Information processing systems, information processing methods

Abstract

To provide a novel information processing system that is superior in convenience, usefulness, or reliability. [Solution] This information processing system consists of three components. Component 1 receives identification information, transmits it to component 3, and provides annotated documents. Component 2 extracts special technical features using a large-scale language model and generates annotated documents. Component 3 receives and shares identification information and special technical features, and creates and shares tables. Component 3 has two subcomponents. Subcomponent 1 manages patent application documents and examination records using a database and management system. Subcomponent 2 creates instructional statements and extracts special technical features and generates annotated documents.

Description

Technical Field

[0001] One aspect of the present invention relates to an information processing system, an information processing method, or a semiconductor device.

[0002] Note that one aspect of the present invention is not limited to the above technical field. The technical field of one aspect of the invention disclosed in this specification or the like relates to an article, a method, or a manufacturing method. Or, one aspect of the present invention relates to a process, a machine, a manufacture, or a composition of matter. Therefore, more specifically, examples of the technical field of one aspect of the present invention disclosed in this specification include an information processing device, a semiconductor device, a storage device, a driving method thereof, or a manufacturing method thereof.

Background Art

[0003] In recent years, the development of language models using neural networks has been actively carried out, and particularly large language models (LLMs) have attracted attention. A large language model is a natural language processing model trained using a large amount of data. A dialogue model that answers, for example, user instructions can be realized by a large language model. In Non-Patent Document 1, GPT-4 (Generative Pre-trained Transformer 4) (registered trademark) is disclosed as a large language model, and ChatGPT is disclosed as a dialogue model.

[0004] By using a large language model, the capabilities of natural language processing models have been significantly improved. On the other hand, due to the enlargement of language models, it is difficult to incorporate and operate a language model by oneself in terms of facilities and costs. Therefore, using an external service that provides a language model has become one form of using a language model.

Prior Art Documents

Non-Patent Documents

[0005] [Non-Patent Document 1] Summary of ChatGPT / GPT-4 Research and Perspective Towards the Future of Large Language Models, Yiheng Liu et al. (Submitted on 4 Apr 2023, [online], Internet)<URL:https: / / arxiv.org / abs / 2304.01852> [Overview of the project] [Problems that the invention aims to solve]

[0006] One aspect of the present invention aims to provide a novel information processing system that is superior in convenience, usefulness, or reliability. Alternatively, it aims to provide a novel information processing method that is superior in convenience, usefulness, or reliability. Alternatively, it aims to provide a novel information processing system, a novel information processing method, or a novel semiconductor device.

[0007] Furthermore, the description of these problems does not preclude the existence of other problems. Moreover, one aspect of the present invention does not need to solve all of these problems. Other problems will naturally become apparent from the description in the specification, drawings, and claims, and it is possible to extract other problems from the description in the specification, drawings, and claims. [Means for solving the problem]

[0008] (1) One aspect of the present invention is an information processing system having a first component, a second component, and a third component.

[0009] The first component includes the function of receiving identification information and transmitting it to the third component, and the function of receiving and providing annotated documents. The identification information includes information that identifies a single patent application.

[0010] The second component includes the function of receiving a first instruction and sending special technical features to the third component, the function of receiving a second instruction and sending an annotated document to the third component, and the function of performing processing using a large-scale language model. The large-scale language model includes the function of extracting special technical features according to the first instruction and the function of generating an annotated document according to the second instruction.

[0011] The third component includes functions for receiving and sharing identification information and special technical features within the third component, creating tables and sharing them within the third component, creating first and second directives and sending them to the second component, and receiving annotated documents and sending them to the first component.

[0012] Furthermore, the third component comprises the first subcomponent and the second subcomponent.

[0013] The first subcomponent includes a function for processing using a database and a management system. The database contains at least one patent application document and at least one examination record, the examination record including a notice of reasons for rejection and a statement of opinion. The management system includes a function for creating tables from the database in response to queries. The tables include the patent application document, the patented claims relating to the patent application document, and the examination record relating to the patented claims. The query includes identification information, and the query requires that the patent application identified by the identification information is the same as the original application.

[0014] The second subcomponent provides the functionality to generate the first and second directives. The first directive includes the first instruction and a table, the first instruction including a procedure for extracting special technical features relating to the patented claims from the table. The second directive also includes the second instruction, special technical features, and a patent application document, the second instruction including a procedure for adding embellishments or annotations to the description of the special technical features contained in the patent application document to generate an annotated document.

[0015] This allows for the collection of patent application documents from a database that are identical to the original application, using identification information. Furthermore, it is possible to collect patent application documents, patented claims related to those patent applications, and examination records related to those patented claims, and create a table. From this table, special technical features related to the patented claims can be extracted. Additionally, descriptions of special technical features included in the patent application documents can be embellished or annotated. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0016] (2) Another aspect of the present invention is the above-described information processing system, wherein the first component has the function of receiving range information and transmitting it to the third component, and the function of receiving and providing an abstract. The range information specifies a part of the patent application document.

[0017] The second component has the function of receiving a third instruction and sending a summary to the third component. The large-scale language model has the function of generating a summary according to the third instruction, and the third component has the function of receiving and sharing range information within the third component, sending the third instruction to the second component, and receiving the summary and sending it to the first component.

[0018] The third component comprises a third subcomponent. The third subcomponent has the function of extracting portions from the patent application documents based on scope information. The second subcomponent also has the function of creating a third instruction. The third instruction includes a third instruction and a portion, the third instruction including a procedure for generating an abstract from the portion.

[0019] This allows for the extraction of portions from patent application documents using scope information. Furthermore, an abstract can be generated from the extracted portions. For example, an abstract can be generated from portions that do not contain embellishments or annotations. Additionally, an abstract can be generated from portions other than those describing special technical features related to the patented claims. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0020] (3) Another aspect of the present invention is the above-described information processing system in which the first component has the function of receiving a revert command and providing an annotated document.

[0021] This allows, for example, users of the information processing system to examine the summary and correct the scope information. As a result, it is possible to provide a novel information processing system that is superior in convenience, usefulness, or reliability.

[0022] (4) Another aspect of the present invention is an information processing system in which the first component has the function of receiving acceptance information and transmitting it to the third component, and the function of receiving and providing a draft claim.

[0023] The second component has the function of receiving the fourth instruction and sending the claim draft to the third component. The large-scale language model has the function of generating the claim draft according to the fourth instruction.

[0024] The third component has a function of receiving acceptance information and sharing it within the third component, a function of sending a fourth instruction to the second component, and a function of receiving a claim draft and sending it to the first component. Note that the second sub-component has a function of creating a fourth instruction. The fourth instruction includes a fourth instruction, special technical features, descriptions related to the special technical features, and a part thereof. The fourth instruction includes a procedure for generating a claim draft from the special technical features, descriptions related to the special technical features, and a part thereof.

[0025] Thereby, a claim draft can be generated using the special technical features related to the patented claims, descriptions related to the special technical features, and a part thereof (for example, a part extracted from a part not provided with decorations or annotations). As a result, a novel information processing system excellent in convenience, usefulness, or reliability can be provided.

[0026] (5) Further, one aspect of the present invention is the above information processing system in which the first component has a function of receiving requirements and sending them to the third component.

[0027] The second component has a function of receiving a fifth instruction and sending a claim draft to the third component. The large language model has a function of generating a claim draft according to the fifth instruction.

[0028] The third component has a function of receiving requirements and sharing them within the third component, and a function of sending a fifth instruction to the second component. Note that the second sub-component has a function of creating a fifth instruction. The fifth instruction includes a fifth instruction, requirements, special technical features, descriptions related to the special technical features, and a part thereof. The fifth instruction includes a procedure for generating a claim draft from the requirements, special technical features, descriptions related to the special technical features, and a part thereof.

[0029] This allows, for example, users of the information processing system to examine the draft claims and add requirements. Furthermore, they can generate draft claims by adding requirements to specific technical features related to the patented claims, descriptions of those specific technical features, and specific sections (e.g., sections excerpted from parts without embellishments or annotations). As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0030] (6) Another aspect of the present invention is the above-mentioned information processing system in which the first component is a display device.

[0031] The display device has the function of displaying annotated documents. Descriptions relating to special technical features contained in the annotated documents are displayed with decoration or annotations using at least one of the following: highlighting, bolding, italics, and underlining.

[0032] This allows, for example, users of the information processing system to easily identify descriptions related to special technical features. As a result, it becomes possible to provide a novel information processing system that is superior in convenience, usefulness, or reliability.

[0033] (7) Another aspect of the present invention is an information processing system comprising a display device and an input device as the first component.

[0034] The display device includes the function of displaying annotated documents and a pointer. Descriptions of special technical features contained in the annotated documents are displayed with decoration or annotations using at least one of the following: highlighting, bolding, italics, and underlining. The input device also includes the function of moving the pointer and the function of inputting range information.

[0035] This allows, for example, users of the information processing system to identify specific portions to extract from patent application documents. As a result, it becomes possible to provide a novel information processing system that is superior in terms of convenience, usefulness, or reliability.

[0036] (8) Another aspect of the present invention is the above-described information processing system in which the first component, the second component, and the third component each comprise a computing device and a communication device, and each communication device is connected to the others via a network.

[0037] (9) Another aspect of the present invention is an information processing method having a first phase. The first phase comprises a first to a twelfth step.

[0038] In the first step of the first phase, the first component receives identification information and transmits it to the second component.

[0039] In the second step of the first phase, the second component receives and shares identification information within the second component. The second component comprises a first subcomponent and a second subcomponent. The first subcomponent has the function of performing processing using a database and a management system. The database contains patent application documents and examination records, and the examination records include notices of reasons for rejection and written opinions.

[0040] In the third step of the first phase, the first subcomponent uses a management system to create tables from the database in response to queries and shares them within the second component. The tables include patent application documents, patented claims related to the patent application documents, and examination records related to the patented claims. Queries include identification information and require the patent application documents to be the same as the original application identified by the identification information.

[0041] In the fourth step of the first phase, the second subcomponent creates a first instruction and sends it to the third component. The first instruction includes a first instruction and a table, the first instruction including a procedure to extract specific technical features relating to the patented claims from the table.

[0042] In the fifth step of the first phase, the third component receives the first instruction and uses a large-scale language model to extract special technical features.

[0043] In the sixth step of the first phase, the third component transmits special technical characteristics to the second component.

[0044] In the seventh step of the first phase, the second component accepts and shares special technical features within the second component.

[0045] In the eighth step of the first phase, the second subcomponent prepares the second instruction document and sends it to the third component. The second instruction document includes the second instruction, special technical features, and patent application documents, and the second instruction includes a procedure for generating an annotated document by adding embellishments or annotations to the description of special technical features included in the patent application documents.

[0046] In the ninth step of the first phase, the third component receives the second instruction and generates an annotated document using a large-scale language model.

[0047] In the tenth step of the first phase, the third component sends the annotated document to the second component.

[0048] In the 11th step of the first phase, the second component receives the annotated document and sends it to the first component.

[0049] In the twelfth step of the first phase, the first component receives and provides annotated documents.

[0050] This allows for the collection of patent application documents from a database that are identical to the original application, using identification information. Furthermore, it is possible to collect patent application documents, patented claims related to those patent applications, and examination records related to those patented claims, and create a table. From this table, special technical features related to the patented claims can be extracted. Additionally, descriptions of special technical features included in the patent application documents can be embellished or annotated. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0051] (10) Another aspect of the present invention is an information processing method having a first phase and a second phase. The second phase follows the first phase, and the second phase comprises a first to tenth step.

[0052] In the first step of the second phase, the first component receives scope information and transmits it to the second component. The scope information identifies a portion of the patent application documents.

[0053] In the second step of the second phase, the second component receives and shares range information within the second component. The second component also comprises a third subcomponent.

[0054] In the third step of the second phase, the third subcomponent extracts portions from the patent application documents based on scope information.

[0055] In the fourth step of the second phase, the second subcomponent creates a third instruction and sends it to the third component. The third instruction includes the third instruction and a portion thereof, and the third instruction includes a procedure for generating a summary from the portion thereof.

[0056] In the fifth step of the second phase, the third component receives the third instruction and generates a summary using a large-scale language model.

[0057] In the sixth step of the second phase, the third component sends the summary to the second component.

[0058] In the seventh step of the second phase, the second component receives the summary and sends it to the first component.

[0059] In the eighth step of the second phase, the first component receives and provides the summary.

[0060] In the ninth step of the second phase, the first component receives the first acceptance information or a return command and sends it to the second component.

[0061] In the tenth step of the second phase, the second component terminates the second phase when it receives the first acceptance information, and proceeds to the first step of the second phase when it receives a return command.

[0062] This allows for the extraction of portions from patent application documents using scope information. Furthermore, an abstract can be generated from the extracted portions. For example, an abstract can be generated from portions that do not contain embellishments or annotations. Additionally, an abstract can be generated from portions other than those describing special technical features related to the patented claims. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0063] (11) Another aspect of the present invention is an information processing method having a first to third phase. The third phase follows the second phase, and the third phase comprises the first to ninth steps.

[0064] In the first step of the third phase, the second subcomponent prepares the fourth instruction and sends it to the third component. The fourth instruction includes the fourth instruction, special technical features, a description of the special technical features and a portion thereof, and the fourth instruction includes a procedure for generating a draft claim from the special technical features, a description of the special technical features and a portion thereof.

[0065] In the second step of the third phase, the third component receives the fourth or fifth directive and generates a claim draft using a large-scale language model.

[0066] In the third step of the third phase, the third component submits the claim draft to the second component.

[0067] In the fourth step of the third phase, the second component receives the draft claim and sends it to the first component.

[0068] In the fifth step of the third phase, the first component receives and provides the draft claims.

[0069] In the sixth step of the third phase, the first component receives the second consent information or requirements and transmits them to the second component.

[0070] In the seventh step of the third phase, the second component terminates the third phase upon receiving the second acceptance information, and the second subcomponent prepares the fifth instruction document and sends it to the third component upon receiving the requirements. The fifth instruction document includes the fifth instruction, requirements, special technical features and parts, and the fifth instruction includes a procedure for generating a claim draft from the requirements, special technical features and parts.

[0071] In the eighth step of the third phase, the third component receives the fifth instruction and generates a claim draft using a large-scale language model.

[0072] In the ninth step of the third phase, the third component submits the claim draft to the second component and proceeds to the fourth step of the third phase.

[0073] This allows for the generation of draft claims using specific technical features and parts related to the patented claims. Furthermore, for example, users of the information processing system can examine the draft claims and add requirements. They can also generate draft claims by adding requirements to specific technical features and parts related to the patented claims. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided. [Effects of the Invention]

[0074] One aspect of the present invention can provide a novel information processing system that is superior in convenience, usefulness, or reliability. Alternatively, it can provide a novel information processing method that is superior in convenience, usefulness, or reliability. Alternatively, it can provide a novel information processing system, a novel information processing method, or a novel semiconductor device.

[0075] Furthermore, the description of these effects does not preclude the existence of other effects. Moreover, one aspect of the present invention does not necessarily have to possess all of these effects. Other effects will naturally become apparent from the description in the specification, drawings, and claims, and it is possible to extract other effects from the description in the specification, drawings, and claims. [Brief explanation of the drawing]

[0076] [Figure 1] Figure 1 is a diagram illustrating the configuration of an information processing system according to an embodiment. [Figure 2] Figure 2 is a diagram illustrating the configuration of components used in the information processing system according to the embodiment. [Figure 3] Figures 3(A) and 3(B) illustrate the configuration of components used in the information processing system according to the embodiment. [Figure 4] Figures 4(A) and 4(B) illustrate the structure of instruction statements used in the information processing system according to the embodiment. [Figure 5] Figure 5(A) is a diagram illustrating the configuration of an annotated document used in the information processing system according to the embodiment, and Figure 5(B) is a diagram illustrating the configuration of a display device that can be used in the information processing system according to the embodiment. [Figure 6] Figure 6 is a diagram illustrating the configuration of an information processing system according to an embodiment. [Figure 7] Figure 7 is a diagram illustrating the configuration of components used in the information processing system according to the embodiment. [Figure 8] Figure 8 is a diagram illustrating the structure of an instruction statement used in an information processing system according to an embodiment. [Figure 9] Figure 9(A) is a diagram illustrating the configuration of a display device used in the information processing system according to the embodiment, and Figure 9(B) is a diagram illustrating the configuration of a display device and an input device that can be used in the information processing system according to the embodiment. [Figure 10]Figure 10 is a diagram illustrating the configuration of an information processing system according to an embodiment. [Figure 11] Figure 11 is a diagram illustrating the configuration of components used in an information processing system according to an embodiment. [Figure 12] Figures 12(A) and 12(B) illustrate the structure of instruction statements used in the information processing system according to the embodiment. [Figure 13] Figure 13 is a diagram illustrating the configuration of an information processing device used in an information processing system according to an embodiment. [Figure 14] Figure 14 is a diagram illustrating an information processing method according to an embodiment. [Figure 15] Figure 15 is a diagram illustrating an information processing method according to an embodiment. [Figure 16] Figure 16 is a diagram illustrating an information processing method according to an embodiment. [Figure 17] Figure 17 is a diagram illustrating an information processing method according to an embodiment. [Figure 18] Figure 18 is a diagram illustrating an information processing method according to an embodiment. [Figure 19] Figure 19 is a diagram illustrating an information processing method according to an embodiment. [Modes for carrying out the invention]

[0077] One aspect of the present invention is an information processing system having a first component, a second component, and a third component.

[0078] The first component includes the function of receiving identification information and transmitting it to the third component, and the function of receiving and providing annotated documents. The identification information includes information that identifies a single patent application.

[0079] The second component includes the function of receiving the first instruction and sending special technical features to the third component, the function of receiving the second instruction and sending an annotated document to the third component, and the function of performing processing using a large-scale language model. The large-scale language model includes the function of extracting special technical features according to the first instruction and the function of generating an annotated document according to the second instruction.

[0080] The third component includes functions for receiving and sharing identification information and special technical features within the third component, creating and sharing tables within the third component, creating first and second instructions and sending them to the second component, and receiving annotated documents and sending them to the first component. The third component also includes a first subcomponent and a second subcomponent.

[0081] The first subcomponent includes the functionality to perform processing using a database and a management system. The database contains patent application documents and examination records, the examination records including notices of reasons for rejection and written opinions. The management system includes the functionality to create tables from the database in response to queries. The tables include patent application documents, patented claims related to the patent application documents, and examination records related to the patented claims. Queries include identification information. Furthermore, queries require that the patent application identified by the identification information is the same as the original application.

[0082] The second subcomponent provides the functionality to generate the first and second directives. The first directive includes a first instruction and a table, the first instruction including a procedure for extracting special technical features relating to the patented claims from the table. The second directive includes a second instruction, special technical features, and a patent application document, the second instruction including a procedure for adding embellishments or annotations to the description relating to the special technical features contained in the patent application document to generate an annotated document.

[0083] This allows for the collection of patent application documents from a database that are identical to the original application, using identification information. Furthermore, it is possible to collect patent application documents, patented claims related to those patent applications, and examination records related to those patented claims, and create a table. From this table, special technical features related to the patented claims can be extracted. Additionally, descriptions of special technical features included in the patent application documents can be embellished or annotated. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0084] Embodiments will be described in detail with reference to the drawings. However, it will be readily apparent to those skilled in the art that the present invention is not limited to the following description, and that its form and details can be modified in various ways without departing from the spirit and scope of the present invention. Accordingly, the present invention is not to be interpreted as being limited to the contents of the embodiments shown below. In the configuration of the invention described below, the same reference numerals are used in common across different drawings for the same parts or parts having similar functions, and repeated descriptions are omitted.

[0085] In this specification, ordinal numbers such as "first," "second," etc., are used to avoid confusion of components and do not limit the number of components or the order of components (e.g., steps, process order, or layering order). Furthermore, even if a term in this specification does not have an ordinal number, an ordinal number may be added in the claims to avoid confusion of components. Even if a term in this specification has an ordinal number, a different ordinal number may be added in the claims. Even if a term in this specification has an ordinal number, an ordinal number may be omitted in the claims.

[0086] In the drawings attached to this specification, components are classified by function and shown as independent blocks in block diagrams. However, in reality, it is difficult to completely separate components by function, and a single component may be involved in multiple functions.

[0087] (Embodiment 1) In this embodiment, an information processing system according to one aspect of the present invention will be described with reference to Figures 1 to 13.

[0088] Figure 1 is a diagram illustrating the configuration of an information processing system according to one embodiment of the present invention.

[0089] Figure 2 is a diagram illustrating the configuration of components used in an information processing system according to one embodiment of the present invention.

[0090] Figure 3(A) is a diagram illustrating the configuration of a database used in an information processing system according to one embodiment of the present invention, and Figure 3(B) is a diagram illustrating the configuration of a table used in an information processing system according to one embodiment of the present invention.

[0091] Figures 4(A) and 4(B) illustrate the structure of instruction statements transmitted and received within an information processing system according to one embodiment of the present invention.

[0092] Figure 5(A) is a diagram illustrating the structure of an annotated document provided by an information processing system according to one embodiment of the present invention, and Figure 5(B) is a diagram illustrating the structure of a display device that can be used in an information processing system according to one embodiment of the present invention.

[0093] Figure 6 is a diagram illustrating the configuration of an information processing system according to one embodiment of the present invention.

[0094] Figure 7 is a diagram illustrating the configuration of components used in an information processing system according to one embodiment of the present invention.

[0095] Figure 8 illustrates the structure of instruction statements transmitted and received within an information processing system according to one embodiment of the present invention.

[0096] Figure 9(A) is a diagram illustrating the configuration of a user interface provided by an information processing system according to one embodiment of the present invention, and Figure 9(B) is a diagram illustrating the configuration of a display device and an input device that can be used in an information processing system according to one embodiment of the present invention.

[0097] Figure 10 is a diagram illustrating the configuration of an information processing system according to one embodiment of the present invention.

[0098] Figure 11 is a diagram illustrating the configuration of components used in an information processing system according to one embodiment of the present invention.

[0099] Figures 12(A) and 12(B) illustrate the structure of instruction statements transmitted and received within an information processing system according to one embodiment of the present invention.

[0100] Figure 13 is a block diagram illustrating the configuration of an information processing device that can be used in an information processing system according to one embodiment of the present invention.

[0101] <Example of an information processing system configuration 1> The information processing system described in this embodiment includes component 110, component 130, and component 120 (see Figure 1).

[0102] Furthermore, the information processing devices that perform the functions of component 110, component 130, and component 120 each include a computing device and a communication device. These communication devices can also be connected to each other, for example, via a network 51, to constitute an information processing system according to one embodiment of the present invention.

[0103] <Component 110 Configuration Example 1> Component 110 includes a function to receive identification information Id and transmit it to component 120, and a function to receive an annotated document AntD and provide it, for example, to a user 99 of the information processing system.

[0104] Furthermore, the identification information ID includes information that identifies a single patent application. For example, an identification number that identifies the applicant, an application number, a reference number, etc., can be used as the identification information ID. This makes it possible to identify a single patent application using a single identification information ID.

[0105] For example, a user 99 of the information processing system inputs identification information Id into component 110. Specifically, the user 99 of the information processing system inputs Id into component 110 using input devices such as a keyboard, mouse, eye-tracking device, or microphone.

[0106] <Component 130 Configuration Example 1> Component 130 has the function of receiving instruction Pt11 and sending special technical feature STF_1 to component 120, and the function of receiving instruction Pt12 and sending annotated document AntD to component 120. It also has the function of performing processing using the large-scale language model LLM.

[0107] 《Example Configuration of a Large-Scale Language Model (LLM) 1》 The large-scale language model LLM has the function of extracting special technical features STF_1 according to instruction Pt11. Furthermore, the large-scale language model LLM has the function of generating annotated documents AntD according to instruction Pt12. In addition, the contribution of the invention to the prior art, for example, a technical feature that clarifies the technical significance of the invention in comparison to the prior art, can be used as the special technical feature STF_1.

[0108] <Component 120 Configuration Example 1> Component 120 has the function of receiving identification information Id and special technical feature STF_1 and sharing them within component 120.

[0109] Furthermore, it includes a function to create a table Tbl and share it within component 120, a function to create instruction statements Pt11 and Pt12 and send them to component 130, and a function to receive annotated document AntD and send it to component 110.

[0110] Component 120 includes subcomponent 120A and subcomponent 120B (see Figure 2).

[0111] 《Example configuration of subcomponent 120A》 Subcomponent 120A has the functionality to perform processing using a database DB and a management system DBMS.

[0112] [Example of database configuration] The database DB comprises region PAD, region ACL, and region RExm (see Figure 3(A)). Region PAD contains the patent application document PAD_1, region ACL contains the patented claims ACL_1, and region RExm contains the examination record RExm_1. Furthermore, the patent application document PAD_1 includes the patented claims ACL_1, and the examination record RExm_1 includes the rejection notice and the statement of opinion.

[0113] [Example configuration of a management system (DBMS)] The management system (DBMS) has the functionality to create a table (Tbl) from the database (DB) in response to query Que1.

[0114] Query Que1 includes the identification information Id, and Query Que1 requests that the patent application specified by the identification information Id be the same as the original application in the patent application document PAD_1. For example, if the patent application specified by the identification information Id is a divisional application, Query Que1 requests all applications that have been divided from the original application of the patent application specified by the identification information Id. Query Que1 can also request applications filed in other countries or territories based on the original application of the patent application specified by the identification information Id. In other words, Query Que1 can request all family applications. Furthermore, the identification information Id can be substituted into pre-prepared template text and used in Query Que1.

[0115] Table Tbl includes the patent application document PAD_1, the patented claims ACL_1 related to the patent application document PAD_1, and the examination record RExm_1 related to the patented claims ACL_1 (see Figure 3(B)). Note that the patent application document PAD_1 specified by identification information Id_1, the patent application document PAD_2 specified by identification information Id_2, and the patent application document PAD_3 specified by identification information Id_3 all originate from the same application.

[0116] 《Example Configuration of Subcomponent 120B》 Subcomponent 120B has the function of creating instruction statement Pt11 and instruction statement Pt12.

[0117] [Example of the structure of instruction sheet Pt11] Instruction Pt11 includes instruction g11() and table Tbl (see Figure 4(A)).

[0118] Instruction g11() includes a procedure for extracting special technical features STF_1 relating to the patented claims ACL_1 from the table Tbl.

[0119] For example, the document in the following paragraph can be used as instruction Pt11.

[0120] "Table: {{ Table Tbl}}" Extract the specific technical features of the approved patent claims from the table.

[0121] [Example of the structure of instruction sheet Pt12] Instruction Pt12 includes instruction g12(), special technical feature STF_1, and patent application document PAD_1 (see Figure 4(B)).

[0122] Instruction g12() includes a procedure for generating an annotated document AntD by adding decorations or annotations to the description TXT_STF1 relating to special technical features contained in the patent application document PAD_1.

[0123] For example, the document in the following paragraph can be used as instruction Pt12.

[0124] "Special technical feature: {{ Special technical feature STF_1}}" Patent Specification: {{ Patent Application Document PAD_1}} In the patent specification, please enclose sections describing special technical features with the following tags: tag: <span class=""stf”"> "

[0125] [Example of AntD configuration for annotated documents] Annotated document AntD includes the patent application document PAD_1 and decorations or annotations (see Figure 5(A)). For example, decorations can be added to the description of special technical features TXT_STF1 and used in the annotated document AntD. Specifically, at least one of the following can be used for text decoration: highlighting, bolding, italics, and underlining. Also, annotations can be added to the description of special technical features TXT_STF1 and used in the annotated document AntD. Specifically, callouts and the like can be used for annotations. Subcomponent 120B can store the description of special technical features TXT_STF1.

[0126] Furthermore, the area for displaying the annotated document AntD can be provided alongside the area for displaying the patent application document PAD_1.

[0127] This allows the system to use an identification information ID to collect patent applications identified by the ID from the database DB, along with the original patent application document PAD_1. Furthermore, it can collect the patent application document PAD_1, the patented claims ACL_1 related to the patent application document PAD_1, and the examination record RExm_1 related to the patented claims ACL_1, and create a table Tbl. From table Tbl, it can extract special technical features STF_1 related to the patented claims ACL_1. Additionally, it can add embellishments or annotations to the description TXT_STF1 related to the special technical features contained in the patent application document PAD_1. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0128] <Component 110 Configuration Example 2> Component 110 includes a display device Dsp (see Figure 5(B)). The display device Dsp has the function of displaying annotated document AntD. Note that the description TXT_STF1 relating to special technical features contained in the annotated document AntD is displayed with decoration or annotations using at least one of the following: highlighting, bolding, italics, and underlining.

[0129] This allows, for example, users of the information processing system to easily identify the description TXT_STF1 relating to special technical features. As a result, it is possible to provide a novel information processing system that is superior in convenience, usefulness, or reliability.

[0130] <Component 110 Configuration Example 3> Component 110 has the function of receiving range information Rng and transmitting it to component 120, and the function of receiving summary Sum and providing it, for example, to a user 99 of the information processing system (see Figure 6). The range information Rng identifies a part of the patent application document PAD_1.

[0131] For example, a user 99 of the information processing system inputs range information Rng into component 110. Specifically, the user 99 of the information processing system inputs the information into component 110 using an input device such as a keyboard, mouse, or eye-tracking device. Alternatively, for example, the user 99 of the information processing system can identify a portion of a section by providing range information Rng to a part that has not been decorated or annotated.

[0132] <Component 130 Configuration Example 2> Component 130 has the function of receiving instruction Pt2 and sending summary Sum to component 120.

[0133] 《Example of a Large-Scale Language Model (LLM) Configuration 2》 The large-scale language model LLM has the functionality to generate a summary (Sum) according to the instruction Pt2.

[0134] <Component 120 Configuration Example 2> Component 120 has the function of receiving range information Rng and sharing it within component 120, the function of sending instruction statement Pt2 to component 130, and the function of receiving summary Sum and sending it to component 110. Component 120 also includes subcomponent 120C (see Figure 7).

[0135] 《Example configuration of subcomponent 120C》 Subcomponent 120C has the function of extracting a portion of Prt from the patent application document PAD_1 based on range information Rng.

[0136] 《Example Configuration of Subcomponent 120B 2》 Subcomponent 120B has the function of creating instruction statement Pt2.

[0137] [Example of the structure of instruction statement Pt2] Instruction Pt2 includes instruction g2() and a part Prt (see Figure 8). Instruction g2() also includes a procedure to generate a summary Sum from the part Prt.

[0138] For example, the document in the following paragraph can be used as instruction statement Pt2.

[0139] ``Text:{{ Part Prt}} Please create a summary of the text.

[0140] This allows for the extraction of a portion of the patent application document PAD_1 using range information Rng. Furthermore, a summary Sum can be generated from the extracted portion of the Prt. Additionally, a summary Sum can be generated from a portion of the Prt extracted from a section without decorative or annotated elements. Furthermore, a summary Sum can be generated from sections other than those describing the special technical features STF_1 related to the patented claims ACL_1. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0141] <Component 110 Configuration Example 4> Component 110 includes a display device Dsp and an input device CID (see Figure 9(B)). The display device Dsp has the function of displaying an annotated document AntD, a summary Sum, and a pointer Pnt (see Figure 9(A)). The description TXT_STF1 relating to special technical features contained in the annotated document AntD is displayed with decoration or annotation using at least one of the following: highlighting, bolding, italics, and underlining. The input device CID has the function of moving the pointer Pnt and inputting range information Rng.

[0142] This allows, for example, users of the information processing system to identify a portion (Prt) to be extracted from the patent application document PAD_1. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0143] <Component 110 Configuration Example 5> Component 110 accepts a return command Und and has the function of providing the annotated document AntD to, for example, a user 99 of the information processing system (see Figure 9(A)).

[0144] For example, user 99 of the information processing system inputs the return command "Und" into component 110. Specifically, user 99 of the information processing system inputs the command into component 110 using an input device CID such as a keyboard, mouse, or eye-tracking device (see Figure 9(B)).

[0145] For example, component 110 can provide an area for entering the return command "Und" and an area for entering acceptance information "Acc2" (see Figure 9(A)).

[0146] This allows, for example, users of the information processing system to examine the summary Sum and correct the range information Rng. As a result, it is possible to provide a novel information processing system that is superior in convenience, usefulness, and reliability.

[0147] <Component 110 Configuration Example 6> Component 110 includes the function of receiving acceptance information Acc2 and transmitting it to component 120, and the function of receiving claim draft DC and providing it, for example, to user 99 of the information processing system (see Figure 10).

[0148] For example, a user 99 of the information processing system inputs consent information Acc2 into component 110. Specifically, the user 99 of the information processing system inputs the information into component 110 using an input device such as a keyboard, mouse, or eye-tracking device.

[0149] <Component 130 Configuration Example 3> Component 130 has the function of receiving instruction Pt31 and sending claim draft DC to component 120.

[0150] 《Example 3 of the configuration of a large-scale language model (LLM)》 The large-scale language model LLM has the function of generating a claim draft DC according to instruction Pt31.

[0151] <Component 120 Configuration Example 3> Component 120 includes the functions of receiving acceptance information Acc2 and sharing it within component 120, sending instruction statement Pt31 to component 130, and receiving claim draft DC and sending it to component 110 (see Figure 10).

[0152] 《Example Configuration of Subcomponent 120B 3》 Subcomponent 120B has the function of creating instruction statement Pt31.

[0153] [Example of the structure of instruction statement Pt31] Instruction Pt31 includes instruction g31(), patented claims ACL_1, special technical features STF_1, description relating to special technical features TXT_STF1, and part Prt (see Figure 12(A)).

[0154] Instruction g31() includes a procedure for generating a draft claim DC from a special technical feature STF_1, a description relating to the special technical feature TXT_STF1, and a portion Prt.

[0155] For example, the document in the following paragraph can be used as instruction Pt31.

[0156] "Allowed Claims: {{ Patented Claims ACL_1}}" Permitted items: {{ Special technical features STF_1}} Supporting section for permitted items: {{ Description of special technical features TXT_STF1}} Description of the additional features: {{ Partial Prt}} Based on the permitted claims, create a new claim focusing on the permitted features and including descriptions of the additional features you wish to add.

[0157] This allows for the generation of a draft claim DC using the special technical features STF_1 relating to the patented claims ACL_1, the description TXT_STF1 relating to the special technical features, and, for example, a portion Prt extracted from the part without embellishments or annotations. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0158] <Component 110 Configuration Example 7> Component 110 has the function of receiving requirements (Req) and sending them to component 120. For example, a user 99 of the information processing system can input requirements (Req) that they believe are missing from the claim draft DC into component 110.

[0159] <Component 130 Configuration Example 4> Component 130 has the function of receiving instruction Pt32 and sending claim draft DC to component 120.

[0160] 《Example of a Large-Scale Language Model (LLM) Configuration 4》 The large-scale language model LLM has the function of generating a claim draft DC according to instruction Pt32.

[0161] <Component 120 Configuration Example 4> Component 120 has the function of receiving requirements (Req) and sharing them within Component 120, and the function of sending instruction statements (Pt32) to Component 130.

[0162] 《Example Configuration of Subcomponent 120B 4》 Subcomponent 120B has the function of creating instruction statement Pt32.

[0163] [Example of the structure of instruction statement Pt32] Instruction Pt32 includes instruction g32(), requirement Req, special technical feature STF_1, description of special technical feature TXT_STF1, and part Prt (see Figure 12(B)).

[0164] Instruction g32() includes a procedure for generating a draft claim DC from requirement Req, special technical feature STF_1, description relating to the special technical feature TXT_STF1, and part Prt.

[0165] For example, the document in the following paragraph can be used as instruction Pt32.

[0166] Claim under consideration: {{ Draft Claim DC}} Permitted items: {{ Special technical features STF_1}} Supporting section for permitted items: {{ Description of special technical features TXT_STF1}} Description of the additional features: {{ Partial Prt}} Comment: {{ Requirements Req}} Please revise the complaint you are currently reviewing, taking your comments into consideration.

[0167] This allows, for example, users of the information processing system to examine the draft claim DC and add requirements Req. Furthermore, they can generate the draft claim DC by adding requirements Req to the special technical features STF_1 related to the patented claims ACL_1, the description TXT_STF1 relating to the special technical features, and, for example, a portion Prt extracted from the part without embellishments or annotations. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0168] <Component 110 Configuration Example 8> Component 110 has the functionality to accept requirements (see Figure 9(A)).

[0169] For example, a user 99 of the information processing system inputs the requirement Req into component 110. Specifically, the user 99 of the information processing system inputs the requirement Req into component 110 using an input device CID such as a keyboard, mouse, or eye-tracking device (see Figure 9(B)).

[0170] For example, component 110 can provide an area for inputting requirements (Req) and an area (Ent) for inputting transmission commands (see Figure 9(A)).

[0171] This allows, for example, users of the information processing system to examine the summary Sum and correct the range information Rng. As a result, it is possible to provide a novel information processing system that is superior in convenience, usefulness, and reliability.

[0172] <Example of an information processing system configuration 2> The information processing system described in this embodiment includes component 110, component 120, and component 130 (see Figure 1).

[0173] For example, an information processing system according to one aspect of the present invention can be configured with an information processing device that performs the functions of component 110, an information processing device that performs the functions of component 120, and an information processing device that performs the functions of component 130. The number of information processing devices constituting the information processing system according to one aspect of the present invention is one or more. Furthermore, for example, an information processing system according to one aspect of the present invention can be configured by connecting multiple information processing devices using a network 51.

[0174] By configuring an information processing system according to one aspect of the present invention using multiple information processing devices, the load related to information processing can be distributed.

[0175] <Example of Information Processing Device Configuration 1> The configuration example 1 of the information processing device described in this embodiment can be used as component 110. The configuration example 1 of the information processing device can also be called a client computer or the like. For example, a desktop computer can be used as component 110.

[0176] Configuration Example 1 of the information processing device can receive data input by a user of an information processing system according to one aspect of the present invention. Furthermore, Configuration Example 1 of the information processing device can provide the user with data output by an information processing system according to one aspect of the present invention.

[0177] In component 110, for example, dedicated application software, a web browser, etc., are operated. Users of an information processing system according to one embodiment of the present invention can access the information processing system through either of these. As a result, they can enjoy services using the information processing system according to one embodiment of the present invention.

[0178] <Example of Information Processing Device Configuration 2> The configuration example 2 of the information processing device described in this embodiment can be used for component 120. For example, a workstation, server computer, supercomputer, etc., can be used for component 120.

[0179] Furthermore, it is preferable that the second example of the information processing device configuration has the functionality of a parallel computer. By using it as a parallel computer, it is possible to perform large-scale calculations necessary for, for example, learning and inference of artificial intelligence (AI).

[0180] Furthermore, the second example of the information processing device configuration can perform processing using a natural language model with AI.

[0181] For example, it is preferable to be able to perform processing using natural language models such as GPT-3®, GPT-3.5, GPT-4®, LaMDA, Llama2, and Llama3.

[0182] <Example of Information Processing Device Configuration 3> For example, the configuration example 3 of the information processing device described in this embodiment can be used for component 130. Note that component 130 is larger in scale and has higher computing power than component 120. For example, a large computer such as a server computer or supercomputer can be used for component 130.

[0183] Furthermore, it is preferable that the information processing device configuration example 3 has the functionality of a parallel computer. By using it as a parallel computer, for example, it can perform large-scale calculations necessary for AI training and inference.

[0184] Furthermore, the third example of the information processing device configuration can perform processing using an AI-based natural language model. In particular, it can execute processing using a general-purpose language model capable of performing various natural language processing tasks.

[0185] For example, processing can be performed using natural language models such as GPT-3(registered trademark), GPT-3.5, GPT-4(registered trademark), LaMDA, Llama2, and Llama3. Processing using GPT-4(registered trademark) is particularly preferable. For instance, being able to perform processing using large-scale language models, which are significantly larger than conventional natural language models, can enable more natural document generation or dialogue.

[0186] Furthermore, those who provide services using an information processing system according to one embodiment of the present invention do not necessarily need to own the configuration example 3 of the information processing device themselves. For example, a service provider can utilize a portion of the services provided by other businesses, etc., using the configuration example 3 of the information processing device.

[0187] <Example of Network 51 Configuration> A network 51 that can be used in an information processing system according to one embodiment of the present invention can connect multiple information processing devices. This allows the connected multiple information processing devices to transmit and receive data from each other. Furthermore, it allows for the distribution of the information processing load.

[0188] When performing wireless communication, communication protocols or technologies such as 4th generation mobile communication systems (4G), 5th generation mobile communication systems (5G), 6th generation mobile communication systems (6G), or specifications standardized by IEEE such as Wi-Fi® and Bluetooth® can be used.

[0189] For example, a local network can be used as network 51. An intranet or extranet can also be used as network 51. Furthermore, PAN (Personal Area Network), LAN (Local Area Network), CAN (Campus Area Network), MAN (Metropolitan Area Network), WAN (Wide Area Network), GAN (Global Area Network), etc., can be used as network 51.

[0190] Furthermore, for example, a global network can be used for network 51. Specifically, the internet, which is the foundation of the World Wide Web (WWW), can be used.

[0191] Furthermore, a person who provides services using an information processing system according to one aspect of the present invention can, for example, provide services using an information processing method according to one aspect of the present invention via a network 51.

[0192] Furthermore, if an information processing system according to one embodiment of the present invention is built within a local network, the possibility of confidential information leakage can be reduced compared to using the Internet.

[0193] <Example of Information Processing Device Configuration 4> An information processing device 20 that can be used in an information processing system according to one embodiment of the present invention includes, for example, an input unit 21, a storage unit 22, a processing unit 23, an output unit 24, and a transmission line 25 (see Figure 13).

[0194] In the drawings attached to this specification, the components are classified by function and shown as independent blocks in the block diagram. However, in reality, it is difficult to completely separate the components by function, and one component may be involved in multiple functions. For example, a part of the processing unit 23 may function as the input unit 21. Also, one function may be involved in multiple components. For example, the processing performed by the processing unit 23 may be executed by different information processing devices depending on the processing.

[0195] Input section 21 The input unit 21 can receive data from outside the information processing device. For example, the input unit 21 can receive data via the network 51. Specifically, a device such as a personal computer equipped with a communication port or communication function can be used.

[0196] The input unit 21 supplies the received data to either or both of the storage unit 22 and the processing unit 23 via the transmission line 25.

[0197] 《Storage section 22》 The memory unit 22 has the function of storing the program executed by the processing unit 23. The memory unit 22 may also have the function of storing data generated by the processing unit 23 (for example, calculation results, analysis results, inference results), data received by the input unit 21, etc.

[0198] The storage unit 22 may have a database. The information processing device may also have a database separate from the storage unit 22. The information processing device may have the function to retrieve data from a database located outside the storage unit 22, outside the information processing device itself, or outside the information processing system. Furthermore, the information processing device may have the function to retrieve data from both its own database and an external database.

[0199] Either or both of the storage and / or file server can be used in the storage unit 22. Furthermore, a database recording the paths of files stored on the file server can be used in the storage unit 22.

[0200] The storage unit 22 includes at least one of volatile memory and non-volatile memory. Examples of volatile memory include DRAM (Dynamic Random Access Memory) and SRAM (Static Random Access Memory). Examples of non-volatile memory include ReRAM (Resistive Random Access Memory), PRAM (Phase Change Random Access Memory), FeRAM (Ferroelectric Random Access Memory), MRAM (Magnetoresistive Random Access Memory), and flash memory. The storage unit 22 may also include at least one of NOSRAM (registered trademark) and DOSRAM (registered trademark). The storage unit 22 may also include a recording media drive. Examples of recording media drives include hard disk drives (HDD) and solid state drives (SSD).

[0201] NOSRAM is an abbreviation for "Nonvolatile Oxide Semiconductor Random Access Memory (RAM)". NOSRAM is a type of memory where the memory cell is a 2-transistor (2T) or 3-transistor (3T) gain cell, and the transistors are transistors that use metal oxide in the channel formation region (also called OS transistors). OS transistors have an extremely small current flowing between the source and drain when off, i.e., a leakage current. By utilizing the characteristic of extremely low leakage current, NOSRAM can be used as a non-volatile memory by holding charge corresponding to the data within the memory cell. In particular, NOSRAM can read the stored data without destroying it (non-destructive read), making it suitable for computational processing that involves repeating data read operations a large amount. Because the data capacity of NOSRAM can be increased by stacking it, it can be used as a large-scale cache memory, main memory, or storage memory to improve the performance of semiconductor devices.

[0202] DOSRAM is an abbreviation for "Dynamic Oxide Semiconductor RAM," and refers to RAM with a 1T (transistor) 1C (capacitance) type memory cell. DOSRAM is a type of DRAM formed using OS transistors, and it is a memory that temporarily stores information sent from an external source. DOSRAM is a memory that takes advantage of the low off-current of OS transistors.

[0203] In this specification, "metal oxide" refers to an oxide of a metal in a broad sense. Metal oxides are classified into oxide insulators, oxide conductors (including transparent oxide conductors), oxide semiconductors (also called oxide semiconductors or simply OS), etc. For example, when a metal oxide is used in the semiconductor layer of a transistor, that metal oxide may be referred to as an oxide semiconductor.

[0204] The metal oxide in the channel-forming region preferably contains indium (In). When the metal oxide in the channel-forming region contains indium, the carrier mobility (electron mobility) of the OS transistor is increased. For example, indium oxide (InOx) or indium gallium zinc oxide (In-Ga-Zn oxide, also written as "IGZO") can be used in the channel-forming region. Furthermore, the metal oxide in the channel-forming region is preferably an oxide semiconductor containing element M. Element M is preferably at least one of aluminum (Al), gallium (Ga), and tin (Sn). Other elements applicable to element M include boron (B), silicon (Si), titanium (Ti), iron (Fe), nickel (Ni), germanium (Ge), yttrium (Y), zirconium (Zr), molybdenum (Mo), lanthanum (La), cerium (Ce), neodymium (Nd), hafnium (Hf), tantalum (Ta), and tungsten (W). However, in some cases, element M may be a combination of multiple elements as mentioned above. Element M is, for example, an element with a high bond energy with oxygen. For example, an element with a higher bond energy with oxygen than indium. Furthermore, the metal oxide containing the channel-forming region is preferably a metal oxide containing zinc (Zn). Metal oxides containing zinc may be more prone to crystallization.

[0205] The metal oxides present in the channel-forming regions are not limited to indium-containing metal oxides. For example, the metal oxides present in the channel-forming regions may be zinc-tin oxides, gallium-tin oxides, or other metal oxides that do not contain indium but contain zinc, gallium, or tin.

[0206] Processing Unit 23 The processing unit 23 has the function of performing calculations, analyses, and inferences using data supplied from either or both of the input unit 21 and the storage unit 22. The processing unit 23 can supply the generated data (e.g., calculation results, analysis results, inference results) to either or both of the storage unit 22 and the output unit 24.

[0207] The processing unit 23 has the function of acquiring data from the storage unit 22. The processing unit 23 may also have the function of recording or registering data in the storage unit 22.

[0208] The processing unit 23 may, for example, have an arithmetic circuit. The processing unit 23 may, for example, have a central processing unit (CPU). The processing unit 23 may also have a graphics processing unit (GPU). The processing unit 23 may also have a neural processing unit (NPU / neural network processing unit).

[0209] The processing unit 23 may have a microprocessor such as a DSP (Digital Signal Processor). The microprocessor can be implemented using a PLD (Programmable Logic Device) such as an FPGA (Field Programmable Gate Array) or FPAA (Field Programmable Analog Array). The processing unit 23 may also have a quantum processor. The processing unit 23 can perform various data processing and program control by interpreting and executing instructions from various programs via the processor. Programs that can be executed by the processor are stored in at least one of the processor's memory area and the storage unit 22.

[0210] The processing unit 23 may have main memory. The main memory may include at least one of volatile memory such as RAM and non-volatile memory such as ROM (Read Only Memory). Furthermore, the main memory may include at least one of the above-mentioned NOSRAM and DOSRAM.

[0211] For RAM, for example, DRAM or SRAM is used, and a virtual memory space is allocated and used as the workspace for the processing unit 23. The operating system, application programs, program modules, program data, and lookup tables stored in the storage unit 22 are loaded into RAM for execution. These data, programs, and program modules loaded into RAM are each directly accessed and manipulated by the processing unit 23.

[0212] ROM can store BIOS (Basic Input / Output System) and firmware, etc., which do not require rewriting. Examples of ROM include mask ROM, OTPROM (One Time Programmable Read Only Memory), and EPROM (Erasable Programmable Read Only Memory). Examples of EPROM include UV-EPROM (Ultra-Violet Erasable Programmable Read Only Memory), which allows data to be erased by ultraviolet irradiation, EEPROM (Electrically Erasable Programmable Read Only Memory), and flash memory.

[0213] The processing unit 23 may have either or both an OS transistor and a transistor having silicon in its channel formation region (Si transistor).

[0214] The processing unit 23 preferably has an OS transistor. Because the OS transistor has an extremely small off-current, using the OS transistor as a switch to hold the charge (data) that has flowed into a capacitive element that functions as a memory element ensures that the data can be retained for a long period of time. By using this characteristic in at least one of the registers and cache memory of the processing unit, the processing unit can be turned off by operating it only when necessary and saving the information of the previous processing to the memory element in other cases. In other words, normally-off computing becomes possible, and the power consumption of the information processing system can be reduced.

[0215] It is preferable for information processing devices to use AI for at least some of their processing.

[0216] Information processing devices preferably utilize artificial neural networks (ANNs, also simply referred to as neural networks). Neural networks are implemented using circuits (hardware) or programs (software).

[0217] In this specification, the term "neural network" refers to any model that mimics the neural network of living organisms, determines the strength of connections between neurons through learning, and possesses problem-solving capabilities. A neural network has an input layer, an intermediate layer (hidden layer), and an output layer.

[0218] In this specification and other documents, when discussing neural networks, the process of determining the connection strength (also called weight coefficient) between neurons from existing information is sometimes referred to as "learning."

[0219] In this specification and other documents, the process of constructing a neural network using connection strengths obtained through learning and deriving new conclusions from it may be referred to as "inference."

[0220] Output section 24 The output unit 24 can output at least one of the calculation results, analysis results, and inference results from the processing unit 23 to the outside of the information processing device. For example, the output unit 24 can transmit data via the network 51. Specifically, a device such as a personal computer equipped with a communication port or communication function can be used. Alternatively, a device equipped with a communication function may be used for both the input unit 21 and the output unit 24.

[0221] Transmission line 25 The transmission line 25 has the function of transmitting data. Data can be transmitted and received between the input unit 21, the storage unit 22, the processing unit 23, and the output unit 24 via the transmission line 25. Specifically, a LAN or the Internet can be used.

[0222] This embodiment can be appropriately combined with other embodiments shown in this specification.

[0223] (Embodiment 2) In this embodiment, an information processing method according to one aspect of the present invention will be described with reference to Figures 14 to 19.

[0224] Figure 14 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0225] Figure 15 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0226] Figure 16 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0227] Figure 17 is a sequence diagram illustrating an information processing method according to one embodiment of the present invention.

[0228] Figure 18 is a sequence diagram illustrating an information processing method according to one embodiment of the present invention.

[0229] Figure 19 is a sequence diagram illustrating an information processing method according to one embodiment of the present invention.

[0230] <Example of information processing method 1> One aspect of the present invention is an information processing method having a phase PH1 (see Figures 14 and 17).

[0231] <Example of Phase PH1> Phase PH1 comprises steps S1 to S12 (see Figure 14).

[0232] Step S1 In step S1 of phase PH1, component 110 receives identification information Id and transmits it to component 120. For example, a user 99 of the information processing system inputs identification information Id. Step S1 corresponds to the arrows extending from (1) and (2) in Figure 17.

[0233] Step S2 In step S2 of phase PH1, component 120 receives identification information Id and shares it within component 120. Component 120 comprises subcomponent 120A and subcomponent 120B.

[0234] Subcomponent 120A has the functionality to perform processing using a database DB and a management system DBMS. The database DB contains patent application documents PAD_1 and examination records RExm_1, and the examination records RExm_1 include notices of reasons for rejection and written opinions.

[0235] Step S3 In step S3 of phase PH1, subcomponent 120A uses the management system DBMS to create a table Tbl from the database DB according to query Que1 and shares it within component 120. Step S3 corresponds to the arrows extending from (3) and (4) in Figure 17.

[0236] Table Tbl includes the patent application document PAD_1, the patented claims ACL_1 relating to the patent application document PAD_1, and the examination record RExm_1 relating to the patented claims ACL_1. Query Que1 includes the identification information Id, and Query Que1 requests that the patent application identified by the identification information Id in the patent application document PAD_1 is the same as the original application.

[0237] Step S4 In step S4 of phase PH1, subcomponent 120B creates instruction statement Pt11 and sends it to component 130. Instruction statement Pt11 includes instruction g11() and table Tbl. Instruction g11() includes a procedure to extract special technical features STF_1 relating to the patented claims ACL_1 from table Tbl. Step S4 corresponds to the arrows extending from (5) and (6) in Figure 17.

[0238] Step S5 In step S5 of phase PH1, component 130 receives instruction Pt11 and uses the large-scale language model LLM to extract special technical feature STF_1.

[0239] Step S6 In step S6 of phase PH1, component 130 transmits a special technical feature STF_1 to component 120. Step S6 corresponds to the arrow extending from (7) in Figure 17.

[0240] Step S7 In step S7 of phase PH1, component 120 receives a special technical feature STF_1 and shares it within component 120.

[0241] Step S8 In step S8 of phase PH1, subcomponent 120B creates instruction statement Pt12 and sends it to component 130. Instruction statement Pt12 includes instruction g12(), special technical feature STF_1, and patent application document PAD_1. Instruction g12() includes a procedure to generate an annotated document AntD by adding decorations or annotations to the description TXT_STF1 relating to the special technical feature contained in patent application document PAD_1. Step S8 corresponds to the arrows extending from (8) and (9) in Figure 17.

[0242] Step S9 In step S9 of phase PH1, component 130 receives instruction Pt12 and generates an annotated document AntD using the large-scale language model LLM.

[0243] Step S10 In step S10 of phase PH1, component 130 sends the annotated document AntD to component 120. Step S10 corresponds to the arrow extending from (10) in Figure 17.

[0244] Step S11 In step S11 of phase PH1, component 120 receives the annotated document AntD and sends it to component 110. Step S11 corresponds to the arrow extending from (11) in Figure 17.

[0245] Step S12 In step S12 of phase PH1, component 110 receives the annotated document AntD and provides it, for example, to a user of the information processing system. Step S12 corresponds to the arrow extending from (12) in Figure 17.

[0246] This allows the collection of patent application documents PAD_1 from the database DB that are the same as the patent application identified by the identification information Id. Furthermore, the patent application documents PAD_1, the patented claims ACL_1 related to the patent application documents PAD_1, and the examination record RExm_1 related to the patented claims ACL_1 can be collected and a table Tbl can be created. Additionally, special technical features STF_1 related to the patented claims ACL_1 can be extracted from table Tbl. Furthermore, decorations or annotations can be added to the description TXT_STF1 related to the special technical features contained in the patent application documents PAD_1. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0247] <Example of information processing method 2> One aspect of the present invention is an information processing method having phase PH1 and phase PH2 (see Figures 15 and 18).

[0248] <Example of Phase PH2> Phase PH2 follows Phase PH1 and comprises steps S1 to S10 (see Figure 15).

[0249] Step S1 In step S1 of phase PH2, component 110 receives range information Rng and transmits it to component 120. The range information Rng identifies a part of the patent application document PAD_1. For example, a user 99 of the information processing system inputs the range information Rng. Step S1 corresponds to the arrows extending from (1) and (2) in Figure 18. Also, parts of steps S1 to S10 correspond to the area enclosed by the rectangular loop in Figure 18.

[0250] Step S2 In step S2 of phase PH2, component 120 receives range information Rng and shares it within component 120. Note that component 120 includes sub-component 120C.

[0251] 《Step S3》 In step S3 of phase PH2, sub-component 120C extracts a part Prt from the patent application documents PAD_1 based on the range information Rng. Note that step S3 corresponds to the arrow extending from (3) in FIG. 18.

[0252] 《Step S4》 In step S4 of phase PH2, sub-component 120B creates an instruction Pt2 and transmits it to component 130. Note that instruction Pt2 includes an instruction g2() and a part Prt. Also, instruction g2() includes a procedure for generating a summary Sum from the part Prt. Note that step S4 corresponds to the arrows extending from (4) and (5) in FIG. 18.

[0253] 《Step S5》 In step S5 of phase PH2, component 130 receives the instruction Pt2 and generates a summary Sum using a large language model LLM.

[0254] 《Step S6》 In step S6 of phase PH2, component 130 transmits the summary Sum to component 120. Note that step S6 corresponds to the arrow extending from (6) in FIG. 18.

[0255] 《Step S7》 In step S7 of phase PH2, component 120 receives the summary Sum and transmits it to component 110. Note that step S7 corresponds to the arrow extending from (7) in FIG. 18.

[0256] 《Step S8》 In step S8 of phase PH2, component 110 receives the summary Sum and provides it, for example, to a user of the information processing system. Step S8 corresponds to the arrow extending from (8) in Figure 18.

[0257] Step S9 In step S9 of phase PH2, component 110 receives acceptance information Acc1 or a return command Und and sends it to component 120. For example, a user of the information processing system inputs acceptance information Acc1 or a return command Und. Steps S9 and S10 correspond to the area enclosed by rectangle alt in Figure 18, and the action when a return command Und is received corresponds to the arrows extending from (9) and (10). The action when acceptance information Acc1 is received corresponds to the arrows extending from (11) and (12).

[0258] Step S10 In step S10 of phase PH2, component 120 terminates phase PH2 when it receives acceptance information Acc1. It also proceeds to step S1 of phase PH2 when it receives the return command Und.

[0259] This allows for the extraction of a portion of the patent application document PAD_1 using range information Rng. Furthermore, a summary Sum can be generated from the extracted portion of the Prt. Additionally, a summary Sum can be generated from a portion of the Prt extracted from a section without decorative or annotated elements. Furthermore, a summary Sum can be generated from sections other than those describing the special technical features STF_1 related to the patented claims ACL_1. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0260] <Example 3 of information processing methods> One aspect of the present invention is an information processing method having phases PH1 to PH3 (see Figures 16 and 19).

[0261] <Example of Phase PH3> Phase PH3 follows Phase PH2 and comprises steps S1 to S9 (see Figure 16).

[0262] Step S1 In step S1 of phase PH3, subcomponent 120B creates instruction statement Pt31 and sends it to component 130. Instruction statement Pt31 includes instruction g31(), special technical feature STF_1, description related to the special technical feature TXT_STF1, and partial Prt. Instruction g31() also includes a procedure to generate a claim draft DC from special technical feature STF_1, description related to the special technical feature TXT_STF1, and partial Prt. Step S1 corresponds to the arrows extending from (1) and (2) in Figure 19.

[0263] Step S2 In step S2 of phase PH3, component 130 receives instruction Pt31 or instruction Pt32 and generates claim draft DC using the large-scale language model LLM.

[0264] Step S3 In step S3 of phase PH3, component 130 sends the claim draft DC to component 120. Step S3 corresponds to the arrow extending from (3) in Figure 19.

[0265] Step S4 In step S4 of phase PH3, component 120 receives the claim draft DC and transmits it to component 110. Step S4 corresponds to the arrow extending from (4) in Figure 19. Steps S4 through S8 correspond to the area enclosed by the rectangular loop in Figure 19.

[0266] Step S5 In step S5 of phase PH3, component 110 receives the claim draft DC and provides it, for example, to a user of an information processing system. Step S5 corresponds to the arrow extending from (5) in Figure 19.

[0267] Step S6 In step S6 of phase PH3, component 110 receives acceptance information Acc2 or requirement Req and transmits it to component 120. For example, a user of the information processing system inputs acceptance information Acc2 or requirement Req. Steps S6 to S8 correspond to the area enclosed by rectangle alt in Figure 19, and the action when requirement Req is received corresponds to the arrows extending from (6) and (7). The action when acceptance information Acc2 is received corresponds to the arrows extending from (11) and (12).

[0268] Step S7 In step S7 of phase PH3, component 120 terminates phase PH3 when it receives acceptance information Acc2. Also, when it receives requirement Req, subcomponent 120B creates instruction statement Pt32 and sends it to component 130. Instruction statement Pt32 includes instruction g32(), requirement Req, special technical feature STF_1, description TXT_STF1 relating to the special technical feature, and partial Prt. Instruction g32() also includes a procedure to generate a claim draft DC from requirement Req, special technical feature STF_1, description TXT_STF1 relating to the special technical feature, and partial Prt. Step S7 corresponds to the arrows extending from (8) and (9) in Figure 19.

[0269] Step S8 In step S8 of phase PH3, component 130 receives the instruction Pt32 and uses the large language model LLM to generate a draft claim DC.

[0270] 《Step S9》 In step S9 of phase PH3, component 130 sends the draft claim DC to component 120 and proceeds to step S4 of phase PH3. Note that step S9 corresponds to the arrow extending from (10) in FIG. 19.

[0271] Thus, the draft claim DC can be generated using the special technical feature STF_1 and summary Sum related to the patented claim scope ACL_1. Also, for example, the user of the information processing system can review the draft claim DC and add requirements Req. Further, the draft claim DC can be generated by adding the requirements Req to the special technical feature STF_1 related to the patented claim scope ACL_1, the description TXT_STF1 related to the special technical feature, and a part Prt. As a result, a novel information processing method excellent in convenience, usefulness, or reliability can be provided.

[0272] Note that this embodiment can be appropriately combined with other embodiments shown in this specification.

Description of Reference Numerals

[0273] ACL_1 Scope alt Rectangle AntD Annotated Document CID Input Device DB Database DBMS Management System Dsp Display Device Ent Region g11() Instruction g12() Instruction g2() Instruction g31() Instruction g32() Instruction Id Identification Information Id_1 Identification Information Id_2 Identification Information Id_3 Identification Information Large-Scale Language Model (LLM) loop rectangle PAD_1 Patent Application Documents PAD_2 Patent Application Documents PAD_3 Patent Application Documents Pnt pointer Prt part Pt11 instructions Pt12 instructions Pt31 instructions Pt32 instruction text Req Requirements RExm_1 Review Record Range information STF_1 Technical Features Sum Summary Tbl Table Und command 20 Information Processing Devices 21 Input section 22 Memory section 23 Processing Unit 24 Output section 25 Transmission lines 51 Network 99 User 110 components 120 components 120A Subcomponent 120B Subcomponent 120C Subcomponents 130 components

Claims

1. The first component and The second component, It has a third component, The first component includes a function for receiving identification information and transmitting it to the third component, and a function for receiving and providing annotated documents. The aforementioned identification information includes information that identifies a single patent application, The second component includes a function to receive a first instruction and transmit special technical features to the third component, a function to receive a second instruction and transmit the annotated document to the third component, and a function to perform processing using a large-scale language model. The large-scale language model includes a function for extracting the special technical features according to the first instruction and a function for generating the annotated document according to the second instruction. The third component includes a function to receive the identification information and the special technical features and share them within the third component, a function to create a table and share it within the third component, a function to create the first instruction and the second instruction and send them to the second component, and a function to receive the annotated document and send it to the first component. The third component comprises a first subcomponent and a second subcomponent, The first subcomponent is equipped with a function to perform processing using a database and a management system, The database comprises at least one patent application document and at least one examination record, The aforementioned examination record includes the notice of reasons for rejection and the written opinion, The management system includes a function to create the table from the database in response to a query. The table includes the patent application documents, the patented claims relating to the patent application documents, and the examination record relating to the patented claims, The query includes the identification information, The query requires that the patent application document is the same as the original application identified by the identification information. The second subcomponent has the function of creating the first instruction and the second instruction, The first instruction statement includes the first instruction and the table, The first instruction includes a procedure for extracting the special technical features relating to the patented claims from the table, The second instruction includes the second instruction, the special technical features and the patent application documents, The second instruction includes a procedure for generating an annotated document by adding embellishments or annotations to the description relating to the special technical features contained in the patent application document.

2. The first component includes a function for receiving range information and transmitting it to the third component, and a function for receiving and providing a summary. The aforementioned scope information identifies a portion of the patent application documents, The second component has the function of receiving a third instruction and transmitting the summary to the third component. The large-scale language model has a function to generate the summary according to the third instruction, The third component includes a function to receive the range information and share it within the third component, a function to transmit the third instruction to the second component, and a function to receive the summary and transmit it to the first component. The third component comprises a third subcomponent, The third subcomponent has a function to extract a portion from the patent application documents based on the scope information, The second subcomponent has the function of creating the third instruction statement, The third instruction statement includes the third instruction and the portion thereof. The information processing system according to claim 1, wherein the third instruction includes a step of generating the summary from the portion.

3. The information processing system according to claim 2, wherein the first component has a function to accept a revert command and provide the annotated document.

4. The first component includes a function for receiving acceptance information and transmitting it to the third component, and a function for receiving and providing a draft claim. The second component has the function of receiving a fourth instruction and transmitting the claim draft to the third component, The large-scale language model has a function to generate the claim draft according to the fourth instruction, The third component includes a function to receive the acceptance information and share it within the third component, a function to transmit the fourth instruction statement to the second component, and a function to receive the claim draft and transmit it to the first component. The second subcomponent has the function of creating the fourth instruction statement, The fourth instruction statement includes the fourth instruction, the special technical features, the description relating to the special technical features, and the part thereof. The information processing system according to claim 2, wherein the fourth instruction includes a procedure for generating the claim draft from the special technical features, the description relating to the special technical features and the portion thereof.

5. The first component has the function of receiving requirements and transmitting them to the third component. The second component has the function of receiving a fifth instruction and transmitting the claim draft to the third component. The large-scale language model has a function to generate the claim draft according to the fifth instruction, The third component includes a function to receive the requirements and share them within the third component, and a function to send the fifth instruction to the second component. The second subcomponent has the function of creating the fifth instruction statement, The fifth instruction includes the fifth instruction, the requirements, the special technical features, the description relating to the special technical features and the part thereof, The information processing system according to claim 4, wherein the fifth instruction includes a procedure for generating the claim draft from the requirements, the special technical features, the description relating to the special technical features and the portion thereof.

6. The first component includes a display device, The display device has a function to display the annotated document, The information processing system according to any one of claims 1 to 5, wherein the description relating to the special technical features included in the annotated document is displayed with decoration or annotation using at least one of highlighting, bolding, italics, and underlining.

7. The first component comprises a display device and an input device, The display device has a function to display the annotated document and the pointer, The description relating to the special technical features contained in the annotated document is displayed with decoration or annotations using at least one of the following: highlighting, bolding, italics, and underlining. The information processing system according to any one of claims 2 to 5, wherein the input device comprises a function for moving the pointer and a function for inputting the range information.

8. The information processing system according to any one of claims 1 to 5, wherein the first component, the second component, and the third component each comprise a computing device and a communication device, and each of the communication devices is connected to one another via a network.

9. An information processing method having a first phase, The first phase comprises a first to a twelfth step, In the first step of the first phase, the first component receives identification information and transmits it to the second component. In the second step of the first phase, the second component receives the identification information and shares it within the second component. The second component comprises a first subcomponent and a second subcomponent, The first subcomponent is equipped with a function to perform processing using a database and a management system, The aforementioned database contains patent application documents and examination records, The aforementioned examination record includes the notice of reasons for rejection and the written opinion, In the third step of the first phase, the first subcomponent uses the management system to create tables from the database according to queries and share them within the second component. The table includes the patent application documents, the patented claims relating to the patent application documents, and the examination record relating to the patented claims, The query includes the identification information, The query requires that the patent application document is the same as the original application identified by the identification information. In the fourth step of the first phase, the second subcomponent creates a first instruction and sends it to the third component. The first instruction statement includes the first instruction and the table, The first instruction includes a procedure for extracting special technical features relating to the patented claims from the table, In the fifth step of the first phase, the third component receives the first instruction and extracts the special technical features using a large-scale language model. In the sixth step of the first phase, the third component transmits the special technical features to the second component. In the seventh step of the first phase, the second component receives and shares the special technical features within the second component. In the eighth step of the first phase, the second subcomponent creates a second instruction and sends it to the third component. The second instruction includes the second instruction, the special technical features and the patent application documents, The second instruction includes a procedure for generating an annotated document by adding embellishments or annotations to the description relating to the special technical features included in the patent application document, In the ninth step of the first phase, the third component receives the second instruction and generates the annotated document using the large-scale language model. In the tenth step of the first phase, the third component transmits the annotated document to the second component. In the eleventh step of the first phase, the second component receives the annotated document and transmits it to the first component. In the twelfth step of the first phase, the first component is an information processing method that receives and provides the annotated document.

10. An information processing method having the first phase and the second phase, The second phase follows the first phase, The second phase comprises the first to tenth steps, In the first step of the second phase, the first component receives range information and transmits it to the second component. The aforementioned scope information identifies a portion of the patent application documents, In the second step of the second phase, the second component receives the range information and shares it within the second component. The second component comprises a third subcomponent, In the third step of the second phase, the third subcomponent extracts a portion from the patent application documents based on the scope information, In the fourth step of the second phase, the second subcomponent creates a third instruction and sends it to the third component. The third instruction statement includes the third instruction and the portion thereof. The third instruction includes a procedure for generating a summary from the portion, In the fifth step of the second phase, the third component receives the third instruction and generates the summary using the large-scale language model. In the sixth step of the second phase, the third component transmits the summary to the second component. In the seventh step of the second phase, the second component receives the summary and transmits it to the first component. In the eighth step of the second phase, the first component receives and provides the summary. In the ninth step of the second phase, the first component receives first acceptance information or a return command and transmits it to the second component. The information processing method according to claim 9, wherein in the tenth step of the second phase, the second component terminates the second phase when it receives the first acceptance information, and proceeds to the first step of the second phase when it receives the return command.

11. An information processing method having the first to third phases, The third phase follows the second phase, The third phase comprises the first to ninth steps, In the first step of the third phase, the second subcomponent creates a fourth instruction and sends it to the third component. The fourth instruction statement includes the fourth instruction, the special technical features, the description relating to the special technical features, and the part thereof. The fourth instruction includes a procedure for generating a draft claim from the special technical features, the description relating to the special technical features and the portion thereof, In the second step of the third phase, the third component receives the fourth instruction or the fifth instruction and generates the claim draft using the large-scale language model. In the third step of the third phase, the third component transmits the claim draft to the second component, In the fourth step of the third phase, the second component receives the claim draft and transmits it to the first component. In the fifth step of the third phase, the first component receives and provides the claim draft. In the sixth step of the third phase, the first component receives the second acceptance information or requirement and transmits it to the second component. In the seventh step of the third phase, when the second component receives the second acceptance information, it terminates the third phase, and when it receives the requirements, the second subcomponent creates the fifth instruction statement and sends it to the third component. The fifth instruction includes the fifth instruction, the requirements, the special technical features, the description relating to the special technical features and the part thereof, The fifth instruction includes a procedure for generating the claim draft from the requirements, the special technical features, the description relating to the special technical features and the portion thereof, In the eighth step of the third phase, the third component receives the fifth instruction and generates the claim draft using the large-scale language model. The information processing method according to claim 10, wherein in the ninth step of the third phase, the third component transmits the claim draft to the second component and proceeds to the fourth step of the third phase.

Images