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. The first component receives documents and objectives and transmits them to the third component, and also receives and provides proposed implementations. The second component receives instructions and generates configurations and proposed implementations using a large-scale language model. The third component receives and shares documents, objectives, and configurations, and receives proposed implementations and transmits them to the first component. It also includes a subcomponent that creates and executes prompt chains. This system proposes configurations not described in documents, proposes configurations related to objectives, and generates proposed implementations based on the configurations. Users can implement the configurations according to these proposals or proposed implementations and verify their effects.

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 and the like relates to an article, a method, or a manufacturing method. Alternatively, one aspect of the present invention relates to a process, a machine, a manufacture, or a composition of matter. Therefore, more specific examples of the technical field of one aspect of the present invention disclosed in this specification include an information processing apparatus, a semiconductor device, a memory device, driving methods thereof, or manufacturing methods thereof. Background Art

[0003] In recent years, language models using neural networks have been actively developed, and large language models (LLMs) have attracted particular attention. A large language model is a natural language processing model trained using a large amount of data. A large language model can realize, for example, a dialogue model that provides a response to a user's instruction. Non-Patent Document 1 discloses GPT-4 (Generative Pre-trained Transformer 4) (registered trademark) as a large language model, and also discloses ChatGPT (registered trademark) as a dialogue model.

[0004] The use of large language models has significantly increased the capability of natural language processing models. On the other hand, due to the increasing size of language models, it is difficult to incorporate and operate a language model in-house in terms of equipment and cost. For this reason, using an external service that provides a language model has become one of the usage forms of language models. 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 Initiative] [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) An information processing system according to one aspect of the present invention comprises a function for receiving documents and objectives, a function for providing proposed embodiments, and a function for performing processing using a large-scale language model. The documents include technical information related to objectives, and the large-scale language model comprises a function for generating a first structure according to a first instruction and a function for generating proposed embodiments according to a second instruction.

[0009] The first instruction includes the first instruction, document, and objective. The first instruction includes a procedure for proposing the first structure, which is a structure not described in the document and related to the objective.

[0010] The second instruction includes the second instruction and the first configuration, and the second instruction includes a procedure for generating a proposed embodiment based on the first configuration.

[0011] (2) One aspect of the present invention is an information processing system having a first component, a second component, and a third component.

[0012] The first component has the function of receiving documents and objectives and transmitting them to the third component, and the function of receiving and providing proposed examples. The documents include technical information related to the objectives.

[0013] The second component includes the function of receiving the first instruction and the second instruction and sending the first configuration and proposed embodiment 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 generating the first configuration according to the first instruction and the function of generating a proposed embodiment according to the second instruction.

[0014] The third component includes the functions of receiving and sharing documents, objectives, and the first configuration within the third component, sending the first and second instructions to the second component, and receiving a proposed embodiment and sending it to the first component. The third component also includes the first subcomponent.

[0015] The first subcomponent has the function of creating and executing a first prompt chain, the first prompt chain including a first instruction and a second instruction.

[0016] The first instruction document includes the first instruction, document, and objective, and the first instruction includes a procedure for proposing the first structure, taking the document into consideration. The first structure is a structure not described in the document, and the first structure is a structure related to the objective.

[0017] The second instruction includes the second instruction and the first configuration, and the second instruction includes a procedure for generating a proposed embodiment based on the first configuration.

[0018] This allows for the proposal of a first configuration not described in the document. It also allows for the proposal of a first configuration related to the objective. Furthermore, it allows for the generation of a proposed embodiment based on the first configuration. For example, a user of the information processing system can try implementing the first configuration according to the proposed embodiment. Furthermore, for example, a user of the information processing system can verify the effectiveness of the first configuration. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided. In this specification, a proposed embodiment includes embodiments and draft embodiments.

[0019] (3) Another aspect of the present invention is the above-described information processing system, wherein the first component has a function to receive adjustment requests and transmit them to the third component. The adjustment requests are requests relating to adjustments to the proposed embodiments.

[0020] The second component has the function of receiving the third instruction and sending a new example of the embodiment to the third component. The large-scale language model also has the function of generating a new example of the embodiment according to the third instruction.

[0021] The third component has the functionality to receive coordination requests and share them within the third component.

[0022] The first subcomponent has the function of generating a third instruction statement. The third instruction statement includes a third instruction, a proposed embodiment, and a request for adjustment, and the third instruction includes a procedure for adjusting the proposed embodiment in response to the request for adjustment.

[0023] Accordingly, for example, a user of the information processing system can request adjustment of an example implementation plan. Further, the information processing system according to one aspect of the present invention can adjust the example implementation plan in response to a request. Further, for example, a user of the information processing system can request adjustment of the proposed first configuration. Further, the information processing system according to one aspect of the present invention can adjust the first configuration in response to a request. As a result, a novel information processing system excellent in convenience, usefulness, or reliability can be provided.

[0024] (4) Further, one aspect of the present invention is the information processing system described above, wherein the first component has a function of receiving and providing a comparative example.

[0025] The second component has a function of receiving a fourth instruction sentence and a fifth instruction sentence, and transmitting a second configuration and a comparative example to a third component. Further, the large language model comprises a function of generating the second configuration in accordance with the fourth instruction sentence, and a function of generating the comparative example in accordance with the fifth instruction sentence.

[0026] The third component has a function of receiving the comparative example and transmitting the comparative example to the first component.

[0027] The first sub-component has a function of creating and executing a second prompt chain, and the second prompt chain includes the fourth instruction sentence and the fifth instruction sentence.

[0028] The fourth instruction sentence includes a fourth instruction, a document, and a target, and the fourth instruction includes a procedure for causing the second configuration to be proposed with reference to the document. Note that the second configuration is a configuration described in the document, and the second configuration is a configuration related to the target.

[0029] The fifth instruction sentence includes a fifth instruction and the second configuration, and the fifth instruction includes a procedure for causing the comparative example to be generated based on the second configuration.

[0030] This allows for the proposal of a second configuration described in the document. Furthermore, a second configuration related to the objective can be proposed. Additionally, comparative examples can be generated based on the second configuration. For example, users of the information processing system can try implementing the second configuration according to the comparative examples. Furthermore, for example, users of the information processing system can verify the effectiveness of the second configuration. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0031] (5) Another aspect of the present invention is the above-described information processing system, wherein the first component has a function to receive evaluations and transmit them to the third component, and a function to receive and provide embodiments. The evaluation is the result of evaluating the effects of the first configuration.

[0032] The second component has the function of receiving the sixth instruction and sending the embodiment to the third component. The large-scale language model has the function of generating the embodiment according to the sixth instruction.

[0033] The third component has the function of receiving evaluations and sharing them internally, and the function of receiving examples and sending them to the first component. The first subcomponent also has the function of creating a sixth instruction statement.

[0034] The sixth instruction includes the sixth instruction, a proposed example, and an evaluation, and the sixth instruction includes a procedure for generating an example based on the proposed example and the evaluation.

[0035] This allows for the generation of embodiments by incorporating evaluations into the proposed embodiments. Furthermore, a first configuration not described in the document, along with its evaluation, can be included in the embodiments. Additionally, significant effects of the first configuration, based on the evaluation, can be described in the embodiments. The operation of the first configuration can also be described in the embodiments. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0036] (6) Another aspect of the present invention is the above-described information processing system, wherein the first component has the function of receiving the title and objective of the invention and transmitting it to the third component, and the function of receiving and providing a document.

[0037] The second component has the function of receiving the seventh instruction and sending the document to the third component. The large-scale language model has the function of selecting a document from the search results according to the seventh instruction.

[0038] The third component includes a function for receiving and sharing the title and objective of the invention within the third component, and a function for receiving a document and transmitting it to the first component, and the third component comprises a second subcomponent.

[0039] The second subcomponent comprises a database and a management system. The database stores technical documents, and the management system has the function of generating search results according to queries.

[0040] The first subcomponent provides the functionality to generate queries and seventh directives. A query includes a request to collect documents related to the title and objectives of the invention from the database as search results.

[0041] Instruction 7 includes Instruction 7, search results, and objectives, and Instruction 7 includes a procedure for selecting appropriate documents relating to the objectives based on the search results.

[0042] This allows for the collection of documents related to the invention's title and objectives from the database into the search results. Furthermore, appropriate documents related to the objectives can be selected from the search results. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0043] (7) One aspect of the present invention is an information processing method having the first to eleventh steps.

[0044] In the first step, the first component receives the document and objectives and transmits them to the second component. The document includes technical information related to the objectives.

[0045] In the second step, the second component receives the document and objectives and shares them within the second component. The second component also comprises a first subcomponent, which has the function of creating and executing the first prompt chain. The first prompt chain includes a first instruction and a second instruction.

[0046] In the third step, the second component sends the first instruction to the third component. The first instruction includes the first instruction, document, and objective, and the first instruction includes a procedure for proposing the first configuration, referring to the document. The first configuration is a configuration not described in the document, and the first configuration is a configuration related to the objective.

[0047] In the fourth step, the third component receives the first instruction and uses a large-scale language model to generate the first construct.

[0048] In the fifth step, the third component sends the first configuration to the second component.

[0049] In the sixth step, the second component accepts the first configuration and shares it within the second component.

[0050] In the seventh step, the second component sends a second instruction to the third component. The second instruction includes a second instruction and a first configuration, and the second instruction includes a procedure for generating a proposed embodiment based on the first configuration.

[0051] In the eighth step, the third component receives the second instruction and generates a proposed embodiment using a large-scale language model.

[0052] In the ninth step, the third component sends the proposed embodiment to the second component.

[0053] In the tenth step, the second component receives the proposed embodiment and transmits it to the first component.

[0054] In the eleventh step, the first component accepts and provides the proposed embodiment.

[0055] This allows for the proposal of a first configuration not described in the document. It also allows for the proposal of a first configuration related to the objective. Furthermore, it allows for the generation of a proposed implementation based on the first configuration. For example, a user of the information processing system can try implementing the first configuration according to the proposed implementation. Furthermore, for example, a user of the information processing system can verify the effectiveness of the first configuration. As a result, a novel information processing method with superior convenience, usefulness, or reliability can be provided.

[0056] (8) Another aspect of the present invention is the above-described information processing method comprising steps 12 to 18.

[0057] In step 12, the first component receives the adjustment request and sends it to the second component.

[0058] In step 13, the second component receives the adjustment request and shares it internally. The first subcomponent has the function of creating the third instruction statement.

[0059] In step 14, the second component sends a third instruction to the third component. The third instruction includes a third instruction, a proposed embodiment, and a request for adjustment, the third instruction including a procedure for adjusting the proposed embodiment in response to the request for adjustment.

[0060] In step 15, the third component receives the third instruction and uses a large-scale language model to adjust the proposed embodiment.

[0061] In step 16, the third component sends the proposed embodiment to the second component.

[0062] In step 17, the second component sends the proposed embodiment to the first component.

[0063] In step 18, the first component accepts and provides the proposed embodiment.

[0064] This allows, for example, a user of the information processing system to request adjustments to the proposed embodiment. Furthermore, an information processing system according to one embodiment of the present invention can adjust the proposed embodiment upon request. Also, for example, a user of the information processing system can request adjustments to the proposed first configuration. Furthermore, an information processing system according to one embodiment of the present invention can adjust the first configuration upon request. As a result, a novel information processing method with superior convenience, usefulness, or reliability can be provided.

[0065] (9) Another aspect of the present invention is the above-described information processing method, comprising steps 19 to 25.

[0066] In step 19, the first component receives the evaluation and sends it to the second component.

[0067] In step 20, the second component receives and shares the evaluation internally. The first subcomponent has the function of creating the fourth instruction statement.

[0068] In step 21, the second component sends a fourth instruction to the third component. The fourth instruction includes a fourth instruction, a proposed embodiment, and an evaluation, and the fourth instruction includes a procedure for generating an embodiment based on the proposed embodiment and the evaluation.

[0069] In step 22, the third component receives the fourth instruction and generates an example using a large-scale language model.

[0070] In step 23, the third component sends the embodiment to the second component.

[0071] In step 24, the second component receives the embodiment and transmits it to the first component.

[0072] In step 25, the first component accepts and provides an embodiment.

[0073] This allows for the generation of embodiments by incorporating evaluations into the proposed embodiments. A first configuration not described in the document, along with its evaluation, can be included in the embodiments. Furthermore, significant effects of the first configuration, based on the evaluation, can be described in the embodiments. Additionally, the operation of the first configuration can be described in the embodiments. As a result, a novel information processing method with superior convenience, usefulness, or reliability can be provided.

[0074] (10) Another aspect of the present invention is an information processing method having steps 26 to 34. The first subcomponent has the function of creating and executing a second prompt chain. The second prompt chain includes a fifth instruction and a sixth instruction.

[0075] In step 26, the second component sends the fifth instruction to the third component. The fifth instruction includes the fifth instruction, document, and objective, and the fifth instruction includes a procedure for proposing the second configuration, with reference to the document. The second configuration is the configuration described in the document, and the second configuration is the configuration related to the objective.

[0076] In step 27, the third component receives the fifth instruction and uses a large-scale language model to generate the second construct.

[0077] In step 28, the third component sends the second configuration to the second component.

[0078] In step 29, the second component accepts the second configuration and shares it within the second component.

[0079] In step 30, the second component sends a sixth instruction to the third component. The sixth instruction includes a sixth instruction and a second configuration, the sixth instruction including a procedure to generate a comparative example based on the second configuration.

[0080] In step 31, the third component receives the sixth instruction and generates a comparative example using a large-scale language model.

[0081] In step 32, the third component sends the comparative example to the second component.

[0082] In step 33, the second component receives the comparative example and sends it to the first component.

[0083] In step 34, the first component accepts and provides a comparative example.

[0084] This allows for the proposal of a second configuration described in the document. Furthermore, a second configuration related to the objective can be proposed. Additionally, comparative examples can be generated based on the second configuration. For example, a user of the information processing system can try implementing the second configuration according to the comparative examples. Furthermore, for example, a user of the information processing system can verify the effectiveness of the second configuration. As a result, a novel information processing method with superior convenience, usefulness, or reliability can be provided.

[0085] (11) Another aspect of the present invention is the above-described information processing method, comprising a first to tenth preprocessing step.

[0086] In the first preprocessing step, the first component receives the title and objective of the invention and transmits them to the second component.

[0087] In the second preprocessing step, the second component receives the title and objective of the invention and shares them internally. The second component comprises a first subcomponent and a second subcomponent. The second subcomponent includes a database and a management system, the database of which stores technical documents.

[0088] In the third preprocessing step, the first subcomponent creates a query. The query includes a request to collect documents related to the title and objectives of the invention from the database as search results.

[0089] In the fourth preprocessing step, the management system generates search results according to the query.

[0090] In the fifth preprocessing step, the first subcomponent creates the seventh instruction statement. The seventh instruction statement includes the seventh instruction, search results, and objectives, the seventh instruction including a procedure for selecting appropriate documents relating to the objectives based on the search results.

[0091] In the sixth preprocessing step, the second component sends the seventh instruction to the third component.

[0092] In the seventh preprocessing step, the third component receives the seventh instruction and generates a document using a large-scale language model.

[0093] In the eighth preprocessing step, the third component sends the document to the second component.

[0094] In the ninth preprocessing step, the second component receives the document and sends it to the first component.

[0095] In the tenth preprocessing step, the first component receives the document and performs the first step described above.

[0096] This allows for the collection of documents related to the invention's title and objectives from the database into the search results. Furthermore, appropriate documents related to the objectives can be selected from the search results. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided. [Effects of the Invention]

[0097] 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.

[0098] 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]

[0099] [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 an information processing system according to an embodiment. [Figure 3] Figure 3 is a diagram illustrating the configuration of components used in the information processing system according to the embodiment. [Figure 4] Figures 4(A) to 4(C) illustrate the structure of instruction statements used in the information processing system according to the embodiment. [Figure 5] Figure 5 is a diagram illustrating the structure of instruction statements used in the information processing system according to the embodiment. [Figure 6] Figures 6(A) to 6(C) illustrate the structure of instruction statements used in the information processing system according to the embodiment. [Figure 7] Figure 7 is a diagram illustrating the structure of an instruction statement used in an information processing system according to an embodiment. [Figure 8] Figure 8 is a diagram illustrating the configuration of an information processing system according to an embodiment. [Figure 9] Figure 9 is a diagram illustrating the configuration of components used in the information processing system according to the embodiment. [Figure 10] Figure 10 is a diagram illustrating the structure of an instruction statement used in an information processing system according to an embodiment. [Figure 11] Figure 11 is a diagram illustrating the configuration of an information processing device used in an information processing system according to an embodiment. [Figure 12] Figure 12 is a diagram illustrating an information processing method according to an embodiment. [Figure 13] Figure 13 is a diagram illustrating an information processing method 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. [Modes for carrying out the invention]

[0100] An information processing system according to one aspect of the present invention comprises a first component, a second component, and a third component.

[0101] The first component has the functionality to receive documents and objectives and transmit them to the third component, and the functionality to receive and provide proposed examples. The documents include technical information related to the objectives.

[0102] The second component includes the function of receiving the first instruction and the second instruction and sending the first configuration and proposed embodiment 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 generating the first configuration according to the first instruction and the function of generating a proposed embodiment according to the second instruction.

[0103] The third component includes the function of receiving and sharing documents, objectives, and the first configuration within the third component, and the function of receiving proposed embodiments and sending them to the first component. The third component also includes the first subcomponent.

[0104] The first subcomponent has the function of creating and executing a first prompt chain, the first prompt chain including a first instruction and a second instruction. The first instruction includes a first instruction, a document, and an objective, and the first instruction includes a procedure to propose a first configuration with reference to the document. The first configuration is a configuration not described in the document, and the first configuration is a configuration related to the objective. The second instruction includes a second instruction and a first configuration, and the second instruction includes a procedure to generate a proposed embodiment based on the first configuration.

[0105] This allows for the proposal of a first configuration not described in the document. Furthermore, it allows for the proposal of a first configuration related to the objective. Additionally, it allows for the generation of a proposed implementation based on the first configuration. For example, a user of the information processing system can try implementing the first configuration according to the proposed implementation. Furthermore, for example, a user of the information processing system can verify the effectiveness of the first configuration. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0106] 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.

[0107] 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., process order or layering order). Furthermore, even if a term does not have an ordinal number in this specification, an ordinal number may be added in the claims to avoid confusion of components. Even if a term has an ordinal number in this specification, a different ordinal number may be added in the claims. Even if a term has an ordinal number in this specification, an ordinal number may be omitted in the claims.

[0108] In the drawings attached to this specification, the components are classified by function and shown as independent blocks in block diagrams. However, in reality, it is difficult to completely separate the components by function, and one component may be involved in multiple functions.

[0109] (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 11.

[0110] Figures 1 and 2 illustrate the configuration of an information processing system according to one embodiment of the present invention.

[0111] Figure 3 is a diagram illustrating the configuration of components used in an information processing system according to one embodiment of the present invention.

[0112] Figure 4(A) is a diagram illustrating the configuration of a prompt chain used in an information processing system according to one embodiment of the present invention, and Figures 4(B) and 4(C) are diagrams illustrating the configuration of instruction statements transmitted and received within the information processing system.

[0113] Figure 5 illustrates the structure of instruction statements transmitted and received within an information processing system according to one embodiment of the present invention.

[0114] Figure 6(A) is a diagram illustrating the configuration of a prompt chain used in an information processing system according to one embodiment of the present invention, and Figures 6(B) and 6(C) are diagrams illustrating the configuration of instruction statements transmitted and received within the information processing system.

[0115] Figure 7 illustrates the structure of instruction statements transmitted and received within an information processing system according to one embodiment of the present invention.

[0116] Figure 8 is a diagram illustrating the configuration of an information processing system according to one embodiment of the present invention.

[0117] Figure 9 is a diagram illustrating the configuration of components used in an information processing system according to one embodiment of the present invention.

[0118] Figure 10 is a diagram illustrating the structure of instruction statements transmitted and received within an information processing system according to one embodiment of the present invention.

[0119] Figure 11 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.

[0120] <Example of an information processing system configuration 1> An information processing system according to one aspect of the present invention includes component 110, component 130, and component 120 (see Figure 1).

[0121] For example, 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. Furthermore, these communication devices can be connected to each other via the network 51 to constitute an information processing system according to one embodiment of the present invention.

[0122] <Component 110 Configuration Example 1> Component 110 has the function of receiving a document (Doc) and a target (Trg) and sending them to component 120 (see Figure 2). The document (Doc) contains technical information related to the target (Trg).

[0123] For example, the required specifications for a product can be used as the target specification (Trg). Furthermore, prior art documents related to the target specification (Trg) can be used in the documentation (Doc). Specifically, the resolution of a display device can be used as the target specification (Trg), and prior art documents related to the resolution of a display device can be used in the documentation (Doc). Additionally, the luminous efficiency of a light-emitting device can be used as the target specification (Trg), and prior art documents related to the luminous efficiency of a light-emitting device can be used in the documentation (Doc).

[0124] Furthermore, one or more references can be used in a document (Doc). Additionally, materials created from multiple references can be used in a document (Doc).

[0125] For example, a user 99 of the information processing system inputs a document (Doc) and a target (Trg) into component 110. Alternatively, for example, a user inputs a command to select and send a document (Doc) and a target (Trg) stored in a storage device into component 110. Specifically, the user 99 of the information processing system inputs into component 110 using an input device such as a keyboard, mouse, facsimile machine, or eye-tracking device.

[0126] Furthermore, component 110 has the function of receiving the embodiment Emb2 and providing it, for example, to the user 99 of the information processing system. Specifically, it provides it to the user 99 of the information processing system using output devices such as a display device, speaker, printer, facsimile machine, and storage device.

[0127] For example, a document showing how to implement the invention can be used in Example Emb2. A document written so that a person with ordinary skill in the art to which the invention for which a patent is sought can implement it can also be used in Example Emb2. Furthermore, a document showing how to implement it specifically can also be used in Example Emb2. Additionally, a document listing at least one best-presumed implementation can be used in Example Emb2. In this specification, Example Emb2 and Example Emb3 include a document describing an embodiment of the invention, and preferably, a document specifically illustrating an embodiment of the invention.

[0128] <Component 130 Configuration Example 1> Component 130 has the function of receiving instruction statements Pt21 and Pt22. Component 130 also has the function of sending configuration Cmp2 and example Emb2 to component 120, and the function of performing processing using the large-scale language model LLM.

[0129] 《Example Configuration of a Large-Scale Language Model (LLM) 1》 The large-scale language model LLM has the function to generate configuration Cmp2 according to instruction Pt21. Furthermore, the large-scale language model LLM has the function to generate example Emb2 according to instruction Pt22.

[0130] A large-scale language model (LLM) is a language model that has been trained on a large amount of document data. For example, large-scale language models such as GPT-3(registered trademark), GPT-3.5, GPT-4(registered trademark), LaMDA, Llama2, or Llama3 can be used in the large-scale language model (LLM). In this specification, textual information written in characters is referred to as a document. A document includes characters, strings of characters, sentences, documents, etc.

[0131] <Component 120 Configuration Example 1> Component 120 includes the function of receiving document Doc, target Trg, and configuration Cmp2 and sharing them internally within component 120, the function of sending instruction statement Pt21 and instruction statement Pt22 to component 130, and the function of receiving embodiment proposal Emb2 and sending it to component 110.

[0132] Furthermore, component 120 includes subcomponent 120A (see Figure 3). For the purposes of this specification, a configuration having one or more functions is referred to as a component or subcomponent.

[0133] 《Example Configuration of Subcomponent 120A》 Subcomponent 120A has the function of creating and executing a prompt chain PC2. Prompt chain PC2 includes instruction statements Pt21 and Pt22 (see Figure 4(A)). A prompt chain is a technique that uses the response to the previous instruction statement as part of the next instruction statement.

[0134] [Directive Pt21] Instruction Pt21 includes instruction g21, document Doc, and objective Trg (see Figure 4(B)). Instruction g21 includes a procedure to propose configuration Cmp2 based on document Doc. Note that configuration Cmp2 is a configuration not described in document Doc. Furthermore, configuration Cmp2 is a configuration related to objective Trg.

[0135] For example, the document in the following paragraph can be used as instruction Pt21.

[0136] "Create a comparative configuration by summarizing the configurations related to the objective (Trg) in document (Doc), and propose configurations (Cmp2) that are not included in the scope of the comparative configuration."

[0137] [Directive Pt22] Instruction Pt22 includes instruction g22 and configuration Cmp2 (see Figure 4(C)). Instruction g22 includes a procedure for generating example Emb2 based on configuration Cmp2.

[0138] For example, the document in the following paragraph can be used as instruction Pt22.

[0139] "Please create an example using the comparative configuration and configuration Cmp2, referring to the document Doc."

[0140] This allows for the proposal of configuration Cmp2 not described in document Doc. It also allows for the proposal of configuration Cmp2 related to target Trg. Furthermore, it allows for the generation of a proposed implementation Emb2 based on configuration Cmp2. For example, users of the information processing system can implement configuration Cmp2 according to the proposed implementation Emb2. Also, for example, users of the information processing system can verify the effectiveness of configuration Cmp2. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0141] <Example of Information Processing System Configuration 2> An information processing system according to one aspect of the present invention includes component 110, component 130, and component 120 (see Figure 2). Note that configuration example 2 of the information processing system differs from configuration example 1 of the information processing system in that it uses adjustment request AR.

[0142] <Component 110 Configuration Example 2> Component 110 has the function of receiving adjustment request AR and transmitting it to component 120. The adjustment request AR is a request for adjustment of the proposed embodiment Emb2.

[0143] For example, a user 99 of the information processing system can modify the content of the provided example implementation Emb2 using an adjustment request AR. They can also modify the proposed configuration Cmp2 using an adjustment request AR. Furthermore, they can modify the target Trg using an adjustment request AR. They can also adjust the content of the example implementation Emb2, configuration Cmp2, or target Trg based on their knowledge, experience, or intuition.

[0144] For example, a user 99 of the information processing system inputs an adjustment request AR into component 110. Alternatively, for example, a user inputs a command to component 110 to select and send an adjustment request AR stored in the memory device.

[0145] <Component 130 Configuration Example 2> Component 130 has the function of receiving instruction Pt23 and sending a new embodiment proposal Emb2 to component 120.

[0146] 《Example Configuration of a Large-Scale Language Model (LLM) 2》 The large-scale language model LLM has the function of generating a new example example Emb2 according to instruction Pt23.

[0147] <Component 120 Configuration Example 2> Component 120 has the function of receiving adjustment requests AR and sharing them internally within component 120.

[0148] 《Example Configuration of Subcomponent 120A 2》 Subcomponent 120A has the function of creating instruction statement Pt23 (see Figure 3).

[0149] [Directive Pt23] Instruction Pt23 includes instruction g23, example Emb2, and adjustment request AR (see Figure 5). Instruction g23 includes a procedure for adjusting example Emb2 in response to adjustment request AR.

[0150] For example, the document in the following paragraph can be used as instruction Pt23.

[0151] "Please make adjustments to Example Emb2 according to the adjustment request AR."

[0152] This allows, for example, a user of the information processing system to request adjustments to the proposed embodiment Emb2. Furthermore, an information processing system according to one embodiment of the present invention can adjust the proposed embodiment Emb2 upon request. Also, for example, a user of the information processing system can request adjustments to the proposed configuration Cmp2. Furthermore, an information processing system according to one embodiment of the present invention can adjust the configuration Cmp2 upon request. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0153] <Example of Information Processing System Configuration 3> An information processing system according to one aspect of the present invention includes component 110, component 130, and component 120 (see Figure 2). Note that configuration example 3 of the information processing system differs from configuration examples 1 and 2 of the information processing system in that it provides comparative example Emb1.

[0154] <Component 110 Configuration Example 3> Component 110 has the function of receiving comparative example Emb1 and providing it, for example, to a user 99 of the information processing system.

[0155] For example, a configuration disclosed in prior art documents can be used in Comparative Example Emb1. Furthermore, a document demonstrating the advantageous effects of configuration Cmp2 can be used in Comparative Example Emb1 by comparing it with Example Emb2, which describes configuration Cmp2.

[0156] <Component 130 Configuration Example 3> Component 130 has the function of receiving instruction statements Pt11 and Pt12. It also has the function of sending configuration Cmp1 and comparative example Emb1 to component 120.

[0157] 《Example 3 of the configuration of a large-scale language model (LLM)》 The large-scale language model LLM has the function of generating construct Cmp1 according to instruction Pt11. Furthermore, the large-scale language model LLM has the function of generating comparative example Emb1 according to instruction Pt12.

[0158] <Component 120 Configuration Example 3> Component 120 includes the function of receiving comparative example Emb1 and sending it to component 110.

[0159] 《Example Configuration of Subcomponent 120A 3》 Subcomponent 120A has the function of creating and executing prompt chain PC1. Prompt chain PC1 includes instruction statements Pt11 and Pt12 (see Figure 6(A)).

[0160] [Instruction Pt11] Instruction Pt11 includes instruction g11, document Doc, and objective Trg (see Figure 6(B)). Instruction g11 includes a procedure to propose configuration Cmp1 based on document Doc. Configuration Cmp1 is the configuration described in document Doc. Furthermore, configuration Cmp1 is a configuration related to objective Trg.

[0161] For example, the document in the following paragraph can be used as instruction Pt21.

[0162] "For document Doc, please create configuration Cmp1 by summarizing the configuration related to objective Trg."

[0163] Furthermore, when a document (Doc) contains multiple references, it is possible to have the system propose a structure related to the target Trg for each reference. Additionally, the proposed structures from each reference can be combined into a single structure (Cmp1).

[0164] [Instructive text Pt12] Instruction Pt12 includes instruction g12 and configuration Cmp1. Instruction g12 includes a procedure for generating comparative example Emb1 based on configuration Cmp1.

[0165] For example, the document in the following paragraph can be used as instruction Pt21.

[0166] "Create Comparative Example Emb1 from the configuration Cmp1, which falls under the category of conventional technology, referring to document Doc."

[0167] This allows for the proposal of configuration Cmp1 described in document Doc. It also allows for the proposal of configuration Cmp1 related to target Trg. Furthermore, comparative example Emb1 can be generated based on configuration Cmp1. For example, users of the information processing system can implement configuration Cmp1 according to comparative example Emb1. Also, for example, users of the information processing system can verify the effectiveness of configuration Cmp1. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0168] <Example of Information Processing System Configuration 4> An information processing system according to one aspect of the present invention includes component 110, component 130, and component 120 (see Figure 2). Note that configuration example 4 of the information processing system differs from configuration examples 1 to 3 of the information processing system in that it uses evaluation Evl.

[0169] <Component 110 Configuration Example 4> Component 110 has the function of receiving evaluation Evl and sending it to component 120. Evl is the result of evaluating the effectiveness of configuration Cmp2.

[0170] For example, a user 99 of the information processing system can implement the provided embodiment Emb2 and evaluate its effects. They can also implement the proposed configuration Cmp2 and evaluate its effects. Furthermore, the evaluation results can be used in evaluation Evl. Specifically, the proposed configuration Cmp2 of the light-emitting device can be implemented to evaluate its luminescence efficiency, and the measured luminescence efficiency can be used in evaluation Evl.

[0171] For example, a user 99 of the information processing system inputs the evaluation Evl into component 110. Alternatively, for example, a user inputs a command to component 110 to select and send an evaluation Evl stored in the storage device.

[0172] Furthermore, component 110 has a function to receive the embodiment Emb3 and provide it, for example, to the user 99 of the information processing system. Specifically, it provides it to the user 99 of the information processing system using output devices such as a display device, speaker, printer, facsimile machine, and storage device.

[0173] For example, Emb2, which describes how to implement the invention, can be used as Emb3 by adding the results of an evaluation of the effects of configuration Cmp2. Furthermore, Emb3 can include a document that enables a person with ordinary skill in the art to which the invention for which a patent is sought can implement the invention.

[0174] <Component 130 Configuration Example 4> Component 130 has the function of receiving instruction Pt3 and sending example Emb3 to component 120.

[0175] 《Example of a Large-Scale Language Model (LLM) Configuration 4》 The large-scale language model LLM has the function of generating an example Emb3 according to the instruction Pt3.

[0176] <Component 120 Configuration Example 4> Component 120 has the function of receiving evaluation Evl and sharing it internally, and the function of receiving example Emb3 and sending it to component 110.

[0177] 《Example Configuration of Subcomponent 120A 4》 Subcomponent 120A has the function of creating instruction statement Pt3.

[0178] [Instructive text Pt3] Instruction Pt3 includes instruction g3, example Emb2, and evaluation Evl (see Figure 7). Instruction g3 includes a procedure for generating example Emb3 based on example Emb2 and evaluation Evl.

[0179] For example, the document in the following paragraph can be used as instruction statement Pt3.

[0180] "Add the evaluation data Evl to Example Emb2 to complete Example Emb3."

[0181] This allows the evaluation Evl to be added to the proposed example Emb2 to generate example Emb3. Furthermore, configuration Cmp2 and its evaluation Evl, which are not described in document Doc, can be included in example Emb3. Additionally, the significant effects of configuration Cmp2, based on the evaluation Evl, can be described in example Emb3. The operation of configuration Cmp2 can also be described in example Emb3. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0182] <Example of an information processing system configuration 5> An information processing system according to one aspect of the present invention includes component 110, component 130, and component 120 (see Figure 8). Note that Information Processing System Configuration Example 5 differs from Information Processing System Configuration Examples 1 to 4 in that it uses the title of the invention ToI, objective Trg, database DB, and management system DBMS.

[0183] <Component 110 Configuration Example 5> Component 110 has the function of receiving the invention title ToI and objective Trg and transmitting them to component 120.

[0184] For example, the name of the product can be used as the title of the invention, ToI. The manufacturing method of the product can also be used as the title of the invention, ToI. The required specifications for the product or its manufacturing method can be used as the objective, Trg.

[0185] For example, a user 99 of the information processing system inputs the title of the invention ToI into component 110. Alternatively, for example, a user inputs a command to select and send the title of the invention ToI stored in a storage device into component 110. Specifically, the user 99 of the information processing system inputs into component 110 using an input device such as a keyboard, mouse, facsimile machine, or eye-tracking device.

[0186] Furthermore, component 110 has the function of receiving a document Doc and providing it, for example, to a user 99 of the information processing system. Specifically, it provides it to the user 99 of the information processing system using output devices such as a display device, speaker, printer, facsimile machine, and storage device.

[0187] <Component 130 Configuration Example 5> Component 130 has the function of receiving instruction Pt0 and sending document Doc to component 120.

[0188] 《Example 5 of the configuration of a large-scale language model (LLM)》 The large-scale language model (LLM) has the functionality to select a document (Doc) from the search results (SR) according to the instruction Pt0.

[0189] <Component 120 Configuration Example 5> Component 120 includes a function to receive the invention title ToI and objective Trg and share them internally within component 120, and a function to receive the document Doc and send it to component 110.

[0190] Furthermore, component 120 includes subcomponent 120B (see Figure 9).

[0191] 《Example Configuration of Subcomponent 120B》 Subcomponent 120B includes a database (DB) and a management system (DBMS). The database (DB) stores technical documents. The management system (DBMS) has the function of generating search results (SRs) according to queries (Que).

[0192] For example, patent databases, academic paper databases, and various databases publicly available on the internet can be used as databases.

[0193] 《Example Configuration of Subcomponent 120A 5》 Subcomponent 120A has the functionality to create a query Que and a directive Pt0.

[0194] [QueryQue] A query (Que) includes a request to collect documents related to the invention title (ToI) and objective (Trg) from the database (DB) into the search result (SR).

[0195] For example, a query (Que) can be created using the invention title (ToI) and target (Trg) as search keywords. Furthermore, relevant published patent applications can be collected from a patent database using the query (Que) to create a search result (SR).

[0196] Alternatively, for example, the document in the following paragraph can be used as an instruction to cause component 130 to generate a query (Que).

[0197] "For the invention title (ToI) and objective (Trg), please suggest patent classifications and keywords. Next, suggest synonyms for each keyword. Finally, create a search query using the patent classifications, keywords, and keyword synonyms."

[0198] [Instructive sentence Pt0] Instruction Pt0 includes instruction g0, search result SR, and target Trg (see Figure 10). Instruction g0 includes a procedure to select an appropriate document Doc related to target Trg based on the search result SR.

[0199] For example, the document in the following paragraph can be used as instruction Pt21.

[0200] "Regarding the target Trg, please select appropriate references from the list of search results (SR) below for reference."

[0201] This allows for the collection of literature related to the invention title (ToI) and target (Trg) from the database (DB) into the search results (SR). Furthermore, appropriate documents (Doc) related to the target (Trg) can be selected from the search results (SR). As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0202] <Example of information processing device configuration> 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 11).

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 《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.

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] The processing unit 23 may have either or both an OS transistor and a transistor having silicon in its channel formation region (Si transistor).

[0223] 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 operated only when necessary, and at other times the information of the previous processing is saved to the memory element, thereby turning off the processing unit. In other words, normally-off computing becomes possible, and the power consumption of the information processing system can be reduced.

[0224] It is preferable for information processing devices to use AI for at least some of their processing.

[0225] 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).

[0226] 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.

[0227] 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."

[0228] 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."

[0229] 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.

[0230] 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, an external bus, LAN, or the internet can be used as the transmission line 25.

[0231] This embodiment can be appropriately combined with other embodiments shown in this specification.

[0232] (Embodiment 2) In this embodiment, an information processing method according to one aspect of the present invention will be described with reference to Figures 12 to 16.

[0233] Figure 12 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0234] Figure 13 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0235] Figure 14 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0236] Figure 15 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0237] Figure 16 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0238] <Example of information processing method 1> An information processing method according to one aspect of the present invention comprises steps S1 to S11 (see Figure 12).

[0239] <Step S1> In step S1, component 110 receives document Doc and target Trg and transmits them to component 120. Document Doc contains technical information related to target Trg.

[0240] For example, a user 99 of the information processing system inputs a document (Doc) and a target (Trg) into component 110. Alternatively, for example, a user inputs a command into component 110 to select and send a document (Doc) and a target (Trg) stored in a storage device.

[0241] <Step S2> In step S2, component 120 receives the document Doc and the objective Trg and shares them internally within component 120.

[0242] Furthermore, component 120 includes subcomponent 120A. Subcomponent 120A has the function of creating and executing a prompt chain PC2, and the prompt chain PC2 includes instruction statements Pt21 and Pt22.

[0243] <Step S3> In step S3, component 120 sends instruction Pt21 to component 130.

[0244] Instruction Pt21 includes instruction g21, document Doc, and objective Trg. Instruction g21 includes a procedure to propose configuration Cmp2 by referring to document Doc. Furthermore, configuration Cmp2 is a configuration not described in document Doc, and configuration Cmp2 is a configuration related to objective Trg.

[0245] <Step S4> In step S4, component 130 receives instruction Pt21 and generates configuration Cmp2 using the large-scale language model LLM.

[0246] <Step S5> In step S5, component 130 sends configuration Cmp2 to component 120.

[0247] <Step S6> In step S6, component 120 receives configuration Cmp2 and shares it internally within component 120.

[0248] <Step S7> In step S7, component 120 sends instruction Pt22 to component 130.

[0249] Instruction Pt22 includes instruction g22 and configuration Cmp2, where instruction g22 includes a procedure for generating example Emb2 based on configuration Cmp2.

[0250] <Step S8> In step S8, component 130 receives instruction Pt22 and generates example Emb2 using the large-scale language model LLM.

[0251] <Step S9> In step S9, component 130 sends the proposed embodiment Emb2 to component 120.

[0252] <Step S10> In step S10, component 120 receives the proposed embodiment Emb2 and transmits it to component 110.

[0253] <Step S11> In step S11, component 110 receives the embodiment Emb2 and provides it, for example, to a user 99 of the information processing system. Step S12 can be executed immediately following step S11.

[0254] This allows for the proposal of configuration Cmp2 not described in document Doc. It also allows for the proposal of configuration Cmp2 related to target Trg. Furthermore, a proposed implementation Emb2 can be generated based on configuration Cmp2. For example, a user of the information processing system can implement configuration Cmp2 according to the proposed implementation Emb2. Also, for example, a user of the information processing system can verify the effectiveness of configuration Cmp2. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0255] <Example of information processing method 2> Furthermore, one embodiment of the present invention includes steps S12 to S18 (see Figure 13).

[0256] <Step S12> In step S12, if there is an input for adjustment request AR (Input: AR), component 110 accepts the adjustment request AR and sends it to component 120. Note that in step S12, step S19 can be executed without inputting an adjustment request AR (Input: go_on).

[0257] For example, a user 99 of the information processing system inputs a command to component 110 to proceed to adjustment request AR or step S19. Alternatively, for example, a user inputs a command to component 110 to select and send a command to proceed to adjustment request AR or step S19 stored in the storage device.

[0258] <Step S13> In step S13, component 120 accepts the adjustment request AR and shares it internally within component 120. Note that sub-component 120A has a function of generating instruction Pt23.

[0259] <Step S14> In step S14, component 120 transmits instruction Pt23 to component 130.

[0260] Instruction Pt23 includes instruction g23, example proposal Emb2 and adjustment request AR, and instruction g23 includes a procedure for adjusting example proposal Emb2 in response to adjustment request AR.

[0261] <Step S15> In step S15, component 130 accepts instruction Pt23, and adjusts example proposal Emb2 using large language model LLM.

[0262] <Step S16> In step S16, component 130 transmits example proposal Emb2 to component 120.

[0263] <Step S17> In step S17, component 120 transmits example proposal Emb2 to component 110.

[0264] <Step S18> In step S18, component 110 accepts example proposal Emb2 and provides it to, for example, user 99 of the information processing system. Note that step S19 can be executed subsequent to step S18.

[0265] This allows, for example, a user of the information processing system to request adjustments to the proposed embodiment Emb2. Furthermore, an information processing system according to one embodiment of the present invention can adjust the proposed embodiment Emb2 upon request. Also, for example, a user of the information processing system can request adjustments to the proposed configuration Cmp2. Furthermore, an information processing system according to one embodiment of the present invention can adjust the configuration Cmp2 upon request. As a result, a novel information processing method with superior convenience, usefulness, or reliability can be provided.

[0266] <Example 3 of information processing methods> Furthermore, an information processing method according to one embodiment of the present invention includes steps S19 to S25 (see Figure 14).

[0267] <Step S19> In step S19, if there is an input for evaluation Evl (Input: Evl), component 110 accepts the evaluation Evl and sends it to component 120. Note that in step S19, step S26 can be executed without inputting an evaluation Evl (Input: go_on).

[0268] For example, a user 99 of the information processing system inputs to component 110 to proceed to evaluation Evl or step S26. Alternatively, for example, inputs to component 110 a command to select and send evaluation Evl or proceed to step S26 stored in the storage device.

[0269] <Step S20> In step S20, component 120 receives the evaluation Evl and shares it internally. Subcomponent 120A has the function of creating instruction statement Pt3.

[0270] <Step S21> In step S21, component 120 sends instruction Pt3 to component 130. Instruction Pt3 includes instruction g3, example Emb2, and evaluation Evl, and instruction g3 includes a procedure to generate example Emb3 based on example Emb2 and evaluation Evl.

[0271] <Step S22> In step S22, component 130 receives instruction Pt3 and generates example Emb3 using the large-scale language model LLM.

[0272] <Step S23> In step S23, component 130 sends the embodiment Emb3 to component 120.

[0273] <Step S24> In step S24, component 120 receives the embodiment Emb3 and sends it to component 110.

[0274] <Step S25> In step S25, component 110 receives the embodiment Emb3 and provides it, for example, to the user 99 of the information processing system. Step S26 can be executed immediately following step S25.

[0275] This allows the evaluation Evl to be added to the proposed example Emb2 to generate example Emb3. Configuration Cmp2 and its evaluation Evl, which are not described in document Doc, can be included in example Emb3. Furthermore, based on the evaluation Evl, the significant effects of configuration Cmp2 can be described in example Emb3. Additionally, the operation of configuration Cmp2 can be described in example Emb3. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0276] <Example of information processing method 4> Furthermore, the information processing method according to one aspect of the present invention includes steps S26 to S34 (see FIG. 15).

[0277] Note that subcomponent 120A has a function of creating and executing prompt chain PC1, and prompt chain PC1 includes instruction sentence Pt11 and instruction sentence Pt12.

[0278] <Step S26> In step S26, component 120 transmits instruction sentence Pt11 to component 130.

[0279] Instruction sentence Pt11 includes instruction g11, document Doc, and target Trg. Note that instruction g11 includes a procedure for causing proposal of configuration Cmp1 with reference to document Doc. Furthermore, configuration Cmp1 is a configuration described in document Doc, and configuration Cmp1 is a configuration related to target Trg.

[0280] <Step S27> In step S27, component 130 receives instruction sentence Pt11, and generates configuration Cmp1 using large language model LLM.

[0281] <Step S28> In step S28, component 130 transmits configuration Cmp1 to component 120.

[0282] <Step S29> In step S29, component 120 receives configuration Cmp1, and shares the configuration Cmp1 internally within component 120.

[0283] <Step S30> In step S30, component 120 transmits instruction sentence Pt12 to component 130.

[0284] Instruction Pt12 includes instruction g12 and configuration Cmp1, where instruction g12 includes a procedure for generating comparative example Emb1 based on configuration Cmp1.

[0285] <Step S31> In step S31, component 130 receives instruction Pt12 and generates comparative example Emb1 using the large-scale language model LLM.

[0286] <Step S32> In step S32, component 130 sends comparative example Emb1 to component 120.

[0287] <Step S33> In step S33, component 120 receives comparative example Emb1 and transmits it to component 110.

[0288] <Step S34> In step S34, component 110 receives comparative example Emb1 and provides it, for example, to a user 99 of the information processing system.

[0289] This allows for the proposal of configuration Cmp1 described in document Doc. It also allows for the proposal of configuration Cmp1 related to target Trg. Furthermore, comparative example Emb1 can be generated based on configuration Cmp1. For example, a user of the information processing system can try implementing configuration Cmp1 according to comparative example Emb1. Also, for example, a user of the information processing system can verify the effectiveness of configuration Cmp1. As a result, a novel information processing method with superior convenience, usefulness, or reliability can be provided.

[0290] <Example 5 of information processing methods> Furthermore, one aspect of the present invention provides an information processing method comprising preprocessing steps Prep1 to Prep10 (see Figure 16).

[0291] <Pre-processing step Prep1> In the preprocessing step Prep1, component 110 receives the invention title ToI and target Trg and transmits them to component 120.

[0292] <Pre-processing step Prep2> In the preprocessing step Prep2, component 120 receives the invention title ToI and objective Trg and shares them internally within component 120.

[0293] Component 120 comprises subcomponent 120A and subcomponent 120B. Subcomponent 120B includes a database DB and a management system DBMS, with the database DB storing technical documents.

[0294] <Pre-processing step Prep3> In the preprocessing step Prep3, subcomponent 120A creates a query Que. The query Que includes a request to collect documents related to the invention title ToI and target Trg from the database DB into the search results SR.

[0295] <Pre-processing step Prep4> In the preprocessing step Prep4, the management system (DBMS) creates the search result SR according to the query Que.

[0296] <Pre-treatment step Prep5> In the preprocessing step Prep5, subcomponent 120A creates instruction statement Pt0. Instruction statement Pt0 includes instruction g0, search result SR, and target Trg, and instruction g0 includes a procedure to select an appropriate document Doc related to target Trg based on the search result SR.

[0297] <Pre-processing step Prep6> In the preprocessing step Prep6, component 120 sends instruction Pt0 to component 130.

[0298] <Pre-processing step Prep7> In the preprocessing step Prep7, component 130 receives instruction Pt0 and generates document Doc using the large-scale language model LLM.

[0299] <Pre-processing step Prep8> In the preprocessing step Prep8, component 130 sends the document Doc to component 120.

[0300] <Pre-processing step Prep9> In the preprocessing step Prep9, component 120 receives the document Doc and sends it to component 110.

[0301] <Pre-processing step Prep10> In the preprocessing step Prep10, component 110 receives the document Doc. Following the preprocessing step Prep10, the process can proceed to step S1 of Example 1 of the information processing method in this embodiment.

[0302] This allows for the collection of literature related to the invention title (ToI) and target (Trg) from the database (DB) into the search results (SR). Furthermore, appropriate documents (Doc) related to the target (Trg) can be selected from the search results (SR). As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0303] This embodiment can be appropriately combined with other embodiments shown in this specification. [Explanation of Symbols]

[0304] AR adjustment request DB Database DBMS Management System Doc document Evl rating g11 instructions g12 instructions g21 instructions g22 instructions g23 instructions Large-Scale Language Model (LLM) Pt11 instructions Pt12 instructions Pt21 instructions Pt22 instructions Pt23 instructions Que Query SR search results ToI name Trg goal 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 130 components

Claims

1. Functions for receiving documents and objectives, The function of providing example embodiments, It has the capability to perform processing using a large-scale language model, The aforementioned document includes technical information relating to the aforementioned objective, The large-scale language model includes a function to generate a first configuration according to a first instruction and a function to generate the proposed embodiment according to a second instruction. The first instruction statement includes the first instruction, the document, and the objective, The first instruction includes a procedure for proposing the first configuration with reference to the aforementioned document, The first configuration described above is a configuration not described in the above document and is a configuration related to the above objective, The second instruction statement includes the second instruction and the first configuration, The second instruction includes a procedure for generating the proposed embodiment based on the first configuration, which is part of an information processing system.

2. The first component and The second component, It has a third component, The first component includes a function to receive documents and objectives and transmit them to the third component, and a function to receive and provide proposed embodiments. The aforementioned document includes technical information relating to the aforementioned objective, The second component has the function of receiving the first instruction and the second instruction and transmitting the first configuration and the proposed embodiment to the third component, It has the capability to perform processing using a large-scale language model, The large-scale language model includes a function to generate the first configuration according to the first instruction and a function to generate the proposed embodiment according to the second instruction, The third component includes a function to receive the document, the objective and the first configuration and share them internally within the third component, a function to transmit the first instruction and the second instruction to the second component, and a function to receive the proposed embodiment and transmit it to the first component. The third component comprises a first subcomponent, The first subcomponent has the function of creating and executing a first prompt chain, The first prompt chain includes the first instruction and the second instruction, The first instruction statement includes the first instruction, the document, and the objective, The first instruction includes a procedure for proposing the first configuration with reference to the aforementioned document, The first configuration described above is a configuration not described in the above document, The first configuration is a configuration related to the objective, The second instruction statement includes the second instruction and the first configuration, The second instruction includes a procedure for generating the proposed embodiment based on the first configuration, which is part of an information processing system.

3. The first component has the function of receiving adjustment requests and transmitting them to the third component. The aforementioned adjustment request is a request for adjustment of the aforementioned embodiment, The second component has a function to receive a third instruction and transmit a new embodiment to the third component. The large-scale language model has a function to generate the new embodiment proposal according to the third instruction, The third component has a function to receive the adjustment request and share it internally within the third component. The first subcomponent has the function of creating the third instruction statement, The third instruction statement includes the third instruction, the proposed embodiment, and the adjustment request, The information processing system according to claim 2, wherein the third instruction includes a procedure for adjusting the proposed embodiment in response to the adjustment request.

4. The first component described above has the function of receiving and providing comparative examples, The second component has the function of receiving the fourth instruction and the fifth instruction and transmitting the second configuration and the comparative example to the third component, The large-scale language model includes a function to generate the second configuration according to the fourth instruction, and a function to generate the comparative example according to the fifth instruction, The third component includes a function to receive the comparative example and transmit it to the first component, The first subcomponent has the function of creating and executing a second prompt chain. The second prompt chain includes the fourth instruction and the fifth instruction, The fourth instruction statement includes the fourth instruction, the document, and the objective, The fourth instruction includes a procedure for proposing the second configuration with reference to the aforementioned document, The second configuration is the configuration described in the above document, The second configuration described above is a configuration related to the objective, The fifth instruction includes the fifth instruction and the second configuration, The information processing system according to claim 2, wherein the fifth instruction includes a step of generating the comparative example based on the second configuration.

5. The first component includes a function to receive evaluations and transmit them to the third component, and a function to receive and provide embodiments. The above evaluation is the result of evaluating the effect of the first configuration, The second component has a function to receive a sixth instruction and transmit the embodiment to the third component. The large-scale language model has a function to generate the embodiment according to the sixth instruction, The third component includes a function to receive the evaluation and share it internally, and a function to receive the embodiment and transmit it to the first component. The first subcomponent has the function of creating the sixth instruction statement, The sixth instruction includes the sixth instruction, the proposed embodiment, and the evaluation. The information processing system according to claim 2, wherein the sixth instruction includes a step of generating the embodiment based on the proposed embodiment and the evaluation.

6. The first component includes a function to receive the title of the invention and the objective and transmit them to the third component, and a function to receive and provide the document. The second component has the function of receiving the seventh instruction and transmitting the document to the third component, The large-scale language model has a function to select the document from the search results in accordance with the seventh instruction, The third component includes a function to receive the title of the invention and the objective and share them internally within the third component, and a function to receive the document and transmit it to the first component. The third component comprises a second subcomponent, The second subcomponent comprises a database and a management system, The aforementioned database stores technical documents, The management system has a function to create the search results according to the query, The first subcomponent has the function of creating the query and the seventh instruction statement, The query includes a request to collect the title of the invention and the literature relating to the objective from the database into the search results. The seventh instruction includes the seventh instruction, the search results, and the objective, The information processing system according to claim 2, wherein the seventh instruction includes a step of selecting an appropriate document relating to the objective based on the search results.

7. An information processing method comprising the first to eleventh steps, In the first step described above, the first component receives the document and objective and transmits them to the second component. The aforementioned document includes technical information relating to the aforementioned objective, In the second step, the second component receives the document and the objective and shares them within the second component. The second component comprises a first subcomponent, The first subcomponent has the function of creating and executing a first prompt chain, The first prompt chain includes a first instruction and a second instruction, In the third step, the second component transmits the first instruction to the third component. The first instruction statement includes the first instruction, the document, and the objective, The first instruction above includes a procedure for proposing a first configuration with reference to the above document, The first configuration described above is a configuration not described in the above document, The first configuration is a configuration related to the objective, In the fourth step, the third component receives the first instruction and generates the first configuration using a large-scale language model. In the fifth step, the third component transmits the first configuration to the second component. In the sixth step, the second component receives the first configuration and shares it within the second component. In the seventh step, the second component transmits the second instruction to the third component. The second instruction statement includes the second instruction and the first configuration, The second instruction includes a procedure for generating a proposed embodiment based on the first configuration, In the eighth step, the third component receives the second instruction and generates the proposed embodiment using the large-scale language model. In the ninth step, the third component transmits the proposed embodiment to the second component. In the tenth step, the second component receives the proposed embodiment and transmits it to the first component. In the eleventh step, the first component is an information processing method that receives and provides the embodiment.

8. An information processing method comprising steps 12 through 18, In the twelfth step, the first component receives an adjustment request and transmits it to the second component. In the 13th step, the second component receives the adjustment request and shares it internally within the second component. The first subcomponent is equipped with the function of creating a third instruction statement, In the 14th step, the second component transmits the third instruction to the third component. The third instruction statement includes the third instruction, the proposed embodiment, and the adjustment request, The third instruction includes a procedure for adjusting the proposed embodiment in response to the adjustment request, In the 15th step, the third component receives the third instruction and adjusts the proposed embodiment using the large-scale language model. In the sixteenth step, the third component transmits the proposed embodiment to the second component. In step 17, the second component transmits the proposed embodiment to the first component. The information processing method according to claim 7, wherein in the 18th step, the first component receives and provides the embodiment.

9. An information processing method comprising steps 19 to 25, In step 19, the first component receives the evaluation and transmits it to the second component. In the 20th step, the second component receives the evaluation and shares it internally within the second component. The first subcomponent described above has the function of creating a fourth instruction statement, In step 21 above, the second component transmits the fourth instruction to the third component, The fourth instruction includes the fourth instruction, the proposed embodiment, and the evaluation. The fourth instruction includes a procedure for generating an embodiment based on the proposed embodiment and the evaluation, In step 22, the third component receives the fourth instruction and generates the embodiment using the large-scale language model. In step 23 above, the third component transmits the embodiment to the second component, In the 24th step, the second component receives the embodiment and transmits it to the first component. In the 25th step, the first component receives and provides the embodiment, the information processing method according to claim 7.

10. An information processing method comprising steps 26 to 34, The first subcomponent has the function of creating and executing a second prompt chain. The second prompt chain includes a fifth instruction and a sixth instruction, In step 26, the second component transmits the fifth instruction to the third component. The fifth instruction statement includes the fifth instruction, the document, and the objective, The fifth instruction includes a procedure for proposing a second configuration with reference to the aforementioned document, The second configuration is the configuration described in the above document, The second configuration described above is a configuration related to the objective, In step 27, the third component receives the fifth instruction and generates the second configuration using the large-scale language model. In step 28 above, the third component transmits the second configuration to the second component, In step 29, the second component receives the second configuration and shares it within the second component. In step 30, the second component transmits the sixth instruction to the third component. The sixth instruction includes the sixth instruction and the second configuration, The sixth instruction includes a procedure for generating a comparative example based on the second configuration, In the 31st step, the third component receives the sixth instruction and generates the comparative example using the large-scale language model. In step 32 above, the third component transmits the comparative example to the second component. In step 33, the second component receives the comparative example and transmits it to the first component. The information processing method according to claim 7, wherein in the 34th step, the first component receives and provides the comparative example.

11. The process comprises a first to tenth pre-treatment step, In the first preprocessing step, the first component receives the title of the invention and the objective and transmits them to the second component. In the second preprocessing step, the second component receives the title of the invention and the objective, and shares them internally within the second component. The second component comprises the first subcomponent and the second subcomponent, The second subcomponent comprises a database and a management system, The aforementioned database stores technical documents, In the third preprocessing step, the first subcomponent creates a query, The query includes a request to collect from the database the title of the invention and the literature relating to the objective, In the fourth preprocessing step, the management system creates the search results according to the query, In the fifth preprocessing step, the first subcomponent creates a seventh instruction statement, The seventh instruction includes the seventh instruction, the search results, and the objective, The seventh instruction includes a procedure for selecting the appropriate document relating to the objective based on the search results, In the sixth preprocessing step, the second component transmits the seventh instruction to the third component. In the seventh preprocessing step, the third component receives the seventh instruction and generates the document using the large-scale language model. In the eighth preprocessing step, the third component transmits the document to the second component. In the ninth preprocessing step, the second component receives the document and transmits it to the first component. The information processing method according to claim 7, wherein in the tenth preprocessing step, the first component receives the document and performs the first step.

Images