System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting and storing a plurality of previously submitted ideas in a database; means for training a generative AI model; means for analyzing the ideas stored in the database using the generative AI model and extracting superior ideas; means for organizing the extracted ideas and combining the plurality of ideas to generate a new innovation; and means for providing the generated new innovation to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In past idea contests, many ideas were very good in content but did not pass the first round due to a lack of presentation skills or the way materials were presented. These ideas end up buried, resulting in a missed opportunity to create new value. The objective of this invention is to solve this problem and provide a system that rediscovers buried good ideas and combines them to provide new innovative ideas. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. First, a means is provided for collecting multiple pieces of idea data submitted in the past and storing them in a database. Next, a means is provided for training a generative AI model on the data. Next, a means is provided for analyzing the idea data stored in the database using the generative AI model and extracting excellent ideas. After that, a means is provided for organizing the extracted ideas and combining multiple ideas to generate new innovation proposals. Finally, a means is provided for providing the generated new innovation proposals to users, thereby solving the problem.

[0006] "Idea data" refers to proposals and plans submitted in contests, etc., and information indicating their contents, including data in text, images, PDF format, etc.

[0007] A "database" is an information system for centrally storing and managing multiple idea data.

[0008] A "generative AI model" is an artificial intelligence model trained specifically for text generation and analysis, such as a natural language processing model like GPT-3.

[0009] "Analysis" refers to the process of using a generative AI model to evaluate and analyze the idea data in the database to find better ideas.

[0010] "Extraction" refers to the process of extracting highly rated idea data using a generative AI model.

[0011] "Organization" refers to the process of structurally reorganizing the extracted idea data and preparing for the generation of new ideas.

[0012] "Combination" refers to the process of integrating multiple idea data to generate new and original ideas.

[0013] An "innovative idea" refers to a new proposal or plan that is created by combining or reconstructing existing ideas.

[0014] "User" refers to the person who receives the generated new innovation ideas and further improves them or uses them in new projects. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The system of this invention runs on a server, collects multiple idea data submitted in past idea contests, and generates new innovative ideas by analyzing, evaluating, and reconstructing them using a generative AI model, which it then provides to users.

[0037] First, the server collects all ideas submitted in past idea contests. This collected data is diverse, including text data, image data, and PDF files. All collected idea data is stored in a database. This database centrally manages multiple idea data and is structured to make it easy to apply to subsequent processing.

[0038] Next, the server trains a generative AI model on the idea data in the database. For example, a text generation model (such as GPT-3) is used as the generative AI model. This model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea.

[0039] The server uses this generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, such as the loss value of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0040] After extracting the top ideas, the server organizes them and reconstructs them into new innovation proposals. This restructuring is done by combining multiple excellent ideas to generate new creative and practical proposals. For example, combining the ideas of an "automatic plant watering system" and a "smart refrigerator" generates a new idea: a system that automatically grows fresh herbs inside a smart refrigerator.

[0041] Finally, the server provides the generated new innovations to the user, who can review the new ideas and apply them to their own projects or work. The generated ideas are provided to the user via a web interface or other communication means.

[0042] In this way, it is possible to rediscover good ideas buried in the past and reconstruct them as innovative proposals.The aim of this system is to promote the creation of new value and provide useful information to users.

[0043] The processing flow will be explained below.

[0044] Step 1:

[0045] The server collects multiple idea data submitted in past idea contests in various formats, such as text data, image data, and PDF files.

[0046] Step 2:

[0047] The server stores the collected idea data in a database, which is used to centrally manage the titles and contents of ideas.

[0048] Step 3:

[0049] The server trains a generative AI model using the idea data in the database. For example, it uses a text generation model like GPT-3. The idea data is input into the model, which then learns through natural language processing and pattern recognition.

[0050] Step 4:

[0051] The server uses a generative AI model to analyze the idea data in the database and extracts superior ideas based on evaluation criteria. The evaluation criteria are the loss values ​​of the generative AI model. Ideas with lower loss values ​​are considered to be more highly rated and are extracted as superior ideas.

[0052] Step 5:

[0053] The server organizes the extracted ideas and combines them with other ideas as needed to generate new innovation proposals. For example, by combining the highly rated ideas "automatic plant watering system" and "smart refrigerator," a new innovation proposal called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0054] Step 6:

[0055] The server provides the generated new innovations to the user via a web interface, email, or other means, allowing the user to review the new ideas and apply them to their own projects or work.

[0056] Example 1

[0057] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0058] Conventional idea generation systems have difficulty effectively utilizing past ideas to generate new, creative ideas. Furthermore, the evaluation criteria for each idea are unclear, making it difficult to extract high-quality ideas. Therefore, there is a need for a system that can efficiently utilize previously submitted ideas to generate new, innovative ideas.

[0059] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0060] In this invention, the server includes means for collecting multiple pieces of information data submitted in the past and storing them in an information storage device, means for training a generative AI model to learn the data, means for analyzing the information data stored in the information storage device using the generative AI model and extracting superior information, means for organizing the extracted information and combining multiple pieces of information to generate new innovation ideas, means for providing the generated new innovation ideas to users, means for temporarily storing data in a temporary storage device, means for converting data into an appropriate format, and means for ranking information based on the evaluation value of the generative AI model, thereby making it possible to reevaluate past ideas and generate new creative and practical ideas.

[0061] "Information data" refers to information such as text data, image data, PDF files, etc. that show the content of ideas that have been submitted in the past.

[0062] An "information storage device" is a database or storage system that efficiently manages collected information data and stores it in a form that can be used for subsequent processing.

[0063] A "generative artificial intelligence model" is an artificial intelligence technology for learning information data and analyzing, evaluating, and generating it, and specifically includes text generation models.

[0064] An "evaluation value" is a numerical value that serves as a standard used by a generative artificial intelligence model when evaluating information data, and includes the model's loss value, etc.

[0065] "Ranking" refers to the process of ranking a plurality of pieces of information data based on evaluation values, so that information with higher evaluations is ranked higher.

[0066] A "temporary storage device" is a storage system for temporarily storing collected information data, and plays a role in improving data processing efficiency.

[0067] "Users" are individuals or organizations that use the new innovations generated and apply them in their own projects or work.

[0068] An "innovative proposal" is a new idea or proposal generated by reconstructing multiple existing pieces of information data.

[0069] The system of this invention is designed to effectively utilize multiple pieces of information data submitted in the past to generate new creative ideas. This system runs on a server and performs a series of processes including collection, storage, analysis, evaluation, reconstruction, and provision.

[0070] The server first collects previously submitted information data. This collection is done using web scraping or an API. The collected data is temporarily stored in a temporary storage device. It is then stored in an information storage device (for example, MongoDB or Amazon S3). This ensures data consistency and creates a structure that makes it easy to apply to subsequent processing.

[0071] Next, the server trains the generative AI model on the information data. A text generation model (e.g., GPT-3) is used as the generative AI model. This model performs natural language processing on the information data and extracts the characteristics of each piece of data. The server then uses the generative AI model to analyze the data stored in the information storage device and extracts superior information based on an evaluation criterion. Specifically, the loss value of the generative AI model is used as the criterion, and information with a lower loss value is considered to be more highly rated.

[0072] After extracting the most highly rated information, the server organizes it and reconstructs it into new innovation ideas. This reconstruction is done by combining multiple excellent pieces of information to generate creative and practical proposals. For example, by combining information on "automatic plant watering systems" and "smart refrigerators," a new idea called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0073] Finally, the server provides the generated new innovation ideas to the user, who can then review the new ideas and apply them to their own projects or work. The generated ideas are provided via a web interface, email, etc.

[0074] Specific examples

[0075] If an "automatic plant watering system" and a "smart refrigerator" are collected as past information data, the text data and outline of each idea are stored in an information storage device. The generative AI model can learn from these and combine them to propose a "system that automatically grows fresh herbs inside a smart refrigerator."

[0076] Prompt Sentence Examples

[0077] "Generate new, innovative ideas based on data from multiple previously submitted ideas. Combine top-rated ideas to create actionable proposals."

[0078] This system allows users to reevaluate past ideas and provide them as new creative proposals, thereby enabling the creation of new value. In this way, the mode for carrying out the invention is specifically shown.

[0079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0080] Step 1:

[0081] Server: Start data collection

[0082] Specific operation: The server collects information data from past idea contests using web scraping and APIs. The collected data includes text data, image data, PDF files, etc.

[0083] Input: Idea contest website or API URL

[0084] Data processing: The server uses the Python BeautifulSoup library to extract text data from websites and retrieve data from APIs.

[0085] Output: raw data collected

[0086] Step 2:

[0087] Server: Temporary data storage

[0088] What it does: The server temporarily stores the collected data in an Amazon S3 bucket, ensuring data consistency and easy retrieval for subsequent processing steps.

[0089] Input: Raw data collected

[0090] Data processing: Save the data as is to Amazon S3

[0091] Output: Temporarily saved data

[0092] Step 3:

[0093] Server: Stored in a database

[0094] How it works: The server uses the Python "pymongo" library to store text data in a MongoDB database, and image data and PDF files in Amazon S3.

[0095] Input: Temporarily saved data

[0096] Data processing: Text data is inserted into MongoDB, and image data and PDF files are moved to Amazon S3

[0097] Output: Data stored in database and storage

[0098] Step 4:

[0099] Server: Prepare the data

[0100] Specific operation: The server uses Python's "pandas" library to format the idea data retrieved from the database and convert it into an input format for the generative AI model.

[0101] Input: Data stored in databases and storage

[0102] Data processing: Format data into tables and clean text data

[0103] Output: Formatted data

[0104] Step 5:

[0105] Server: Model training

[0106] How it works: The server uses a generative AI model (e.g., GPT-3) to train on the formatted idea data, allowing the model to understand the characteristics of each idea and evaluate them accordingly.

[0107] Input: Formatted data

[0108] Data processing: feature extraction, pattern recognition

[0109] Output: A trained generative AI model

[0110] Step 6:

[0111] Server: Data analysis

[0112] How it works: The server uses a generative AI model to analyze idea data and evaluate each idea based on its loss value.

[0113] Input: Trained generative AI model, idea data

[0114] Data calculation: Calculating loss values, evaluating ideas

[0115] Output: Evaluation results (loss values ​​and rankings of ideas)

[0116] Step 7:

[0117] Server: Idea ranking

[0118] Specific operation: The server ranks the idea data based on the loss value. The information with a lower loss value is rated higher.

[0119] Input: Evaluation result

[0120] Data processing: Idea ranking

[0121] Output: A ranked list of ideas

[0122] Step 8:

[0123] Server: Extracting and Reconstructing Great Ideas

[0124] How it works: The server extracts the top ranked ideas and selects them for restructuring. It then combines them to generate new innovations. For example, it combines an "automatic plant watering system" with a "smart refrigerator" to generate a new "system that automatically grows fresh herbs inside a smart refrigerator."

[0125] Input: A ranked list of ideas

[0126] Data processing: Combining ideas and generating new proposals

[0127] Output: New innovations

[0128] Step 9:

[0129] Server: Idea distribution

[0130] Specific operation: The server provides the generated new innovations to the user via a web interface, email, etc.

[0131] Input: New innovation idea

[0132] Data processing: Converting to a presentation format

[0133] Output: New innovations provided to the user

[0134] Step 10:

[0135] User: Checking the idea

[0136] Specific Action: Users review the new ideas provided and apply them to their own projects or work.

[0137] Input: New innovation ideas provided

[0138] Output: User confirmation and application of new ideas

[0139] This series of processes enables the system to reevaluate past information data, generate new creative and practical ideas, and provide them to users.

[0140] (Application example 1)

[0141] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0142] With conventional methods, it was difficult to effectively utilize the ideas submitted in idea contests, and the process of efficiently extracting and reconstructing the best ideas from among them was particularly laborious and time-consuming.In addition, there were no well-established methods for quickly generating new innovative ideas and providing them to users.

[0143] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0144] In this invention, the server includes means for collecting a plurality of idea data submitted in the past and storing them in a database, means for training a generative AI model to learn the data, means for analyzing the idea data stored in the database using the generative AI model and extracting good ideas, means for organizing the extracted ideas and combining the plurality of ideas to generate new innovation proposals, and means for using a web interface to provide the generated new innovation proposals to users. This enables effective use of ideas submitted in the past and enables new innovation proposals to be quickly generated and provided to users.

[0145] "Idea data" refers to multiple proposals submitted in past idea contests, and can range from text data, image data, and PDF files.

[0146] A "database" is a storage medium that centrally manages collected idea data and has a structure that makes it easy to apply to subsequent processing.

[0147] A "generative AI model" is an artificial intelligence model that uses, for example, a text generation model (such as GPT-3) to analyze, evaluate, and reconstruct idea data.

[0148] "Web Interface" means a user interface via an internet browser for presenting generated new innovations to a user.

[0149] "Loss value" is a metric used to evaluate the performance of a generative AI model, with lower values ​​indicating more accurate predictions by the model.

[0150] The system for implementing the present invention includes various components for effectively collecting, analyzing, evaluating, and generating new innovation ideas for users. Specific embodiments are described in detail below.

[0151] First, the server collects multiple pieces of idea data that have been submitted in the past and stores them in a database. This data includes text data, image data, PDF files, etc. The database centrally manages this data and has a structure that makes it easy to apply to subsequent processing.

[0152] Next, the server trains a generative AI model (for example, GPT-3, a text generation model) on the idea data in this database. The generative AI model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea. The loss value of the generative AI model is used as the evaluation criterion, with a lower loss value being considered a higher evaluation.

[0153] The server then uses the generative AI model to analyze the idea data stored in the database and extract the highly rated ideas. The extracted ideas are then further organized and multiple ideas are combined to generate new innovations. This process efficiently combines diverse ideas to produce novel and practical proposals.

[0154] The new innovations generated are then presented to the user through a web interface designed to allow users to easily explore the generated ideas and apply them to their own projects and work.

[0155] For example, the following prompts can be fed into a generative AI model to evaluate and reconstruct ideas:

[0156] "Rate this idea: An application for personal finance management."

[0157] "Combine these ideas to generate new innovations:\n- A smart budgeting tool\n- A goal tracking app\n- An intuitive spending insights dashboard"

[0158] In this way, new innovations can be generated efficiently and useful information can be provided to users quickly.

[0159] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0160] Step 1:

[0161] The server collects multiple idea data submitted in the past. This idea data is diverse, including text data, image data, and PDF files. All collected idea data is stored in a database. The input is past idea data, which is processed by collecting and storing it, and then output in a structured format to the database.

[0162] Step 2:

[0163] The server trains the generative AI model on the idea data in the database. For example, a text generation model (GPT-3) is used as the generative AI model. The input for training is the idea data stored in the database, and training the AI ​​model improves its pattern recognition and natural language processing capabilities. This enables the generative AI model to analyze and evaluate ideas.

[0164] Step 3:

[0165] The server uses a generative AI model to analyze idea data stored in a database and extract highly rated ideas. The input is the idea data in the database and the generative AI model, and by running the generative AI model, it evaluates the idea data and extracts superior ideas based on loss values. The output is a list of highly rated ideas.

[0166] Step 4:

[0167] The server organizes the extracted ideas and combines multiple ideas to generate new innovation proposals. The input is a list of highly rated ideas, and new ideas are generated using a reconstruction algorithm. This results in novel and practical proposals. The output is new innovation proposals.

[0168] Step 5:

[0169] The server uses a web interface to provide the generated new innovation proposals to the user. The input is the generated innovation proposals, which are displayed to the user through the web interface, allowing the user to easily check the new ideas and apply them to their own projects or work. The output is the provision of the innovation proposals to the user.

[0170] The above is the flow of processing of the program of the system that realizes the application example.

[0171] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0172] The system of this invention runs on a server, collects multiple idea data submitted in past idea contests, and generates new innovation proposals by analyzing, evaluating, and reconstructing them using a generative AI model, and provides them to users. Furthermore, it has the function of recognizing user emotions by combining an emotion engine and selecting the innovation proposals to provide based on the user's emotions.

[0173] First, the server collects all ideas submitted in past idea contests. This is done in a variety of formats, including text data, image data, and PDF files. All collected idea data is stored in a database. This database centrally manages multiple idea data and is structured to make it easy to apply to subsequent processing.

[0174] Next, the server trains a generative AI model on the idea data in the database. For example, a text generation model such as GPT-3 is used as the generative AI model. This model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea.

[0175] The server uses this generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, such as the loss value of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0176] After extracting the top ideas, the server organizes them and combines them to generate new innovations. For example, combining the ideas of an "automatic plant watering system" and a "smart refrigerator" generates a new idea called a "system for automatically growing fresh herbs inside a smart refrigerator."

[0177] The server then analyzes the user's emotions using an emotion engine, which recognizes the user's facial expressions, tone of voice, and incompatibility data to quantitatively evaluate the user's emotional state. Based on the evaluation results obtained by the emotion engine, the server selects and provides the user with the most suitable innovation proposal.

[0178] Finally, the server provides the generated new innovations to the user via a web interface, email, or other means. The user can review the new ideas and apply them to their own projects or work. User feedback is also fed back into the system for further improvements.

[0179] For example, if a user expresses interest in a "system that automatically grows fresh herbs inside a smart refrigerator," the emotion engine will recognize the user's positive response and prioritize innovation proposals on a similar theme. In this way, by combining emotion engines, it becomes possible to provide innovation proposals that match the user's needs and emotions.

[0180] This system makes it possible to rediscover good ideas that have been buried in the past and reconstruct them as innovative proposals, with the aim of promoting the creation of new value.

[0181] The processing flow will be explained below.

[0182] Step 1:

[0183] The server collects multiple idea data submitted in past idea contests in various formats, such as text data, image data, and PDF files.

[0184] Step 2:

[0185] The server stores the collected idea data in a database, which is used to centrally manage the titles and contents of ideas.

[0186] Step 3:

[0187] The server trains a generative AI model using the idea data in the database. For example, it uses a text generation model like GPT-3. The idea data is input into the model, which then learns through natural language processing and pattern recognition.

[0188] Step 4:

[0189] The server uses a generative AI model to analyze the idea data in the database and extracts superior ideas based on evaluation criteria. The evaluation criteria are the loss values ​​of the generative AI model. Ideas with lower loss values ​​are considered to be more highly rated and are extracted as superior ideas.

[0190] Step 5:

[0191] The server organizes the extracted ideas and combines them with other ideas as needed to generate new innovation proposals. For example, by combining the highly rated ideas "automatic plant watering system" and "smart refrigerator," a new innovation proposal called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0192] Step 6:

[0193] The server analyzes the user's emotions using an emotion engine, which recognizes the user's facial expressions, tone of voice, and incompatibility data to quantitatively evaluate the user's emotional state.

[0194] Step 7:

[0195] The server selects the most suitable innovation proposal for the user based on the evaluation results of the emotion engine. For example, if the user has a positive reaction, it will prioritize the innovation proposal that matches that emotion.

[0196] Step 8:

[0197] The server provides the generated new innovations to the user via a web interface, email, or other means, allowing the user to review the new ideas and apply them to their own projects or work.

[0198] Step 9:

[0199] User feedback is fed back into the system to help it further improve, allowing it to continually update and generate better innovations.

[0200] Example 2

[0201] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0202] There is a need for a system that can generate new innovation proposals using previously submitted proposal data and provide those proposals to users efficiently and effectively. However, conventional systems do not automate the collection and analysis of proposal data, which requires time and effort. In addition, determining whether the generated innovation proposals match the user's emotions and needs is often done manually, making it difficult to improve user satisfaction. Therefore, there is a need for technology that can automatically collect and analyze past proposal data and provide optimal innovation proposals based on user emotions.

[0203] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0204] In this invention, the server includes means for collecting multiple proposal data submitted in the past and storing them in a storage device, means for training a generative AI model to learn the data, means for analyzing the proposal data stored in the storage device using the generative AI model and extracting excellent proposals, means for organizing the extracted proposals and combining multiple proposals to generate new innovative proposals, means for recognizing the emotional state of a user using an emotion recognition engine, and means for selecting and providing the new innovative proposals based on the emotional state. This makes it possible to efficiently generate effective innovative proposals based on past proposal data and provide them to users.

[0205] "Proposal data" refers to data that includes information on ideas, concepts, designs, etc. that have been submitted in the past.

[0206] "Storage device" refers to hardware and software for storing and managing data.

[0207] A "generative AI model" is an artificial intelligence model that performs text generation and natural language processing.

[0208] A "loss value" is an evaluation metric that indicates the error when a generative AI model is trained.

[0209] An "emotion recognition engine" is a technology that quantitatively evaluates a user's emotional state based on facial expressions, tone of voice, etc.

[0210] An "emotional state" is a state that represents a user's current feelings or mood.

[0211] An "innovative proposal" is a new proposal or concept that is generated based on existing ideas or technologies.

[0212] "Selection" refers to the process of selecting the best innovation from multiple proposals.

[0213] "Providing" refers to the act of notifying or presenting the generated innovation proposal to the user.

[0214] The system of the present invention executes a series of processes running on a server to collect multiple proposal data submitted in the past, generate new innovation proposals, and provide them to users. It also has a function to recognize the user's emotional state using an emotion recognition engine and select the innovation proposal that is most suitable for the user.

[0215] First, the server collects proposal data in the form of text data, image data, and PDF files from past proposal contests and databases. Web scraping tools and APIs are used for the collection. For example, Python and Selenium are used as web scraping tools. The collected data is then stored in a storage device such as MongoDB.

[0216] Next, the server uses a generative AI model to train the collected data. The generative AI model used is the language generation model GPT-3. The server inputs the preprocessed proposal data into the generative AI model and evaluates each proposal using natural language processing and pattern recognition. In this process, loss values ​​are used as the evaluation criterion, and proposals with low loss values ​​are extracted as superior.

[0217] The server then generates new innovation proposals based on the highly rated proposals. For example, by combining two proposals, "automatic plant watering system" and "smart refrigerator," a new innovation proposal such as "a system that automatically grows fresh herbs inside the smart refrigerator" is generated.

[0218] The server then analyzes the user's emotional state using an emotion recognition engine, which collects data on the user's facial expressions, tone of voice, and disapproval, and quantitatively evaluates the user's emotional state using technologies such as Amazon Rekognition and Google Cloud Speech-to-Text.

[0219] Based on the evaluation results of the emotion recognition engine, the server selects the most suitable innovation proposals from the generated proposals and provides them to the user via a web interface, email, or other methods. The web interface is built using the Django framework, and email notifications are sent using a Python mail sending library.

[0220] Examples of specific prompts include the following:

[0221] "Generate new refrigerator-related innovation ideas based on past idea data. Make them as relevant as possible to user emotions."

[0222] In this way, the system of the present invention can efficiently collect and analyze past proposal data and provide innovative proposals that match the user's emotional state, thereby promoting the creation of new value.

[0223] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0224] Step 1:

[0225] The server collects proposal data from past proposal contests and databases. The collected data ranges from text data, image data, and PDF files. For example, data is automatically scraped from specific websites using Python's Selenium library. The input is a list of website URLs, and the output is the proposal data.

[0226] Step 2:

[0227] The server stores the collected proposal data in a storage device such as MongoDB. The proposal data is stored in various formats (e.g., text, image, PDF). A database schema is defined to store the collected data appropriately. The input is the proposal data, and the output is the data stored in the storage device.

[0228] Step 3:

[0229] The server trains a generative AI model (e.g., GPT-3) with the stored proposal data. During this process, natural language processing (NLP) techniques are used to preprocess the data and input it into the generative AI model. For example, NLP libraries are used to tokenize and normalize the text data. The input is the data in storage, and the output is the trained generative AI model.

[0230] Step 4:

[0231] The server uses the generative AI model to analyze the proposal data stored in the storage device. This analysis involves pattern recognition and evaluation of each proposal. Loss value is used as the evaluation metric, and proposals with low loss values ​​are extracted as superior. The input is the trained generative AI model and proposal data, and the output is a list of evaluated proposals.

[0232] Step 5:

[0233] The server generates new innovation proposals based on the highly rated proposals. This is a process of combining multiple proposals to create new ideas. For example, the proposals for an "automatic plant watering system" and a "smart refrigerator" can be combined to generate a "system that automatically grows fresh herbs inside a smart refrigerator." The input is a list of evaluated proposals, and the output is a new innovation proposal.

[0234] Step 6:

[0235] The server analyzes the user's emotional state using an emotion recognition engine. It captures data on the user's facial expressions, tone of voice, and incompatibility to evaluate the emotional state. For example, it uses a webcam and microphone to collect data in real time and inputs it into the emotion recognition model. The input is the user's real-time data, and the output is an evaluation of the user's emotional state.

[0236] Step 7:

[0237] The server provides new innovation proposals to the user based on the emotional state evaluation results. This is done through a web interface or email. For example, it uses the Django framework to render web pages and a Python email library to send notifications. The inputs are the new innovation proposals and the emotional state evaluation results, and the output is the innovation proposals provided to the user.

[0238] Step 8:

[0239] The user reviews the proposed innovation and provides feedback. The server inputs this feedback back into the system to help improve it further. The input is the user's feedback, and the output is the system improvement data.

[0240] Through the above steps, a system is realized that efficiently generates new innovation proposals based on past proposal data and provides them according to the user's emotional state.

[0241] (Application example 2)

[0242] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0243] In recent years, many companies and organizations have been devoting significant efforts to generating innovative ideas. However, previously submitted ideas often go to waste or are not properly evaluated and utilized. Furthermore, there is a lack of systems that provide innovative ideas tailored to individual users' emotions and needs, resulting in a lack of an improved user experience. Furthermore, in brick-and-mortar stores, it would be effective to provide product and service suggestions based on the customer's emotional state, but such a system does not yet exist. These issues need to be resolved.

[0244] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0245] In this invention, the server includes means for collecting a plurality of previously submitted idea data and storing them in a database, means for training a generative AI model to learn the data, means for analyzing the idea data stored in the database using the generative AI model and extracting excellent ideas, means for organizing the extracted ideas and combining the plurality of ideas to generate new innovative ideas, and means for selecting and providing the generated new innovative ideas based on the emotional state of the user using an emotion recognition engine. This makes it possible to provide innovative ideas that match the emotional state of the user, improving the customer experience in physical stores and making effective use of hidden ideas.

[0246] "Idea data" refers to information about multiple ideas, proposals, and concepts that have been submitted in the past, and exists in multiple formats such as text data, image data, and PDF files.

[0247] A "database" is a collection of information that centrally manages and stores collected idea data and has a structure that makes it easy to apply to subsequent processing.

[0248] A "generative AI model" is a machine learning model used to learn from collected idea data, analyze and evaluate it, and generate new ideas. A typical example is a text generation model (e.g., GPT-3).

[0249] An "emotion recognition engine" is a system that quantitatively evaluates a user's emotional state by recognizing the user's facial expressions, tone of voice, and incompatibility data.

[0250] "Innovative ideas" refer to proposals or concepts that are newly created by combining multiple excellent ideas that have been extracted.

[0251] "User's emotional state" refers to a quantitative assessment result of the user's current emotion obtained by an emotion recognition engine.

[0252] A system for realizing the present invention is implemented with the following configuration and procedure.

[0253] First, the server collects multiple idea data submitted in the past and stores it in a database. This idea data includes information in various formats, such as text data, image data, and PDF files. The database is used to centrally manage this data and store it in a format that is convenient for subsequent processing.

[0254] Next, the server trains a generative AI model on the stored idea data. For example, a text generation model (e.g., GPT-3) is used as the generative AI model. This model performs pattern recognition and natural language processing based on the input text data and evaluates each idea.

[0255] The server uses the generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, which are the loss values ​​of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0256] The extracted ideas are organized by the server, and new innovations are generated by combining multiple ideas. For example, the ideas for an "automatic plant watering system" and a "smart refrigerator" can be combined to create a new idea for a "system that automatically grows fresh herbs inside a smart refrigerator."

[0257] The generated new innovation proposals are selected based on the user's emotional state using an emotion recognition engine. Specifically, the user's facial expressions and tone of voice are captured in real time using a camera and microphone, and the emotion recognition engine analyzes the data to quantitatively evaluate the user's emotional state. Based on the results of this evaluation, the server selects the most suitable innovation proposal for the user and provides it to the user via a smartphone app or a robot installed in a physical store.

[0258] For example, in-store sales history, customer reviews, and past marketing data can be used to generate ideas for new sales strategies and product improvements, while an emotion recognition engine can provide further relevant innovation suggestions when customers express interest.

[0259] An example of a prompt for a generative AI model is:

[0260] Generate new ideas for eco-friendly gift wrapping services based on past sales history and customer reviews, including suggestions on what materials to use and promotional strategies.

[0261] In this way, the present invention makes it possible to provide innovative ideas that are suited to the user's emotional state, thereby improving the customer experience in physical stores and making effective use of good ideas that have been buried in the past.

[0262] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0263] Step 1:

[0264] The server collects previously submitted idea data and stores it in a database. This data includes text data, image data, PDF files, etc. This data is extracted from information sources, formatted, and stored in the database. Idea data is used as input, and a formatted database entry is obtained as output.

[0265] Step 2:

[0266] The server trains a generative AI model on the idea data stored in the database. A text generation model (e.g., GPT-3) is used as the generative AI model. The idea data in the database is used as input, and the evaluation results and specific patterns for each idea are obtained as output. Specific operations include analyzing the text data and updating the model parameters.

[0267] Step 3:

[0268] The server uses a generative AI model to analyze idea data stored in a database and extract superior ideas. The loss value of the generative AI model is used as the evaluation criterion. The trained model and the idea data in the database are used as input, and a list of highly rated ideas is obtained as output. Specific operations include feedforward processing of the model and calculation of loss values.

[0269] Step 4:

[0270] The server organizes the extracted excellent ideas and combines multiple ideas to generate new innovation proposals. The input is a list of highly rated ideas, and the output is new innovation proposals. Specific operations include combining and re-evaluating ideas. For example, an "automatic plant watering system" and a "smart refrigerator" can be combined to generate a "system that automatically grows fresh herbs inside a smart refrigerator."

[0271] Step 5:

[0272] The generated innovation proposals are selected and presented based on the user's emotional state using an emotion recognition engine. Specifically, the user's facial expressions and tone of voice are captured using a camera and microphone and analyzed by the emotion recognition engine. The user's facial expression data and voice data are used as input, and an emotional evaluation result is obtained as output. Based on the evaluation result, the server selects the most suitable innovation proposal for the user.

[0273] Step 6:

[0274] The server provides the selected innovation proposals to the user via a smartphone app or a robot in a physical store. The innovation proposals based on the emotional evaluation results are used as input, and the innovation proposals presented to the user are obtained as output. Specific operations include sending the innovation proposals and displaying them on the interface. If the user shows interest, further related innovation proposals are suggested.

[0275] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0276] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0277] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0278] [Second embodiment]

[0279] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0280] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0281] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0282] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0283] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0284] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0285] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0286] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0287] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0288] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0289] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0290] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0291] The system of this invention runs on a server, collects multiple idea data submitted in past idea contests, and generates new innovative ideas by analyzing, evaluating, and reconstructing them using a generative AI model, which it then provides to users.

[0292] First, the server collects all ideas submitted in past idea contests. This collected data is diverse, including text data, image data, and PDF files. All collected idea data is stored in a database. This database centrally manages multiple idea data and is structured to make it easy to apply to subsequent processing.

[0293] Next, the server trains a generative AI model on the idea data in the database. For example, a text generation model (such as GPT-3) is used as the generative AI model. This model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea.

[0294] The server uses this generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, such as the loss value of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0295] After extracting the top ideas, the server organizes them and reconstructs them into new innovation proposals. This restructuring is done by combining multiple excellent ideas to generate new creative and practical proposals. For example, combining the ideas of an "automatic plant watering system" and a "smart refrigerator" generates a new idea: a system that automatically grows fresh herbs inside a smart refrigerator.

[0296] Finally, the server provides the generated new innovations to the user, who can review the new ideas and apply them to their own projects or work. The generated ideas are provided to the user via a web interface or other communication means.

[0297] In this way, it is possible to rediscover good ideas buried in the past and reconstruct them as innovative proposals.The aim of this system is to promote the creation of new value and provide useful information to users.

[0298] The processing flow will be explained below.

[0299] Step 1:

[0300] The server collects multiple idea data submitted in past idea contests in various formats, such as text data, image data, and PDF files.

[0301] Step 2:

[0302] The server stores the collected idea data in a database, which is used to centrally manage the titles and contents of ideas.

[0303] Step 3:

[0304] The server trains a generative AI model using the idea data in the database. For example, it uses a text generation model like GPT-3. The idea data is input into the model, which then learns through natural language processing and pattern recognition.

[0305] Step 4:

[0306] The server uses a generative AI model to analyze the idea data in the database and extracts superior ideas based on evaluation criteria. The evaluation criteria are the loss values ​​of the generative AI model. Ideas with lower loss values ​​are considered to be more highly rated and are extracted as superior ideas.

[0307] Step 5:

[0308] The server organizes the extracted ideas and combines them with other ideas as needed to generate new innovation proposals. For example, by combining the highly rated ideas "automatic plant watering system" and "smart refrigerator," a new innovation proposal called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0309] Step 6:

[0310] The server provides the generated new innovations to the user via a web interface, email, or other means, allowing the user to review the new ideas and apply them to their own projects or work.

[0311] Example 1

[0312] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0313] Conventional idea generation systems have difficulty effectively utilizing past ideas to generate new, creative ideas. Furthermore, the evaluation criteria for each idea are unclear, making it difficult to extract high-quality ideas. Therefore, there is a need for a system that can efficiently utilize previously submitted ideas to generate new, innovative ideas.

[0314] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0315] In this invention, the server includes means for collecting multiple pieces of information data submitted in the past and storing them in an information storage device, means for training a generative AI model to learn the data, means for analyzing the information data stored in the information storage device using the generative AI model and extracting superior information, means for organizing the extracted information and combining multiple pieces of information to generate new innovation ideas, means for providing the generated new innovation ideas to users, means for temporarily storing data in a temporary storage device, means for converting data into an appropriate format, and means for ranking information based on the evaluation value of the generative AI model, thereby making it possible to reevaluate past ideas and generate new creative and practical ideas.

[0316] "Information data" refers to information such as text data, image data, PDF files, etc. that show the content of ideas that have been submitted in the past.

[0317] An "information storage device" is a database or storage system that efficiently manages collected information data and stores it in a form that can be used for subsequent processing.

[0318] A "generative artificial intelligence model" is an artificial intelligence technology for learning information data and analyzing, evaluating, and generating it, and specifically includes text generation models.

[0319] An "evaluation value" is a numerical value that serves as a standard used by a generative artificial intelligence model when evaluating information data, and includes the model's loss value, etc.

[0320] "Ranking" refers to the process of ranking a plurality of pieces of information data based on evaluation values, so that information with higher evaluations is ranked higher.

[0321] A "temporary storage device" is a storage system for temporarily storing collected information data, and plays a role in improving data processing efficiency.

[0322] "Users" are individuals or organizations that use the new innovations generated and apply them in their own projects or work.

[0323] An "innovative proposal" is a new idea or proposal generated by reconstructing multiple existing pieces of information data.

[0324] The system of this invention is designed to effectively utilize multiple pieces of information data submitted in the past to generate new creative ideas. This system runs on a server and performs a series of processes including collection, storage, analysis, evaluation, reconstruction, and provision.

[0325] The server first collects previously submitted information data. This collection is done using web scraping or an API. The collected data is temporarily stored in a temporary storage device. It is then stored in an information storage device (for example, MongoDB or Amazon S3). This ensures data consistency and creates a structure that makes it easy to apply to subsequent processing.

[0326] Next, the server trains the generative AI model on the information data. A text generation model (e.g., GPT-3) is used as the generative AI model. This model performs natural language processing on the information data and extracts the characteristics of each piece of data. The server then uses the generative AI model to analyze the data stored in the information storage device and extracts superior information based on an evaluation criterion. Specifically, the loss value of the generative AI model is used as the criterion, and information with a lower loss value is considered to be more highly rated.

[0327] After extracting the most highly rated information, the server organizes it and reconstructs it into new innovation ideas. This reconstruction is done by combining multiple excellent pieces of information to generate creative and practical proposals. For example, by combining information on "automatic plant watering systems" and "smart refrigerators," a new idea called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0328] Finally, the server provides the generated new innovation ideas to the user, who can then review the new ideas and apply them to their own projects or work. The generated ideas are provided via a web interface, email, etc.

[0329] Specific examples

[0330] If an "automatic plant watering system" and a "smart refrigerator" are collected as past information data, the text data and outline of each idea are stored in an information storage device. The generative AI model can learn from these and combine them to propose a "system that automatically grows fresh herbs inside a smart refrigerator."

[0331] Prompt Sentence Examples

[0332] "Generate new, innovative ideas based on data from multiple previously submitted ideas. Combine top-rated ideas to create actionable proposals."

[0333] This system allows users to reevaluate past ideas and provide them as new creative proposals, thereby enabling the creation of new value. In this way, the mode for carrying out the invention is specifically shown.

[0334] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0335] Step 1:

[0336] Server: Start data collection

[0337] Specific operation: The server collects information data from past idea contests using web scraping and APIs. The collected data includes text data, image data, PDF files, etc.

[0338] Input: Idea contest website or API URL

[0339] Data processing: The server uses the Python BeautifulSoup library to extract text data from websites and retrieve data from APIs.

[0340] Output: raw data collected

[0341] Step 2:

[0342] Server: Temporary data storage

[0343] What it does: The server temporarily stores the collected data in an Amazon S3 bucket, ensuring data consistency and easy retrieval for subsequent processing steps.

[0344] Input: Raw data collected

[0345] Data processing: Save the data as is to Amazon S3

[0346] Output: Temporarily saved data

[0347] Step 3:

[0348] Server: Stored in a database

[0349] How it works: The server uses the Python "pymongo" library to store text data in a MongoDB database, and image data and PDF files in Amazon S3.

[0350] Input: Temporarily saved data

[0351] Data processing: Text data is inserted into MongoDB, and image data and PDF files are moved to Amazon S3

[0352] Output: Data stored in database and storage

[0353] Step 4:

[0354] Server: Prepare the data

[0355] Specific operation: The server uses Python's "pandas" library to format the idea data retrieved from the database and convert it into an input format for the generative AI model.

[0356] Input: Data stored in databases and storage

[0357] Data processing: Format data into tables and clean text data

[0358] Output: Formatted data

[0359] Step 5:

[0360] Server: Model training

[0361] How it works: The server uses a generative AI model (e.g., GPT-3) to train on the formatted idea data, allowing the model to understand the characteristics of each idea and evaluate them accordingly.

[0362] Input: Formatted data

[0363] Data processing: feature extraction, pattern recognition

[0364] Output: A trained generative AI model

[0365] Step 6:

[0366] Server: Data analysis

[0367] How it works: The server uses a generative AI model to analyze idea data and evaluate each idea based on its loss value.

[0368] Input: Trained generative AI model, idea data

[0369] Data calculation: Calculating loss values, evaluating ideas

[0370] Output: Evaluation results (loss values ​​and rankings of ideas)

[0371] Step 7:

[0372] Server: Idea ranking

[0373] Specific operation: The server ranks the idea data based on the loss value. The information with a lower loss value is rated higher.

[0374] Input: Evaluation result

[0375] Data processing: Idea ranking

[0376] Output: A ranked list of ideas

[0377] Step 8:

[0378] Server: Extracting and Reconstructing Great Ideas

[0379] How it works: The server extracts the top ranked ideas and selects them for restructuring. It then combines them to generate new innovations. For example, it combines an "automatic plant watering system" with a "smart refrigerator" to generate a new "system that automatically grows fresh herbs inside a smart refrigerator."

[0380] Input: A ranked list of ideas

[0381] Data processing: Combining ideas and generating new proposals

[0382] Output: New innovations

[0383] Step 9:

[0384] Server: Idea distribution

[0385] Specific operation: The server provides the generated new innovations to the user via a web interface, email, etc.

[0386] Input: New innovation idea

[0387] Data processing: Converting to a presentation format

[0388] Output: New innovations provided to the user

[0389] Step 10:

[0390] User: Checking the idea

[0391] Specific Action: Users review the new ideas provided and apply them to their own projects or work.

[0392] Input: New innovation ideas provided

[0393] Output: User confirmation and application of new ideas

[0394] This series of processes enables the system to reevaluate past information data, generate new creative and practical ideas, and provide them to users.

[0395] (Application example 1)

[0396] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0397] With conventional methods, it was difficult to effectively utilize the ideas submitted in idea contests, and the process of efficiently extracting and reconstructing the best ideas from among them was particularly laborious and time-consuming.In addition, there were no well-established methods for quickly generating new innovative ideas and providing them to users.

[0398] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0399] In this invention, the server includes means for collecting a plurality of idea data submitted in the past and storing them in a database, means for training a generative AI model to learn the data, means for analyzing the idea data stored in the database using the generative AI model and extracting good ideas, means for organizing the extracted ideas and combining the plurality of ideas to generate new innovation proposals, and means for using a web interface to provide the generated new innovation proposals to users. This enables effective use of ideas submitted in the past and enables new innovation proposals to be quickly generated and provided to users.

[0400] "Idea data" refers to multiple proposals submitted in past idea contests, and can range from text data, image data, PDF files, and more.

[0401] A "database" is a storage medium that centrally manages collected idea data and has a structure that makes it easy to apply to subsequent processing.

[0402] A "generative AI model" is an artificial intelligence model that uses, for example, a text generation model (such as GPT-3) to analyze, evaluate, and reconstruct idea data.

[0403] "Web Interface" means a user interface via an internet browser for presenting generated new innovations to a user.

[0404] "Loss value" is a metric used to evaluate the performance of a generative AI model, with lower values ​​indicating more accurate predictions by the model.

[0405] The system for implementing the present invention includes various components for effectively collecting, analyzing, evaluating, and generating new innovation ideas for users. Specific embodiments are described in detail below.

[0406] First, the server collects multiple pieces of idea data that have been submitted in the past and stores them in a database. This data includes text data, image data, PDF files, etc. The database centrally manages this data and has a structure that makes it easy to apply to subsequent processing.

[0407] Next, the server trains a generative AI model (for example, GPT-3, a text generation model) on the idea data in this database. The generative AI model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea. The loss value of the generative AI model is used as the evaluation criterion, with a lower loss value being considered a higher evaluation.

[0408] The server then uses the generative AI model to analyze the idea data stored in the database and extract the highly rated ideas. The extracted ideas are then further organized and multiple ideas are combined to generate new innovations. This process efficiently combines diverse ideas to produce novel and practical proposals.

[0409] The new innovations generated are then presented to the user through a web interface designed to allow users to easily explore the generated ideas and apply them to their own projects and work.

[0410] For example, the following prompts can be fed into a generative AI model to evaluate and reconstruct ideas:

[0411] "Rate this idea: An application for personal finance management."

[0412] "Combine these ideas to generate new innovations:\n- A smart budgeting tool\n- A goal tracking app\n- An intuitive spending insights dashboard"

[0413] In this way, new innovations can be generated efficiently and useful information can be provided to users quickly.

[0414] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0415] Step 1:

[0416] The server collects multiple idea data submitted in the past. This idea data is diverse, including text data, image data, and PDF files. All collected idea data is stored in a database. The input is past idea data, which is processed by collecting and storing it, and then output in a structured format to the database.

[0417] Step 2:

[0418] The server trains the generative AI model on the idea data in the database. For example, a text generation model (GPT-3) is used as the generative AI model. The input for training is the idea data stored in the database, and training the AI ​​model improves its pattern recognition and natural language processing capabilities. This enables the generative AI model to analyze and evaluate ideas.

[0419] Step 3:

[0420] The server uses a generative AI model to analyze idea data stored in a database and extract highly rated ideas. The input is the idea data in the database and the generative AI model, and by running the generative AI model, it evaluates the idea data and extracts superior ideas based on loss values. The output is a list of highly rated ideas.

[0421] Step 4:

[0422] The server organizes the extracted ideas and combines multiple ideas to generate new innovation proposals. The input is a list of highly rated ideas, and new ideas are generated using a reconstruction algorithm. This results in novel and practical proposals. The output is new innovation proposals.

[0423] Step 5:

[0424] The server uses a web interface to provide the generated new innovation proposals to the user. The input is the generated innovation proposals, which are displayed to the user through the web interface, allowing the user to easily check the new ideas and apply them to their own projects or work. The output is the provision of the innovation proposals to the user.

[0425] The above is the flow of processing of the program of the system that realizes the application example.

[0426] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0427] The system of this invention runs on a server, collects multiple idea data submitted in past idea contests, and generates new innovation proposals by analyzing, evaluating, and reconstructing them using a generative AI model, and provides them to users. Furthermore, it has the function of recognizing user emotions by combining an emotion engine and selecting the innovation proposals to provide based on the user's emotions.

[0428] First, the server collects all ideas submitted in past idea contests. This is done in a variety of formats, including text data, image data, and PDF files. All collected idea data is stored in a database. This database centrally manages multiple idea data and is structured to make it easy to apply to subsequent processing.

[0429] Next, the server trains a generative AI model on the idea data in the database. For example, a text generation model such as GPT-3 is used as the generative AI model. This model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea.

[0430] The server uses this generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, such as the loss value of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0431] After extracting the top ideas, the server organizes them and combines them to generate new innovations. For example, combining the ideas of an "automatic plant watering system" and a "smart refrigerator" generates a new idea called a "system for automatically growing fresh herbs inside a smart refrigerator."

[0432] The server then analyzes the user's emotions using an emotion engine, which recognizes the user's facial expressions, tone of voice, and incompatibility data to quantitatively evaluate the user's emotional state. Based on the evaluation results obtained by the emotion engine, the server selects and provides the user with the most suitable innovation proposal.

[0433] Finally, the server provides the generated new innovations to the user via a web interface, email, or other means. The user can review the new ideas and apply them to their own projects or work. User feedback is also fed back into the system for further improvements.

[0434] For example, if a user expresses interest in a "system that automatically grows fresh herbs inside a smart refrigerator," the emotion engine will recognize the user's positive response and prioritize innovation proposals on a similar theme. In this way, by combining emotion engines, it becomes possible to provide innovation proposals that match the user's needs and emotions.

[0435] This system makes it possible to rediscover good ideas that have been buried in the past and reconstruct them as innovative proposals, with the aim of promoting the creation of new value.

[0436] The processing flow will be explained below.

[0437] Step 1:

[0438] The server collects multiple idea data submitted in past idea contests in various formats, such as text data, image data, and PDF files.

[0439] Step 2:

[0440] The server stores the collected idea data in a database, which is used to centrally manage the titles and contents of ideas.

[0441] Step 3:

[0442] The server trains a generative AI model using the idea data in the database. For example, it uses a text generation model like GPT-3. The idea data is input into the model, which then learns through natural language processing and pattern recognition.

[0443] Step 4:

[0444] The server uses a generative AI model to analyze the idea data in the database and extracts superior ideas based on evaluation criteria. The evaluation criteria are the loss values ​​of the generative AI model. Ideas with lower loss values ​​are considered to be more highly rated and are extracted as superior ideas.

[0445] Step 5:

[0446] The server organizes the extracted ideas and combines them with other ideas as needed to generate new innovation proposals. For example, by combining the highly rated ideas "automatic plant watering system" and "smart refrigerator," a new innovation proposal called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0447] Step 6:

[0448] The server analyzes the user's emotions using an emotion engine, which recognizes the user's facial expressions, tone of voice, and incompatibility data to quantitatively evaluate the user's emotional state.

[0449] Step 7:

[0450] The server selects the most suitable innovation proposal for the user based on the evaluation results of the emotion engine. For example, if the user has a positive reaction, it will prioritize the innovation proposal that matches that emotion.

[0451] Step 8:

[0452] The server provides the generated new innovations to the user via a web interface, email, or other means, allowing the user to review the new ideas and apply them to their own projects or work.

[0453] Step 9:

[0454] User feedback is fed back into the system to help it further improve, allowing it to continually update and generate better innovations.

[0455] Example 2

[0456] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0457] There is a need for a system that can generate new innovation proposals using previously submitted proposal data and provide those proposals to users efficiently and effectively. However, conventional systems do not automate the collection and analysis of proposal data, which requires time and effort. In addition, determining whether the generated innovation proposals match the user's emotions and needs is often done manually, making it difficult to improve user satisfaction. Therefore, there is a need for technology that can automatically collect and analyze past proposal data and provide optimal innovation proposals based on user emotions.

[0458] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0459] In this invention, the server includes means for collecting multiple proposal data submitted in the past and storing them in a storage device, means for training a generative AI model to learn the data, means for analyzing the proposal data stored in the storage device using the generative AI model and extracting excellent proposals, means for organizing the extracted proposals and combining multiple proposals to generate new innovative proposals, means for recognizing the emotional state of a user using an emotion recognition engine, and means for selecting and providing the new innovative proposals based on the emotional state. This makes it possible to efficiently generate effective innovative proposals based on past proposal data and provide them to users.

[0460] "Proposal data" refers to data that includes information on ideas, concepts, designs, etc. that have been submitted in the past.

[0461] "Storage device" refers to hardware and software for storing and managing data.

[0462] A "generative AI model" is an artificial intelligence model that performs text generation and natural language processing.

[0463] A "loss value" is an evaluation metric that indicates the error when a generative AI model is trained.

[0464] An "emotion recognition engine" is a technology that quantitatively evaluates a user's emotional state based on facial expressions, tone of voice, etc.

[0465] An "emotional state" is a state that represents a user's current feelings or mood.

[0466] An "innovative proposal" is a new proposal or concept that is generated based on existing ideas or technologies.

[0467] "Selection" refers to the process of selecting the best innovation from multiple proposals.

[0468] "Providing" refers to the act of notifying or presenting the generated innovation proposal to the user.

[0469] The system of the present invention executes a series of processes running on a server to collect multiple proposal data submitted in the past, generate new innovation proposals, and provide them to users. It also has a function to recognize the user's emotional state using an emotion recognition engine and select the innovation proposal that is most suitable for the user.

[0470] First, the server collects proposal data in the form of text data, image data, and PDF files from past proposal contests and databases. Web scraping tools and APIs are used for the collection. For example, Python and Selenium are used as web scraping tools. The collected data is then stored in a storage device such as MongoDB.

[0471] Next, the server uses a generative AI model to train the collected data. The generative AI model used is the language generation model GPT-3. The server inputs the preprocessed proposal data into the generative AI model and evaluates each proposal using natural language processing and pattern recognition. In this process, loss values ​​are used as the evaluation criterion, and proposals with low loss values ​​are extracted as superior.

[0472] The server then generates new innovation proposals based on the highly rated proposals. For example, by combining two proposals, "automatic plant watering system" and "smart refrigerator," a new innovation proposal such as "a system that automatically grows fresh herbs inside the smart refrigerator" is generated.

[0473] The server then analyzes the user's emotional state using an emotion recognition engine, which collects data on the user's facial expressions, tone of voice, and disapproval, and quantitatively evaluates the user's emotional state using technologies such as Amazon Rekognition and Google Cloud Speech-to-Text.

[0474] Based on the evaluation results of the emotion recognition engine, the server selects the most suitable innovation proposals from the generated proposals and provides them to the user via a web interface, email, or other methods. The web interface is built using the Django framework, and email notifications are sent using a Python mail sending library.

[0475] Examples of specific prompts include the following:

[0476] "Generate new refrigerator-related innovation ideas based on past idea data. Make them as relevant as possible to user emotions."

[0477] In this way, the system of the present invention can efficiently collect and analyze past proposal data and provide innovative proposals that match the user's emotional state, thereby promoting the creation of new value.

[0478] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0479] Step 1:

[0480] The server collects proposal data from past proposal contests and databases. The collected data ranges from text data, image data, and PDF files. For example, data is automatically scraped from specific websites using Python's Selenium library. The input is a list of website URLs, and the output is the proposal data.

[0481] Step 2:

[0482] The server stores the collected proposal data in a storage device such as MongoDB. The proposal data is stored in various formats (e.g., text, image, PDF). A database schema is defined to store the collected data appropriately. The input is the proposal data, and the output is the data stored in the storage device.

[0483] Step 3:

[0484] The server trains a generative AI model (e.g., GPT-3) with the stored proposal data. During this process, natural language processing (NLP) techniques are used to preprocess the data and input it into the generative AI model. For example, NLP libraries are used to tokenize and normalize the text data. The input is the data in storage, and the output is the trained generative AI model.

[0485] Step 4:

[0486] The server uses the generative AI model to analyze the proposal data stored in the storage device. This analysis involves pattern recognition and evaluation of each proposal. Loss value is used as the evaluation metric, and proposals with low loss values ​​are extracted as superior. The input is the trained generative AI model and proposal data, and the output is a list of evaluated proposals.

[0487] Step 5:

[0488] The server generates new innovation proposals based on the highly rated proposals. This is a process of combining multiple proposals to create new ideas. For example, the proposals for an "automatic plant watering system" and a "smart refrigerator" can be combined to generate a "system that automatically grows fresh herbs inside a smart refrigerator." The input is a list of evaluated proposals, and the output is a new innovation proposal.

[0489] Step 6:

[0490] The server analyzes the user's emotional state using an emotion recognition engine. It captures data on the user's facial expressions, tone of voice, and incompatibility to evaluate the emotional state. For example, it uses a webcam and microphone to collect data in real time and inputs it into the emotion recognition model. The input is the user's real-time data, and the output is an evaluation of the user's emotional state.

[0491] Step 7:

[0492] The server provides new innovation proposals to the user based on the emotional state evaluation results. This is done through a web interface or email. For example, it uses the Django framework to render web pages and a Python email library to send notifications. The inputs are the new innovation proposals and the emotional state evaluation results, and the output is the innovation proposals provided to the user.

[0493] Step 8:

[0494] The user reviews the proposed innovation and provides feedback. The server inputs this feedback back into the system to help improve it further. The input is the user's feedback, and the output is the system improvement data.

[0495] Through the above steps, a system is realized that efficiently generates new innovation proposals based on past proposal data and provides them according to the user's emotional state.

[0496] (Application example 2)

[0497] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0498] In recent years, many companies and organizations have been devoting significant efforts to generating innovative ideas. However, previously submitted ideas often go to waste or are not properly evaluated and utilized. Furthermore, there is a lack of systems that provide innovative ideas tailored to individual users' emotions and needs, resulting in a lack of an improved user experience. Furthermore, in brick-and-mortar stores, it would be effective to provide product and service suggestions based on the customer's emotional state, but such a system does not yet exist. These issues need to be resolved.

[0499] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0500] In this invention, the server includes means for collecting a plurality of previously submitted idea data and storing them in a database, means for training a generative AI model to learn the data, means for analyzing the idea data stored in the database using the generative AI model and extracting excellent ideas, means for organizing the extracted ideas and combining the plurality of ideas to generate new innovative ideas, and means for selecting and providing the generated new innovative ideas based on the emotional state of the user using an emotion recognition engine. This makes it possible to provide innovative ideas that match the emotional state of the user, improving the customer experience in physical stores and making effective use of hidden ideas.

[0501] "Idea data" refers to information about multiple ideas, proposals, and concepts that have been submitted in the past, and exists in multiple formats such as text data, image data, and PDF files.

[0502] A "database" is a collection of information that centrally manages and stores collected idea data and has a structure that makes it easy to apply to subsequent processing.

[0503] A "generative AI model" is a machine learning model used to learn from collected idea data, analyze and evaluate it, and generate new ideas. A typical example is a text generation model (e.g., GPT-3).

[0504] An "emotion recognition engine" is a system that quantitatively evaluates a user's emotional state by recognizing the user's facial expressions, tone of voice, and incompatibility data.

[0505] "Innovative ideas" refer to proposals or concepts that are newly created by combining multiple excellent ideas that have been extracted.

[0506] "User's emotional state" refers to a quantitative assessment result of the user's current emotion obtained by an emotion recognition engine.

[0507] A system for realizing the present invention is implemented with the following configuration and procedure.

[0508] First, the server collects multiple idea data submitted in the past and stores it in a database. This idea data includes information in various formats, such as text data, image data, and PDF files. The database is used to centrally manage this data and store it in a format that is convenient for subsequent processing.

[0509] Next, the server trains a generative AI model on the stored idea data. For example, a text generation model (e.g., GPT-3) is used as the generative AI model. This model performs pattern recognition and natural language processing based on the input text data and evaluates each idea.

[0510] The server uses the generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, which are the loss values ​​of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0511] The extracted ideas are organized by the server, and new innovations are generated by combining multiple ideas. For example, the ideas for an "automatic plant watering system" and a "smart refrigerator" can be combined to create a new idea for a "system that automatically grows fresh herbs inside a smart refrigerator."

[0512] The generated new innovation proposals are selected based on the user's emotional state using an emotion recognition engine. Specifically, the user's facial expressions and tone of voice are captured in real time using a camera and microphone, and the emotion recognition engine analyzes the data to quantitatively evaluate the user's emotional state. Based on the results of this evaluation, the server selects the most suitable innovation proposal for the user and provides it to the user via a smartphone app or a robot installed in a physical store.

[0513] For example, in-store sales history, customer reviews, and past marketing data can be used to generate ideas for new sales strategies and product improvements, while an emotion recognition engine can provide further relevant innovation suggestions when customers express interest.

[0514] An example of a prompt for a generative AI model is:

[0515] Generate new ideas for eco-friendly gift wrapping services based on past sales history and customer reviews, including suggestions on what materials to use and promotional strategies.

[0516] In this way, the present invention makes it possible to provide innovative ideas that are suited to the user's emotional state, thereby improving the customer experience in physical stores and making effective use of good ideas that have been buried in the past.

[0517] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0518] Step 1:

[0519] The server collects previously submitted idea data and stores it in a database. This data includes text data, image data, PDF files, etc. This data is extracted from information sources, formatted, and stored in the database. Idea data is used as input, and a formatted database entry is obtained as output.

[0520] Step 2:

[0521] The server trains a generative AI model on the idea data stored in the database. A text generation model (e.g., GPT-3) is used as the generative AI model. The idea data in the database is used as input, and the evaluation results and specific patterns for each idea are obtained as output. Specific operations include analyzing the text data and updating the model parameters.

[0522] Step 3:

[0523] The server uses a generative AI model to analyze idea data stored in a database and extract superior ideas. The loss value of the generative AI model is used as the evaluation criterion. The trained model and the idea data in the database are used as input, and a list of highly rated ideas is obtained as output. Specific operations include feedforward processing of the model and calculation of loss values.

[0524] Step 4:

[0525] The server organizes the extracted excellent ideas and combines multiple ideas to generate new innovation proposals. The input is a list of highly rated ideas, and the output is new innovation proposals. Specific operations include combining and re-evaluating ideas. For example, an "automatic plant watering system" and a "smart refrigerator" can be combined to generate a "system that automatically grows fresh herbs inside a smart refrigerator."

[0526] Step 5:

[0527] The generated innovation proposals are selected and presented based on the user's emotional state using an emotion recognition engine. Specifically, the user's facial expressions and tone of voice are captured using a camera and microphone and analyzed by the emotion recognition engine. The user's facial expression data and voice data are used as input, and an emotional evaluation result is obtained as output. Based on the evaluation result, the server selects the most suitable innovation proposal for the user.

[0528] Step 6:

[0529] The server provides the selected innovation proposals to the user via a smartphone app or a robot in a physical store. The innovation proposals based on the emotional evaluation results are used as input, and the innovation proposals presented to the user are obtained as output. Specific operations include sending the innovation proposals and displaying them on the interface. If the user shows interest, further related innovation proposals are suggested.

[0530] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0531] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0532] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0533] [Third embodiment]

[0534] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0535] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0536] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0537] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0538] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0539] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0540] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0541] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0542] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0543] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0544] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0545] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0546] The system of this invention runs on a server, collects multiple idea data submitted in past idea contests, and generates new innovative ideas by analyzing, evaluating, and reconstructing them using a generative AI model, which it then provides to users.

[0547] First, the server collects all ideas submitted in past idea contests. This collected data is diverse, including text data, image data, and PDF files. All collected idea data is stored in a database. This database centrally manages multiple idea data and is structured to make it easy to apply to subsequent processing.

[0548] Next, the server trains a generative AI model on the idea data in the database. For example, a text generation model (such as GPT-3) is used as the generative AI model. This model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea.

[0549] The server uses this generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, such as the loss value of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0550] After extracting the top ideas, the server organizes them and reconstructs them into new innovation proposals. This restructuring is done by combining multiple excellent ideas to generate new creative and practical proposals. For example, combining the ideas of an "automatic plant watering system" and a "smart refrigerator" generates a new idea: a system that automatically grows fresh herbs inside a smart refrigerator.

[0551] Finally, the server provides the generated new innovations to the user, who can review the new ideas and apply them to their own projects or work. The generated ideas are provided to the user via a web interface or other communication means.

[0552] In this way, it is possible to rediscover good ideas buried in the past and reconstruct them as innovative proposals.The aim of this system is to promote the creation of new value and provide useful information to users.

[0553] The processing flow will be explained below.

[0554] Step 1:

[0555] The server collects multiple idea data submitted in past idea contests in various formats, such as text data, image data, and PDF files.

[0556] Step 2:

[0557] The server stores the collected idea data in a database, which is used to centrally manage the titles and contents of ideas.

[0558] Step 3:

[0559] The server trains a generative AI model using the idea data in the database. For example, it uses a text generation model like GPT-3. The idea data is input into the model, which then learns through natural language processing and pattern recognition.

[0560] Step 4:

[0561] The server uses a generative AI model to analyze the idea data in the database and extracts superior ideas based on evaluation criteria. The evaluation criteria are the loss values ​​of the generative AI model. Ideas with lower loss values ​​are considered to be more highly rated and are extracted as superior ideas.

[0562] Step 5:

[0563] The server organizes the extracted ideas and combines them with other ideas as needed to generate new innovation proposals. For example, by combining the highly rated ideas "automatic plant watering system" and "smart refrigerator," a new innovation proposal called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0564] Step 6:

[0565] The server provides the generated new innovations to the user via a web interface, email, or other means, allowing the user to review the new ideas and apply them to their own projects or work.

[0566] Example 1

[0567] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0568] Conventional idea generation systems have difficulty effectively utilizing past ideas to generate new, creative ideas. Furthermore, the evaluation criteria for each idea are unclear, making it difficult to extract high-quality ideas. Therefore, there is a need for a system that can efficiently utilize previously submitted ideas to generate new, innovative ideas.

[0569] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0570] In this invention, the server includes means for collecting multiple pieces of information data submitted in the past and storing them in an information storage device, means for training a generative AI model to learn the data, means for analyzing the information data stored in the information storage device using the generative AI model and extracting superior information, means for organizing the extracted information and combining multiple pieces of information to generate new innovation ideas, means for providing the generated new innovation ideas to users, means for temporarily storing data in a temporary storage device, means for converting data into an appropriate format, and means for ranking information based on the evaluation value of the generative AI model, thereby making it possible to reevaluate past ideas and generate new creative and practical ideas.

[0571] "Information data" refers to information such as text data, image data, PDF files, etc. that show the content of ideas that have been submitted in the past.

[0572] An "information storage device" is a database or storage system that efficiently manages collected information data and stores it in a form that can be used for subsequent processing.

[0573] A "generative artificial intelligence model" is an artificial intelligence technology for learning information data and analyzing, evaluating, and generating it, and specifically includes text generation models.

[0574] An "evaluation value" is a numerical value that serves as a standard used by a generative artificial intelligence model when evaluating information data, and includes the model's loss value, etc.

[0575] "Ranking" refers to the process of ranking a plurality of pieces of information data based on evaluation values, so that information with higher evaluations is ranked higher.

[0576] A "temporary storage device" is a storage system for temporarily storing collected information data, and plays a role in improving data processing efficiency.

[0577] "Users" are individuals or organizations that use the new innovations generated and apply them in their own projects or work.

[0578] An "innovative proposal" is a new idea or proposal generated by reconstructing multiple existing pieces of information data.

[0579] The system of this invention is designed to effectively utilize multiple pieces of information data submitted in the past to generate new creative ideas. This system runs on a server and performs a series of processes including collection, storage, analysis, evaluation, reconstruction, and provision.

[0580] The server first collects previously submitted information data. This collection is done using web scraping or an API. The collected data is temporarily stored in a temporary storage device. It is then stored in an information storage device (for example, MongoDB or Amazon S3). This ensures data consistency and creates a structure that makes it easy to apply to subsequent processing.

[0581] Next, the server trains the generative AI model on the information data. A text generation model (e.g., GPT-3) is used as the generative AI model. This model performs natural language processing on the information data and extracts the characteristics of each piece of data. The server then uses the generative AI model to analyze the data stored in the information storage device and extracts superior information based on an evaluation criterion. Specifically, the loss value of the generative AI model is used as the criterion, and information with a lower loss value is considered to be more highly rated.

[0582] After extracting the most highly rated information, the server organizes it and reconstructs it into new innovation ideas. This reconstruction is done by combining multiple excellent pieces of information to generate creative and practical proposals. For example, by combining information on "automatic plant watering systems" and "smart refrigerators," a new idea called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0583] Finally, the server provides the generated new innovation ideas to the user, who can then review the new ideas and apply them to their own projects or work. The generated ideas are provided via a web interface, email, etc.

[0584] Specific examples

[0585] If an "automatic plant watering system" and a "smart refrigerator" are collected as past information data, the text data and outline of each idea are stored in an information storage device. The generative AI model can learn from these and combine them to propose a "system that automatically grows fresh herbs inside a smart refrigerator."

[0586] Prompt Sentence Examples

[0587] "Generate new, innovative ideas based on data from multiple previously submitted ideas. Combine top-rated ideas to create actionable proposals."

[0588] This system allows users to reevaluate past ideas and provide them as new creative proposals, thereby enabling the creation of new value. In this way, the mode for carrying out the invention is specifically shown.

[0589] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0590] Step 1:

[0591] Server: Start data collection

[0592] Specific operation: The server collects information data from past idea contests using web scraping and APIs. The collected data includes text data, image data, PDF files, etc.

[0593] Input: Idea contest website or API URL

[0594] Data processing: The server uses the Python BeautifulSoup library to extract text data from websites and retrieve data from APIs.

[0595] Output: raw data collected

[0596] Step 2:

[0597] Server: Temporary data storage

[0598] What it does: The server temporarily stores the collected data in an Amazon S3 bucket, ensuring data consistency and easy retrieval for subsequent processing steps.

[0599] Input: Raw data collected

[0600] Data processing: Save the data as is to Amazon S3

[0601] Output: Temporarily saved data

[0602] Step 3:

[0603] Server: Stored in a database

[0604] How it works: The server uses the Python "pymongo" library to store text data in a MongoDB database, and image data and PDF files in Amazon S3.

[0605] Input: Temporarily saved data

[0606] Data processing: Text data is inserted into MongoDB, and image data and PDF files are moved to Amazon S3

[0607] Output: Data stored in database and storage

[0608] Step 4:

[0609] Server: Prepare the data

[0610] Specific operation: The server uses Python's "pandas" library to format the idea data retrieved from the database and convert it into an input format for the generative AI model.

[0611] Input: Data stored in databases and storage

[0612] Data processing: Format data into tables and clean text data

[0613] Output: Formatted data

[0614] Step 5:

[0615] Server: Model training

[0616] How it works: The server uses a generative AI model (e.g., GPT-3) to train on the formatted idea data, allowing the model to understand the characteristics of each idea and evaluate them accordingly.

[0617] Input: Formatted data

[0618] Data processing: feature extraction, pattern recognition

[0619] Output: A trained generative AI model

[0620] Step 6:

[0621] Server: Data analysis

[0622] How it works: The server uses a generative AI model to analyze idea data and evaluate each idea based on its loss value.

[0623] Input: Trained generative AI model, idea data

[0624] Data calculation: Calculating loss values, evaluating ideas

[0625] Output: Evaluation results (loss values ​​and rankings of ideas)

[0626] Step 7:

[0627] Server: Idea ranking

[0628] Specific operation: The server ranks the idea data based on the loss value. The information with a lower loss value is rated higher.

[0629] Input: Evaluation result

[0630] Data processing: Idea ranking

[0631] Output: A ranked list of ideas

[0632] Step 8:

[0633] Server: Extracting and Reconstructing Great Ideas

[0634] How it works: The server extracts the top ranked ideas and selects them for restructuring. It then combines them to generate new innovations. For example, it combines an "automatic plant watering system" with a "smart refrigerator" to generate a new "system that automatically grows fresh herbs inside a smart refrigerator."

[0635] Input: A ranked list of ideas

[0636] Data processing: Combining ideas and generating new proposals

[0637] Output: New innovations

[0638] Step 9:

[0639] Server: Idea distribution

[0640] Specific operation: The server provides the generated new innovations to the user via a web interface, email, etc.

[0641] Input: New innovation idea

[0642] Data processing: Converting to a presentation format

[0643] Output: New innovations provided to the user

[0644] Step 10:

[0645] User: Checking the idea

[0646] Specific Action: Users review the new ideas provided and apply them to their own projects or work.

[0647] Input: New innovation ideas provided

[0648] Output: User confirmation and application of new ideas

[0649] This series of processes enables the system to reevaluate past information data, generate new creative and practical ideas, and provide them to users.

[0650] (Application example 1)

[0651] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0652] With conventional methods, it was difficult to effectively utilize the ideas submitted in idea contests, and the process of efficiently extracting and reconstructing the best ideas from among them was particularly laborious and time-consuming.In addition, there were no well-established methods for quickly generating new innovative ideas and providing them to users.

[0653] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0654] In this invention, the server includes means for collecting a plurality of idea data submitted in the past and storing them in a database, means for training a generative AI model to learn the data, means for analyzing the idea data stored in the database using the generative AI model and extracting good ideas, means for organizing the extracted ideas and combining the plurality of ideas to generate new innovation proposals, and means for using a web interface to provide the generated new innovation proposals to users. This enables effective use of ideas submitted in the past and enables new innovation proposals to be quickly generated and provided to users.

[0655] "Idea data" refers to multiple proposals submitted in past idea contests, and can range from text data, image data, PDF files, and more.

[0656] A "database" is a storage medium that centrally manages collected idea data and has a structure that makes it easy to apply to subsequent processing.

[0657] A "generative AI model" is an artificial intelligence model that uses, for example, a text generation model (such as GPT-3) to analyze, evaluate, and reconstruct idea data.

[0658] "Web Interface" means a user interface via an internet browser for presenting generated new innovations to a user.

[0659] "Loss value" is a metric used to evaluate the performance of a generative AI model, with lower values ​​indicating more accurate predictions by the model.

[0660] The system for implementing the present invention includes various components for effectively collecting, analyzing, evaluating, and generating new innovation ideas for users. Specific embodiments are described in detail below.

[0661] First, the server collects multiple pieces of idea data that have been submitted in the past and stores them in a database. This data includes text data, image data, PDF files, etc. The database centrally manages this data and has a structure that makes it easy to apply to subsequent processing.

[0662] Next, the server trains a generative AI model (for example, GPT-3, a text generation model) on the idea data in this database. The generative AI model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea. The loss value of the generative AI model is used as the evaluation criterion, with a lower loss value being considered a higher evaluation.

[0663] The server then uses the generative AI model to analyze the idea data stored in the database and extract the highly rated ideas. The extracted ideas are then further organized and multiple ideas are combined to generate new innovations. This process efficiently combines diverse ideas to produce novel and practical proposals.

[0664] The new innovations generated are then presented to the user through a web interface designed to allow users to easily explore the generated ideas and apply them to their own projects and work.

[0665] For example, the following prompts can be fed into a generative AI model to evaluate and reconstruct ideas:

[0666] "Rate this idea: An application for personal finance management."

[0667] "Combine these ideas to generate new innovations:\n- A smart budgeting tool\n- A goal tracking app\n- An intuitive spending insights dashboard"

[0668] In this way, new innovations can be generated efficiently and useful information can be provided to users quickly.

[0669] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0670] Step 1:

[0671] The server collects multiple idea data submitted in the past. This idea data is diverse, including text data, image data, and PDF files. All collected idea data is stored in a database. The input is past idea data, which is processed by collecting and storing it, and then output in a structured format to the database.

[0672] Step 2:

[0673] The server trains the generative AI model on the idea data in the database. For example, a text generation model (GPT-3) is used as the generative AI model. The input for training is the idea data stored in the database, and training the AI ​​model improves its pattern recognition and natural language processing capabilities. This enables the generative AI model to analyze and evaluate ideas.

[0674] Step 3:

[0675] The server uses a generative AI model to analyze idea data stored in a database and extract highly rated ideas. The input is the idea data in the database and the generative AI model, and by running the generative AI model, it evaluates the idea data and extracts superior ideas based on loss values. The output is a list of highly rated ideas.

[0676] Step 4:

[0677] The server organizes the extracted ideas and combines multiple ideas to generate new innovation proposals. The input is a list of highly rated ideas, and new ideas are generated using a reconstruction algorithm. This results in novel and practical proposals. The output is new innovation proposals.

[0678] Step 5:

[0679] The server uses a web interface to provide the generated new innovation proposals to the user. The input is the generated innovation proposals, which are displayed to the user through the web interface, allowing the user to easily check the new ideas and apply them to their own projects or work. The output is the provision of the innovation proposals to the user.

[0680] The above is the flow of processing of the program of the system that realizes the application example.

[0681] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0682] The system of this invention runs on a server, collects multiple idea data submitted in past idea contests, and generates new innovation proposals by analyzing, evaluating, and reconstructing them using a generative AI model, and provides them to users. Furthermore, it has the function of recognizing user emotions by combining an emotion engine and selecting the innovation proposals to provide based on the user's emotions.

[0683] First, the server collects all ideas submitted in past idea contests. This is done in a variety of formats, including text data, image data, and PDF files. All collected idea data is stored in a database. This database centrally manages multiple idea data and is structured to make it easy to apply to subsequent processing.

[0684] Next, the server trains a generative AI model on the idea data in the database. For example, a text generation model such as GPT-3 is used as the generative AI model. This model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea.

[0685] The server uses this generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, such as the loss value of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0686] After extracting the top ideas, the server organizes them and combines them to generate new innovations. For example, combining the ideas of an "automatic plant watering system" and a "smart refrigerator" generates a new idea called a "system for automatically growing fresh herbs inside a smart refrigerator."

[0687] The server then analyzes the user's emotions using an emotion engine, which recognizes the user's facial expressions, tone of voice, and incompatibility data to quantitatively evaluate the user's emotional state. Based on the evaluation results obtained by the emotion engine, the server selects and provides the user with the most suitable innovation proposal.

[0688] Finally, the server provides the generated new innovations to the user via a web interface, email, or other means. The user can review the new ideas and apply them to their own projects or work. User feedback is also fed back into the system for further improvements.

[0689] For example, if a user expresses interest in a "system that automatically grows fresh herbs inside a smart refrigerator," the emotion engine will recognize the user's positive response and prioritize innovation proposals on a similar theme. In this way, by combining emotion engines, it becomes possible to provide innovation proposals that match the user's needs and emotions.

[0690] This system makes it possible to rediscover good ideas that have been buried in the past and reconstruct them as innovative proposals, with the aim of promoting the creation of new value.

[0691] The processing flow will be explained below.

[0692] Step 1:

[0693] The server collects multiple idea data submitted in past idea contests in various formats, such as text data, image data, and PDF files.

[0694] Step 2:

[0695] The server stores the collected idea data in a database, which is used to centrally manage the titles and contents of ideas.

[0696] Step 3:

[0697] The server trains a generative AI model using the idea data in the database. For example, it uses a text generation model like GPT-3. The idea data is input into the model, which then learns through natural language processing and pattern recognition.

[0698] Step 4:

[0699] The server uses a generative AI model to analyze the idea data in the database and extracts superior ideas based on evaluation criteria. The evaluation criteria are the loss values ​​of the generative AI model. Ideas with lower loss values ​​are considered to be more highly rated and are extracted as superior ideas.

[0700] Step 5:

[0701] The server organizes the extracted ideas and combines them with other ideas as needed to generate new innovation proposals. For example, by combining the highly rated ideas "automatic plant watering system" and "smart refrigerator," a new innovation proposal called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0702] Step 6:

[0703] The server analyzes the user's emotions using an emotion engine, which recognizes the user's facial expressions, tone of voice, and incompatibility data to quantitatively evaluate the user's emotional state.

[0704] Step 7:

[0705] The server selects the most suitable innovation proposal for the user based on the evaluation results of the emotion engine. For example, if the user has a positive reaction, it will prioritize the innovation proposal that matches that emotion.

[0706] Step 8:

[0707] The server provides the generated new innovations to the user via a web interface, email, or other means, allowing the user to review the new ideas and apply them to their own projects or work.

[0708] Step 9:

[0709] User feedback is fed back into the system to help it further improve, allowing it to continually update and generate better innovations.

[0710] Example 2

[0711] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0712] There is a need for a system that can generate new innovation proposals using previously submitted proposal data and provide those proposals to users efficiently and effectively. However, conventional systems do not automate the collection and analysis of proposal data, which requires time and effort. In addition, determining whether the generated innovation proposals match the user's emotions and needs is often done manually, making it difficult to improve user satisfaction. Therefore, there is a need for technology that can automatically collect and analyze past proposal data and provide optimal innovation proposals based on user emotions.

[0713] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0714] In this invention, the server includes means for collecting multiple proposal data submitted in the past and storing them in a storage device, means for training a generative AI model to learn the data, means for analyzing the proposal data stored in the storage device using the generative AI model and extracting excellent proposals, means for organizing the extracted proposals and combining multiple proposals to generate new innovative proposals, means for recognizing the emotional state of a user using an emotion recognition engine, and means for selecting and providing the new innovative proposals based on the emotional state. This makes it possible to efficiently generate effective innovative proposals based on past proposal data and provide them to users.

[0715] "Proposal data" refers to data that includes information on ideas, concepts, designs, etc. that have been submitted in the past.

[0716] "Storage device" refers to hardware and software for storing and managing data.

[0717] A "generative AI model" is an artificial intelligence model that performs text generation and natural language processing.

[0718] A "loss value" is an evaluation metric that indicates the error when a generative AI model is trained.

[0719] An "emotion recognition engine" is a technology that quantitatively evaluates a user's emotional state based on facial expressions, tone of voice, etc.

[0720] An "emotional state" is a state that represents a user's current feelings or mood.

[0721] An "innovative proposal" is a new proposal or concept that is generated based on existing ideas or technologies.

[0722] "Selection" refers to the process of selecting the best innovation from multiple proposals.

[0723] "Providing" refers to the act of notifying or presenting the generated innovation proposal to the user.

[0724] The system of the present invention executes a series of processes running on a server to collect multiple proposal data submitted in the past, generate new innovation proposals, and provide them to users. It also has a function to recognize the user's emotional state using an emotion recognition engine and select the innovation proposal that is most suitable for the user.

[0725] First, the server collects proposal data in the form of text data, image data, and PDF files from past proposal contests and databases. Web scraping tools and APIs are used for the collection. For example, Python and Selenium are used as web scraping tools. The collected data is then stored in a storage device such as MongoDB.

[0726] Next, the server uses a generative AI model to train the collected data. The generative AI model used is the language generation model GPT-3. The server inputs the preprocessed proposal data into the generative AI model and evaluates each proposal using natural language processing and pattern recognition. In this process, loss values ​​are used as the evaluation criterion, and proposals with low loss values ​​are extracted as superior.

[0727] The server then generates new innovation proposals based on the highly rated proposals. For example, by combining two proposals, "automatic plant watering system" and "smart refrigerator," a new innovation proposal such as "a system that automatically grows fresh herbs inside the smart refrigerator" is generated.

[0728] The server then analyzes the user's emotional state using an emotion recognition engine, which collects data on the user's facial expressions, tone of voice, and disapproval, and quantitatively evaluates the user's emotional state using technologies such as Amazon Rekognition and Google Cloud Speech-to-Text.

[0729] Based on the evaluation results of the emotion recognition engine, the server selects the most suitable innovation proposals from the generated proposals and provides them to the user via a web interface, email, or other methods. The web interface is built using the Django framework, and email notifications are sent using a Python mail sending library.

[0730] Examples of specific prompts include the following:

[0731] "Generate new refrigerator-related innovation ideas based on past idea data. Make them as relevant as possible to user emotions."

[0732] In this way, the system of the present invention can efficiently collect and analyze past proposal data and provide innovative proposals that match the user's emotional state, thereby promoting the creation of new value.

[0733] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0734] Step 1:

[0735] The server collects proposal data from past proposal contests and databases. The collected data ranges from text data, image data, and PDF files. For example, data is automatically scraped from specific websites using Python's Selenium library. The input is a list of website URLs, and the output is the proposal data.

[0736] Step 2:

[0737] The server stores the collected proposal data in a storage device such as MongoDB. The proposal data is stored in various formats (e.g., text, image, PDF). A database schema is defined to store the collected data appropriately. The input is the proposal data, and the output is the data stored in the storage device.

[0738] Step 3:

[0739] The server trains a generative AI model (e.g., GPT-3) with the stored proposal data. During this process, natural language processing (NLP) techniques are used to preprocess the data and input it into the generative AI model. For example, NLP libraries are used to tokenize and normalize the text data. The input is the data in storage, and the output is the trained generative AI model.

[0740] Step 4:

[0741] The server uses the generative AI model to analyze the proposal data stored in the storage device. This analysis involves pattern recognition and evaluation of each proposal. Loss value is used as the evaluation metric, and proposals with low loss values ​​are extracted as superior. The input is the trained generative AI model and proposal data, and the output is a list of evaluated proposals.

[0742] Step 5:

[0743] The server generates new innovation proposals based on the highly rated proposals. This is a process of combining multiple proposals to create new ideas. For example, the proposals for an "automatic plant watering system" and a "smart refrigerator" can be combined to generate a "system that automatically grows fresh herbs inside a smart refrigerator." The input is a list of evaluated proposals, and the output is a new innovation proposal.

[0744] Step 6:

[0745] The server analyzes the user's emotional state using an emotion recognition engine. It captures data on the user's facial expressions, tone of voice, and incompatibility to evaluate the emotional state. For example, it uses a webcam and microphone to collect data in real time and inputs it into the emotion recognition model. The input is the user's real-time data, and the output is an evaluation of the user's emotional state.

[0746] Step 7:

[0747] The server provides new innovation proposals to the user based on the emotional state evaluation results. This is done through a web interface or email. For example, it uses the Django framework to render web pages and a Python email library to send notifications. The inputs are the new innovation proposals and the emotional state evaluation results, and the output is the innovation proposals provided to the user.

[0748] Step 8:

[0749] The user reviews the proposed innovation and provides feedback. The server inputs this feedback back into the system to help improve it further. The input is the user's feedback, and the output is the system improvement data.

[0750] Through the above steps, a system is realized that efficiently generates new innovation proposals based on past proposal data and provides them according to the user's emotional state.

[0751] (Application example 2)

[0752] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0753] In recent years, many companies and organizations have been devoting significant efforts to generating innovative ideas. However, previously submitted ideas often go to waste or are not properly evaluated and utilized. Furthermore, there is a lack of systems that provide innovative ideas tailored to individual users' emotions and needs, resulting in a lack of an improved user experience. Furthermore, in brick-and-mortar stores, it would be effective to provide product and service suggestions based on the customer's emotional state, but such a system does not yet exist. These issues need to be resolved.

[0754] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0755] In this invention, the server includes means for collecting a plurality of previously submitted idea data and storing them in a database, means for training a generative AI model to learn the data, means for analyzing the idea data stored in the database using the generative AI model and extracting excellent ideas, means for organizing the extracted ideas and combining the plurality of ideas to generate new innovative ideas, and means for selecting and providing the generated new innovative ideas based on the emotional state of the user using an emotion recognition engine. This makes it possible to provide innovative ideas that match the emotional state of the user, improving the customer experience in physical stores and making effective use of hidden ideas.

[0756] "Idea data" refers to information about multiple ideas, proposals, and concepts that have been submitted in the past, and exists in multiple formats such as text data, image data, and PDF files.

[0757] A "database" is a collection of information that centrally manages and stores collected idea data and has a structure that makes it easy to apply to subsequent processing.

[0758] A "generative AI model" is a machine learning model used to learn from collected idea data, analyze and evaluate it, and generate new ideas. A typical example is a text generation model (e.g., GPT-3).

[0759] An "emotion recognition engine" is a system that quantitatively evaluates a user's emotional state by recognizing the user's facial expressions, tone of voice, and incompatibility data.

[0760] "Innovative ideas" refer to proposals or concepts that are newly created by combining multiple excellent ideas that have been extracted.

[0761] "User's emotional state" refers to a quantitative assessment result of the user's current emotion obtained by an emotion recognition engine.

[0762] A system for realizing the present invention is implemented with the following configuration and procedure.

[0763] First, the server collects multiple idea data submitted in the past and stores it in a database. This idea data includes information in various formats, such as text data, image data, and PDF files. The database is used to centrally manage this data and store it in a format that is convenient for subsequent processing.

[0764] Next, the server trains a generative AI model on the stored idea data. For example, a text generation model (e.g., GPT-3) is used as the generative AI model. This model performs pattern recognition and natural language processing based on the input text data and evaluates each idea.

[0765] The server uses the generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, which are the loss values ​​of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0766] The extracted ideas are organized by the server, and new innovations are generated by combining multiple ideas. For example, the ideas for an "automatic plant watering system" and a "smart refrigerator" can be combined to create a new idea for a "system that automatically grows fresh herbs inside a smart refrigerator."

[0767] The generated new innovation proposals are selected based on the user's emotional state using an emotion recognition engine. Specifically, the user's facial expressions and tone of voice are captured in real time using a camera and microphone, and the emotion recognition engine analyzes the data to quantitatively evaluate the user's emotional state. Based on the results of this evaluation, the server selects the most suitable innovation proposal for the user and provides it to the user via a smartphone app or a robot installed in a physical store.

[0768] For example, in-store sales history, customer reviews, and past marketing data can be used to generate ideas for new sales strategies and product improvements, while an emotion recognition engine can provide further relevant innovation suggestions when customers express interest.

[0769] An example of a prompt for a generative AI model is:

[0770] Generate new ideas for eco-friendly gift wrapping services based on past sales history and customer reviews, including suggestions on what materials to use and promotional strategies.

[0771] In this way, the present invention makes it possible to provide innovative ideas that are suited to the user's emotional state, thereby improving the customer experience in physical stores and making effective use of good ideas that have been buried in the past.

[0772] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0773] Step 1:

[0774] The server collects previously submitted idea data and stores it in a database. This data includes text data, image data, PDF files, etc. This data is extracted from information sources, formatted, and stored in the database. Idea data is used as input, and a formatted database entry is obtained as output.

[0775] Step 2:

[0776] The server trains a generative AI model on the idea data stored in the database. A text generation model (e.g., GPT-3) is used as the generative AI model. The idea data in the database is used as input, and the evaluation results and specific patterns for each idea are obtained as output. Specific operations include analyzing the text data and updating the model parameters.

[0777] Step 3:

[0778] The server uses a generative AI model to analyze idea data stored in a database and extract superior ideas. The loss value of the generative AI model is used as the evaluation criterion. The trained model and the idea data in the database are used as input, and a list of highly rated ideas is obtained as output. Specific operations include feedforward processing of the model and calculation of loss values.

[0779] Step 4:

[0780] The server organizes the extracted excellent ideas and combines multiple ideas to generate new innovation proposals. The input is a list of highly rated ideas, and the output is new innovation proposals. Specific operations include combining and re-evaluating ideas. For example, an "automatic plant watering system" and a "smart refrigerator" can be combined to generate a "system that automatically grows fresh herbs inside a smart refrigerator."

[0781] Step 5:

[0782] The generated innovation proposals are selected and presented based on the user's emotional state using an emotion recognition engine. Specifically, the user's facial expressions and tone of voice are captured using a camera and microphone and analyzed by the emotion recognition engine. The user's facial expression data and voice data are used as input, and an emotional evaluation result is obtained as output. Based on the evaluation result, the server selects the most suitable innovation proposal for the user.

[0783] Step 6:

[0784] The server provides the selected innovation proposals to the user via a smartphone app or a robot in a physical store. The innovation proposals based on the emotional evaluation results are used as input, and the innovation proposals presented to the user are obtained as output. Specific operations include sending the innovation proposals and displaying them on the interface. If the user shows interest, further related innovation proposals are suggested.

[0785] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0786] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0787] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0788] [Fourth embodiment]

[0789] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0790] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0791] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0792] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0793] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0794] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0795] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0796] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0797] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0798] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0799] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0800] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0801] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0802] The system of this invention runs on a server, collects multiple idea data submitted in past idea contests, and generates new innovative ideas by analyzing, evaluating, and reconstructing them using a generative AI model, which it then provides to users.

[0803] First, the server collects all ideas submitted in past idea contests. This collected data is diverse, including text data, image data, and PDF files. All collected idea data is stored in a database. This database centrally manages multiple idea data and is structured to make it easy to apply to subsequent processing.

[0804] Next, the server trains a generative AI model on the idea data in the database. For example, a text generation model (such as GPT-3) is used as the generative AI model. This model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea.

[0805] The server uses this generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, such as the loss value of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0806] After extracting the top ideas, the server organizes them and reconstructs them into new innovation proposals. This restructuring is done by combining multiple excellent ideas to generate new creative and practical proposals. For example, combining the ideas of an "automatic plant watering system" and a "smart refrigerator" generates a new idea: a system that automatically grows fresh herbs inside a smart refrigerator.

[0807] Finally, the server provides the generated new innovations to the user, who can review the new ideas and apply them to their own projects or work. The generated ideas are provided to the user via a web interface or other communication means.

[0808] In this way, it is possible to rediscover good ideas buried in the past and reconstruct them as innovative proposals.The aim of this system is to promote the creation of new value and provide useful information to users.

[0809] The processing flow will be explained below.

[0810] Step 1:

[0811] The server collects multiple idea data submitted in past idea contests in various formats, such as text data, image data, and PDF files.

[0812] Step 2:

[0813] The server stores the collected idea data in a database, which is used to centrally manage the titles and contents of ideas.

[0814] Step 3:

[0815] The server trains a generative AI model using the idea data in the database. For example, it uses a text generation model like GPT-3. The idea data is input into the model, which then learns through natural language processing and pattern recognition.

[0816] Step 4:

[0817] The server uses a generative AI model to analyze the idea data in the database and extracts superior ideas based on evaluation criteria. The evaluation criteria are the loss values ​​of the generative AI model. Ideas with lower loss values ​​are considered to be more highly rated and are extracted as superior ideas.

[0818] Step 5:

[0819] The server organizes the extracted ideas and combines them with other ideas as needed to generate new innovation proposals. For example, by combining the highly rated ideas "automatic plant watering system" and "smart refrigerator," a new innovation proposal called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0820] Step 6:

[0821] The server provides the generated new innovations to the user via a web interface, email, or other means, allowing the user to review the new ideas and apply them to their own projects or work.

[0822] Example 1

[0823] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0824] Conventional idea generation systems have difficulty effectively utilizing past ideas to generate new, creative ideas. Furthermore, the evaluation criteria for each idea are unclear, making it difficult to extract high-quality ideas. Therefore, there is a need for a system that can efficiently utilize previously submitted ideas to generate new, innovative ideas.

[0825] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0826] In this invention, the server includes means for collecting multiple pieces of information data submitted in the past and storing them in an information storage device, means for training a generative AI model to learn the data, means for analyzing the information data stored in the information storage device using the generative AI model and extracting superior information, means for organizing the extracted information and combining multiple pieces of information to generate new innovation ideas, means for providing the generated new innovation ideas to users, means for temporarily storing data in a temporary storage device, means for converting data into an appropriate format, and means for ranking information based on the evaluation value of the generative AI model, thereby making it possible to reevaluate past ideas and generate new creative and practical ideas.

[0827] "Information data" refers to information such as text data, image data, PDF files, etc. that show the content of ideas that have been submitted in the past.

[0828] An "information storage device" is a database or storage system that efficiently manages collected information data and stores it in a form that can be used for subsequent processing.

[0829] A "generative artificial intelligence model" is an artificial intelligence technology for learning information data and analyzing, evaluating, and generating it, and specifically includes text generation models.

[0830] An "evaluation value" is a numerical value that serves as a standard used by a generative artificial intelligence model when evaluating information data, and includes the model's loss value, etc.

[0831] "Ranking" refers to the process of ranking a plurality of pieces of information data based on evaluation values, so that information with higher evaluations is ranked higher.

[0832] A "temporary storage device" is a storage system for temporarily storing collected information data, and plays a role in improving data processing efficiency.

[0833] "Users" are individuals or organizations that use the new innovations generated and apply them in their own projects or work.

[0834] An "innovative proposal" is a new idea or proposal generated by reconstructing multiple existing pieces of information data.

[0835] The system of this invention is designed to effectively utilize multiple pieces of information data submitted in the past to generate new creative ideas. This system runs on a server and performs a series of processes including collection, storage, analysis, evaluation, reconstruction, and provision.

[0836] The server first collects previously submitted information data. This collection is done using web scraping or an API. The collected data is temporarily stored in a temporary storage device. It is then stored in an information storage device (for example, MongoDB or Amazon S3). This ensures data consistency and creates a structure that makes it easy to apply to subsequent processing.

[0837] Next, the server trains the generative AI model on the information data. A text generation model (e.g., GPT-3) is used as the generative AI model. This model performs natural language processing on the information data and extracts the characteristics of each piece of data. The server then uses the generative AI model to analyze the data stored in the information storage device and extracts superior information based on an evaluation criterion. Specifically, the loss value of the generative AI model is used as the criterion, and information with a lower loss value is considered to be more highly rated.

[0838] After extracting the most highly rated information, the server organizes it and reconstructs it into new innovation ideas. This reconstruction is done by combining multiple excellent pieces of information to generate creative and practical proposals. For example, by combining information on "automatic plant watering systems" and "smart refrigerators," a new idea called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0839] Finally, the server provides the generated new innovation ideas to the user, who can then review the new ideas and apply them to their own projects or work. The generated ideas are provided via a web interface, email, etc.

[0840] Specific examples

[0841] If an "automatic plant watering system" and a "smart refrigerator" are collected as past information data, the text data and outline of each idea are stored in an information storage device. The generative AI model can learn from these and combine them to propose a "system that automatically grows fresh herbs inside a smart refrigerator."

[0842] Prompt Sentence Examples

[0843] "Generate new, innovative ideas based on data from multiple previously submitted ideas. Combine top-rated ideas to create actionable proposals."

[0844] This system allows users to reevaluate past ideas and provide them as new creative proposals, thereby enabling the creation of new value. In this way, the mode for carrying out the invention is specifically shown.

[0845] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0846] Step 1:

[0847] Server: Start data collection

[0848] Specific operation: The server collects information data from past idea contests using web scraping and APIs. The collected data includes text data, image data, PDF files, etc.

[0849] Input: Idea contest website or API URL

[0850] Data processing: The server uses the Python BeautifulSoup library to extract text data from websites and retrieve data from APIs.

[0851] Output: raw data collected

[0852] Step 2:

[0853] Server: Temporary data storage

[0854] What it does: The server temporarily stores the collected data in an Amazon S3 bucket, ensuring data consistency and easy retrieval for subsequent processing steps.

[0855] Input: Raw data collected

[0856] Data processing: Save the data as is to Amazon S3

[0857] Output: Temporarily saved data

[0858] Step 3:

[0859] Server: Stored in a database

[0860] How it works: The server uses the Python "pymongo" library to store text data in a MongoDB database, and image data and PDF files in Amazon S3.

[0861] Input: Temporarily saved data

[0862] Data processing: Text data is inserted into MongoDB, and image data and PDF files are moved to Amazon S3

[0863] Output: Data stored in database and storage

[0864] Step 4:

[0865] Server: Prepare the data

[0866] Specific operation: The server uses Python's "pandas" library to format the idea data retrieved from the database and convert it into an input format for the generative AI model.

[0867] Input: Data stored in databases and storage

[0868] Data processing: Format data into tables and clean text data

[0869] Output: Formatted data

[0870] Step 5:

[0871] Server: Model training

[0872] How it works: The server uses a generative AI model (e.g., GPT-3) to train on the formatted idea data, allowing the model to understand the characteristics of each idea and evaluate them accordingly.

[0873] Input: Formatted data

[0874] Data processing: feature extraction, pattern recognition

[0875] Output: A trained generative AI model

[0876] Step 6:

[0877] Server: Data analysis

[0878] How it works: The server uses a generative AI model to analyze idea data and evaluate each idea based on its loss value.

[0879] Input: Trained generative AI model, idea data

[0880] Data calculation: Calculating loss values, evaluating ideas

[0881] Output: Evaluation results (loss values ​​and rankings of ideas)

[0882] Step 7:

[0883] Server: Idea ranking

[0884] Specific operation: The server ranks the idea data based on the loss value. The information with a lower loss value is rated higher.

[0885] Input: Evaluation result

[0886] Data processing: Idea ranking

[0887] Output: A ranked list of ideas

[0888] Step 8:

[0889] Server: Extracting and Reconstructing Great Ideas

[0890] How it works: The server extracts the top ranked ideas and selects them for restructuring. It then combines them to generate new innovations. For example, it combines an "automatic plant watering system" with a "smart refrigerator" to generate a new "system that automatically grows fresh herbs inside a smart refrigerator."

[0891] Input: A ranked list of ideas

[0892] Data processing: Combining ideas and generating new proposals

[0893] Output: New innovations

[0894] Step 9:

[0895] Server: Idea distribution

[0896] Specific operation: The server provides the generated new innovations to the user via a web interface, email, etc.

[0897] Input: New innovation idea

[0898] Data processing: Converting to a presentation format

[0899] Output: New innovations provided to the user

[0900] Step 10:

[0901] User: Checking the idea

[0902] Specific Action: Users review the new ideas provided and apply them to their own projects or work.

[0903] Input: New innovation ideas provided

[0904] Output: User confirmation and application of new ideas

[0905] This series of processes enables the system to reevaluate past information data, generate new creative and practical ideas, and provide them to users.

[0906] (Application example 1)

[0907] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0908] With conventional methods, it was difficult to effectively utilize the ideas submitted in idea contests, and the process of efficiently extracting and reconstructing the best ideas from among them was particularly laborious and time-consuming.In addition, there were no well-established methods for quickly generating new innovative ideas and providing them to users.

[0909] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0910] In this invention, the server includes means for collecting a plurality of idea data submitted in the past and storing them in a database, means for training a generative AI model to learn the data, means for analyzing the idea data stored in the database using the generative AI model and extracting good ideas, means for organizing the extracted ideas and combining the plurality of ideas to generate new innovation proposals, and means for using a web interface to provide the generated new innovation proposals to users. This enables effective use of ideas submitted in the past and enables new innovation proposals to be quickly generated and provided to users.

[0911] "Idea data" refers to multiple proposals submitted in past idea contests, and can range from text data, image data, PDF files, and more.

[0912] A "database" is a storage medium that centrally manages collected idea data and has a structure that makes it easy to apply to subsequent processing.

[0913] A "generative AI model" is an artificial intelligence model that uses, for example, a text generation model (such as GPT-3) to analyze, evaluate, and reconstruct idea data.

[0914] "Web Interface" means a user interface via an internet browser for presenting generated new innovations to a user.

[0915] "Loss value" is a metric used to evaluate the performance of a generative AI model, with lower values ​​indicating more accurate predictions by the model.

[0916] The system for implementing the present invention includes various components for effectively collecting, analyzing, evaluating, and generating new innovation ideas for users. Specific embodiments are described in detail below.

[0917] First, the server collects multiple pieces of idea data that have been submitted in the past and stores them in a database. This data includes text data, image data, PDF files, etc. The database centrally manages this data and has a structure that makes it easy to apply to subsequent processing.

[0918] Next, the server trains a generative AI model (for example, GPT-3, a text generation model) on the idea data in this database. The generative AI model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea. The loss value of the generative AI model is used as the evaluation criterion, with a lower loss value being considered a higher evaluation.

[0919] The server then uses the generative AI model to analyze the idea data stored in the database and extract the highly rated ideas. The extracted ideas are then further organized and multiple ideas are combined to generate new innovations. This process efficiently combines diverse ideas to produce novel and practical proposals.

[0920] The new innovations generated are then presented to the user through a web interface designed to allow users to easily explore the generated ideas and apply them to their own projects and work.

[0921] For example, the following prompts can be fed into a generative AI model to evaluate and reconstruct ideas:

[0922] "Rate this idea: An application for personal finance management."

[0923] "Combine these ideas to generate new innovations:\n- A smart budgeting tool\n- A goal tracking app\n- An intuitive spending insights dashboard"

[0924] In this way, new innovations can be generated efficiently and useful information can be provided to users quickly.

[0925] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0926] Step 1:

[0927] The server collects multiple idea data submitted in the past. This idea data is diverse, including text data, image data, and PDF files. All collected idea data is stored in a database. The input is past idea data, which is processed by collecting and storing it, and then output in a structured format to the database.

[0928] Step 2:

[0929] The server trains the generative AI model on the idea data in the database. For example, a text generation model (GPT-3) is used as the generative AI model. The input for training is the idea data stored in the database, and training the AI ​​model improves its pattern recognition and natural language processing capabilities. This enables the generative AI model to analyze and evaluate ideas.

[0930] Step 3:

[0931] The server uses a generative AI model to analyze idea data stored in a database and extract highly rated ideas. The input is the idea data in the database and the generative AI model, and by running the generative AI model, it evaluates the idea data and extracts superior ideas based on loss values. The output is a list of highly rated ideas.

[0932] Step 4:

[0933] The server organizes the extracted ideas and combines multiple ideas to generate new innovation proposals. The input is a list of highly rated ideas, and new ideas are generated using a reconstruction algorithm. This results in novel and practical proposals. The output is new innovation proposals.

[0934] Step 5:

[0935] The server uses a web interface to provide the generated new innovation proposals to the user. The input is the generated innovation proposals, which are displayed to the user through the web interface, allowing the user to easily check the new ideas and apply them to their own projects or work. The output is the provision of the innovation proposals to the user.

[0936] The above is the flow of processing of the program of the system that realizes the application example.

[0937] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0938] The system of this invention runs on a server, collects multiple idea data submitted in past idea contests, and generates new innovation proposals by analyzing, evaluating, and reconstructing them using a generative AI model, and provides them to users. Furthermore, it has the function of recognizing user emotions by combining an emotion engine and selecting the innovation proposals to provide based on the user's emotions.

[0939] First, the server collects all ideas submitted in past idea contests. This is done in a variety of formats, including text data, image data, and PDF files. All collected idea data is stored in a database. This database centrally manages multiple idea data and is structured to make it easy to apply to subsequent processing.

[0940] Next, the server trains a generative AI model on the idea data in the database. For example, a text generation model such as GPT-3 is used as the generative AI model. This model receives the text of the idea data as input, performs pattern recognition and natural language processing, and evaluates each idea.

[0941] The server uses this generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, such as the loss value of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[0942] After extracting the top ideas, the server organizes them and combines them to generate new innovations. For example, combining the ideas of an "automatic plant watering system" and a "smart refrigerator" generates a new idea called a "system for automatically growing fresh herbs inside a smart refrigerator."

[0943] The server then analyzes the user's emotions using an emotion engine, which recognizes the user's facial expressions, tone of voice, and incompatibility data to quantitatively evaluate the user's emotional state. Based on the evaluation results obtained by the emotion engine, the server selects and provides the user with the most suitable innovation proposal.

[0944] Finally, the server provides the generated new innovations to the user via a web interface, email, or other means. The user can review the new ideas and apply them to their own projects or work. User feedback is also fed back into the system for further improvements.

[0945] For example, if a user expresses interest in a "system that automatically grows fresh herbs inside a smart refrigerator," the emotion engine will recognize the user's positive response and prioritize innovation proposals on a similar theme. In this way, by combining emotion engines, it becomes possible to provide innovation proposals that match the user's needs and emotions.

[0946] This system makes it possible to rediscover good ideas that have been buried in the past and reconstruct them as innovative proposals, with the aim of promoting the creation of new value.

[0947] The processing flow will be explained below.

[0948] Step 1:

[0949] The server collects multiple idea data submitted in past idea contests in various formats, such as text data, image data, and PDF files.

[0950] Step 2:

[0951] The server stores the collected idea data in a database, which is used to centrally manage the titles and contents of ideas.

[0952] Step 3:

[0953] The server trains a generative AI model using the idea data in the database. For example, it uses a text generation model like GPT-3. The idea data is input into the model, which then learns through natural language processing and pattern recognition.

[0954] Step 4:

[0955] The server uses a generative AI model to analyze the idea data in the database and extracts superior ideas based on evaluation criteria. The evaluation criteria are the loss values ​​of the generative AI model. Ideas with lower loss values ​​are considered to be more highly rated and are extracted as superior ideas.

[0956] Step 5:

[0957] The server organizes the extracted ideas and combines them with other ideas as needed to generate new innovation proposals. For example, by combining the highly rated ideas "automatic plant watering system" and "smart refrigerator," a new innovation proposal called "a system that automatically grows fresh herbs inside a smart refrigerator" is generated.

[0958] Step 6:

[0959] The server analyzes the user's emotions using an emotion engine, which recognizes the user's facial expressions, tone of voice, and incompatibility data to quantitatively evaluate the user's emotional state.

[0960] Step 7:

[0961] The server selects the most suitable innovation proposal for the user based on the evaluation results of the emotion engine. For example, if the user has a positive reaction, it will prioritize the innovation proposal that matches that emotion.

[0962] Step 8:

[0963] The server provides the generated new innovations to the user via a web interface, email, or other means, allowing the user to review the new ideas and apply them to their own projects or work.

[0964] Step 9:

[0965] User feedback is fed back into the system to help it further improve, allowing it to continually update and generate better innovations.

[0966] Example 2

[0967] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0968] There is a need for a system that can generate new innovation proposals using previously submitted proposal data and provide those proposals to users efficiently and effectively. However, conventional systems do not automate the collection and analysis of proposal data, which requires time and effort. In addition, determining whether the generated innovation proposals match the user's emotions and needs is often done manually, making it difficult to improve user satisfaction. Therefore, there is a need for technology that can automatically collect and analyze past proposal data and provide optimal innovation proposals based on user emotions.

[0969] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0970] In this invention, the server includes means for collecting multiple proposal data submitted in the past and storing them in a storage device, means for training a generative AI model to learn the data, means for analyzing the proposal data stored in the storage device using the generative AI model and extracting excellent proposals, means for organizing the extracted proposals and combining multiple proposals to generate new innovative proposals, means for recognizing the emotional state of a user using an emotion recognition engine, and means for selecting and providing the new innovative proposals based on the emotional state. This makes it possible to efficiently generate effective innovative proposals based on past proposal data and provide them to users.

[0971] "Proposal data" refers to data that includes information on ideas, concepts, designs, etc. that have been submitted in the past.

[0972] "Storage device" refers to hardware and software for storing and managing data.

[0973] A "generative AI model" is an artificial intelligence model that performs text generation and natural language processing.

[0974] A "loss value" is an evaluation metric that indicates the error when a generative AI model is trained.

[0975] An "emotion recognition engine" is a technology that quantitatively evaluates a user's emotional state based on facial expressions, tone of voice, etc.

[0976] An "emotional state" is a state that represents a user's current feelings or mood.

[0977] An "innovative proposal" is a new proposal or concept that is generated based on existing ideas or technologies.

[0978] "Selection" refers to the process of selecting the best innovation from multiple proposals.

[0979] "Providing" refers to the act of notifying or presenting the generated innovation proposal to the user.

[0980] The system of the present invention executes a series of processes running on a server to collect multiple proposal data submitted in the past, generate new innovation proposals, and provide them to users. It also has a function to recognize the user's emotional state using an emotion recognition engine and select the innovation proposal that is most suitable for the user.

[0981] First, the server collects proposal data in the form of text data, image data, and PDF files from past proposal contests and databases. Web scraping tools and APIs are used for the collection. For example, Python and Selenium are used as web scraping tools. The collected data is then stored in a storage device such as MongoDB.

[0982] Next, the server uses a generative AI model to train the collected data. The generative AI model used is the language generation model GPT-3. The server inputs the preprocessed proposal data into the generative AI model and evaluates each proposal using natural language processing and pattern recognition. In this process, loss values ​​are used as the evaluation criterion, and proposals with low loss values ​​are extracted as superior.

[0983] The server then generates new innovation proposals based on the highly rated proposals. For example, by combining two proposals, "automatic plant watering system" and "smart refrigerator," a new innovation proposal such as "a system that automatically grows fresh herbs inside the smart refrigerator" is generated.

[0984] The server then analyzes the user's emotional state using an emotion recognition engine, which collects data on the user's facial expressions, tone of voice, and disapproval, and quantitatively evaluates the user's emotional state using technologies such as Amazon Rekognition and Google Cloud Speech-to-Text.

[0985] Based on the evaluation results of the emotion recognition engine, the server selects the most suitable innovation proposals from the generated proposals and provides them to the user via a web interface, email, or other methods. The web interface is built using the Django framework, and email notifications are sent using a Python mail sending library.

[0986] Examples of specific prompts include the following:

[0987] "Generate new refrigerator-related innovation ideas based on past idea data. Make them as relevant as possible to user emotions."

[0988] In this way, the system of the present invention can efficiently collect and analyze past proposal data and provide innovative proposals that match the user's emotional state, thereby promoting the creation of new value.

[0989] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0990] Step 1:

[0991] The server collects proposal data from past proposal contests and databases. The collected data ranges from text data, image data, and PDF files. For example, data is automatically scraped from specific websites using Python's Selenium library. The input is a list of website URLs, and the output is the proposal data.

[0992] Step 2:

[0993] The server stores the collected proposal data in a storage device such as MongoDB. The proposal data is stored in various formats (e.g., text, image, PDF). A database schema is defined to store the collected data appropriately. The input is the proposal data, and the output is the data stored in the storage device.

[0994] Step 3:

[0995] The server trains a generative AI model (e.g., GPT-3) with the stored proposal data. During this process, natural language processing (NLP) techniques are used to preprocess the data and input it into the generative AI model. For example, NLP libraries are used to tokenize and normalize the text data. The input is the data in storage, and the output is the trained generative AI model.

[0996] Step 4:

[0997] The server uses the generative AI model to analyze the proposal data stored in the storage device. This analysis involves pattern recognition and evaluation of each proposal. Loss value is used as the evaluation metric, and proposals with low loss values ​​are extracted as superior. The input is the trained generative AI model and proposal data, and the output is a list of evaluated proposals.

[0998] Step 5:

[0999] The server generates new innovation proposals based on the highly rated proposals. This is a process of combining multiple proposals to create new ideas. For example, the proposals for an "automatic plant watering system" and a "smart refrigerator" can be combined to generate a "system that automatically grows fresh herbs inside a smart refrigerator." The input is a list of evaluated proposals, and the output is a new innovation proposal.

[1000] Step 6:

[1001] The server analyzes the user's emotional state using an emotion recognition engine. It captures data on the user's facial expressions, tone of voice, and incompatibility to evaluate the emotional state. For example, it uses a webcam and microphone to collect data in real time and inputs it into the emotion recognition model. The input is the user's real-time data, and the output is an evaluation of the user's emotional state.

[1002] Step 7:

[1003] The server provides new innovation proposals to the user based on the emotional state evaluation results. This is done through a web interface or email. For example, it uses the Django framework to render web pages and a Python email library to send notifications. The inputs are the new innovation proposals and the emotional state evaluation results, and the output is the innovation proposals provided to the user.

[1004] Step 8:

[1005] The user reviews the proposed innovation and provides feedback. The server inputs this feedback back into the system to help improve it further. The input is the user's feedback, and the output is the system improvement data.

[1006] Through the above steps, a system is realized that efficiently generates new innovation proposals based on past proposal data and provides them according to the user's emotional state.

[1007] (Application example 2)

[1008] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1009] In recent years, many companies and organizations have been devoting significant efforts to generating innovative ideas. However, previously submitted ideas often go to waste or are not properly evaluated and utilized. Furthermore, there is a lack of systems that provide innovative ideas tailored to individual users' emotions and needs, resulting in a lack of an improved user experience. Furthermore, in brick-and-mortar stores, it would be effective to provide product and service suggestions based on the customer's emotional state, but such a system does not yet exist. These issues need to be resolved.

[1010] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1011] In this invention, the server includes means for collecting a plurality of previously submitted idea data and storing them in a database, means for training a generative AI model to learn the data, means for analyzing the idea data stored in the database using the generative AI model and extracting excellent ideas, means for organizing the extracted ideas and combining the plurality of ideas to generate new innovative ideas, and means for selecting and providing the generated new innovative ideas based on the emotional state of the user using an emotion recognition engine. This makes it possible to provide innovative ideas that match the emotional state of the user, improving the customer experience in physical stores and making effective use of hidden ideas.

[1012] "Idea data" refers to information about multiple ideas, proposals, and concepts that have been submitted in the past, and exists in multiple formats such as text data, image data, and PDF files.

[1013] A "database" is a collection of information that centrally manages and stores collected idea data and has a structure that makes it easy to apply to subsequent processing.

[1014] A "generative AI model" is a machine learning model used to learn from collected idea data, analyze and evaluate it, and generate new ideas. A typical example is a text generation model (e.g., GPT-3).

[1015] An "emotion recognition engine" is a system that quantitatively evaluates a user's emotional state by recognizing the user's facial expressions, tone of voice, and incompatibility data.

[1016] "Innovative ideas" refer to proposals or concepts that are newly created by combining multiple excellent ideas that have been extracted.

[1017] "User's emotional state" refers to a quantitative assessment result of the user's current emotion obtained by an emotion recognition engine.

[1018] A system for realizing the present invention is implemented with the following configuration and procedure.

[1019] First, the server collects multiple idea data submitted in the past and stores it in a database. This idea data includes information in various formats, such as text data, image data, and PDF files. The database is used to centrally manage this data and store it in a format that is convenient for subsequent processing.

[1020] Next, the server trains a generative AI model on the stored idea data. For example, a text generation model (e.g., GPT-3) is used as the generative AI model. This model performs pattern recognition and natural language processing based on the input text data and evaluates each idea.

[1021] The server uses the generative AI model to analyze the idea data stored in the database and extracts superior ideas based on evaluation criteria, which are the loss values ​​of the generative AI model, with ideas with lower loss values ​​being considered higher-rated.

[1022] The extracted ideas are organized by the server, and new innovations are generated by combining multiple ideas. For example, the ideas for an "automatic plant watering system" and a "smart refrigerator" can be combined to create a new idea for a "system that automatically grows fresh herbs inside a smart refrigerator."

[1023] The generated new innovation proposals are selected based on the user's emotional state using an emotion recognition engine. Specifically, the user's facial expressions and tone of voice are captured in real time using a camera and microphone, and the emotion recognition engine analyzes the data to quantitatively evaluate the user's emotional state. Based on the results of this evaluation, the server selects the most suitable innovation proposal for the user and provides it to the user via a smartphone app or a robot installed in a physical store.

[1024] For example, in-store sales history, customer reviews, and past marketing data can be used to generate ideas for new sales strategies and product improvements, while an emotion recognition engine can provide further relevant innovation suggestions when customers express interest.

[1025] An example of a prompt for a generative AI model is:

[1026] Generate new ideas for eco-friendly gift wrapping services based on past sales history and customer reviews, including suggestions on what materials to use and promotional strategies.

[1027] In this way, the present invention makes it possible to provide innovative ideas that are suited to the user's emotional state, thereby improving the customer experience in physical stores and making effective use of good ideas that have been buried in the past.

[1028] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1029] Step 1:

[1030] The server collects previously submitted idea data and stores it in a database. This data includes text data, image data, PDF files, etc. This data is extracted from information sources, formatted, and stored in the database. Idea data is used as input, and a formatted database entry is obtained as output.

[1031] Step 2:

[1032] The server trains a generative AI model on the idea data stored in the database. A text generation model (e.g., GPT-3) is used as the generative AI model. The idea data in the database is used as input, and the evaluation results and specific patterns for each idea are obtained as output. Specific operations include analyzing the text data and updating the model parameters.

[1033] Step 3:

[1034] The server uses a generative AI model to analyze idea data stored in a database and extract superior ideas. The loss value of the generative AI model is used as the evaluation criterion. The trained model and the idea data in the database are used as input, and a list of highly rated ideas is obtained as output. Specific operations include feedforward processing of the model and calculation of loss values.

[1035] Step 4:

[1036] The server organizes the extracted excellent ideas and combines multiple ideas to generate new innovation proposals. The input is a list of highly rated ideas, and the output is new innovation proposals. Specific operations include combining and re-evaluating ideas. For example, an "automatic plant watering system" and a "smart refrigerator" can be combined to generate a "system that automatically grows fresh herbs inside a smart refrigerator."

[1037] Step 5:

[1038] The generated innovation proposals are selected and presented based on the user's emotional state using an emotion recognition engine. Specifically, the user's facial expressions and tone of voice are captured using a camera and microphone and analyzed by the emotion recognition engine. The user's facial expression data and voice data are used as input, and an emotional evaluation result is obtained as output. Based on the evaluation result, the server selects the most suitable innovation proposal for the user.

[1039] Step 6:

[1040] The server provides the selected innovation proposals to the user via a smartphone app or a robot in a physical store. The innovation proposals based on the emotional evaluation results are used as input, and the innovation proposals presented to the user are obtained as output. Specific operations include sending the innovation proposals and displaying them on the interface. If the user shows interest, further related innovation proposals are suggested.

[1041] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1042] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1043] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1044] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1045] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1046] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1047] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1048] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1049] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1050] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1051] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1052] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1053] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1054] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1055] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1056] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1057] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1058] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1059] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1060] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1061] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1062] The following is further disclosed regarding the above embodiment.

[1063] (Claim 1)

[1064] A means for collecting and storing data on multiple ideas submitted in the past in a database;

[1065] means for training a generative AI model on the data;

[1066] A means for analyzing idea data stored in the database using the generative AI model and extracting good ideas;

[1067] A means for organizing the extracted ideas and combining multiple ideas to generate new innovation proposals;

[1068] means for providing the generated new innovation ideas to a user;

[1069] A system including:

[1070] (Claim 2)

[1071] 2. The system of claim 1, wherein the generative AI model is a text generation model.

[1072] (Claim 3)

[1073] The system of claim 1, wherein a loss value of the generative AI model is used when evaluating the idea data stored in the database.

[1074] "Example 1"

[1075] (Claim 1)

[1076] A means for collecting a plurality of pieces of information data that have been submitted in the past and storing them in an information storage device;

[1077] means for training a generative artificial intelligence model on the data;

[1078] A means for analyzing the information data stored in the information storage device using the generative artificial intelligence model and extracting superior information;

[1079] A means for organizing the extracted information and combining multiple pieces of information to generate new innovation ideas;

[1080] A means for providing the generated new innovation ideas to users;

[1081] means for temporarily storing data in a temporary storage device;

[1082] a means of converting the data into an appropriate format;

[1083] A means for ranking information based on the evaluation value of the generative artificial intelligence model;

[1084] A system including:

[1085] (Claim 2)

[1086] 2. The system of claim 1, wherein the generative artificial intelligence model is a text generation model.

[1087] (Claim 3)

[1088] The system of claim 1, wherein a loss value of the generative artificial intelligence model is used when evaluating the information data stored in the information storage device.

[1089] "Application Example 1"

[1090] (Claim 1)

[1091] A means for collecting and storing data on multiple ideas submitted in the past in a database;

[1092] means for training a generative AI model on the data;

[1093] A means for analyzing idea data stored in the database using the generative AI model and extracting good ideas;

[1094] A means for organizing the extracted ideas and combining multiple ideas to generate new innovation proposals;

[1095] means using a web interface for presenting the generated new innovations to a user;

[1096] A system including:

[1097] (Claim 2)

[1098] 2. The system of claim 1, wherein the generative AI model is a text generation model.

[1099] (Claim 3)

[1100] The system of claim 1, wherein a loss value of the generative AI model is used when evaluating the idea data stored in the database.

[1101] "Example 2: Combining Emotion Engines"

[1102] (Claim 1)

[1103] A means for collecting a plurality of pieces of proposal data that have been submitted in the past and storing them in a storage device;

[1104] means for training a generative AI model on the data;

[1105] A means for analyzing the proposal data stored in the storage device using the generative AI model and extracting excellent proposals;

[1106] A means for organizing the extracted proposals and combining multiple proposals to generate new innovation ideas;

[1107] means for generating new innovation proposals based on proposal data in the storage device using the generative AI model;

[1108] means for recognizing the emotional state of a user using an emotion recognition engine;

[1109] means for selecting and providing the new innovations based on the emotional state;

[1110] A system including:

[1111] (Claim 2)

[1112] 2. The system of claim 1, wherein the generative AI model is a language generation model.

[1113] (Claim 3)

[1114] The system according to claim 1, characterized in that an evaluation index value of the generative AI model is used when evaluating the proposal data stored in the storage device.

[1115] "Application example 2 when combining emotion engines"

[1116] (Claim 1)

[1117] A means for collecting and storing data on multiple ideas submitted in the past in a database;

[1118] means for training a generative AI model on the data;

[1119] A means for analyzing idea data stored in the database using the generative AI model and extracting good ideas;

[1120] A means for organizing the extracted ideas and combining multiple ideas to generate new innovation proposals;

[1121] a means for selecting and providing the generated new innovation proposals based on the emotional state of the user using an emotion recognition engine;

[1122] A system including:

[1123] (Claim 2)

[1124] 2. The system of claim 1, wherein the generative AI model is a text generation model.

[1125] (Claim 3)

[1126] The system of claim 1, wherein a loss value of the generative AI model is used when evaluating the idea data stored in the database. [Explanation of symbols]

[1127] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting and storing data on multiple ideas submitted in the past in a database; means for training a generative AI model on the data; A means for analyzing idea data stored in the database using the generative AI model and extracting good ideas; A means for organizing the extracted ideas and combining multiple ideas to generate new innovation proposals; means for providing the generated new innovation ideas to a user; A system including:

2. 2. The system of claim 1, wherein the generative AI model is a text generation model.

3. The system of claim 1, wherein a loss value of the generative AI model is used when evaluating the idea data stored in the database.

Images