Information processing systems, information processing methods

Abstract

To provide a novel information processing system that is superior in convenience, usefulness, or reliability. [Solution] An information processing system consisting of a first component, a second component, and a third component. The first component has the function of receiving and transmitting opinions and receiving words to prompt responses. The second component has the function of receiving instruction sentences and prompting responses. A large-scale language model generates words to prompt responses and opinions according to the instruction sentences. The third component has the function of receiving opinions, transmitting instruction sentences, and receiving the generated words to prompt responses and opinions. It also has the function of creating instruction sentences. The instruction sentences contain background information and consensus, and can extract novel and inventive ideas and enhance patentability. The system allows users to input opinions and extract novel and inventive ideas. Users can also engage in dialogue by playing the role of a player, deepening their thinking.

Description

Technical Field

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

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

Background Art

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

[0004] By using a large language model, the capabilities of natural language processing models have been significantly improved. On the other hand, due to the enlargement of language models, it is difficult to build and operate a language model on one's own in terms of facilities and costs. Therefore, using services that provide language models, services that use language models (for example, AI chat services or AI agent services), etc. has become one form of using 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) One aspect of the present invention is an information processing system having a function to receive a first opinion and create a first instruction, a second instruction, a third instruction, and a fourth instruction; and a function to receive a response prompting word, a second opinion that is positive to the first opinion, and a third opinion that is negative to the first opinion from a large-scale language model and transmit a response prompting word.

[0009] The first instruction includes a procedure for generating words that prompt the player to respond, the second instruction includes a procedure for generating words that prompt a response based on the first opinion, the second opinion, or the third opinion, the third instruction includes a procedure for generating the second opinion, and the fourth instruction includes a procedure for generating the third opinion.

[0010] The large-scale language model includes a function to generate words that prompt a response according to a first and second instruction, a function to generate a new second opinion according to a third instruction, and a function to generate a new third opinion according to a fourth instruction.

[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 includes the function of receiving a first opinion and sending it to the third component, and the function of receiving and providing words to prompt a response.

[0013] The second component includes the function of receiving the first, second, third, and fourth instructions and sending response prompts, a second opinion, and a third opinion to the third component, as well as the function of processing using a large-scale language model. The large-scale language model includes the function of generating response prompts according to the first and second instructions, the function of generating a second opinion according to the third instruction, and the function of generating a third opinion according to the fourth instruction. The response prompts are words that prompt a response from any one of the first, second, or third players.

[0014] The third component includes the function of receiving a first opinion from the first component and sending a first instruction, a second instruction, a third instruction, and a fourth instruction to the second component; the function of receiving a prompting word, a second opinion, and a third opinion from the second component; and the function of sending a prompting word to the first component when the prompting word prompts the first player to respond.

[0015] The third component comprises a first subcomponent, the first subcomponent comprising a function to create a first instruction sentence, and a function to create a second instruction sentence when a first opinion, a second opinion, or a third opinion is received. It also comprises a function to create a third instruction sentence when a response prompting word prompts a second player to respond. It also comprises a function to create a fourth instruction sentence when a response prompting word prompts a third player to respond.

[0016] The first instruction includes the first instruction and the first background information, and the first instruction includes a procedure for generating words that prompt the first player to respond, based on the first background information. The first background information includes information that specifies the consensus and the tendency of the words that prompt a response, and the consensus includes the purpose of working with other players to extract novel and inventive ideas from the first player's first opinion and to enhance patentability.

[0017] The second instruction includes the second instruction and the first opinion, the second opinion, or the third opinion, and the second instruction includes a procedure to select one of the first player, the second player, and the third player as the target to prompt a response based on the first background information, and to generate words to prompt a response based on the first opinion, the second opinion, or the third opinion.

[0018] The third instruction includes the third instruction, the first opinion, the second opinion, or the third opinion, and the second background information, and the third instruction includes a procedure for generating a new second opinion based on the second background information and taking into account the first opinion, the second opinion, or the third opinion. The second background information includes information specifying the consensus and the tendency of the second opinion.

[0019] The fourth instruction includes the fourth instruction, the first opinion, the second opinion, or the third opinion, and the third background information, and the fourth instruction includes a procedure for generating a new third opinion based on the third background information and taking into account the first opinion, the second opinion, or the third opinion. The third background information includes information that specifies the consensus and the tendency of the third opinion.

[0020] As a result, for example, a user of an information processing system according to one embodiment of the present invention can input a first opinion into a first component. Furthermore, the information processing system according to one embodiment of the present invention can extract novel and inventive ideas from the first opinion. Furthermore, it can refine the first opinion into a novel and inventive idea. Furthermore, it can enhance patentability. Furthermore, for example, a user of the information processing system according to one embodiment of the present invention can play the role of a first player. Furthermore, the first player can interact with the second and third players. Furthermore, for example, a user of the information processing system according to one embodiment of the present invention can deepen their thinking through the interaction. Furthermore, the information processing system according to one embodiment of the present invention can select one of the first, second, or third players to solicit an opinion for the purpose of extracting novel and inventive ideas and enhancing patentability. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0021] (3) Also, one aspect of the present invention is the above-described information processing system in which the first component has a function of receiving and providing a dialogue record and a specification. The dialogue record includes words prompting a response, a first opinion, a second opinion, and a third opinion. The specification has items and fields corresponding to the items. The items are items required for novel and inventive ideas.

[0022] The second component has a function of receiving a second instruction and transmitting a value to the third component. The large language model has a function of generating a value according to the second instruction.

[0023] The third component has a function of receiving a value from the second component and sharing it within the third component, and a function of transmitting the dialogue record and the specification to the first component.

[0024] The third component includes a second sub-component, and the second sub-component has a function of creating a dialogue record and a function of storing a value in a field and creating a specification.

[0025] Also, the above second instruction includes a procedure for generating a value corresponding to an item based on the first opinion, the second opinion, and the third opinion.

[0026] Thereby, the information processing system according to one aspect of the present invention can extract a novel and inventive idea from the first opinion and arrange it in the form of a specification. As a result, a novel information processing system excellent in convenience, usefulness, or reliability can be provided.

[0027] (4) Also, one aspect of the present invention is the above-described information processing system in which the first component has a function of receiving approval information and transmitting it to the third component. The third component has a function of receiving approval information and transmitting the dialogue record and the specification to the first component.

[0028] This allows, for example, a user of the information processing system to input approval information into the first component and terminate the interaction with the second and third players. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0029] (5) Another aspect of the present invention is the above-described information processing system, wherein the third component has a function for measuring elapsed time. When the elapsed time since the first component sent a message prompting the first player to respond exceeds a set time, the first subcomponent has a function to rewrite the second instruction sentence, adding the fact that the set time has been exceeded to the first background information.

[0030] As a result, for example, when a user of an information processing system according to one embodiment of the present invention is unable to respond, the information processing system according to one embodiment of the present invention can select one of the first player, second player, and third player to generate words prompting a response again. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0031] (6) Another aspect of the present invention is the above-described information processing system, wherein the third component comprises a third subcomponent. The third subcomponent has a function for processing using a database, and includes a function for collecting first information from the database and adding it to second background information, and a function for collecting second information from the database and adding it to third background information. The first information includes positive information regarding novelty or inventive step. The second information includes negative information regarding novelty or inventive step.

[0032] As a result, an information processing system according to one embodiment of the present invention can generate a positive second opinion regarding novelty and inventiveness by referring to prior art documents. Furthermore, it can generate a negative third opinion regarding novelty and inventiveness by referring to prior art documents. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0033] (7) Another aspect of the present invention is the above-described information processing system, in which the first background information includes a setting that, when generating words to prompt a response, imitates the words and actions of a facilitator that prompts speech, summarizes opinions, and leads to a conclusion.

[0034] Furthermore, the second set of background information includes a scenario that emulates the behavior of a patent attorney, focusing on the novelty and inventiveness of the idea and highlighting its positive aspects when generating the second opinion.

[0035] Furthermore, the third background information includes a setting that emulates the behavior of a patent attorney, focusing on the novelty and inventiveness of the idea and pointing out any doubts when generating the third opinion.

[0036] As a result, an information processing system according to one aspect of the present invention can, for example, provide a constructive dialogue environment to the user of the information processing system. Consequently, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0037] (8) One aspect of the present invention is an information processing method having steps 1 to 15.

[0038] In the first step, the first component transmits a first instruction to the second component. The first component comprises a first subcomponent, the first subcomponent having the function of creating the first instruction. The first instruction includes a first instruction and first background information, the first instruction including a procedure to generate words prompting a response from the first player based on the first background information. The first background information includes information specifying the consensus and the tendency of the words prompting a response. The consensus also includes the purpose of collaborating with other players to extract novel and inventive ideas from the first opinion of the first player and to enhance patentability.

[0039] In the second step, the second component receives the first instruction and uses a large-scale language model to generate words that prompt the first player to respond.

[0040] In the third step, the second component sends a message to the first component prompting the first player to respond.

[0041] In the fourth step, the first component receives a word prompting the first player to respond and sends it to the third component.

[0042] In the fifth step, the third component receives and provides words prompting a response from the first player.

[0043] In the sixth step, the third component receives the feedback from the first component and sends it back to the first component.

[0044] In step 7, the first component receives the first opinion and shares it within the first component.

[0045] In step eighth, the first subcomponent creates a second instruction and sends it to the second component. The second instruction includes a second instruction and a first opinion, a second opinion, or a third opinion, and the second instruction includes a procedure to select one of the first player, the second player, and the third player as the target for prompting a response based on the first background information, and to generate a prompting statement that takes into account the first opinion, the second opinion, or the third opinion.

[0046] In the ninth step, the second component receives the second instruction and uses a large-scale language model to generate a response prompt.

[0047] In the tenth step, the second component sends a message to the first component prompting a response.

[0048] In step 11, the first component receives a prompt word. When the prompt word prompts the first player to respond, it sends the prompt word to the third component and proceeds to step 5. Also, when the prompt word prompts the second player to respond, and when the prompt word prompts the third player to respond, it proceeds to step 12.

[0049] In step 12, the first subcomponent creates a third instruction and sends it to the second component when the prompting word prompts the second player to respond. It also creates a fourth instruction and sends it to the second component when the prompting word prompts the third player to respond.

[0050] The third instruction includes the third instruction, the first opinion, the second opinion, or the third opinion, and the second background information, and the third instruction includes a procedure for generating a new second opinion based on the second background information and taking into account the first opinion, the second opinion, or the third opinion. The second background information includes information specifying the consensus and the tendency of the second opinion.

[0051] The fourth instruction includes the fourth instruction, the first opinion, the second opinion, or the third opinion, and third background information, the fourth instruction including a procedure for generating a new third opinion based on the third background information and taking into account the first opinion, the second opinion, or the third opinion. The third background information includes information specifying the consensus and the tendency of the third opinion.

[0052] In step 13, the second component receives a third or fourth instruction and generates a second opinion using a large-scale language model when a prompting word prompts a response from the second player. It also generates a third opinion using a large-scale language model when a prompting word prompts a response from the third player.

[0053] In step 14, the second component submits a second or third opinion to the first component.

[0054] In step 15, the first component receives the second or third opinion, shares it within the first component, and proceeds to step 8.

[0055] As a result, for example, a user of an information processing system according to one embodiment of the present invention can input a first opinion into a third component. Furthermore, the information processing system according to one embodiment of the present invention can extract novel and inventive ideas from the first opinion. Furthermore, it can refine the first opinion into a novel and inventive idea. Furthermore, it can enhance patentability. Furthermore, for example, a user of the information processing system according to one embodiment of the present invention can play the role of a first player. Furthermore, the first player can interact with the second and third players. Furthermore, for example, a user of the information processing system according to one embodiment of the present invention can deepen their thinking through the interaction. Furthermore, the information processing system according to one embodiment of the present invention can select one of the first, second, or third players to solicit an opinion for the purpose of extracting novel and inventive ideas and enhancing patentability. As a result, a novel information processing method with superior convenience, usefulness, or reliability can be provided.

[0056] (9) Another aspect of the present invention is the above-described information processing method, comprising steps 16 to 19. The second instruction includes a procedure for generating values ​​corresponding to items, taking into account the first opinion, the second opinion, and the third opinion.

[0057] Steps 16 through 19 are located between step 11 and step 12.

[0058] In the ninth step, the second component receives the second instruction and generates a value using a large-scale language model.

[0059] In the tenth step, the second component sends the value to the first component.

[0060] In the 11th step, the first component receives the value, shares it within the first component, and proceeds to the 16th step. The first component comprises a second subcomponent.

[0061] In step 16, the second subcomponent creates a specification by storing values ​​in fields. The specification includes items and corresponding fields. These items are those required for novel and inventive ideas.

[0062] In step 17, the second subcomponent creates a transcript of the dialogue. The transcript includes prompts for a response, a first opinion, a second opinion, and a third opinion.

[0063] In step 18, the second subcomponent shares the specifications and dialogue within the first component and sends them to the third component.

[0064] In step 19, the third component provides the specifications and dialogue, and proceeds to step 12.

[0065] As a result, an information processing system according to one embodiment of the present invention can extract novel and inventive ideas from the first opinion and organize them into a specification. Consequently, it is possible to provide a novel information processing method that is superior in convenience, usefulness, or reliability.

[0066] (10) Another aspect of the present invention is the above-described information processing method, comprising the 20th step and the 21st step. The 20th step and the 21st step follow the 6th step.

[0067] In step 6, when the third component receives approval information, it transmits that approval information to the first component and proceeds to step 20.

[0068] In step 20, the first component receives approval information and sends the specifications and dialogue to the third component.

[0069] In step 21, the third component provides the specifications and dialogue.

[0070] This allows, for example, a user of the information processing system to input approval information into a third component and terminate the interaction with the second and third players. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided. [Effects of the Invention]

[0071] 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.

[0072] 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]

[0073] [Figure 1] Figure 1 is a diagram illustrating the configuration of an information processing system according to an embodiment. [Figure 2] Figure 2 is a diagram illustrating the configuration of components used in the information processing system according to the embodiment. [Figure 3] Figure 3 is a diagram illustrating the structure of instruction statements 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] Figures 5(A) to 5(C) illustrate 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 configuration of information used in the information processing system according to the embodiment. [Figure 8] Figure 8 is a diagram illustrating the configuration of an information processing device used in an information processing system according to an embodiment. [Figure 9] Figure 9 is a diagram illustrating an information processing method according to an embodiment. [Figure 10] Figure 10 is a diagram illustrating an information processing method according to an embodiment. [Figure 11] Figure 11 is a diagram illustrating an information processing method according to an embodiment. [Modes for carrying out the invention]

[0074] An information processing system according to one aspect of the present invention comprises a first component, a second component, and a third component.

[0075] The first component includes the function of receiving a first opinion and sending it to the third component, and the function of receiving and providing words to prompt a response.

[0076] The second component includes the function of receiving the first, second, third, and fourth instructions and sending response prompts, a second opinion, and a third opinion to the third component, as well as the function of processing using a large-scale language model. The large-scale language model includes the function of generating response prompts according to the first and second instructions, the function of generating a second opinion according to the third instruction, and the function of generating a third opinion according to the fourth instruction. The response prompts a response from any one of the first, second, or third players.

[0077] The third component includes the function of receiving a first opinion from the first component and sending a first instruction, a second instruction, a third instruction, and a fourth instruction to the second component; the function of receiving a prompting word, a second opinion, and a third opinion from the second component; and the function of sending a prompting word to the first component when the prompting word prompts the first player to respond.

[0078] Furthermore, the third component comprises a first subcomponent, the first subcomponent comprising a function for creating a first instruction, a function for creating a second instruction when a first opinion, a second opinion, or a third opinion is received, a function for creating a third instruction when a response prompting word prompts a second player to respond, and a function for creating a fourth instruction when a response prompting word prompts a third player to respond.

[0079] The first instruction includes the first instruction and the first background information, and the first instruction includes a procedure for generating words that prompt a response from the first player based on the first background information. The first background information includes information that specifies the consensus and the tendency of the words that prompt a response. The consensus also includes the purpose of working with other players to extract novel and inventive ideas from the first player's first opinion and to enhance patentability.

[0080] The second instruction includes the second instruction and the first opinion, the second opinion, or the third opinion, and the second instruction includes a procedure to select one of the first player, the second player, and the third player as the target to prompt a response based on the first background information, and to generate words to prompt a response based on the first opinion, the second opinion, or the third opinion.

[0081] The third instruction includes the third instruction, the first opinion, the second opinion, or the third opinion, and the second background information, and the third instruction includes a procedure for generating a new second opinion based on the second background information and taking into account the first opinion, the second opinion, or the third opinion. The second background information includes information specifying the consensus and the tendency of the second opinion.

[0082] The fourth instruction includes the fourth instruction, the first opinion, the second opinion, or the third opinion, and the third background information, and the fourth instruction includes a procedure for generating a new third opinion based on the third background information and taking into account the first opinion, the second opinion, or the third opinion. The third background information includes information that specifies the consensus and the tendency of the third opinion.

[0083] As a result, for example, a user of an information processing system according to one embodiment of the present invention can input a first opinion into a first component. Furthermore, the information processing system according to one embodiment of the present invention can extract novel and inventive ideas from the first opinion. Furthermore, it can refine the first opinion into a novel and inventive idea. Furthermore, it can enhance patentability. Furthermore, for example, a user of the information processing system according to one embodiment of the present invention can play the role of a first player. Furthermore, the first player can interact with the second and third players. Furthermore, for example, a user of the information processing system according to one embodiment of the present invention can deepen their thinking through the interaction. Furthermore, the information processing system according to one embodiment of the present invention can select one of the first, second, or third players to solicit an opinion for the purpose of extracting novel and inventive ideas and enhancing patentability. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided. As a result, the information processing system according to one embodiment of the present invention can extract novel and inventive ideas from the first opinion and organize them into a specification format. As a result, it becomes possible to provide a novel information processing system that is superior in terms of convenience, usefulness, or reliability.

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

[0085] In this specification, ordinal numbers such as "first," "second," etc., are used to avoid confusion of components and do not limit the number of components or the order of components (e.g., 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.

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

[0087] (Embodiment 1) In this embodiment, an information processing system according to one aspect of the present invention will be described with reference to Figures 1 to 11.

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

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

[0090] Figure 3 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.

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

[0092] Figures 5(A) to 5(C) illustrate the structure of instruction statements transmitted and received within an information processing system according to one embodiment of the present invention.

[0093] Figures 6(A) to 6(C) illustrate the structure of instruction statements transmitted and received within an information processing system according to one embodiment of the present invention.

[0094] Figure 7 illustrates the structure of a specification document created by an information processing system according to one embodiment of the present invention.

[0095] Figure 8 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.

[0096] <Example of an information processing system configuration 1> The information processing system described in this embodiment includes component 110, component 130, and component 120 (see Figure 1).

[0097] 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 are connected to each other via a network 51 to form an information processing system according to one embodiment of the present invention.

[0098] <Component 110 Configuration Example 1> Component 110 has the function of receiving opinion Op(I) and transmitting it to component 120. It also has the function of receiving a response prompt WES 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, and storage device.

[0099] For example, a user 99 of the information processing system inputs an opinion Op(I) into component 110. Alternatively, for example, a user inputs a command to select and send an opinion Op(I) stored in a memory 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, or eye-tracking device.

[0100] Specifically, the opinions or suggestions of the users 99 of the information processing system relating to the invention idea can be used in Opinion Op(I).

[0101] <Component 130 Configuration Example 1> Component 130 has the function of receiving instruction sentences Pt0, Pt1, Pt2(P), and Pt2(A). It also has the function of sending the response prompt WES, opinion Op(P), and opinion Op(A) to component 120, and the function of performing processing using the large-scale language model LLM.

[0102] 《Example Configuration of a Large-Scale Language Model (LLM) 1》 The large-scale language model LLM has the function of generating response prompts (WES) according to directives Pt0 and Pt1. It also has the function of generating opinions (Op(P)) according to directives Pt2(P) and the function of generating opinions (Op(A)) according to directives Pt2(A).

[0103] The prompt word WES is a word that prompts a response from one of the following players: Player Inv, Player Pro, or Player Ant. For example, the prompt word WES can be a word that prompts Player Inv to state opinion Op(I), a word that prompts Player Pro to state opinion Op(P), or a word that prompts Player Ant to state opinion Op(A).

[0104] Furthermore, 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.

[0105] <Component 120 Configuration Example 1> Component 120 has the function of receiving opinion Op(I) from component 110 and sending instruction statements Pt0, Pt1, Pt2(P), and Pt2(A) to component 130.

[0106] Component 120 has the function of receiving the prompt word WES, opinion Op(P), and opinion Op(A) from Component 130. Furthermore, when the prompt word WES prompts a response from Player Inv, it has the function of sending the prompt word WES to Component 110.

[0107] Furthermore, component 120 includes subcomponent 120A (see Figure 2). For the purposes of this specification, a configuration having one or more functions is referred to as a component or subcomponent.

[0108] 《Example configuration of subcomponent 120A》 Subcomponent 120A has the function of creating instruction statement Pt0 and the function of creating instruction statement Pt1 when it receives opinion Op(I), opinion Op(P), or opinion Op(A).

[0109] Furthermore, subcomponent 120A has the function of creating instruction sentence Pt2(P) when the prompting word WES prompts player Pro to respond. Furthermore, subcomponent 120A has the function of creating instruction sentence Pt2(A) when the prompting word WES prompts player Ant to respond.

[0110] [Example of the structure of instruction statement Pt0] Instruction Pt0 includes instruction g0 and background information BGI (see Figure 3). Instruction g0 includes a procedure to generate the word WES that prompts player Inv to respond, based on the background information BGI.

[0111] [Example of Background Information BGI Configuration 1] The background information (BGI) includes information specifying the tendencies of the consensus (Con) and the response-promoting words (WES).

[0112] [Example of a consensus-based discussion (CON) structure] Furthermore, the consensus (Con) aims to extract novel and inventive ideas from the opinions (Op(I)) of player Inv in cooperation with other players, thereby enhancing their patentability.

[0113] For example, the document in the following paragraph can be used as instruction Pt0.

[0114] "###Background information BGI You are the moderator. The invention is being discussed in a meeting involving two players, one acting as the inventor and the other as the patent attorney. One player, Pro, acting as the patent attorney, gives positive feedback, while the other player, Ant, acting as the patent attorney, gives negative feedback. ###Instruction g0 Prompt Player Inv to explain their invention idea.

[0115] [Example 1 of the structure of instruction statement Pt1] Instruction Pt1 includes instruction g1 and opinion Op(I), opinion Op(P), or opinion Op(A) (see Figures 4(A) to 4(C)). Instruction g1 includes a procedure to select one of player Inv, player Pro, and player Ant as the target to prompt a response based on background information BGI, and to generate a word WES that prompts a response based on opinion Op(I), opinion Op(P), or opinion Op(A).

[0116] For example, when Op(I) is the subject of discussion, the document in the following paragraph can be used as instruction Pt1. The dialogue record DRec records the prompting words WES, Op(I), Op(P), and Op(A). The specification SS records, for example, the items required for novel and inventive ideas, and the values ​​corresponding to the items generated based on Op(I), Op(P), and Op(A).

[0117] "###Background information BGI You are the moderator. The invention is being discussed in a meeting involving two players, one acting as the inventor and the other as the patent attorney. One player, Pro, acting as the patent attorney, gives positive feedback, while the other player, Ant, acting as the patent attorney, gives negative feedback. ### Opinion Op(I) ###Instruction g1 Based on the specifications document SS and the dialogue log DRec, determine which player should speak next and encourage them to make a statement that takes Op(I) into consideration.

[0118] [Example of the structure of instruction statement Pt2(P) 1] Instruction Pt2(P) includes instruction g2(P), opinion Op(I), opinion Op(P), or opinion Op(A), and background information BGI(P) (see Figures 5(A) to 5(C)). Instruction g2(P) includes a procedure for generating a new opinion Op(P) based on background information BGI(P) and taking into account opinion Op(I), opinion Op(P), or opinion Op(A).

[0119] [Example 1 of background information BGI(P) configuration] Furthermore, background information BGI(P) includes information specifying the trends of the consensus Con and opinions Op(P).

[0120] For example, the document in the following paragraph can be used as instruction Pt2(P).

[0121] "###Background information BGI You are a patent attorney. Review the inventor's proposed invention, focusing on its strengths, and propose its effectiveness, novelty, or inventive step. Refer to related application information and work with another patent attorney to complete the invention. ### Opinion Op(I) ###Instruction g2(P) Please make a positive statement, taking Op(I) into consideration.

[0122] [Example of the structure of instruction statement Pt2(A) 1] Instruction Pt2(A) includes instruction g2(A), opinion Op(I), opinion Op(P), or opinion Op(A), and background information BGI(A) (see Figures 6(A) to 6(C)). Instruction g2(A) includes a procedure for generating a new opinion Op(A) based on background information BGI(A) and taking into account opinion Op(I), opinion Op(P), or opinion Op(A).

[0123] [Example 1 of background information BGI(A) configuration] Background information BGI(A) includes information specifying the trends of consensus Con and opinion Op(A).

[0124] For example, the document in the following paragraph can be used as instruction Pt2(A).

[0125] "###Background information BGI You are a patent attorney. Please rigorously review the inventor's proposed invention and propose ways to make it robust enough to avoid rejection grounds or invalidation lawsuits. Refer to relevant application information and work with another patent attorney to complete the invention. ###Opinion Op(P) ###Instruction g2(A) Please make negative comments, taking Op(P) into consideration.

[0126] As a result, for example, a user of an information processing system according to one embodiment of the present invention can input an opinion Op(I) into component 110. Furthermore, the information processing system according to one embodiment of the present invention can extract novel and inventive ideas from opinion Op(I). Furthermore, it can refine opinion Op(I) into novel and inventive ideas. Furthermore, it can enhance patentability. Furthermore, for example, a user of the information processing system according to one embodiment of the present invention can play the role of player Inv. Furthermore, player Inv can interact with player Pro and player Ant. Furthermore, for example, a user of the information processing system according to one embodiment of the present invention can deepen their thinking through interaction. Furthermore, the information processing system according to one embodiment of the present invention can select one from player Inv, player Pro, or player Ant to solicit an opinion, with the aim of extracting novel and inventive ideas and enhancing patentability. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0127] <Component 110 Configuration Example 2> Component 110 has the function of receiving the dialogue record DRec and specification document SS and providing them, for example, to the user 99 of the information processing system. Specifically, it provides them to the user 99 of the information processing system using output devices such as a display device, speaker, printer, and storage device.

[0128] The dialogue transcript DRec includes prompts for response (WES), Op(I), Op(P), and Op(A).

[0129] Specification SS includes item K(X) and the corresponding field Fld(X). Item K(X) is the item required for novel and inventive ideas (see Figure 7). Note that the item is also called the Key, and the value corresponding to each item is also called the Value.

[0130] For example, items such as "Title of Invention," "Summary of Invention," "Technical Field," "Background Art," "Prior Art Documents," "Problem to be Solved by the Invention," "Means for Solving the Problem," "Effects of the Invention," "Mode for Carrying Out the Invention," "Novelty and Inventive Step," and "Feasibility" can be used as items in Specification SS. In addition, numerical values, symbols, strings of characters, or sentences can be used for the values ​​corresponding to each item.

[0131] <Component 130 Configuration Example 2> Component 130 has the function of receiving instruction Pt1 and sending value V(X) to component 120.

[0132] 《Example Configuration of a Large-Scale Language Model (LLM) 2》 The large-scale language model LLM has the function of generating a value V(X) according to the instruction Pt1.

[0133] <Component 120 Configuration Example 2> Component 120 has the function of receiving a value V(X) from component 130 and sharing it within component 120, and the function of sending the dialogue log DRec and specification document SS to component 110.

[0134] Furthermore, component 120 includes subcomponent 120B (see Figure 2).

[0135] 《Example configuration of subcomponent 120B》 Subcomponent 120B includes a function to create a dialogue log DRec and a function to create a specification document SS by storing the value V(X) in the field Fld(X).

[0136] [Example of the structure of instruction statement Pt1 2] Instruction g1 includes a procedure for generating a value V(X) corresponding to item K(X) based on opinions Op(I), Op(P), and Op(A) (see Figures 4(A) to 4(C)). For example, the document in the following paragraph can be used as instruction Pt1.

[0137] "###Item K ### Opinion Op(I) ###Instruction g1 Please extract the elements corresponding to item K from the content of opinion Op(I).

[0138] As a result, one embodiment of the present invention allows for the extraction of novel and inventive ideas from Op(I) and their preparation into the format of Specification SS. Consequently, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0139] <Component 110 Configuration Example 3> Component 110 has the function of receiving approval information ApI and sending it to component 120 (see Figure 1).

[0140] <Component 120 Configuration Example 3> Component 120 has the function of receiving approval information ApI and sending the dialogue record DRec and specification document SS to component 110.

[0141] This allows, for example, a user of the information processing system to input approval information ApI into component 110 and terminate the interaction with Player Pro and Player Ant. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0142] <Component 120 Configuration Example 4> Component 120 has a function to measure elapsed time T. When the elapsed time T since sending the word WES prompting a response from player Inv to component 110 exceeds the set time, subcomponent 120A has a function to add the fact that the set time has been exceeded to background information BGI and to recreate the instruction statement Pt1.

[0143] As a result, for example, when a user of an information processing system according to one embodiment of the present invention is unable to respond, the information processing system according to one embodiment of the present invention can select one from player Inv, player Pro, and player Ant and generate the phrase WES to prompt a response again. As a result, a novel information processing system with superior convenience, usefulness, and reliability can be provided.

[0144] <Component 120 Configuration Example 5> Component 120 includes subcomponent 120C (see Figure 2).

[0145] 《Example configuration of subcomponent 120C》 Subcomponent 120C has the functionality to perform processing using a database (DB). For example, a database containing prior art documents can be used as the database (DB). Furthermore, information related to novelty or inventiveness can be searched using a management system (DBMS).

[0146] Subcomponent 120C has the function of collecting information Inf(P) from the database DB and adding it to background information BGI(P). Subcomponent 120C also has the function of collecting information Inf(A) from the database DB and adding it to background information BGI(A).

[0147] Furthermore, Information Inf(P) includes positive information regarding novelty or inventive step. Information Inf(A) includes negative information regarding novelty or inventive step.

[0148] As a result, an information processing system according to one embodiment of the present invention can generate a positive opinion Op(P) regarding novelty and inventive step by referring to prior art documents. Furthermore, it can generate a negative opinion Op(A) regarding novelty and inventive step by referring to prior art documents. As a result, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0149] [Example of Background Information BGI Configuration 2] The background information (BGI) includes settings that mimic the facilitator's behavior—encouraging participation, summarizing opinions, and leading to conclusions—when generating the response prompts (WES).

[0150] [Example 2 of background information BGI(P) configuration] The background information (BGI(P)) includes settings that emulate the behavior of a patent attorney, focusing on the novelty and inventiveness of the idea when generating the opinion (Op(P)), and highlighting its positive aspects.

[0151] [Example 2 of background information BGI(A) configuration] Background information BGI(A) includes settings that mimic the behavior of a patent attorney, focusing on the novelty and inventiveness of the idea and pointing out any doubts when generating opinion Op(A).

[0152] As a result, an information processing system according to one aspect of the present invention can, for example, provide a constructive dialogue environment to the user of the information processing system. Consequently, a novel information processing system with superior convenience, usefulness, or reliability can be provided.

[0153] <Example of Information Processing Device Configuration 2> 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 8).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 《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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] The processing unit 23 may have either or both an OS transistor and a transistor having silicon in its channel formation region (Si transistor).

[0174] 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.

[0175] It is preferable for information processing devices to use AI for at least some of their processing.

[0176] 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).

[0177] 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.

[0178] 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."

[0179] 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."

[0180] 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.

[0181] 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.

[0182] This embodiment can be appropriately combined with other embodiments shown in this specification.

[0183] (Embodiment 2) In this embodiment, an information processing method according to one aspect of the present invention will be described with reference to Figures 9 to 11.

[0184] Figure 9 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0185] Figure 10 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0186] Figure 11 is a flowchart illustrating an information processing method according to one embodiment of the present invention.

[0187] <Example of information processing method 1> One aspect of the present invention is an information processing method comprising steps S1 to S15 (see Figure 9).

[0188] [Step S1] In step S1, component 120 sends instruction Pt0 to component 130.

[0189] Furthermore, component 120 includes a subcomponent 120A, and subcomponent 120A has the function of creating instruction statement Pt0.

[0190] Instruction Pt0 includes instruction g0 and background information BGI. Instruction g0 includes a procedure for generating a word WES that prompts player Inv to respond, based on the background information BGI. The background information BGI includes information specifying the consensus Con and the tendency of the word WES that prompts response. Furthermore, the consensus Con includes the purpose of collaborating with other players to extract novel and inventive ideas from player Inv's opinion Op(I) and enhance patentability.

[0191] [Step S2] In step S2, component 130 receives instruction Pt0 and uses the large-scale language model LLM to generate the word WES, which prompts player Inv to respond.

[0192] [Step S3] In step S3, component 130 sends the word WES to component 120, prompting player Inv to respond.

[0193] [Step S4] In step S4, component 120 receives the word WES prompting player Inv to respond and sends it to component 110.

[0194] [Step S5] In step S5, component 110 receives the word WES prompting player Inv to respond and provides it, for example, to a user of an information processing system.

[0195] [Example 1 of Step S6] In step S6, component 110 receives the opinion Op(I) and sends it to component 120. For example, a user of the information processing system inputs the opinion Op(I) to component 110.

[0196] [Step S7] In step S7, component 120 receives feedback Op(I) and shares it within component 120.

[0197] [Step S8] In step S8, subcomponent 120A creates instruction statement Pt1 and sends it to component 130. Instruction statement Pt1 includes instruction g1 and opinion Op(I), opinion Op(P), or opinion Op(A). Instruction g1 includes a procedure to select one from player Inv, player Pro, and player Ant as the target to prompt a response based on background information BGI, and to generate a word WES that prompts a response based on opinion Op(I), opinion Op(P), or opinion Op(A).

[0198] [Example 1 of Step S9] In step S9, component 130 receives instruction Pt1 and uses the large-scale language model LLM to generate a response prompt WES.

[0199] [Example 1 of Step S10] In step S10, component 130 sends the response prompt WES to component 120.

[0200] [Example 1 of Step S11] In step S11, component 120 receives the prompt word WES. When the prompt word WES prompts player Inv to respond, it sends the prompt word WES to component 110 and proceeds to step S5.

[0201] Furthermore, when the prompting word WES prompts player Pro to respond, and when the prompting word WES prompts player Ant to respond, the process proceeds to step S12.

[0202] [Step S12] In step S12, when the prompting word WES prompts player Pro to respond, subcomponent 120A creates instruction sentence Pt2(P) and sends it to component 130. Also, when the prompting word WES prompts player Ant to respond, subcomponent 120A creates instruction sentence Pt2(A) and sends it to component 130.

[0203] Instruction Pt2(P) includes instruction g2(P), opinion Op(I), opinion Op(P), or opinion Op(A), and background information BGI(P). Instruction g2(P) includes a procedure for generating a new opinion Op(P) based on background information BGI(P) and taking into account opinion Op(I), opinion Op(P), or opinion Op(A). Background information BGI(P) also includes information specifying the consensus Con and the trend of opinion Op(P).

[0204] Instruction Pt2(A) includes instruction g2(A), opinion Op(I), opinion Op(P), or opinion Op(A), and background information BGI(A). Instruction g2(A) includes a procedure for generating a new opinion Op(A) based on the background information BGI(A) and taking into account opinion Op(I), opinion Op(P), or opinion Op(A). Background information BGI(A) also includes information specifying the consensus Con and the trend of opinion Op(A).

[0205] [Step S13] In step S13, component 130 receives an instruction Pt2(P) or instruction Pt2(A). When the prompting word WES prompts player Pro to respond, it generates an opinion Op(P) using the large-scale language model LLM. Also, when the prompting word WES prompts player Ant to respond, it generates an opinion Op(A) using the large-scale language model LLM.

[0206] [Step S14] In step S14, component 130 sends opinion Op(P) or opinion Op(A) to component 120.

[0207] [Step S15] In step S15, component 120 receives opinion Op(P) or opinion Op(A), shares it within component 120, and proceeds to step S8.

[0208] As a result, for example, a user of an information processing system according to one embodiment of the present invention can input an opinion Op(I) into component 110. Furthermore, the information processing system according to one embodiment of the present invention can extract novel and inventive ideas from opinion Op(I). Furthermore, it can refine opinion Op(I) into novel and inventive ideas. Furthermore, it can enhance patentability. Furthermore, for example, a user of the information processing system according to one embodiment of the present invention can play the role of player Inv. Furthermore, player Inv can interact with player Pro and player Ant. Furthermore, for example, a user of the information processing system according to one embodiment of the present invention can deepen their thinking through interaction. Furthermore, the information processing system according to one embodiment of the present invention can select one from player Inv, player Pro, or player Ant to solicit an opinion, with the aim of extracting novel and inventive ideas and enhancing patentability. As a result, a novel information processing method with superior convenience, usefulness, or reliability can be provided.

[0209] <Example of information processing method 2> The above information processing method includes steps S16 to S19 (see Figure 10). Steps S16 to S19 are located between steps S11 and S12. Instruction g1 also includes a procedure for generating a value V(X) corresponding to item K(X) based on opinion Op(I), opinion Op(P), and opinion Op(A).

[0210] [Example 2 of Step S9] In step S9, component 130 receives instruction Pt1 and generates value V(X) using the large-scale language model LLM.

[0211] [Example 2 of Step S10] In step S10, component 130 sends the value V(X) to component 120.

[0212] [Example 2 of Step S11] In step S11, component 120 receives the value V(X), shares it within component 120, and proceeds to step S16. Component 120 includes a subcomponent 120B.

[0213] [Step S16] In step S16, subcomponent 120B stores the value V(X) in the field Fld(X) and creates specification document SS. Specification document SS includes item K(X) and the field Fld(X) corresponding to item K(X). Item K(X) is an item required for an idea to be novel and inventive.

[0214] [Step S17] In step S17, subcomponent 120B creates a dialogue transcript DRec. The dialogue transcript DRec includes the prompting words WES, opinion Op(I), opinion Op(P), and opinion Op(A).

[0215] [Step S18] In step S18, subcomponent 120B shares the specification SS and the dialogue record DRec within component 120 and sends them to component 110.

[0216] [Step S19] In step S19, component 110 provides the specification SS and the dialogue record DRec to, for example, a user of the information processing system, and proceeds to step S12.

[0217] As a result, an information processing system according to one embodiment of the present invention can extract novel and inventive ideas from opinion Op(I) and organize them into the format of specification SS. Consequently, it is possible to provide a novel information processing method that is superior in convenience, usefulness, or reliability.

[0218] <Example 3 of information processing methods> The above information processing method includes steps S20 and S21 (see Figure 11). Steps S20 and S21 are followed by step S6.

[0219] [Example 2 of Step S6] In step S6, when component 110 receives the approval information ApI, it sends the approval information ApI to component 120 and proceeds to step S20. For example, a user of the information processing system inputs the approval information ApI into component 110.

[0220] [Step S20] In step S20, component 120 receives approval information ApI and sends specification SS and dialogue record DRec to component 110.

[0221] [Step S21] In step S21, component 110 provides the specification SS and the dialogue record DRec to, for example, a user of the information processing system.

[0222] This allows, for example, a user of the information processing system to input approval information ApI into component 110 and terminate the interaction with player Pro and player Ant. As a result, a novel information processing method with superior convenience, usefulness, and reliability can be provided.

[0223] This embodiment can be appropriately combined with other embodiments shown in this specification. [Explanation of Symbols]

[0224] ApI Approval Information BGI background information DB Database DRec Dialogue Fld Field Inf information K item Large-Scale Language Model (LLM) Opinions on melody SS Specifications V value WES response prompts 20 Information Processing Devices 21 Input section 22 Memory section 23 Processing Unit 24 Output section 25 Transmission lines 51 Network 99 User 110 components 120 components 120A Subcomponent 120B Subcomponent 120C Subcomponents 130 components

Claims

1. It has a function to receive a first opinion and generate a first instruction, a second instruction, a third instruction, and a fourth instruction, and a function to receive a response prompting word, a second opinion that is positive to the first opinion, and a third opinion that is negative to the first opinion from a large-scale language model, and transmit the response prompting word. The first instruction includes a procedure to cause the player to generate words that prompt the response, The second instruction includes a procedure for generating words that prompt the response based on the first opinion, the second opinion, or the third opinion, The third instruction includes a procedure for generating a new second opinion, The fourth instruction includes a procedure for generating a new third opinion, The large-scale language model is an information processing system comprising: a function to generate words that prompt the response according to the first instruction and the second instruction; a function to generate the second opinion according to the third instruction; and a function to generate the third opinion according to the fourth instruction.

2. The first component and The second component, It has a third component, The first component includes a function for receiving a first opinion and transmitting it to the third component, and a function for receiving and providing words prompting a response. The second component includes a function to receive a first instruction, a second instruction, a third instruction, and a fourth instruction, and to transmit a response prompt, a second opinion, and a third opinion to the third component, and a function to perform processing using a large-scale language model. The large-scale language model includes a function to generate words that prompt the response according to the first instruction and the second instruction, a function to generate the second opinion according to the third instruction, and a function to generate the third opinion according to the fourth instruction. The aforementioned words prompting a response are words that prompt a response from any one of the first player, the second player, or the third player. The third component includes a function to receive a first opinion from the first component and transmit a first instruction, a second instruction, a third instruction, and a fourth instruction to the second component; a function to receive a response prompting word, a second opinion, and a third opinion from the second component; and a function to transmit the response prompting word to the first component when the response prompting word prompts the first player to respond. The third component comprises a first subcomponent, The first subcomponent has the function of creating the first instruction statement, A function to generate the second instruction statement when the first opinion, the second opinion, or the third opinion is received, The function of creating the third instruction sentence when the aforementioned response prompts the second player to respond, The system includes a function to create a fourth instruction sentence when the aforementioned response prompts the third player to respond, The first instruction statement includes the first instruction and the first background information, The first instruction includes a procedure to cause the first player to generate words prompting the response based on the first background information, The first background information includes information that specifies the general consensus and the tendency of the language to prompt the response, The aforementioned consensus includes the purpose of collaborating with other players to extract novel and inventive ideas from the first opinion of the first player and to enhance their patentability. The second instruction statement includes the second instruction and the first opinion, the second opinion, or the third opinion, The second instruction includes a procedure to select one of the first player, the second player, and the third player as the target to prompt a response based on the first background information, and to generate a response prompting statement that takes into account the first opinion, the second opinion, or the third opinion. The third instruction statement includes the third instruction, the first opinion, the second opinion, or the third opinion, and the second background information. The third instruction includes a procedure for generating a new second opinion based on the second background information, taking into account the first opinion, the second opinion, or the third opinion. The second background information includes information that specifies the general consensus and the trend of the second opinion, The fourth instruction statement includes the fourth instruction, the first opinion, the second opinion, or the third opinion, and the third background information. The fourth instruction includes a procedure for generating a new third opinion based on the third background information, taking into account the first opinion, the second opinion, or the third opinion. An information processing system in which the third background information includes information specifying the trend of the consensus and the third opinion.

3. The first component has the function of receiving and providing dialogue logs and specifications, The aforementioned dialogue transcript includes the words prompting the response, the first opinion, the second opinion, and the third opinion, The aforementioned specification includes items and fields corresponding to those items, The aforementioned items are requirements for the novelty and inventiveness of the aforementioned idea, The second component has the function of receiving the second instruction and sending a value to the third component. The large-scale language model has a function to generate the value according to the second instruction, The third component includes a function to receive the value from the second component and share it within the third component, and a function to transmit the dialogue record and the specification to the first component. The third component comprises a second subcomponent, The second subcomponent comprises a function for creating the dialogue record and a function for storing the values ​​in the field to create the specification document, The information processing system according to claim 2, wherein the second instruction includes a procedure for generating the value corresponding to the item based on the first opinion, the second opinion and the third opinion.

4. The first component has a function to receive approval information and transmit it to the third component. The information processing system according to claim 3, wherein the third component has the function of receiving the approval information and transmitting the dialogue record and the specification to the first component.

5. The third component is equipped with a function for measuring elapsed time, The information processing system according to claim 2, wherein when the elapsed time since the first component sent the words prompting the first player to respond exceeds a set time, the first subcomponent has a function to rewrite the second instruction sentence, adding the fact that the set time has been exceeded to the first background information.

6. The third component comprises a third subcomponent, The third subcomponent described above has a function for performing processing using a database, The database has a function to collect first information and add it to the second background information, The system includes a function to collect second information from the aforementioned database and add it to the third background information, The first piece of information described above includes positive information regarding novelty or inventive step, The information processing system according to claim 2, wherein the second information includes negative information regarding novelty or inventive step.

7. The first background information includes a setting that, when generating the words to prompt the response, imitates the words and actions of a facilitator that encourage speech, summarize opinions, and lead to a conclusion. The second background information includes a setting that emulates the behavior of a patent attorney, focusing on the novelty and inventiveness of the idea when generating the second opinion, and highlighting its good points. The information processing system according to claim 2, wherein the third background information includes a setting that mimics the behavior of a patent attorney who, when generating the third opinion, focuses on the novelty and inventiveness of the idea and points out doubts.

8. An information processing method comprising the first to fifteenth steps, In the first step described above, the first component sends the first instruction to the second component, The first component comprises a first subcomponent, The first subcomponent has a function for creating the first instruction statement, The first instruction statement includes the first instruction and the first background information, The first instruction includes a procedure for generating words that prompt a response from the first player based on the first background information, The first background information includes information that specifies the general consensus and the tendency of the language to prompt the response, The aforementioned consensus includes the purpose of collaborating with other players to extract novel and inventive ideas from the first opinion of the first player and to enhance their patentability. In the second step, the second component receives the first instruction and uses a large-scale language model to generate words prompting the first player to respond. In the third step, the second component transmits to the first component the words prompting the first player to respond. In the fourth step, the first component receives the words prompting the first player to respond and transmits them to the third component. In the fifth step, the third component receives and provides the first player with the words prompting the response. In the sixth step, the third component receives the first opinion and transmits it to the first component. In the seventh step, the first component receives the first opinion and shares it within the first component. In the eighth step, the first subcomponent creates a second instruction and sends it to the second component. The second instruction statement includes the second instruction and the first opinion, the second opinion, or the third opinion, The second instruction includes a procedure to select one of the first player, the second player, and the third player as the target to prompt a response based on the first background information, and to generate a response prompting statement that takes into account the first opinion, the second opinion, or the third opinion. In the ninth step, the second component receives the second instruction and uses the large-scale language model to generate words that prompt the response. In the tenth step, the second component transmits the words prompting the response to the first component. In the eleventh step, the first component receives the words prompting the response, When the prompting words prompt the first player to respond, the prompting words are sent to the third component, and the process proceeds to the fifth step. When the response prompting words prompt the second player to respond, and when the response prompting words prompt the third player to respond, proceed to step 12. In the 12th step, the first subcomponent creates a third instruction and sends it to the second component when the prompting word prompts the second player to respond, and creates a fourth instruction and sends it to the second component when the prompting word prompts the third player to respond. The third instruction statement includes the third instruction, the first opinion, the second opinion, or the third opinion, and the second background information. The third instruction includes a procedure for generating a new second opinion based on the second background information, taking into account the first opinion, the second opinion, or the third opinion. The second background information includes information that specifies the general consensus and the trend of the second opinion, The fourth instruction statement includes the fourth instruction, the first opinion, the second opinion, or the third opinion, and the third background information. The fourth instruction includes a procedure for generating a new third opinion based on the third background information, taking into account the first opinion, the second opinion, or the third opinion. The third background information includes information that specifies the general consensus and the trend of the third opinion, In the 13th step, the second component receives the third instruction or the fourth instruction, and generates the second opinion using the large-scale language model when the response prompting word prompts the second player to respond, and generates the third opinion using the large-scale language model when the response prompting word prompts the third player to respond. In the 14th step, the second component transmits the second opinion or the third opinion to the first component. An information processing method in which, in step 15, the first component receives the second opinion or the third opinion, shares it within the first component, and proceeds to step 8.

9. An information processing method according to claim 8, comprising steps 16 to 19, The second instruction includes a procedure for generating values ​​corresponding to items, taking into account the first opinion, the second opinion, and the third opinion, Steps 16 through 19 are located between step 11 and step 12. In the ninth step, the second component receives the second instruction and generates the value using the large-scale language model. In the tenth step, the second component transmits the value to the first component. In the 11th step, the first component receives the value, shares it within the first component, and proceeds to the 16th step. The first component comprises a second subcomponent, In the sixteenth step, the second subcomponent stores the value in a field to create a specification, The specification document comprises the items and the fields corresponding to the items, The aforementioned items are requirements for the novelty and inventiveness of the aforementioned idea, In the seventeenth step, the second subcomponent creates a dialogue record, The aforementioned dialogue transcript includes the words prompting the response, the first opinion, the second opinion, and the third opinion, In step 18, the second subcomponent shares the specification and the dialogue within the first component and transmits them to the third component. An information processing method wherein, in the 19th step, the third component provides the specification and the dialogue record, and the process proceeds to the 12th step.

10. An information processing method according to claim 9, comprising a 20th step and a 21st step, Steps 20 and 21 follow step 6, In the sixth step, when the third component receives the approval information, it transmits the approval information to the first component and proceeds to the 20th step. In the 20th step, the first component receives the approval information and transmits the specification and the dialogue record to the third component. In the 21st step, the third component is an information processing method that provides the specification and the dialogue record.

Images