Images