Idea evaluation system and program

Abstract

To automatically evaluate a created idea from various perspectives, including feasibility, marketability, and patentability or the like by using a large-scale language model.SOLUTION: A computer is caused to execute: a prompt input step of inputting a prompt related to a created idea into a large-scale language model; and an evaluation information acquisition step of acquiring evaluation information in which an evaluation related to the idea output from the large-scale language model is attached to the prompt input in the prompt input step.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an idea evaluation system and program that utilize a foundation model to evaluate ideas created.

Background Art

[0002] Patent Document 1 proposes a problem-solving support system that can dig deep into and develop numerous peripheral deformation forms from the seeds of an invented invention and further strengthen the technology group by reflecting information on market needs.

[0003] Patent Document 2 proposes a creative support program that is suitable for supporting the creation of innovation by effectively presenting specific examples in which a solution concept is reflected to a creator.

[0004] In the disclosed technologies of these Patent Documents 1 and 2, when technical information such as patent information is learned by artificial intelligence and information on problems to be solved and issues related to an invention to be newly created is input, an optimal solution concept is proposed via artificial intelligence.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, a system for evaluating solution concepts and inventions completed with the help of these artificial intelligence capabilities has not been proposed conventionally. For this reason, when a large number of solution concepts and inventions are automatically generated by artificial intelligence, they cannot be sorted out, and it becomes difficult to summarize them into the necessary technologies for linking them to the value provided to customers. There is also a problem that hallucination (information not based on facts) may be included and information contamination occurs because it cannot be automatically detected.

[0007] Therefore, the present invention has been devised in view of the above-described problems, and an object thereof is to provide an idea evaluation system and program capable of automatically evaluating created ideas from viewpoints such as feasibility, marketability, and patentability by using a base model (a large-scale model trained with a large amount of data and adaptable to various tasks).

Means for Solving the Problems

[0008] The idea evaluation system according to the present invention includes a prompt input means for inputting a prompt related to an idea into a base model, and an evaluation information acquisition means for acquiring evaluation information with an evaluation related to the idea output from the base model for the prompt input to the prompt input means.

[0009] The idea evaluation program according to the present invention causes a computer to execute a prompt input step of inputting a prompt related to an idea into a base model, and an evaluation information acquisition step of acquiring evaluation information with an evaluation related to the idea output from the base model for the prompt input in the prompt input step.

Effects of the Invention

[0010] According to the present invention, by using a large language model, the created ideas can be automatically evaluated from various perspectives such as feasibility, marketability, patentability, etc. As a result, it is possible to automatically evaluate the solution concepts and inventions completed with the help of artificial intelligence, organize them when a large number of solution concepts and inventions are automatically generated by artificial intelligence, automatically extract and remove hallucinations (information not based on facts) even if they are included, and easily realize the work of summarizing the necessary technologies for linking to the value provided to customers.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out the Invention

[0012] Hereinafter, an idea evaluation system to which the present invention is applied will be described in detail with reference to the drawings.

[0013] First Embodiment FIG. 1 is a configuration diagram schematically showing the configuration of a network including an idea evaluation system 1 to which the present invention is applied. As shown in the figure, the server 10 is communicably connected to the user terminal 30 via a communication network 20 such as the Internet. In FIG. 1, only one user terminal 30 is shown, but the server 10 may be communicably connected to two or more user terminals 30. The server 10 provides the evaluation result specified by the user to the user who operates the user terminal 30.

[0014] First, the hardware configuration of the server 10 will be described. The server 10 is configured as a general computer and includes a computer processor 11, a memory 12, an input / output I / F 13, a communication I / F 14, and a storage 15 as shown in FIG. 1. These components in the server 10 are electrically connected via a bus (not shown) or the like.

[0015] The computer processor 11 is configured as a CPU or a GPU, etc., reads various programs stored in the storage 15, etc. into the memory 12, and executes various instructions included in the programs. The memory 12 is composed of, for example, DRAM or the like.

[0016] The input / output I / F 13 includes various input / output devices for exchanging information with an operator or the like. The input / output I / F 13 includes, for example, information input devices such as a keyboard, a mouse, a pointing device such as a touch panel, a voice input device such as a microphone, and an image input device such as a camera. The input / output I / F 13 also includes an image output device such as a display and a voice output device such as a speaker.

[0017] The communication I / F 14 is implemented as hardware such as a network adapter, various communication software, or a combination thereof, and is configured to enable wired or wireless communication via the communication network 20 or the like.

[0018] Storage 15 is constituted by, for example, a magnetic disk or a flash memory. Storage 15 stores various programs including an operating system and various data. For example, as shown in FIG. 1, storage 15 has an evaluation information management table 152 that manages evaluation information to which an evaluation regarding an idea is attached.

[0019] Also, storage 15 stores a server - side program 40 according to an embodiment of the present invention. The program 40 is a program for causing server 10 to function as all or part of a system for providing services of an idea evaluation system. At least a part of the server - side program 40 may be configured to be executed on the user terminal 30 side via a terminal - side program 42 described later.

[0020] In the present embodiment, server 10 may be configured using a plurality of computers each having the above - described hardware configuration. In such a case, server 10 is constituted by a plurality of server devices.

[0021] Server 10 configured in this way can be configured to have functions as a web server and an application server, execute various processes in response to requests from user terminal 30, and transmit screen data and control data composed of HTML data or the like according to the results of the processes to user terminal 30. On user terminal 30, a screen based on the received data is output.

[0022] Next, the hardware configuration of user terminal 30 will be described. User terminal 30 is configured as a general computer and includes, as shown in FIG. 1, a computer processor 31, a memory 32, an input / output I / F 33, a communication I / F 34, and a storage 35. These components are electrically connected via a bus (not shown).

[0023] The computer processor 31 is configured as a CPU, GPU, etc., reads various programs stored in the storage 35, etc. into the memory 32, and executes various instructions included in the programs. The memory 32 is composed of, for example, DRAM, etc.

[0024] The input / output I / F 33 includes various input / output devices for exchanging information with an operator, etc. The input / output I / F 33 includes, for example, information input devices such as pointing devices like keyboards, mice, touch panels, etc., voice input devices such as microphones, and image input devices such as cameras. Also, the input / output I / F 33 includes image output devices such as displays, and voice output devices such as speakers.

[0025] The communication I / F 34 is implemented as hardware such as a network adapter, various communication software, and combinations thereof, and is configured to enable wired or wireless communication via a communication network 20, etc.

[0026] The storage 35 is composed of, for example, a magnetic disk or flash memory, etc. The storage 35 stores various programs including an operating system and various data, etc. The programs stored in the storage 35 can be downloaded and installed from an application market, etc. Also, the storage 35 stores the above-described terminal-side program 42. The program 42 is configured as a web browser or other application, and as described above, can be configured to execute at least a part of the server-side program 40.

[0027] Note that the user terminal 30 is configured as a mobile phone, smartphone, tablet terminal, wearable terminal, personal computer, etc.

[0028] A user who operates the user terminal 30 configured as described above can utilize the services of the idea evaluation system provided by the server 10 by executing communication with the server 10 via the terminal-side program 42 installed in the storage 35 or the like.

[0029] Next, the functions of the server 10 configured as described above will be explained. As shown in FIG. 1, the computer processor 11 of the server 10 is configured to function by executing a program read into the memory 12 or instructions included in at least a part of the server-side program 40.

[0030] Then, server 10 acquires evaluation information based on the information received from user terminal 30 or the information generated on the server 10 side. At this time, server 10 inputs a prompt regarding the created idea into the base model, and acquires evaluation information to which an evaluation regarding that idea generated by the base model is attached. The base model is an AI neural network trained with a large amount of unlabeled dataset, and is a type of machine learning model trained to execute various tasks from text translation to medical image analysis. The base model is programmed to function by understanding the general context of patterns, structures, and expressions. Based on this fundamental understanding of communication methods and pattern identification methods, a knowledge baseline is created. By further modifying or fine-tuning this, tasks in specific areas of almost all industries can be executed. Many base models, especially those used in natural language processing (NLP), computer vision, and audio processing, are pre-trained using deep learning techniques. The base model may be a model trained to be able to generate, identify, classify, predict, translate, etc. natural language, still images, moving images, and music by performing transfer learning, fine-tuning, and distillation. The base model may be a model trained to be able to detect information that is ethically problematic, discriminatory and harmful, factually unfounded, or simply useless. The base model may be a model trained to be able to detect factually unfounded information in natural science using a natural science simulator. Since the base model may include hallucinations, it may be a model fine-tuned to detect hallucinations by reinforcement learning from human feedback (RLHF: Reinforcement Learning from Human Feedback). The base model may be a model that reflects "human value criteria" such as human preferences and intentions by reinforcement learning from human feedback.

[0031] A foundation model trained in natural language processing can recognize context, grammar, and language structure, and generate and extract information from the data used for training. A foundation model trained in natural language processing is, for example, a trained model that performs natural language processing according to an instruction sentence and generates a response sentence. The instruction sentence may at least include information about the created idea. The foundation model may be a dialogue-type, so-called chat-type or conversation-type model that alternately receives an instruction sentence and generates a response sentence. The natural language model may be a large language model (LLM) trained with a large amount of text data, or a model obtained by transfer learning of the large language model. Also, the natural language model is not limited to being constructed within the server 10, and may be constructed in a system external to the idea evaluation system 1. Further, the foundation model may be a diffusion model used in image generation AI.

[0032] A large language model is a deep learning model that pre-learns from vast amounts of data a language model called one that models human spoken language by its occurrence probability. That is, a large language model is a natural language processing model trained using a large amount of text data, which takes a sentence as input and outputs a sentence. When a large language model is applied to a system that performs question and answer, when a question sentence is input to the large language model, an answer sentence is output from the large language model.

[0033] When server 10 receives the text data (prompt) of a request, it uses a large language model to statistically estimate the generation probability of the next word from the text included in the received prompt, and transmits the estimation result to the request source. As the large language model, for example, as an Internet site, known technologies described in "https: / / huggingface.co / datasets / databricks / databricks-dolly-15k", "https: / / huggingface.co / datasets / togethercomputer / RedPajama-Data-1T", etc. can be adopted. Also, as the large language model, for example, GPT-4 provided by OpenAI in the United States may be used.

[0034] As shown in FIG. 2, a prompt regarding an idea is input. This prompt regarding an idea is composed of text data describing the content of the idea. This prompt may be composed of each item such as the summary of the invention (for example, "adopting a vertical axis wind turbine to capture wind energy from all directions", etc.), the problem to be solved (for example, "the wind hitting is limited in the conventional horizontal axis wind turbine", etc.), the solution method (for example, "introducing a vertical axis wind turbine that captures wind energy from all directions", etc.), the effect of the invention (for example, "improvement in flexibility with respect to changes in the wind direction", etc.), or may be, for example, something that expresses the invention concept or the solution method in one word such as "make it a nested structure".

[0035] This prompt may be one that the user came up with through their own creative activities, or it may be based on an idea generated by artificial intelligence based on well-known technologies shown in Patent Documents 1 and 2, for example. In such a case, by pre-training with patent information, a pre-prepared learned model for searching for solutions to the input text data is prepared in advance. Then, by inputting text data such as "How can the power generation efficiency of wind power generation be improved?" into the learned model, an idea consisting of the outline of the invention, the problem to be solved, the solution method, the effects of the invention, etc. is output. The output idea may be one that expresses the invention concept or the solution method in one sentence.

[0036] The text information of the idea created by the user themselves or output from the learned model is input as a prompt. The input of the prompt may be via the user terminal 30, or if it has already been stored in the storage 35 of the user terminal 30, that may be used. Alternatively, it may be input on the server 10 side, or if it has already been stored in the storage 15 of the server 10, that may be used.

[0037] Particularly for ideas generated by the learned model, since they may already be stored in the user terminal 30 or the server 10, they may be used as they are.

[0038] Next, the input prompt is input into the large language model, and evaluation information with an evaluation regarding the idea is obtained. This operation is basically performed via the large language model on the server 10 side. For this reason, the prompt obtained on the user terminal 30 is transmitted to the server 10 via the communication network 20. The server 10 may display the evaluation information obtained via the large language model via the input / output I / F 13, or transmit the evaluation information to the user terminal 30 via the communication network 20 and display it via the input / output I / F 33 on the user terminal 30. In addition to being embodied as such an idea evaluation system 1, the present invention may also be embodied as a program capable of implementing these functions.

[0039] In addition, when the function of generating evaluation information based on a large language model for the input prompt is provided on the server 10 side, these operations are executed via the storage 15 and the server-side program 40. In addition, the function of generating evaluation information based on a large language model for the input prompt may be provided not on the server 10 but on the user terminal 30 side. In such a case, these operations are executed via the storage 35 and the terminal-side program 42 in the user terminal 30. Then, the prompt acquired in the user terminal 30 is input directly into the large language model in the user terminal 30 without being transmitted to the server 10.

[0040] In addition, as the evaluation regarding the idea, any one or more of the resources or costs required to provide a product or service including the idea to customers, the marketability of the idea, and the customer satisfaction of the idea may be included.

[0041] Details, outlines, specifications, manufacturing methods, manufacturing man-hours, required materials, import and export destinations, information on logistics required for transporting products and materials, etc. of products or services including the idea can also be obtained through the large language model. After searching for these information once, the resources and costs required to provide the product or service to customers may be calculated from the unit prices prepared in advance as templates from the manufacturing man-hours, labor costs, material costs, etc., or these resources and costs may also be obtained through the large language model, or the resources and costs required to provide the product or service to customers may be directly obtained from the input prompt. In addition, the evaluation of costs and resources may be performed by preparing existing cost calculation programs, man-hour calculation programs, etc. in advance and using the results calculated by inputting parameters into these programs.

[0042] In addition to simply outputting the necessary resources or costs through this large language model, it is also possible to evaluate and include in the evaluation information the actual business potential itself, based on the quantity of resources and the magnitude of costs.

[0043] Marketability indicates information regarding the likelihood that the idea will be accepted by customers in the market, in other words, the likelihood that customers will purchase the idea, the share that can be obtained in the market, etc. The marketability of an idea is determined through a large language model from a prompt regarding the idea, and if necessary, based on information on the Internet, and the result is output.

[0044] At this time, as shown in FIG. 3, a market simulator 51 that performs a marketability simulation may be used.

[0045] The market simulator 51 is a tool that performs the above-described simulation regarding marketability based on the input parameters. This market simulator 51 may use any existing tool. Examples of information implemented in the market simulator 51 include settlement information of listed companies, expert comments and opinions regarding futures predictions and reasons for stock price increases or decreases published in analyst reports and newspaper articles, etc. Further examples of information implemented in the market simulator 51 include expert opinions regarding the entire Nikkei average futures, or opinions regarding specific segments or industries, and furthermore, opinions regarding individual futures, which may incorporate comments and upward or downward predictions by experts (analysts) published on the Internet. Also, examples of information implemented in the market simulator 51 may include information such as interest rates, futures, foreign exchange rates, stock prices of each brand, crude oil, precious metals, price movements of Bitcoin, etc., with serial charts, line graphs, Bollinger Bands, trading volume, MACD, moving averages, etc. Examples of information implemented in the market simulator 51 may include various data regarding politics, economy, society, technology, etc., such as GDP, employment statistics, mining and industrial production indices, capital investment, labor force surveys, business sentiment indices, consumer spending, new car sales volume, consumer price indices, etc.

[0046] The market simulator 51 performs a marketability simulation based on a well-known simulation method based on parameters according to information based on an input prompt or an idea output from a large language model. Then, evaluation information with an evaluation of the marketability of the idea may be obtained based on the result of the simulation by this market simulator 51. At this time, regarding the degree of acceptance in the market, the simulation may be performed while also referring to examples of markets, similar products, and services similar to the idea. Also, the market simulator 51 may refer to data on future predictions of the market, society, politics, economy, and technology in the future, and simulate marketability. Also, the market simulator 51 may determine the rarity, etc. based on the degree of existence of products and services similar to the idea, and simulate marketability from the determination result.

[0047] In addition to outputting the simulation result itself output from the market simulator 51 as evaluation information, the large language model may perform a solution search again based on the simulation result and output evaluation information. In such a case, the evaluation information is obtained by inputting a prompt reflecting the result of the simulation by the market simulator 51 into the large language model.

[0048] Regarding the customer satisfaction of the idea, it may be evaluated while also referring to examples of markets, similar products, and services similar to the idea. At this time, it may be determined from examples of markets, similar products, and services similar to the idea how much feedback there has been from customers in the past, or from data on sales and satisfaction. In such a case, based on information posted on SNS and Internet information, the degree of empathy may also be referred to, for example, the number of posts expressing empathy such as "like" on the Internet.

[0049] In addition, as an evaluation of an idea, the feasibility of the idea may be included. The feasibility here relates to whether it is technically feasible, but is not limited to this, and may also include whether it holds in terms of a business model, or the possibility of being infeasible due to factors other than technology such as politics, economy, and society. In such a case, the feasibility of the idea is evaluated using a large language model that has learned information about politics, economy, society, etc.

[0050] Among them, in evaluating the feasibility based on whether it is technically feasible or not, the feasibility of the idea is evaluated using a large language model that has learned information about natural science. The information about natural science here includes all papers in the natural science field, non-patent documents including those published in academic conferences and drafts of international conferences, patent documents, and furthermore, all technical information publicly available on the Internet.

[0051] At this time, as shown in FIG. 3, a natural science simulator 52 that performs a natural science simulation may be used.

[0052] The natural science simulator 52 is a tool that performs the above-described natural science simulation based on the input parameters. This natural science simulator 52 may use any existing tool. As the natural science simulator 52, for example, an FEM simulator that analyzes stress fields and strains based on the finite element method, a simulation of chemical reactions, a simulation of chemical engineering including plants, a simulation of electrical circuits, a simulation of fluid dynamics, a simulation of quantum mechanics, etc., tools capable of simulating physical phenomena, chemical phenomena, and thus all natural sciences are used.

[0053] The natural science simulator 52 performs simulations of natural science based on well-known simulation methods according to parameters corresponding to the input prompt or the ideas output from the large language model. And through this natural science simulator 52, it may be determined whether the idea itself can be technically realized. For example, if it violates the law of universal gravitation that violates natural laws, the fact may be added to the evaluation.

[0054] In addition to whether it can be realized scientifically, if it can be realized scientifically, the magnitude of its effect may also be determined through the natural science simulator 52.

[0055] In addition to outputting the simulation result itself output from the natural science simulator 52 as evaluation information, the large language model may perform a new solution search based on the simulation result and output evaluation information. In such a case, evaluation information is obtained by inputting a prompt reflecting the result of the simulation by the natural science simulator 52 into the large language model.

[0056] According to the present invention, evaluation information regarding the novelty or inventiveness of the above idea may be obtained by a large language model that has learned patent information. That is, the patent information includes not only all text data of published published gazettes and patent gazettes (hereinafter, these are collectively referred to as patent gazettes), but also patent classifications. In the large language model, related patent gazettes are searched based on the obtained prompt. Then, the patent information described in the searched known patent gazettes is compared with the content of the prompt of the obtained idea. Then, it is determined whether there are differences between the patent information described in the known patent gazettes and the content of the idea prompt, and the degree of the differences, and an evaluation of novelty or inventiveness is performed based on the determination result.

[0057] In such a case, by pre-training the patent information, a pre-established learned model for searching for similar patent gazettes for the input text data may be provided. Then, the input prompt is input into the learned model. As a result, similar patent gazettes (patent documents) for the input prompt are searched from the learned model. That is, text data of similar patent gazettes for the created idea can be obtained from the learned model. Next, it is determined whether there are differences between the patent information described in the known patent gazette and the content of the idea prompt, and the degree of the differences, and an evaluation of novelty or inventiveness is performed based on the determination result. The searched patent gazette (patent document) may be obtained as one piece of evaluation information.

[0058] At this time, the prompt may be input into a large language model, and text data based on the idea output therefrom may be obtained once. The text data based on the idea is information about the idea organized through the large language model from the prompt, or is generated in a language suitable for solution search. An evaluation of novelty or inventiveness may be performed based on the text data of the known patent gazette output by inputting this into the learned model.

[0059] In the present invention, as shown in FIG. 4, request information for ideas to be newly created may be generated based on the acquired evaluation information. This request information is, so to speak, a prompt (input text shown in FIG. 4) for generating ideas by artificial intelligence, which utilizes a learned model that explores solutions for the input text data. If better request information can be generated based on the evaluation information in this way, the artificial intelligence (learned model) can generate better ideas accordingly. Particularly when the evaluation result is not good, request information necessary for further improving the invention can be efficiently generated. For example, in the case of an evaluation result that the novelty and inventiveness are lacking in "a plurality of blades and a rotor" among the solution methods of the idea, as request information necessary for further improving "responding to wind speed", "In a wind power generation combining a low-speed cross-flow type windmill and a high-speed Darrieus type windmill according to wind speed, what is the method for enhancing the power generation effect of wind power generation?" can be generated. For example, in the case where novelty and inventiveness are lacking, etc., the idea can be further improved by generating request information necessary for showing inventiveness.

[0060] Note that this request information may be input into a large language model. And information regarding the ideas to be newly created output from the large language model for the input request information may be output. That is, a large language model may be applied when generating ideas by artificial intelligence.

[0061] Also, a large language model may be utilized when generating request information from the evaluation information. That is, as shown in FIG. 5, the generated evaluation information is input into the large language model. And request information is output from the large language model for the input evaluation information. That is, a large language model may also be applied when generating request information from the evaluation information.

[0062] According to the present invention as described above, by using a large language model, the created ideas can be automatically evaluated from various perspectives such as feasibility, marketability, patentability, etc. As a result, it is possible to automatically evaluate the solution concepts and inventions completed with the help of artificial intelligence, and when a large number of solution concepts and inventions are automatically generated by artificial intelligence, these can be sorted out, and it is also possible to easily realize the work of summarizing them into the necessary technologies for linking to the value provided to customers.

[0063] Also, even when the evaluation results are not satisfactory, the large language model can generate the request information necessary to further improve the invention.

[0064] Note that the present invention is not limited to the above-described embodiments. For example, based on the evaluation information, it may be possible to search for companies that promote the utilization of the idea.

[0065] The companies that can utilize the idea refer to companies that actually want to use the idea and companies that can gain benefits through partnerships through open innovation. In searching for such companies, the search is performed based on public information, that is, the patent information and non-patent literature content of each company, and the information on the company's website and news releases. The search itself may be carried out using artificial intelligence, or even using a large language model. In such a case, the evaluation information is input into the large language model, and the large language model outputs the companies that promote the utilization of the idea based on the above-described various information.

[0066] Second Embodiment Hereinafter, the second embodiment will be described. In the second embodiment, the configuration of the idea evaluation system 1 described in the first embodiment above is used as it is, and the processing operations described in the first embodiment are appropriately combined and executed.

[0067] In the second embodiment, a prompt related to an idea is input into the base model, and story information related to a business story that makes use of the idea output from the base model for the input prompt is acquired.

[0068] A business story that makes use of an idea refers to a context consisting of a stage or characters, a conflict, and a big idea that leads to a solution constituted by that idea, as shown in FIG. 6.

[0069] The stage or characters indicate the situation or background necessary for leading to that idea, i.e., the solution. The characters are the actual characters that appear in the story, and the characters are those with personalities that the audience such as customers, business partners, partner companies, employees, and stakeholders can empathize with.

[0070] The context is formed through this stage or characters. For example, in the case of an idea (solution) related to two-dimensional code technology, a story (text information) consisting of the stage of the two-dimensional code payment market is generated, and the characters include the party proposing this solution (e.g., a company developing and producing two-dimensional codes). Note that the characters may be omitted in forming this context.

[0071] And the conflict indicates what problems or unfortunate events may occur if the current situation remains unchanged. For example, in the case of an idea (solution) related to two-dimensional code technology, a story is generated that causes a conflict in the mind such as if the current two-dimensional code continues to be used, various security-related incidents will occur frequently, and something must be done to get out of this situation. That is, through the conflict, excitement is created, a strong impression that cannot be forgotten by the other party is implanted, getting out of a boring story, and the other party will become interested and listen eagerly.

[0072] A big idea is not the solution itself, but rather a more high-level conceptualization of the solution, or a summary of the solution expressed in a catchphrase or the like. Create a single catchphrase that will calm the listener and leave a lasting impression when they hear the big idea. This big idea may be generated, for example, based on the context and conflicts generated in the previous stage in addition to the idea. Examples of big ideas include "Introducing a system for measuring biological data 〇〇 without needles," "Building a 〇〇 investment platform that is easy for 〇〇 investors to use," and "Providing a 〇〇 prevention function in the two-dimensional code itself," which may convey what one wants to do in a single phrase.

[0073] In generating such a story, it is also possible to propose through the generated story how to link the generated idea to business and monetize it. Also, a suitable business model for realizing such a story may be generated and proposed.

[0074] When proposing this story, it may be shown as the evaluation information shown in the first embodiment described above.

[0075] Also, simulation may be performed using the market simulator in the first embodiment, and story information may be obtained based on the results of the simulation. In such a case, if the product or service does not seem likely to sell well as a result of the simulation by the simulator, one may work to generate a story that causes a more powerful impactful conflict.

[0076] Also, by inputting a prompt reflecting the result of the simulation by the market simulator into the base model, a new story may be generated according to the result of the simulation. When an evaluation regarding the novelty or inventiveness of the idea is obtained at this time, story information based on this may be acquired. For example, when there is no inventiveness, a context corresponding thereto may be created.

[0077] Also, based on the acquired story information, request information for an idea to be newly created may be generated. That is, when there is a further solution in the acquired story and it leads to a more effective solution to the conflict, request information corresponding thereto may be generated.

[0078] In this second embodiment, as a basis, as shown in FIG. 6, information regarding the evaluation of the novelty or inventiveness of the idea, or patent information output in the first embodiment may be shown. Thereby, it can be shown that the solution, that is, the idea itself has patentability, and it can also be implied that the entire generated business story is protected by a patent.

[0079] Note that the present invention is not limited to the above-described embodiments. As a prompt to be input into the base model, instead of a prompt regarding an idea, a prompt regarding a technical need may be input.

[0080] The prompt regarding the technical need here may be limited in detail to technologies such as, for example, a wide range of technologies such as NFT technology, AI technology, nanotechnology, and metaverse technology, and specifically, nanoimprint technology and nanorobot technology of nanotechnology.

[0081] Then, for the prompt regarding such technological needs, obtain need information regarding business needs that make use of the technological needs output from the base model. This need information indicates in which actual marketing segments and customer groups there are needs for the specific value provided by making use of the technological needs.

[0082] Conversely, when a prompt regarding need information is input, information regarding technological needs may be output from the base model.

[0083] Note that in both the first embodiment and the second embodiment, the prompt input to the base model is not limited to text data, and image data may be input. In such a case, text information may be extracted from the image data using well-known techniques, or data obtained by vectorizing the semantic content of the image data may be input to the base model as a prompt.

[0084] Similarly, in both the first embodiment and the second embodiment, the information output from the base model is not limited to the case where it is text data, sentences, or character strings, and it may output diagrams, tables, image data, etc. In particular, when generating story information, not only text data but also outputting it as an image may make the story easier to understand, or it is often easier to understand when a combination of image and text data is used.

Explanation of Reference Numerals

[0085] 1 Idea Evaluation System 10 Server 11, 31 Computer Processor 12, 32 Memory 15, 35 Storage 20 Communication Network 30 User Terminal 40 Server-Side Program 42 Terminal-Side Program 51 Market Simulator 52 Natural Science Simulator 152 Evaluation Information Management Table

Claims

1. Prompt input means for inputting a prompt related to an idea into a base model, and evaluation information acquisition means for acquiring evaluation information with an evaluation related to the idea output from the base model for the prompt input to the prompt input means. An idea evaluation system characterized by the above.

2. The evaluation information acquisition means includes, as an evaluation related to the idea, any one or more of resources or costs required to provide a product or service including the idea to customers, the marketability of the idea, and the customer satisfaction of the idea. The idea evaluation system according to Claim 1, characterized by the above.

3. The evaluation information acquisition means includes, as an evaluation related to the idea, the feasibility of the idea. The idea evaluation system according to Claim 1, characterized by the above.

4. The evaluation information acquisition means acquires evaluation information with an evaluation of the feasibility of the idea by the base model that has learned information related to natural science. The idea evaluation system according to Claim 3, characterized by the above.

5. Further comprising a natural science simulator that performs a simulation of that natural science based on the input parameters, the natural science simulator performs a simulation using, as the parameters, the prompt input to the prompt input means or information based on the idea output from the base model, and the evaluation information acquisition means acquires evaluation information with an evaluation of the feasibility of the idea based on the result of the simulation by the natural science simulator. The idea evaluation system according to Claim 3, characterized by the above.

6. Further comprising a natural science simulator that performs a simulation of that natural science based on the input parameters, the natural science simulator performs a simulation using, as the parameters, the prompt input to the prompt input means or information based on the idea output from the base model, and the prompt input means inputs a prompt reflecting the result of the simulation by the natural science simulator into the base model. The idea evaluation system according to Claim 3, characterized by the above.

7. Further comprising a market simulator that performs a simulation of its marketability based on the input parameters, The market simulator performs a simulation using, as the parameters, the prompt input to the prompt input means or information based on the idea output from the base model, the evaluation information acquisition means acquires evaluation information in which the marketability of the idea is evaluated based on the result of the simulation by the market simulator The idea evaluation system according to claim 2, characterized in that.

8. further comprising a market simulator that performs a simulation of its marketability based on the input parameters, the market simulator performs a simulation using, as the parameters, the prompt input to the prompt input means or information based on the idea output from the base model, the prompt input means inputs a prompt in which the result of the simulation by the market simulator is reflected into the base model The idea evaluation system according to claim 2, characterized in that.

9. the evaluation information acquisition means acquires evaluation information in which the novelty or inventiveness of the idea is evaluated by the base model that has learned patent information The idea evaluation system according to claim 1, characterized in that.

10. further comprising a learned model that searches for similar patent document numbers for the input text data by pre-learning patent information, acquiring, as the evaluation information, the patent documents output by inputting the prompt input to the prompt input means or the text data based on the idea output from the base model into the learned model The idea evaluation system according to claim 1, characterized in that.

11. further comprising a learned model that searches for similar patent document numbers for the input text data by pre-learning patent information, acquiring evaluation information in which the novelty or inventiveness of the idea is evaluated based on the text data of the patent documents output by inputting the prompt input to the prompt input means or the text data based on the idea output from the base model into the learned model The idea evaluation system according to claim 1, characterized in that.

12. Further comprising request information generation means for generating request information for an idea to be newly created based on the evaluation information acquired by the above evaluation information acquisition means The idea evaluation system according to claim 1, characterized in that.

13. Request information input means for inputting the request information generated by the above request information generation means into a base model, and Further comprising idea generation means for outputting information regarding an idea to be newly created, which is output from the base model with respect to the request information input to the above request information input means The idea evaluation system according to claim 12, characterized in that.

14. Further comprising enterprise search means for searching for an enterprise that promotes the utilization of the idea based on the evaluation information acquired by the above evaluation information acquisition means The idea evaluation system according to claim 1, characterized in that.

15. A prompt input step of inputting a prompt regarding an idea into a base model, and Causing a computer to execute an evaluation information acquisition step of acquiring evaluation information with an evaluation regarding the idea output from the base model for the prompt input in the above prompt input step An idea evaluation program, characterized in that.

Images