System

Abstract

To provide a system.SOLUTION: A system includes: theme input means for receiving input of a theme from a user; generative AI means for generating ideas or questions relating to the theme; evaluation means for supporting extension with respect to the ideas generated by the generative AI means; emotion recognition means for recognizing an emotion of the user; means for evaluating the ideas or the questions on the basis of the emotion recognized by the emotion recognition means to generate new ideas or questions; and cooperation means with input means and conference tools.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 conventional brainstorming, idea generation, information organization, and evaluation are all done manually, resulting in variations in the quality and quantity of ideas and requiring a great deal of time and effort. [Means for solving the problem]

[0005] This invention uses generative AI to generate related ideas and questions based on a topic input from the user. It also provides evaluation buttons for generated ideas, such as "original," "realistic," and "review from a management perspective," to help expand on the ideas. Furthermore, in addition to input from the WebUI, it also utilizes information from meeting minutes by linking with web conferencing tools. This streamlines the brainstorming process, including idea generation, information organization, and evaluation, and makes it possible to improve the quality and quantity of ideas. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] The brainstreaming support system of the present invention uses generative AI to generate related ideas and questions based on a theme input by the user. Specifically, when a user inputs "new business development" as a theme, the generative AI generates questions such as "What are the market needs for new business development?" and "What resources are needed for new business development?", as well as ideas such as "Leverage the existing customer base for new business development" and "Consider introducing new technology for new business development."

[0029] "Example 2"

[0030] For the generated ideas, evaluation buttons such as "Be original," "Be realistic," and "Review from a management perspective" are provided to support the expansion of the ideas. Specifically, when a user presses the "Be original" evaluation button for the generated idea "Consider introducing new technology to develop new businesses," the generative AI will generate new ideas such as "What kind of original businesses will become possible by introducing new technology?"

[0031] "Example 3"

[0032] The system of the present invention not only utilizes input from the WebUI, but also utilizes information from meeting minutes by linking with web conferencing tools. Specifically, minutes from meetings held using web conferencing tools such as Zoom are imported, and the generative AI generates new ideas based on the information contained in the minutes. For example, if the minutes contain information such as "new technology needs to be introduced to develop new businesses," the generative AI can use this information to generate new ideas such as "what kind of new businesses can be developed by introducing new technology?"

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The user accesses the brainstorming support system's Web UI and enters "new business development" as the theme.

[0036] Step 2: The system's generative AI receives topic input from the user and generates related ideas and questions. Specifically, it generates questions such as "What are the market needs for new business development?" and "What resources are needed for new business development?", as well as ideas such as "Leverage the existing customer base for new business development" and "Consider introducing new technology for new business development."

[0037] Step 3: The generated ideas and questions are presented to the user, who can then add their own thoughts or rate the presented ideas.

[0038] "Example 2"

[0039] Step 1: The user clicks the "Be original" rating button for the generated idea, "Consider introducing new technology to develop new businesses."

[0040] Step 2: The system's generative AI receives user evaluation input and generates new ideas based on the evaluation. Specifically, it generates new ideas such as "What kind of original business will become possible by introducing new technology?"

[0041] Step 3: The generated new ideas are presented to the user, who can then add their own thoughts or rate the presented ideas.

[0042] "Example 3"

[0043] Step 1: Users hold meetings using web conferencing tools such as Zoom and import the minutes into the system.

[0044] Step 2: The system's generative AI analyzes the information from the minutes and generates new ideas based on that information. For example, if the minutes contain information such as "new technology needs to be introduced to develop new businesses," the generative AI will use this information to generate new ideas such as "what kind of new businesses can be developed by introducing new technology?"

[0045] Step 3: The generated new ideas are presented to the user, who can then add their own thoughts or rate the presented ideas.

[0046] Example 1

[0047] Next, a description will be given of Example 1 of Form 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."

[0048] Conventional brainstreaming support systems lack the ability to automatically generate specific ideas and questions related to a topic when the user inputs it. They also lack the means to evaluate and further expand on the generated ideas and questions. Furthermore, they lack integration with web conferencing tools, making it difficult to effectively utilize information obtained during meetings.

[0049] 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.

[0050] In this invention, the server includes a means for inputting a theme from a user, a means for converting the theme into a prompt, a means for transmitting the prompt to a generative AI model, a means for receiving output from the generative AI model, a means for displaying generated ideas and questions to the user, and a means for input from a Web UI and a means for linking with a web conferencing tool. This makes it possible to automatically generate specific ideas and questions based on the theme input by the user, and to evaluate and expand them. Furthermore, linking with a web conferencing tool makes it possible to effectively utilize information obtained during a conference.

[0051] The "means for user theme input" is a means for providing an interface for the user to input a brainstorming theme.

[0052] The "means for converting the theme into a prompt sentence" refers to a means for converting the theme entered by the user into a prompt sentence in a format suitable for the generative AI model.

[0053] The "means for transmitting the prompt sentence to the generative AI model" refers to a means for transmitting the generated prompt sentence to the generative AI model.

[0054] "Means for receiving output from the generative AI model" refers to means for receiving ideas or questions returned from the generative AI model.

[0055] "Means for displaying generated ideas and questions to the user" means means for displaying ideas and questions received from the generative AI model to the user.

[0056] "Means for input from WebUI" refers to the means by which a user can input information through a web interface.

[0057] "Means of integration with web conferencing tools" refers to means of integrating with web conferencing tools to obtain information and utilize it within the system.

[0058] MODE FOR CARRYING OUT THE INVENTION

[0059] This invention is a brainstreaming support system that uses a generative AI model to generate related ideas and questions based on a user-input topic. Specific embodiments of this system are described below.

[0060] System configuration

[0061] The system consists of the following main components:

[0062] 1. User theme input method

[0063] 2. A means of converting the theme into a prompt sentence

[0064] 3. Means for sending the prompt sentence to the generative AI model

[0065] 4. A means of receiving output from a generative AI model

[0066] 5. A way to display generated ideas and questions to users

[0067] 6. Input method from WebUI

[0068] 7. How to integrate with web conferencing tools

[0069] Hardware and software used

[0070] Hardware: Servers, devices (users' PCs and smartphones)

[0071] Software: Generative AI model (e.g., GPT-4 (registered trademark)), web browser, HTML, JavaScript (registered trademark), Python

[0072] Program processing

[0073] The user inputs a theme through a web browser. For example, the theme is "new business development." The device sends this theme to the server. The server converts the received theme into a prompt. Specifically, it generates the prompt, "Please generate questions or ideas related to 'new business development.'"

[0074] The server sends this prompt to a generative AI model (GPT-4), which generates relevant questions and ideas based on the prompt. For example, it generates content such as "What are the market needs for new business development?" or "Leverage the existing customer base to develop new businesses."

[0075] The generated questions and ideas are sent to the device via the server, and the device displays this information in a web browser, allowing users to brainstorm based on this information.

[0076] Specific examples

[0077] The user inputs the theme "new business development." The device sends this theme to the server. The server generates a prompt message saying, "Generate questions and ideas related to 'new business development,'" and sends this to the generative AI model (GPT-4). The generative AI model generates questions and ideas such as, "What are the market needs for new business development?" and "Leverage the existing customer base to develop new businesses." The server receives these generated results and sends them to the device. The device displays the received questions and ideas on the browser, and the user uses them to brainstorm.

[0078] In this way, users can get diverse perspectives and ideas related to the topic and receive brainstorming support.

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

[0080] Step 1:

[0081] The user inputs a theme.

[0082] The user accesses the interface on a web browser and enters the theme they want to brainstream into the theme input field. For example, they might enter "new business development." The entered theme is temporarily stored in the device's memory.

[0083] Step 2:

[0084] The device sends the theme to the server.

[0085] The terminal sends the theme entered by the user to the server as an HTTP request. This request is made using the JavaScript fetch function. The input data is the theme "New Business Development", and the output is a request sent to the server.

[0086] Step 3:

[0087] The server converts the theme into a prompt.

[0088] The server generates a prompt based on the received theme. For example, for the theme "New Business Development," it creates the prompt "Please generate questions and ideas related to 'New Business Development'." The input data is the theme "New Business Development," and the output is the prompt "Please generate questions and ideas related to 'New Business Development'."

[0089] Step 4:

[0090] The server sends the prompt to the generative AI model.

[0091] The server sends the generated prompt sentence to the generative AI model (GPT-4). This communication is performed using an API request. The input data is the prompt sentence, and the output is a request sent to the generative AI model.

[0092] Step 5:

[0093] Generative AI models generate questions and ideas.

[0094] The generative AI model generates relevant questions and ideas based on the prompt it receives, such as "What are the market needs for new business development?" or "Leverage the existing customer base to develop new businesses." The input data is the prompt, and the output is the generated questions and ideas.

[0095] Step 6:

[0096] The server receives the generated questions and ideas.

[0097] The server receives the questions and ideas returned by the generative AI model. This data is received in JSON format. The input data is the output from the generative AI model, and the output is the data received by the server.

[0098] Step 7:

[0099] The server sends questions and ideas to the device.

[0100] The server sends the received questions and ideas to the terminal as an HTTP response. This response is also in JSON format. The input data is the generated questions and ideas, and the output is the data sent to the terminal.

[0101] Step 8:

[0102] The device displays questions and ideas to the user.

[0103] The device displays the questions and ideas received from the server on the browser. Users can brainstorm based on this information. The input data is the response from the server, and the output is what is displayed on the browser.

[0104] (Application example 1)

[0105] Next, a description will be given of Application Example 1 of Embodiment 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."

[0106] Conventional brainstreaming support systems have the ability to generate ideas and questions based on themes entered by users, but they lack support specialized for specific industries or applications. In particular, they lack the ability to generate specific ideas and questions to improve production efficiency within factories, making it difficult for factory managers and engineers to efficiently find ways to improve production lines.

[0107] 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.

[0108] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conference tool, a means for generating ideas and questions for improving production efficiency in a factory, and a learning means for providing feedback on the generated ideas and questions and reflecting the feedback in future generation. This enables factory managers and engineers to efficiently generate specific ideas and questions for improving production efficiency and find improvement measures.

[0109] The "user topic input means" is an interface that allows the user to input a specific topic or problem.

[0110] "Generative AI methods" are artificial intelligence functions that generate related ideas and questions based on an input topic.

[0111] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion and improvement of the ideas based on the evaluation results.

[0112] "WebUI input means" means a means by which a user inputs information through a web user interface.

[0113] "Means for linking with web conferencing tools" refers to a function that links with web conferencing tools to share information and utilize data such as minutes.

[0114] The "means for generating ideas and questions to improve production efficiency in a factory" is a function for generating ideas and questions specialized for improving production efficiency in a factory.

[0115] "Learning means that provides feedback on generated ideas and questions and reflects it in future generations" is a function that collects feedback from users and allows the generative AI to reflect that feedback in the generation of future ideas and questions.

[0116] As an embodiment of the present invention, a brainstreaming support system for improving production efficiency within a factory will be specifically described.

[0117] System Configuration

[0118] The system includes the following major hardware and software components:

[0119] Server: Hosts the generative AI model, receives thematic input from users, and generates relevant ideas and questions.

[0120] User terminal: A device (e.g., PC, tablet) where factory managers and engineers can input topics and review generated ideas and questions.

[0121] Web User Interface (WebUI): The interface through which users can enter topics and view generated ideas and questions.

[0122] Web conferencing tools: Tools to capture meeting minutes and integrate with systems.

[0123] Program processing

[0124] The server processes and calculates data using the following means:

[0125] 1. Theme input method: The user inputs a theme through the Web UI. For example, the user inputs the theme "improving production line efficiency."

[0126] 2. Generative AI means: Generative AI models such as OpenAI's GPT-3 are used to generate relevant ideas and questions based on the input topic. The generated ideas and questions are processed on the server and sent to the user's device.

[0127] 3. Evaluation method: Users evaluate the generated ideas and questions. The evaluation results are sent to the server and reflected in future generation.

[0128] 4. Input from WebUI: Users provide feedback through the WebUI and evaluate the generated ideas and questions.

[0129] 5. Means of integration with web conferencing tools: Information is obtained from the minutes of web conferencing tools and used as training data for generative AI models.

[0130] 6. Learning method: The generative AI model is updated based on user feedback and reflected in the generation of ideas and questions from the next time onwards.

[0131] Specific examples

[0132] For example, if a factory manager inputs the theme "improving production line efficiency," the generative AI model will generate ideas and questions like the following:

[0133] "Where is the bottleneck on the production line?"

[0134] "What processes can be automated?"

[0135] "Would changing the layout of the production line improve efficiency?"

[0136] These ideas and questions are displayed on the user's device's WebUI, where users can rate and provide feedback.

[0137] Prompt Sentence Examples

[0138] Theme: Improving production line efficiency

[0139] Generate relevant ideas and questions.

[0140] In this way, specific ideas and questions for improving production efficiency within the factory can be efficiently generated, enabling managers and engineers to find improvement measures.

[0141] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0142] Step 1:

[0143] The user enters the theme through the WebUI.

[0144] Input: The user inputs a theme such as "improving production line efficiency."

[0145] Output: The input theme is sent to the server.

[0146] Specific operation: The user enters a theme into the input field of the WebUI and clicks the "Submit" button.

[0147] Step 2:

[0148] The server uses a generative AI model to generate relevant ideas and questions based on the input topic.

[0149] Input: The server receives the theme submitted by the user.

[0150] Output: A list of ideas and questions generated by the generative AI model.

[0151] How it works: The server sends a theme as a prompt to a generative AI model such as OpenAI's GPT-3, and receives the generated ideas and questions.

[0152] Step 3:

[0153] The server transmits the generated ideas and questions to the user terminal.

[0154] Input: A list of ideas or questions generated by a generative AI model.

[0155] Output: Ideas and questions displayed on the user's terminal.

[0156] Specific operation: The server sends the generated ideas and questions to the WebUI on the user's device and displays them.

[0157] Step 4:

[0158] Users rate the generated ideas and questions.

[0159] Input: Users rate the ideas and questions displayed.

[0160] Output: The evaluation result is sent to the server.

[0161] Specific operation: The user clicks on an evaluation button on the Web UI, such as "Be original," "Be realistic," or "Review from a management perspective."

[0162] Step 5:

[0163] The server receives the evaluation results from the user and saves them as learning data to be reflected in future generations.

[0164] Input: The evaluation results submitted by the user.

[0165] Output: The evaluation results are saved and used as training data for the generative AI model.

[0166] Specific operation: The server stores the evaluation results in a database and provides them as feedback to the learning algorithm of the generative AI model.

[0167] Step 6:

[0168] The server obtains information from the minutes of the web conferencing tool and uses it as learning data for the generative AI model.

[0169] Input: Minutes data from a web conferencing tool.

[0170] Output: The minutes data is used as training data for the generative AI model.

[0171] Specific operation: The server obtains the minutes data through the API of the web conferencing tool and provides it to the learning algorithm of the generative AI model.

[0172] In this way, specific ideas and questions for improving production efficiency within the factory can be efficiently generated, enabling managers and engineers to find improvement measures.

[0173] Example 2

[0174] Next, a description will be given of Example 2 of Form 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."

[0175] Conventional brainstorming support systems have had the problem of not being able to provide appropriate feedback or expansion on the ideas entered by users. Furthermore, the evaluation criteria are limited, making it difficult to expand on ideas from multiple perspectives. Furthermore, there is a lack of concrete methods for improving the quality and relevance of generated ideas.

[0176] 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.

[0177] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, a means for generating a prompt sentence based on the evaluation, a means for sending the generated prompt sentence to a generative AI model, a means for returning a response from the generative AI model to the user, and a means for input from a Web UI and a means for linking with a Web conferencing tool. This enables the ideas input by the user to be evaluated and expanded from multiple perspectives, thereby improving the quality and relevance of the generated ideas.

[0178] The "means for user theme input" is an interface that allows users to input ideas and themes into the system.

[0179] "Generative AI methods" are artificial intelligence functions that generate relevant ideas and questions based on a topic entered by the user.

[0180] The "evaluation means" is an interface that allows users to evaluate the generated ideas, and includes evaluation buttons such as "original," "realistic," and "review from a management perspective."

[0181] The "means for generating prompt sentences" is a function that creates prompt sentences to be sent to the generative AI model based on the user's evaluation.

[0182] "Means for sending to the generative AI model" refers to a communication means for sending the generated prompt sentence to the generative AI model.

[0183] "Means for returning responses from the generative AI model to the user" refers to a function for returning new ideas and answers received from the generative AI model to the user.

[0184] "Input means from WebUI" means a means by which a user inputs information into the system through a web interface.

[0185] "Means of integration with web conferencing tools" refers to a function that allows you to utilize information such as minutes by integrating with web conferencing tools.

[0186] This invention is a system that utilizes a generative AI model based on a theme entered by a user to support the evaluation and expansion of ideas. Specific embodiments of this system are described below.

[0187] First, the user uses a device (such as a PC or smartphone) to input a theme into the system's Web UI. For example, the user might input "Consider introducing new technology for new business development."

[0188] Next, the user presses one of the evaluation buttons for the entered theme, such as "creative," "realistic," or "review from a management perspective." For example, the user presses the "creative" button.

[0189] The server generates an appropriate prompt based on the evaluation button pressed by the user. For example, if the "Be creative" button is pressed, the server generates the prompt "What kind of creative business will become possible with the introduction of new technology?"

[0190] Next, the server sends the generated prompt to a generative AI model (e.g., OpenAI's GPT-4) via an API.

[0191] The generative AI model generates new ideas based on the prompt it receives. For example, in response to the prompt, "What kind of unique business will become possible with the introduction of new technology?", it generates ideas such as "A new logistics service that utilizes AI-powered autonomous driving technology."

[0192] Finally, the server returns the new ideas received from the generative AI model to the user by displaying them on the device screen.

[0193] The system allows users to evaluate and expand on ideas from multiple perspectives, improving the quality and relevance of the generated ideas. It can also utilize information from meeting minutes by linking with web conferencing tools.

[0194] As a concrete example, consider the case where a user inputs "Consider introducing new technology for new business development" and presses the evaluation button for "Review from the perspective of management." In this case, the server generates a prompt message asking, "What are the advantages and risks of introducing new technology from the perspective of management?" The generative AI model generates new ideas and reviews based on this prompt message, and the server returns the results to the user.

[0195] Examples of prompts include:

[0196] "What kind of creative business will become possible with the introduction of new technology?"

[0197] "What are the benefits and risks of introducing new technology from a management perspective?"

[0198] "What practical impact will the introduction of new technologies have?"

[0199] In this way, users can evaluate and further expand their ideas using generative AI models.

[0200] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0201] Step 1:

[0202] The user inputs a theme into the input form on the terminal.

[0203] Input: Theme entered by the user (e.g., "Consider introducing new technology for new business development")

[0204] Output: The input theme is sent to the server.

[0205] Specific operation: The user uses the device's WebUI to enter a theme and press the send button.

[0206] Step 2:

[0207] The user presses the rating button.

[0208] Input: A rating button that the user selects (e.g., "Creatively").

[0209] Output: The selected rating is sent to the server.

[0210] Specific operation: The user presses one of the evaluation buttons for the entered theme, such as "original," "realistic," or "review from a management perspective."

[0211] Step 3:

[0212] The server generates a prompt.

[0213] Input: User-entered theme and rating button selection information

[0214] Output: Generated prompt (e.g., "What creative ventures will become possible with the introduction of new technology?")

[0215] Specific operation: The server generates an appropriate prompt sentence based on the rating button pressed by the user.

[0216] Step 4:

[0217] The server sends a prompt to the generative AI model.

[0218] Input: Generated prompt text

[0219] Output: The prompt sent to the generative AI model

[0220] Specific operation: The server sends the generated prompt sentence to the generative AI model (e.g., OpenAI's GPT-4) via an API.

[0221] Step 5:

[0222] Generative AI models generate new ideas.

[0223] Input: The prompt sent to the generative AI model

[0224] Output: Generated new ideas (e.g., "A new logistics service utilizing AI-based autonomous driving technology")

[0225] Specific operation: The generative AI model generates new ideas based on the received prompt.

[0226] Step 6:

[0227] The server returns the generated ideas to the user.

[0228] Input: New ideas received from the generative AI model

[0229] Output: The new idea displayed on the user's terminal

[0230] Specific operation: The server sends new ideas received from the generative AI model to the user's device and displays them on the screen.

[0231] (Application example 2)

[0232] Next, a description will be given of Application Example 2 of Form 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."

[0233] Conventional brainstorming support systems lacked specific means for users to further expand on the ideas they generated. They also lacked functionality to help content creators generate new content ideas and further expand them using a rating button. This made it difficult to improve creativity and generate ideas efficiently.

[0234] 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.

[0235] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conference tool, a means for supporting content creators in generating new content ideas and further expanding them using a rating button, and an application means installed on a smartphone or a head-mounted display. This allows users to further expand on their generated ideas using the rating button, thereby improving creativity and realizing efficient idea generation.

[0236] The "user theme input means" is an interface that allows a user to input a specific theme or topic into the system.

[0237] "Generative AI methods" are artificial intelligence functions that automatically generate related ideas and questions based on an input topic.

[0238] The "evaluation tool" is an interface that allows users to evaluate the generated ideas, such as "originality," "realism," and "review from a management perspective."

[0239] "WebUI input means" means a means by which a user inputs information through a web user interface.

[0240] "Means for linking with web conferencing tools" refers to a function that links with web conferencing tools to utilize information such as minutes.

[0241] "A means to assist content creators in generating new content ideas and further developing them using the rating button" is a support function that enables content creators to generate new ideas and further develop them using the rating button.

[0242] "Application means installed on a smartphone or head-mounted display" refers to a means for using the system through an application installed on a smartphone or head-mounted display.

[0243] A system for implementing this invention includes a means for user theme input, a generative AI means, an evaluation means, an input means from a Web UI, a means for linking with a Web conferencing tool, a means for supporting content creators in generating new content ideas and further expanding them using evaluation buttons, and an application means to be installed on a smartphone or head-mounted display.

[0244] System program processing explanation

[0245] Hardware and Software Use

[0246] Hardware:

[0247] Smartphone

[0248] head-mounted display

[0249] server

[0250] software:

[0251] OpenAI API

[0252] Python Program

[0253] WebUI

[0254] Web conferencing tools

[0255] Data processing and calculation

[0256] User Action:

[0257] Users use a smartphone or head-mounted display to input a theme, such as "Consider introducing new technology to develop new businesses."

[0258] Generative AI processing:

[0259] The server uses generative AI (e.g., GPT-3) to generate related ideas and questions based on the input topic. Generated ideas might include, for example, "What kind of creative business will become possible with the introduction of new technology?"

[0260] Operation of the assessment instrument:

[0261] For each generated idea, users can rate it with buttons such as "original," "realistic," or "review from a management perspective." For example, if users press the "original" rating button, the generative AI will generate a new idea such as "By introducing new technology, we will provide a personalized content distribution service using AI."

[0262] Integration with WebUI and web conferencing tools:

[0263] Users can input information through the WebUI and utilize information from the minutes of the web conferencing tool, enabling more detailed idea generation.

[0264] Supporting content creators:

[0265] Content creators can further expand on generated ideas using the rating button and generate new content ideas, which will improve creativity and make idea generation more efficient.

[0266] Examples and prompts

[0267] Examples:

[0268] Initial idea: "Consider introducing new technology to develop new businesses."

[0269] User rating: "Ingenious"

[0270] Generated idea: "By introducing new technology, we will provide a personalized content delivery service using AI."

[0271] Example prompt sentence:

[0272] "When developing new businesses, it is important to think creatively about introducing new technologies."

[0273] In this way, the generative AI generates new ideas based on user evaluations, supporting the creativity of content creators.

[0274] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0275] Step 1:

[0276] The user inputs a theme using a smartphone or head-mounted display. For example, they input a theme such as "Consider introducing new technology for new business development." The input theme is sent to the server.

[0277] Input: The theme entered by the user

[0278] Output: The theme sent to the server

[0279] Step 2:

[0280] The server sends the received theme to a generative AI model (e.g., GPT-3) to generate related ideas and questions. The generative AI model generates prompts based on the theme and outputs corresponding ideas.

[0281] Input: The theme sent to the server

[0282] Output: Ideas and questions generated by the generative AI model

[0283] Step 3:

[0284] The server sends the generated ideas and questions to the user's device, where the user can view the generated ideas via a smartphone or head-mounted display.

[0285] Input: Ideas or questions generated by a generative AI model

[0286] Output: Ideas and questions sent to the user's device

[0287] Step 4:

[0288] The user presses evaluation buttons for the generated ideas, such as "original," "realistic," and "review from a managerial perspective." The information selected by the evaluation button is sent to the server.

[0289] Input: User's rating button selection information

[0290] Output: Rating button selection information sent to the server

[0291] Step 5:

[0292] The server generates a new prompt sentence based on the selection information of the rating button and sends it to the generative AI model again. The generative AI model generates further expanded ideas based on the new prompt sentence.

[0293] Input: Rating button selection information sent to the server

[0294] Output: Augmented ideas generated by the generative AI model

[0295] Step 6:

[0296] The server sends the augmented ideas to the user's device, where the user can view the augmented ideas via a smartphone or head-mounted display.

[0297] Input: Augmented ideas generated by a generative AI model

[0298] Output: The extension idea sent to the user's device

[0299] Step 7:

[0300] The user can continue to hit the rating button and expand on the idea as needed, and the process repeats until the user is satisfied.

[0301] Input: User's rating button selection information

[0302] Output: Further expanded ideas generated by the generative AI model

[0303] In this way, the user can further expand on the generated ideas using the rating buttons, which improves creativity and allows for more efficient idea generation.

[0304] Example 3

[0305] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0306] Conventional brainstreaming support systems allow users to input topics and generate ideas using generative AI, but they lack sufficient integration with web conferencing tools, making it difficult to effectively utilize information obtained from meeting minutes. Furthermore, support for evaluating and expanding on generated ideas is limited, making it difficult for users to obtain the specific, practical ideas they desire. This poses a challenge, reducing the efficiency and effectiveness of brainstreaming.

[0307] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0308] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from a Web UI and a means for linking with a Web conferencing tool, a means for analyzing minutes of the Web conferencing tool and extracting important information, a means for creating and sending prompts to the generative AI model based on the extracted information, and a means for displaying ideas generated by the generative AI model to the user. This makes it possible to effectively utilize information obtained from minutes of the Web conferencing tool to generate specific and practical ideas that users desire.

[0309] The "means for user theme input" refers to a means for providing an interface for users to input specific themes or topics to the system.

[0310] "Generative AI methods" are methods that use artificial intelligence technology to generate related ideas and questions based on an input topic.

[0311] The "evaluation means" is a means for users to evaluate and provide feedback on the generated ideas.

[0312] "Input means from WebUI" refers to the means by which a user inputs information into the system via a web browser.

[0313] "Means for linking with web conferencing tools" refers to the means for linking the system with web conferencing tools and importing meeting minutes and other information into the system.

[0314] "Means for analyzing minutes from a web conferencing tool and extracting important information" refers to means for analyzing minutes obtained from a web conferencing tool and extracting important information from them.

[0315] "Means for creating and sending prompt sentences to a generative AI model" refers to means for creating appropriate prompt sentences for a generative AI model based on extracted information and sending them.

[0316] "Means for displaying ideas generated from a generative AI model to a user" refers to means for displaying ideas generated from a generative AI model to a user.

[0317] The present invention is a brainstreaming support system in which a user, a terminal, and a server work together. A specific embodiment of this system will be described below.

[0318] User Actions

[0319] Users access the system's WebUI using a web browser. The WebUI has input fields such as text boxes and drop-down menus, where users can enter information such as "I want to generate ideas for new business development."

[0320] Device operation

[0321] Users use devices (PCs or smartphones) to launch a web conferencing tool and hold a meeting. The content discussed during the meeting is recorded using the conferencing tool's recording and minutes-creation functions. After the meeting ends, the device uploads the meeting minutes to the server, either automatically or via user operation. The minutes are saved as text files or PDF format.

[0322] Server Processing

[0323] The server receives the uploaded minutes and analyzes them using natural language processing (NLP) technology. Specifically, it uses tools such as Python's NLTK library and SpaCy to extract important information from the minutes, such as "New business development requires the introduction of new technology."

[0324] Based on the extracted information, the server creates a prompt to be sent to the generative AI model. For example, it creates a prompt such as, "What new businesses can be developed by introducing new technology?" The created prompt is sent to the generative AI model via an API.

[0325] A generative AI model (e.g., OpenAI's GPT-3) generates new ideas based on the prompt it receives, and the generated ideas are returned to the server in text format.

[0326] The server receives the ideas returned by the generative AI model and sends them to the device using communication protocols such as HTTP requests or WebSockets.

[0327] Terminal display

[0328] The terminal displays the ideas received from the server to the user. The generated ideas are displayed on the Web UI, allowing the user to review them. The user can provide feedback and request the idea generation again if necessary.

[0329] Specific examples

[0330] 1. The user enters through the WebUI, "I would like you to generate ideas for new business development."

[0331] 2. A user holds a meeting using a web conferencing tool and uploads the minutes to the system.

[0332] 3. The server analyzes the minutes and extracts the information that "new technology needs to be introduced to develop new businesses."

[0333] 4. The server creates a prompt for the generative AI model: "What new businesses can be developed by introducing new technology?"

[0334] 5. The generative AI model generates new ideas and displays them to the user via their device.

[0335] Prompt Sentence Examples

[0336] "Generate ideas about what new businesses can be developed with the introduction of new technologies."

[0337] In this way, the system of the present invention utilizes information obtained from minutes by linking the Web UI and the web conferencing tool, and generates new ideas using the generative AI model. This allows users to obtain specific and practical ideas. The flow of the identification process in Example 3 will be described with reference to Figure 15.

[0338] Step 1:

[0339] The user enters information through the WebUI.

[0340] The user opens a web browser and accesses the system's WebUI. The WebUI has input fields such as text boxes and drop-down menus, where the user enters information such as "I would like you to generate ideas for new business development." The entered information is sent to the server, where the server receives the input data in text format.

[0341] Step 2:

[0342] The device will hold the meeting using a web conferencing tool.

[0343] Users use their devices (PCs or smartphones) to launch a web conferencing tool and hold a meeting. The content discussed during the meeting is recorded using the recording and minutes-creation functions of the conferencing tool. After the meeting ends, the device uploads the minutes to the server, either automatically or via user operation. The minutes are saved as text files or PDF format. The input data is the minutes file, which is received by the server.

[0344] Step 3:

[0345] The server analyzes the minutes and extracts important information.

[0346] The server receives the uploaded minutes and analyzes them using natural language processing (NLP) technology. Specifically, it uses tools such as Python's NLTK library and SpaCy to extract important information from the minutes, such as "New technology needs to be introduced for new business development." The input data is the text of the minutes, and the output data is the extracted important information.

[0347] Step 4:

[0348] The server creates and sends a prompt to the generative AI model.

[0349] The server creates a prompt to be sent to the generative AI model based on the extracted information. For example, it creates a prompt such as, "What new businesses can be developed by introducing new technology?" The created prompt is sent to the generative AI model via an API. The input data is the extracted information, and the output data is the prompt.

[0350] Step 5:

[0351] Generative AI models generate new ideas.

[0352] A generative AI model (e.g., OpenAI's GPT-3) generates new ideas based on the received prompt. The generated ideas are returned to the server in text format. The input data is the prompt, and the output data is the generated ideas.

[0353] Step 6:

[0354] The server transmits the generated ideas to the terminal.

[0355] The server receives the ideas returned by the generative AI model and sends them to the device. The transmission uses communication protocols such as HTTP requests and WebSockets. The input data is the generated ideas, and the output data is the ideas sent to the device.

[0356] Step 7:

[0357] The terminal displays the generated ideas to the user.

[0358] The terminal displays the ideas received from the server to the user. The generated ideas are displayed on the WebUI, allowing the user to review them. The user can provide feedback and request the idea to be generated again if necessary. The input data are the ideas sent from the server, and the output data are the ideas displayed to the user.

[0359] (Application example 3)

[0360] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0361] Conventional brainstorming support systems utilize themes input by users and minutes of meetings linked to web conferencing tools, but they do not support the generation of ideas for specific manufacturing processes or efficiency improvements within factories. Therefore, there is a need for a system that can generate ideas for new manufacturing processes and efficiency improvements based on meeting minutes within factories.

[0362] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for inputting a theme from the user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from the Web UI and a linking means with a Web conferencing tool, and a means for importing minutes of meetings held in the factory and generating ideas for new manufacturing processes and efficiency improvements based on that information. This makes it possible to generate ideas for new manufacturing processes and efficiency improvements based on the minutes of meetings held in the factory.

[0363] The "means for user topic input" is an interface that allows users to input topics for discussion and idea generation into the system.

[0364] "Generative AI methods" are artificial intelligence functions that generate related ideas and questions based on an input topic.

[0365] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion and improvement of the ideas based on the evaluation results.

[0366] "WebUI input means" means a user inputting information into the system through a web user interface.

[0367] "Means for linking with web conferencing tools" refers to the means for linking the system with web conferencing tools and importing meeting minutes and other information into the system.

[0368] "A means of importing minutes from meetings held within the factory and generating ideas for new manufacturing processes and efficiency improvements based on that information" is a function that imports minutes from meetings held within the factory into the system and generates ideas for new manufacturing processes and efficiency improvements based on those minutes.

[0369] The system for implementing this invention includes a means for user input of themes, a generative AI means, an evaluation means, an input means from a Web UI, a means for linking with a Web conferencing tool, and a means for capturing minutes of meetings held within a factory and generating ideas for new manufacturing processes and efficiency improvements based on that information.

[0370] The server provides an interface for users to input a theme. The theme input by the user is sent to the generative AI means, which generates related ideas and questions. The generated ideas are evaluated by the user through the evaluation means, and the ideas are expanded or improved based on the evaluation results.

[0371] The WebUI input method allows users to input information into the system through a web user interface, allowing users to easily input themes and evaluation results.

[0372] The means of linking with web conferencing tools is a means of linking the system with web conferencing tools and incorporating meeting minutes and other information into the system. For example, minutes can be obtained from web conferencing tools such as Zoom, and generative AI can generate new ideas based on that information.

[0373] The means for importing minutes of meetings held within the factory and generating ideas for new manufacturing processes and efficiency improvements based on that information is a function for importing minutes of meetings held within the factory into the system and generating ideas for new manufacturing processes and efficiency improvements based on those minutes. This makes it possible to generate ideas for new manufacturing processes and efficiency improvements based on the minutes of meetings held within the factory.

[0374] For example, the following prompts can be fed to a generative AI model:

[0375] Example prompt sentence:

[0376] Minutes: The production line needs to be made more efficient. In particular, there is a bottleneck in the assembly process. Please propose ideas for solving this problem by introducing new technologies or methods.

[0377] Based on this prompt, a generative AI might generate ideas like:

[0378] 1. The introduction of robotic arms will advance automation of the assembly process.

[0379] 2. Introduce a quality inspection system using AI to enable early detection of defective products.

[0380] 3. Redesign the production line layout to improve work efficiency.

[0381] In this way, ideas for new manufacturing processes and efficiency improvements can be generated based on the minutes of meetings held within the factory.

[0382] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0383] Step 1:

[0384] The user inputs a topic. The user inputs a topic for discussion or idea generation through a web user interface. The input topic is sent to the server. The input data is in text format, and the server receives it and passes it on to the next process.

[0385] Step 2:

[0386] The server generates ideas and questions using generative AI means. The server inputs the theme received in step 1 into the generative AI model to generate related ideas and questions. The generative AI model processes the data based on the theme and outputs related ideas and questions in text format.

[0387] Step 3:

[0388] The server sends the generated ideas to the evaluation means. The server then sends the ideas and questions output from the generative AI model to the evaluation means. The evaluation means provides an interface for users to evaluate the ideas. Users evaluate the ideas using evaluation buttons such as "Be original," "Be realistic," and "Review from a management perspective."

[0389] Step 4:

[0390] The user evaluates the ideas. The user evaluates the generated ideas through the evaluation means. The evaluation results are sent to the server and used for the next process. The evaluation data is in numerical or text format, and the server receives it and passes it on to the next process.

[0391] Step 5:

[0392] The server expands or improves the idea based on the evaluation results. The server expands or improves the idea by again using the generative AI model based on the evaluation results received from the user. The generative AI model uses the evaluation results as input data to expand or improve the idea.

[0393] Step 6:

[0394] The server retrieves the minutes using a means of linking with the web conferencing tool. The server retrieves the minutes of the meeting from the web conferencing tool (for example, Zoom). The retrieved minutes are in text format, and the server passes them on to the next process.

[0395] Step 7:

[0396] The server inputs the minutes into a generative AI means to generate ideas for new manufacturing processes and efficiency improvements. The server inputs the acquired minutes into a generative AI model to generate ideas for new manufacturing processes and efficiency improvements based on the minutes. The generative AI model analyzes the contents of the minutes and outputs related ideas in text format.

[0397] Step 8:

[0398] The server provides the generated ideas to the user. The server provides ideas for new manufacturing processes and efficiency improvements output from the generative AI model to the user. The user can review these ideas through a web user interface and provide evaluation and feedback as necessary.

[0399] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the identification processing unit 290 estimates the user's emotion using the emotion identification model 59, and performs a calculation using the user's emotion.

[0400] A specific process may also be performed.

[0401] "Example 1"

[0402] One embodiment of the present invention is a brainstreaming assistance system that includes an emotion engine that recognizes a user's emotions. The system receives a topic input from the user and generates ideas and questions related to the topic. The generated ideas are evaluated based on the user's emotions, and new ideas are generated based on the evaluation results. Specifically, if the user expresses joy, positive ideas that match the emotion are generated. Conversely, if the user expresses sadness, ideas that propose solutions corresponding to the emotion are generated.

[0403] "Example 2"

[0404] Another embodiment of the present invention is a brainstreaming support system in which an emotion engine adjusts the evaluation criteria of an evaluation means. In this system, the evaluation criteria are adjusted based on the user's emotions. Specifically, when the user is in an excited state, the evaluation criteria are set high to match the user's emotions, making it easier to evaluate more challenging ideas. Conversely, when the user is in a calm state, the evaluation criteria are set low to match the user's emotions, making it easier to evaluate more realistic ideas.

[0405] "Example 3"

[0406] Another embodiment of the present invention is a brainstreaming support system that utilizes information from minutes of a web conferencing tool. In this system, new ideas are generated based on information obtained from the minutes of a web conferencing tool. Specifically, an emotion engine analyzes the user's emotional information recorded in the minutes, and idea generation and evaluation adjustments are performed based on the results. For example, if the minutes record "expectations for new business development," positive ideas that match those expectations are generated based on that information.

[0407] The processing flow of each embodiment will be described below.

[0408] "Example 1"

[0409] Step 1: Receive theme input from the user.

[0410] Step 2: Generate ideas and questions related to the theme.

[0411] Step 3: Recognize the user's emotions with the emotion engine.

[0412] Step 4: Evaluate the generated ideas based on the perceived emotions.

[0413] Step 5: Generate new ideas based on the evaluation results.

[0414] "Example 2"

[0415] Step 1: Recognize the user's emotions with the emotion engine.

[0416] Step 2: Adjust the rating scale of the assessment instrument based on the perceived emotions.

[0417] Step 3: Evaluate the ideas based on the adjusted evaluation criteria.

[0418] Step 4: Generate new ideas based on the evaluation results.

[0419] "Example 3"

[0420] Step 1: Get information from the meeting minutes in your web conferencing tool.

[0421] Step 2: Generate new ideas based on the information obtained.

[0422] Step 3: Analyze the user's emotional information recorded in the minutes using the emotion engine.

[0423] Step 4: Adjust idea generation and evaluation based on the analysis results.

[0424] Example 1

[0425] Next, a description will be given of Example 1 of Form 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."

[0426] Conventional brainstorming support systems generate ideas and questions without considering the user's emotions, making it difficult to provide appropriate ideas and questions that reflect the user's emotional state. Furthermore, the generated ideas and questions are not evaluated based on the user's emotions, which can lead to a decrease in user satisfaction. Furthermore, there is a problem of insufficient integration with meeting tools and the inability to utilize information from meeting minutes, which reduces the efficiency of brainstorming.

[0427] 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.

[0428] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an emotion recognition means for recognizing the user's emotions, a means for evaluating ideas and questions based on the emotion information and generating new ideas and questions, and a means for linking the input means with the conference tool. This makes it possible to provide appropriate ideas and questions according to the user's emotional state, thereby improving user satisfaction. Furthermore, by utilizing information from the minutes of the conference tool, the efficiency of brainstorming can be improved.

[0429] The "means for user theme input" is an interface that allows the user to input the brainstorming theme.

[0430] A "generative AI method" is an artificial intelligence mechanism that generates related ideas and questions based on a topic entered by the user.

[0431] The "evaluation means" is a function for evaluating the generated ideas and questions and providing feedback to the user.

[0432] "Emotion recognition means" is a technology for recognizing a user's emotional state by analyzing their facial expressions and tone of voice.

[0433] The "means for evaluating ideas and questions based on emotional information and generating new ideas and questions" is a function for evaluating generated ideas and questions based on the recognized emotional information of the user, and further generating new ideas and questions.

[0434] "Input means" refers to an interface that allows a user to input information to the system.

[0435] "Means of collaboration with conference tools" refers to a function that allows collaboration with conference tools to utilize information such as minutes.

[0436] This invention is a brainstreaming support system that generates related ideas and questions based on a topic input from a user, and evaluates and expands them according to the user's emotional state. Specific embodiments of this system are described below.

[0437] First, the user enters a topic into the device's input field. For example, they might enter "new business development." The device then sends this topic to the server. The server then uses a generative AI model (for example, a general natural language processing model) to generate ideas and questions related to the topic. Examples of generated ideas and questions include the following:

[0438] Example questions:

[0439] "What are the market needs for new business development?"

[0440] "What resources are needed for new business development?"

[0441] Example ideas:

[0442] "We will utilize our existing customer base to develop new businesses."

[0443] "When developing new businesses, we consider introducing new technologies."

[0444] The generated ideas and questions are sent from the server to the device. The device recognizes the user's emotions using emotion recognition means (e.g., general emotion recognition software). It analyzes the user's facial expressions and tone of voice to determine their emotional state. For example, if the user is smiling, it recognizes the emotion of joy.

[0445] The device sends the recognized emotional information to the server. The server evaluates the generated ideas and questions based on the emotional information and generates new ideas and questions. For example, if the user expresses joy, the server generates positive ideas that match that emotion. Conversely, if the user expresses sadness, the server generates ideas that propose solutions that correspond to that emotion.

[0446] Finally, the server sends the evaluated ideas and questions to the device, which displays them to the user, who can use them to further their brainstorming.

[0447] As a concrete example, if a user inputs the topic "new business development," the generative AI model will generate questions and ideas such as the following:

[0448] Example questions:

[0449] "What are the market needs for new business development?"

[0450] "What resources are needed for new business development?"

[0451] Example ideas:

[0452] "We will utilize our existing customer base to develop new businesses."

[0453] "When developing new businesses, we consider introducing new technologies."

[0454] An example of a prompt sentence might be:

[0455] "Generate ideas for new business development."

[0456] "Generate questions about market needs for new business development."

[0457] In this way, a system is realized in which the server, terminals, and users work together to support brainstorming.

[0458] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0459] Step 1:

[0460] The user inputs a theme.

[0461] The user inputs a theme into the input field of the terminal and clicks the send button. For example, the user inputs "New Business Development." The input data is the theme text.

[0462] Step 2:

[0463] The device sends the theme to the server.

[0464] The terminal uses an HTTP POST request to send the input theme "New Business Development" to the server. The input data is the theme text, and the output data is the request to the server.

[0465] Step 3:

[0466] The server uses a generative AI model to generate relevant ideas and questions.

[0467] The server inputs the received theme into a generative AI model to generate related ideas and questions. For example, it generates questions such as "What are the market needs for new business development?" and "What resources are needed for new business development?", as well as ideas such as "Leverage the existing customer base for new business development" and "Consider introducing new technology for new business development." The input data is the theme text, and the output data is a list of generated ideas and questions.

[0468] Step 4:

[0469] The server sends generated ideas and questions to the device.

[0470] The server sends the generated ideas and questions to the terminal in JSON format. The input data is the list of generated ideas and questions, and the output data is the response to the terminal.

[0471] Step 5:

[0472] The terminal recognizes the user's emotions using an emotion engine.

[0473] The device uses the emotion engine to analyze the user's facial expression and tone of voice to recognize their emotional state. For example, if the user is smiling, the emotion of joy is recognized. The input data is the user's facial expression and tone of voice, and the output data is the recognized emotional information.

[0474] Step 6:

[0475] The device transmits the recognized emotion information to the server.

[0476] The device sends the recognized emotion information to the server in JSON format. The input data is the recognized emotion information, and the output data is the request to the server.

[0477] Step 7:

[0478] The server evaluates ideas and questions based on the emotional information and generates new ideas and questions.

[0479] The server evaluates the generated ideas and questions based on the received emotional information. For example, if the user expresses happiness, it generates positive ideas that match that emotion. Conversely, if the user expresses sadness, it generates ideas that propose solutions that correspond to that emotion. The input data is the emotional information and a list of generated ideas and questions, and the output data is a list of evaluated ideas and questions.

[0480] Step 8:

[0481] The server sends the final ideas and questions to the device.

[0482] The server finally sends the evaluated ideas and questions to the terminal in JSON format. The input data is the list of evaluated ideas and questions, and the output data is the response to the terminal.

[0483] Step 9:

[0484] The device displays the final ideas and questions to the user.

[0485] The terminal displays the final ideas and questions it receives to the user, who can then use these ideas and questions to further their brainstorming. The input data is the list of evaluated ideas and questions, and the output data is what is displayed to the user.

[0486] (Application example 1)

[0487] Next, a description will be given of Application Example 1 of Embodiment 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."

[0488] Conventional brainstreaming support systems can generate ideas and questions based on user input, but they do not take user emotions into account when generating or evaluating ideas, making it difficult to provide appropriate ideas that reflect the user's emotions. Furthermore, there is a lack of concrete means for generating ideas for new production processes and efficiency improvements within factories, making them less practical for on-site use.

[0489] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conferencing tool, an emotion recognition means for recognizing the user's emotions, a means for evaluating the generated ideas based on the emotions and generating new ideas, and a means installed in a robot for generating ideas for new production processes and efficiency improvements in a factory. This makes it possible to provide appropriate ideas according to the user's emotions, thereby increasing practicality in a factory.

[0490] The "user theme input means" is an interface that allows a user to input a specific theme or topic.

[0491] "Generative AI methods" are artificial intelligence functions that generate relevant ideas and questions based on a topic entered by the user.

[0492] The "evaluation means" is a function for expanding and evaluating the generated ideas.

[0493] "Input means from WebUI" means a means for a user to enter input through a web user interface.

[0494] "Means for linking with web conferencing tools" refers to means for linking with web conferencing tools to share information and utilize information from meeting minutes.

[0495] "Emotion recognition means" is a function for recognizing the user's emotions.

[0496] The "means for evaluating ideas generated based on emotions and generating new ideas" is a function for evaluating ideas generated based on the user's emotions and generating new ideas based on the results.

[0497] "Means installed in robots to generate ideas for new production processes and efficiency improvements within factories" refers to functions installed in robots to generate ideas for new production processes and efficiency improvements within factories.

[0498] The system for implementing this invention includes a means for inputting a theme from a user, a generative AI means, an evaluation means, an input means from a Web UI, a means for linking with a Web conferencing tool, an emotion recognition means, a means for evaluating ideas generated based on emotions and generating new ideas, and a means installed on a robot for generating ideas for new production processes and efficiency improvements within a factory.

[0499] Program processing explanation

[0500] The server provides an interface for receiving topic input from a user. Once the user inputs a topic, the server uses a generative AI mechanism to generate ideas and questions related to the topic. The generative AI mechanism utilizes a generative AI model, such as the OpenAI API, to generate relevant ideas and questions based on the topic.

[0501] The generated ideas are expanded and evaluated using an evaluation tool that provides evaluation buttons such as "original," "realistic," and "review from a management perspective," allowing users to evaluate the generated ideas.

[0502] Furthermore, the system uses an emotion recognition mechanism to recognize the user's emotions. The emotion recognition mechanism analyzes the user's emotions using the Emotion Recognition library and the camera. Based on the recognized emotions, the generated ideas are evaluated and a mechanism for generating new ideas is activated. For example, if the user shows an emotion of joy, a positive idea is added.

[0503] This also includes a means installed on the robot to generate ideas for new production processes and efficiency improvements within the factory. The robot patrols the factory, receives topic input from workers, and uses generative AI means to generate related ideas and questions. The generated ideas are evaluated based on the workers' sentiment, and new ideas are added as needed.

[0504] Specific examples

[0505] For example, if a user inputs the theme "improving the efficiency of a new production line," the generative AI method will generate ideas and questions such as the following:

[0506] Example prompt sentence:

[0507] Theme: Improving efficiency of new production lines

[0508] Generate relevant ideas and questions.

[0509] Ideas and questions generated:

[0510] Where are the bottlenecks on the production line?

[0511] What technologies are needed to advance automation?

[0512] How can you reduce the burden on workers?

[0513] Add positive ideas.

[0514] Introducing a new robotic arm to improve work efficiency.

[0515] Increase worker motivation by increasing break time.

[0516] In this way, it becomes possible to provide appropriate ideas that correspond to the user's emotions, increasing practicality within the factory.

[0517] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0518] Step 1:

[0519] The user inputs a theme. The user inputs a theme through a web user interface (WebUI). The input theme is sent to the server. The input data is text information of the theme.

[0520] Step 2:

[0521] The server receives the input theme and passes it to the generative AI means. The generative AI means uses a generative AI model such as the OpenAI API to generate ideas and questions related to the theme. The input data is text information about the theme, and the output data is text information about the generated ideas and questions.

[0522] Step 3:

[0523] The server passes the generated ideas and questions to the evaluation means. The evaluation means provides evaluation buttons such as "original," "realistic," and "review from a managerial perspective," allowing users to evaluate the generated ideas. The input data is the text information of the generated ideas and questions, and the output data is the evaluation results by the users.

[0524] Step 4:

[0525] The server uses an emotion recognition means to recognize the user's emotions. The emotion recognition means analyzes the user's emotions using the Emotion Recognition library and a camera. The input data is the user's facial image and voice data, and the output data is information on the recognized emotions.

[0526] Step 5:

[0527] The server evaluates the generated ideas based on the recognized emotions and uses a means to generate new ideas. For example, if the user expresses joy, a positive idea is added. The input data is the recognized emotion information and text information of the generated ideas or questions, and the output data is text information of the new ideas evaluated based on the emotions.

[0528] Step 6:

[0529] The server uses the means installed on the robot to generate ideas for new production processes and efficiency improvements within the factory. The robot patrols the factory, receives topic input from workers, and generates related ideas and questions using generative AI means. The input data is text information on the topic from the workers, and the output data is text information of the generated ideas and questions.

[0530] Step 7:

[0531] The server presents the generated ideas and questions to the workers, who can then consider new production processes and ways to improve efficiency based on the presented ideas and questions. The input data is the text information of the generated ideas and questions, and the output data is the feedback and new suggestions from the workers.

[0532] Example 2

[0533] Next, a description will be given of Example 2 of Form 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."

[0534] Conventional brainstreaming support systems have had problems with providing appropriate feedback and expansion to ideas generated by users, resulting in insufficient improvement in the quality and creativity of ideas. Furthermore, because evaluation criteria are set without taking the user's emotional state into account, there is also the issue of not being able to appropriately evaluate ideas according to the user's state. Furthermore, there is also the issue of insufficient integration with web conferencing tools, making it difficult to effectively utilize ideas generated during meetings and meeting minutes.

[0535] 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.

[0536] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, a means for generating a prompt sentence based on the type of evaluation button, a means for sending the generated prompt sentence to the generative AI means, a means for displaying new ideas returned by the generative AI means to the user, an emotion engine means for analyzing the user's emotional state, a means for adjusting evaluation criteria based on the analysis results of the emotion engine means, and a means for inputting from a Web UI and for linking with a Web conferencing tool. This enables the setting of appropriate evaluation criteria according to the user's emotional state and the generation and expansion of high-quality ideas by the generative AI. Furthermore, linking with a Web conferencing tool allows for the effective use of ideas and minutes generated during meetings.

[0537] "User theme input means" is an interface that allows users to input themes such as new business development into the system.

[0538] "Generative AI methods" are artificial intelligence functions that generate relevant ideas and questions based on a topic entered by the user.

[0539] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion of the ideas based on the evaluation.

[0540] The "evaluation button" is a button for making evaluations such as "creative," "realistic," and "review from a management perspective."

[0541] The "means for generating a prompt sentence" is a function that generates a prompt sentence to be sent to the generative AI means based on the type of evaluation button pressed by the user.

[0542] The "means for sending to the generative AI means" is a function for sending the generated prompt sentence to the generative AI means.

[0543] "Means for displaying new ideas returned by the generative AI means to the user" refers to a function that receives new ideas returned by the generative AI means and displays them on the user's device.

[0544] The "emotion engine means" is a function for analyzing the user's emotional state.

[0545] The "means for adjusting the evaluation criteria" is a function for adjusting the evaluation criteria based on the analysis results of the emotion engine means.

[0546] "Input means from WebUI" is a function that allows users to input information into the system through a web interface.

[0547] "Means for linking with web conferencing tools" refers to a function that links with web conferencing tools and allows ideas and minutes raised during meetings to be imported into the system.

[0548] This invention is a system that uses a generative AI means to generate ideas and questions related to a theme input by a user, such as new business development, and supports the expansion of the generated ideas. Specific embodiments of this system are described below.

[0549] Hardware and software used

[0550] Server: The central processing unit of the system, running the generative AI model, storing data, and providing the user interface.

[0551] Terminal: A device operated by a user, such as a PC or smartphone.

[0552] Generative AI models: Use generative AI models such as OpenAI's GPT-4.

[0553] Emotion engine: Software for analyzing a user's emotional state, for example, using the emotion recognition API from Microsoft® Azure® Cognitive Services.

[0554] System processing flow

[0555] 1. Users enter their ideas

[0556] The user uses a terminal to input ideas for new business development into the system's input form. For example, the user might input, "We are considering introducing new technology to develop new businesses."

[0557] 2. The user presses the rating button

[0558] For the ideas entered by the user, they press one of the evaluation buttons, such as "Be original," "Be realistic," or "Review from a management perspective."

[0559] 3. The server generates a prompt

[0560] The server generates a prompt to send to the generative AI model based on the type of evaluation button pressed by the user. For example, if the "Be creative" button is pressed, the server generates a prompt such as "What kind of creative business will become possible with the introduction of new technology?"

[0561] 4. The server sends a prompt to the generative AI model

[0562] The server sends the generated prompt to the generative AI model, which runs on the cloud.

[0563] 5. Generative AI models generate new ideas

[0564] The generative AI model generates new ideas based on the prompt, such as "The introduction of new technology will enable personalized marketing using AI."

[0565] 6. The server displays the generated ideas to the user

[0566] The server receives new ideas returned by the generative AI model and displays them on the user's device.

[0567] 7. Emotion Engine Analyzes User Emotions (Alternative Embodiment)

[0568] While the user is typing their idea, the emotion engine analyzes their facial expressions and voice to determine whether they are excited or calm.

[0569] 8. Server Adjusts Evaluation Criteria (Alternative Embodiment)

[0570] The server receives the analysis results of the emotion engine, and if the user is in an excited state, it sets the evaluation criteria high, making it easier for challenging ideas to be evaluated. Conversely, if the user is in a calm state, it sets the evaluation criteria low, making it easier for realistic ideas to be evaluated.

[0571] Specific examples

[0572] Example 1: Expanding an idea

[0573] User action: The user enters the idea "Consider introducing new technology to develop new businesses" and presses the "Be original" rating button.

[0574] Server processing: The server sends a prompt to the generative AI model: "What kind of creative business will become possible with the introduction of new technology?"

[0575] Response of the generative AI model: The generative AI model generates a new idea, such as "The introduction of new technology will make personalized marketing using AI possible."

[0576] Displaying the results: The server displays the generated ideas on the user's device.

[0577] Example 2: Using the Emotion Engine

[0578] User action: The user inputs the idea, "Consider introducing new technology to develop new businesses," and the emotion engine detects the user's state of excitement.

[0579] Server processing: The server sets the evaluation criteria high based on the analysis results of the emotion engine and sends a prompt to the generative AI model asking, "What challenging business will become possible with the introduction of new technology?"

[0580] Response from the generative AI model: The generative AI model generates challenging ideas such as "The introduction of new technologies will make it possible to build fully automated smart cities."

[0581] Displaying the results: The server displays the generated ideas on the user's device.

[0582] Prompt Sentence Examples

[0583] "What kind of creative business will become possible with the introduction of new technology?"

[0584] "What practical businesses will become possible with the introduction of new technologies?"

[0585] "What benefits does the introduction of new technology bring from the perspective of management?"

[0586] The above is a specific embodiment of this system.

[0587] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0588] Step 1:

[0589] The user inputs an idea.

[0590] The user opens a browser on their device and accesses the system's web page. They enter "We are considering introducing new technology for new business development" into the input form. The entered data is sent from the device to the server.

[0591] Input: User-entered ideas

[0592] Output: Idea data sent to the server

[0593] Step 2:

[0594] The user presses the rating button.

[0595] The user clicks one of the rating buttons, such as "Be original," "Be realistic," or "Review from a management perspective." When the button is clicked, the information is sent from the terminal to the server.

[0596] Input: Information about the rating button pressed by the user

[0597] Output: Rating button information sent to the server

[0598] Step 3:

[0599] The server generates a prompt.

[0600] Based on the information on the evaluation buttons received by the server, the server generates a prompt to send to the generative AI model. For example, if the "Be creative" button is pressed, the server generates a prompt such as "What kind of creative business will become possible with the introduction of new technology?"

[0601] Input: Rating button information

[0602] Output: Generated prompt statement

[0603] Step 4:

[0604] The server sends a prompt to the generative AI model.

[0605] The server sends the generated prompt to the generative AI model, which runs on the cloud.

[0606] Input: Generated prompt statement

[0607] Output: The prompt sent to the generative AI model

[0608] Step 5:

[0609] Generative AI models generate new ideas.

[0610] The generative AI model analyzes the prompt and generates new ideas, such as "The introduction of new technology will enable personalized marketing using AI." The generated ideas are returned to the server.

[0611] Input: prompt statement

[0612] Output: New ideas generated

[0613] Step 6:

[0614] The server displays the generated ideas to the user.

[0615] The server receives the new ideas returned by the generative AI model and sends them to the user's device, which then displays the new ideas on its screen.

[0616] Input: Generated new ideas

[0617] Output: The idea displayed on the user's device

[0618] Step 7:

[0619] An emotion engine analyzes the user's emotions (another embodiment).

[0620] While the user is inputting their idea, the emotion engine analyzes their facial expressions and voice to determine whether they are excited or calm, and the analysis results are sent to the server.

[0621] Input: User facial and voice data

[0622] Output: Analysis results by the emotion engine

[0623] Step 8:

[0624] The server adjusts the evaluation criteria (alternative embodiment).

[0625] The server receives the analysis results of the emotion engine, and if the user is in an excited state, it sets the evaluation criteria high, making it easier for challenging ideas to be evaluated. Conversely, if the user is in a calm state, it sets the evaluation criteria low, making it easier for realistic ideas to be evaluated.

[0626] Input: Analysis results of emotion engine

[0627] Output: adjusted metrics

[0628] (Application example 2)

[0629] Next, a description will be given of Application Example 2 of Form 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."

[0630] Conventional brainstorming support systems evaluate ideas without considering the user's emotional state, making it difficult to generate appropriate ideas that reflect the user's emotions. Furthermore, since the system does not take into consideration use on mobile devices such as smartphones, users are unable to easily generate ideas anywhere.

[0631] 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.

[0632] In this invention, the server includes a means for inputting a theme from the user, a generative AI means for generating ideas and questions related to the theme, and an evaluation means for supporting the expansion of the generated ideas. This makes it possible to detect the emotional state of the user and adjust the evaluation criteria based on that. In addition, by including an application means to be installed on a smartphone, users can easily generate ideas anywhere.

[0633] The "theme input means" is an interface that allows users to input brainstorming themes or topics.

[0634] "Generative AI means" is an artificial intelligence function that automatically generates ideas and questions related to an input topic.

[0635] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion of the ideas based on the evaluation.

[0636] "WebUI input means" means a means by which a user inputs information through a web user interface.

[0637] "Means of integration with web conferencing tools" refers to means of integrating with web conferencing tools to share information and utilize data such as minutes.

[0638] The "emotion engine means" is a function for detecting the user's emotional state and adjusting the system's operation based on that information.

[0639] The "means for adjusting evaluation criteria" is a function that dynamically changes the evaluation criteria for ideas based on the user's emotional state.

[0640] The "application means installed on a smartphone" refers to the application functions that are installed on a smartphone and that can be used by the user anywhere.

[0641] As an embodiment of the present invention, the following system can be constructed.

[0642] First, the user inputs a brainstorming theme using an application installed on the smartphone. The theme input unit receives the theme input by the user and transmits it to the server.

[0643] The server uses a generative AI means to generate ideas and questions related to the input topic. This generative AI means can use a generative AI model such as GPT-3. The generated ideas are displayed on the user's smartphone.

[0644] Next, the user presses rating buttons for the displayed ideas, such as "original," "realistic," and "review from a management perspective." The rating tool receives the user's rating and helps expand the idea based on it.

[0645] Furthermore, an emotion engine means detects the user's emotional state. An emotion detection library such as Affectiva can be used as the emotion engine means. Based on the emotional state, an evaluation criterion adjustment means operates to set an appropriate evaluation criterion according to the user's emotion.

[0646] The system also includes a means for inputting information from a Web UI and a means for linking with a web conferencing tool, which can extract information from meeting minutes and use it for idea generation.

[0647] As a concrete example, if a user inputs the theme "Consider introducing new technologies for new business development," the generative AI means can generate the following prompt sentence:

[0648] Example prompt sentence:

[0649] "When developing a new business, we consider introducing new technologies. What kind of technologies should we introduce as a creative approach?"

[0650] Based on this prompt, the generative AI model generates new ideas and provides them to the user. When the user presses the "Be creative" evaluation button, the generative AI means generates new ideas such as "What kind of creative business can be made possible by introducing new technology?"

[0651] In this way, a system is realized in which generative AI provides new ideas based on the user's emotional state and evaluation criteria.

[0652] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0653] Step 1:

[0654] The user launches the application installed on their smartphone and enters the brainstorming topic.

[0655] Input: Theme entered by the user (e.g., "Consider introducing new technology for new business development")

[0656] Output: The input theme is sent to the server.

[0657] Specific behavior: The user enters a theme into the application's input field and presses the "Submit" button.

[0658] Step 2:

[0659] The server uses generative AI tools to generate ideas and questions related to the input topic.

[0660] Input: The theme entered by the user

[0661] Output: Generated ideas and questions (e.g., "What unique business ventures will be made possible by introducing new technologies?")

[0662] How it works: The server inputs a theme as a prompt into a generative AI model such as GPT-3 and retrieves the generated ideas.

[0663] Step 3:

[0664] The generated ideas are displayed on the user's smartphone.

[0665] Input: Generated ideas and questions

[0666] Output: Ideas and questions displayed on the smartphone screen

[0667] How it works: The server sends the generated ideas to the smartphone, where the application displays them.

[0668] Step 4:

[0669] Users press rating buttons for the displayed ideas, such as "original," "realistic," and "review from a management perspective."

[0670] Input: User rating (e.g., "creatively")

[0671] Output: The evaluation result is sent to the server.

[0672] Specific behavior: The user selects a rating button and presses the "Submit" button.

[0673] Step 5:

[0674] The server uses an emotion engine means to detect the user's emotional state.

[0675] Input: User emotion data (e.g., input from camera or microphone)

[0676] Output: Detected emotional state (e.g., "excited")

[0677] What it does: The server uses an emotion detection library such as Affectiva to analyze the user's emotional state.

[0678] Step 6:

[0679] A means operates to adjust the evaluation criteria based on the emotional state.

[0680] Input: Detected emotional state

[0681] Output: Adjusted evaluation criteria (e.g., "creatively")

[0682] Specific operation: The server resets the evaluation criteria according to the emotional state.

[0683] Step 7:

[0684] The server generates new ideas based on the evaluation criteria.

[0685] Input: Adjusted criteria, initial ideas

[0686] Output: New ideas (e.g., "What unique business ventures can be made possible by introducing new technology?")

[0687] Specific operation: The server again inputs the prompt into the generative AI model to generate new ideas.

[0688] Step 8:

[0689] New ideas are displayed on the user's smartphone.

[0690] Input: Newly generated ideas

[0691] Output: New ideas displayed on a smartphone screen

[0692] What it does: The server sends new ideas to the smartphone, and the application displays them.

[0693] Example 3

[0694] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0695] Conventional brainstreaming support systems primarily generate ideas based on user input and are unable to utilize meeting minutes from web conferencing tools. As a result, important information and ideas discussed during meetings are not fully utilized, making efficient idea generation difficult. Furthermore, support for evaluating and expanding on generated ideas is insufficient, making it difficult for users to effectively utilize the generated ideas.

[0696] The identification process by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes a theme input means from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conference tool, a means for acquiring minutes data from the Web conference tool, a means for analyzing the acquired minutes data and extracting important information, a means for generating and sending prompt sentences to the generative AI model based on the extracted information, and a means for saving the generated ideas. This makes it possible to efficiently generate new ideas by utilizing the minutes data of the Web conference tool and support evaluation and expansion of the generated ideas.

[0697] The "user topic input means" is an interface that allows a user to input information about a particular topic or theme.

[0698] "Generative AI methods" are artificial intelligence functions that generate related ideas and questions based on an input topic.

[0699] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion and improvement of the ideas based on the evaluation results.

[0700] "WebUI input means" means a user inputting information through a web user interface.

[0701] "Means of linking with web conferencing tools" refers to a function that links the system with web conferencing tools to acquire and utilize information during meetings.

[0702] "Means for obtaining meeting minutes data from a web conferencing tool" refers to a function for automatically obtaining meeting minutes data from a web conferencing tool.

[0703] The "means for analyzing the acquired minutes data and extracting important information" is a function for analyzing the acquired minutes data and extracting important information that was discussed during the meeting.

[0704] "Means for generating and sending prompt sentences to a generative AI model based on extracted information" refers to a function for generating and sending prompt sentences to a generative AI model based on extracted information.

[0705] "Means for saving generated ideas" refers to a function for saving ideas generated from a generative AI model in a database, etc.

[0706] This invention is a system that includes a means for user theme input, a generative AI means, an evaluation means, an input means from a Web UI, a means for linking with a web conferencing tool, a means for acquiring minutes data from the web conferencing tool, a means for analyzing the acquired minutes data and extracting important information, a means for generating and sending a prompt sentence to a generative AI model based on the extracted information, and a means for saving the generated ideas.

[0707] Server Operation

[0708] The server first obtains the minutes data from the web conferencing tool (e.g., a general web conferencing tool). To do this, it uses the web conferencing tool's API. The obtained minutes data is then analyzed using a natural language processing library (e.g., NLTK or SpaCy). As a result of the analysis, important keywords and phrases are extracted.

[0709] Next, the server generates a prompt to be sent to a generative AI model (such as OpenAI's GPT-3) based on the extracted information. For example, if the minutes contain the information that "new technology needs to be introduced to develop new businesses," the server generates a prompt that asks, "What new businesses can be developed by introducing new technologies?"

[0710] The generated prompt sentences are sent to a generative AI model to generate new ideas, which are then stored in a database by the server and later provided to the user.

[0711] Device behavior

[0712] The device sends information entered by the user through the WebUI to the server. For example, the user enters specific questions or requests regarding new business development. The device also receives ideas generated by the server and displays them to the user. The user can then provide further feedback based on the displayed ideas, which is also sent from the device to the server.

[0713] User Actions

[0714] Users input information about new business development through the Web UI. For example, they can enter specific questions such as, "I'm looking for ideas for introducing new technology." Users also hold meetings using a web conferencing tool, and the minutes of those meetings are imported into the system. Users can then review the generated ideas and provide feedback as needed.

[0715] Specific examples

[0716] 1. Minutes: "New business development requires the introduction of new technology."

[0717] 2. Prompt for the generative AI model: "What new businesses can be developed by introducing new technologies?"

[0718] A generative AI model might generate ideas like the following based on this prompt:

[0719] "Development of a customer support system using AI"

[0720] "Building a supply chain management system using blockchain technology"

[0721] In this way, the system of the present invention utilizes the minutes data of the web conference tool and generates new ideas using the generative AI model. This allows users to efficiently obtain ideas for new businesses. The flow of the identification process in Example 3 will be described with reference to Figure 21.

[0722] Step 1:

[0723] The server obtains the minutes data from the web conferencing tool. Specifically, it downloads the minutes data of the meeting using the web conferencing tool's API. The input is authentication information such as the meeting ID and API key, and the output is the obtained minutes data.

[0724] Step 2:

[0725] The server analyzes the acquired minutes data. Specifically, it performs text analysis using a natural language processing library (e.g., NLTK or SpaCy). The input is the minutes data, and the output is the extracted important keywords and phrases.

[0726] Step 3:

[0727] The server generates a prompt to send to the generative AI model based on the analysis results. For example, if the information includes the message, "New business development requires the introduction of new technology," it generates a prompt such as, "What kind of new business can be developed by introducing new technology?" The input is the extracted keywords and phrases, and the output is the generated prompt.

[0728] Step 4:

[0729] The server sends the generated prompt to a generative AI model (e.g., OpenAI's GPT-3) via an API request. The input is the prompt, and the output is the generated idea.

[0730] Step 5:

[0731] The server stores the ideas returned by the generative AI model in a database by executing an INSERT query against the database. The input is the generated idea, and the output is confirmation of the stored idea.

[0732] Step 6:

[0733] The terminal sends the information entered by the user through the WebUI to the server. Specifically, the user enters information into an input form and presses the send button. The input is the information entered by the user, and the output is the information sent to the server.

[0734] Step 7:

[0735] The terminal receives the generated ideas from the server and displays them to the user. Specifically, it receives the response from the server and displays it on the WebUI. The input is the idea received from the server, and the output is the idea displayed to the user.

[0736] Step 8:

[0737] The terminal sends the feedback provided by the user to the server. Specifically, the user enters information into the feedback form and presses the send button. The input is the feedback entered by the user, and the output is the feedback sent to the server.

[0738] Step 9:

[0739] The user inputs information about new business development through the WebUI. Specifically, the user enters information into an input form and presses the send button. The input is the information entered by the user, and the output is the information sent to the terminal.

[0740] Step 10:

[0741] A user holds a meeting using a web conferencing tool. Specifically, the user starts a meeting and minutes are automatically recorded. The input is the audio and text of the meeting, and the output is the recorded minutes data.

[0742] Step 11:

[0743] The user reviews the generated ideas displayed on the terminal and provides feedback. Specifically, the user evaluates the displayed ideas, enters information in a feedback form, and presses the submit button. The input is the displayed idea and the user's feedback, and the output is the feedback sent to the terminal.

[0744] (Application example 3)

[0745] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0746] Conventional brainstreaming support systems rely on user input of themes and the generation of ideas using generative AI, but they do not fully utilize the content of discussions in meetings or the emotional information of participants, which limits the quality and realism of the generated ideas. Furthermore, evaluations and proposals of generated ideas tend to be subjective, making it difficult to efficiently select the most useful ideas.

[0747] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conferencing tool, an analysis means for analyzing the contents of the minutes and extracting keywords and emotional information, an idea generation means for generating new ideas based on the extracted information, and an evaluation and proposal means for evaluating the generated ideas and proposing the most useful ideas. This enables the generation of high-quality, realistic ideas based on the contents of discussions in meetings and the emotional information of participants, and the efficient evaluation and proposal of ideas.

[0748] The "means for user topic input" is an interface that allows users to input topics for discussion and idea generation into the system.

[0749] "Generative AI methods" are artificial intelligence functions that generate related ideas and questions based on an input topic.

[0750] The "evaluation means" is a function for expanding and evaluating the generated ideas.

[0751] "WebUI input means" means a means for receiving input from a user through a web user interface.

[0752] "Means for linking with web conferencing tools" refers to the means for linking the system with web conferencing tools and importing meeting minutes and other information.

[0753] The "analysis means for analyzing the contents of minutes" is a function for analyzing the contents of minutes imported from a web conferencing tool and extracting important keywords and emotional information.

[0754] The "idea generation means" is a function for generating new ideas based on the information extracted by the analysis means.

[0755] The "evaluation and suggestion means" is a function for evaluating the generated ideas and proposing the most useful ideas.

[0756] The following system configuration will be described as an embodiment of the present invention.

[0757] System Configuration

[0758] This system includes a means for users to input themes, a generative AI means, an evaluation means, an input means from the Web UI, a means for linking with web conferencing tools, an analysis means for analyzing the contents of minutes, a means for generating ideas, and a means for evaluation and proposal.

[0759] Program processing

[0760] The server performs the following process.

[0761] 1. User theme input method:

[0762] It provides an interface for users to input topics for discussion and idea generation into the system, for example, using a form that runs on a web browser.

[0763] 2. Generative AI means:

[0764] It generates relevant ideas and questions based on the input topic, using a generative AI model such as OpenAI's GPT-3.

[0765] 3. Evaluation method:

[0766] The generated ideas can be expanded and evaluated using evaluation buttons such as "Be original," "Be realistic," and "Review from a management perspective."

[0767] 4. Input method from WebUI:

[0768] It receives input from users through a web user interface, for example, by users clicking on rating buttons to enter a rating.

[0769] 5. Integration with web conferencing tools:

[0770] Integrate the system with web conferencing tools (e.g., Zoom) to capture meeting minutes and other information. Automatically obtain meeting minutes using API.

[0771] 6. Analysis methods for analyzing the contents of the minutes:

[0772] Analyze the contents of minutes imported from web conferencing tools and extract important keywords and sentiment information. Here, use a natural language processing library such as TextBlob.

[0773] 7. Idea generation methods:

[0774] New ideas are generated based on the information extracted by the analytical method. A generative AI model is used to generate prompt sentences and generate ideas.

[0775] 8. Evaluation proposal method:

[0776] Evaluate the generated ideas and suggest the most useful ones. Based on the evaluation results, present the most highly rated ideas to the user.

[0777] Specific examples

[0778] For example, if the Zoom minutes state that "a new robotic arm is needed," the analytics tool will extract this information and send a prompt to the generative AI model, such as:

[0779] Example prompt sentence:

[0780] Minutes Keywords: New robotic arm, introduction, production efficiency

[0781] Emotional information: Positive

[0782] Use this information to generate ideas for new manufacturing techniques and production line improvements.

[0783] Based on this prompt, the generative AI model generates ideas on how the introduction of a new robotic arm can improve production efficiency. The generated ideas are evaluated by an evaluation tool, and the most useful ideas are suggested to the user.

[0784] In this way, it becomes possible to generate high-quality, realistic ideas based on the content of discussions in meetings and the emotional information of participants, and to efficiently evaluate and propose ideas.

[0785] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0786] Step 1:

[0787] The user inputs the topic. The user inputs the topic for discussion or idea generation using a form on a web browser. The input topic is sent to the server and stored in a database.

[0788] Step 2:

[0789] The server generates ideas using generative AI methods. Based on the saved themes, the server sends prompts to a generative AI model (e.g., OpenAI's GPT-3) to generate related ideas and questions. The generated ideas are returned to the server and stored in a database.

[0790] Step 3:

[0791] The server provides the evaluation method. Users can review the generated ideas through the web UI and enter their evaluation by clicking evaluation buttons such as "original," "realistic," and "review from a management perspective." The evaluation results are sent to the server and stored in a database.

[0792] Step 4:

[0793] The server retrieves the minutes using a method linked to the web conferencing tool. The server automatically retrieves the minutes of the meeting using the API of the web conferencing tool (e.g., Zoom). The retrieved minutes are stored on the server.

[0794] Step 5:

[0795] The server analyzes the contents of the minutes. The server analyzes the saved minutes and extracts important keywords and sentiment information using a natural language processing library such as TextBlob. The extracted information is stored on the server.

[0796] Step 6:

[0797] The server generates new ideas using the idea generation means. The server sends prompts to the generative AI model based on the extracted keywords and emotional information to generate new ideas. The generated ideas are returned to the server and stored in a database.

[0798] Step 7:

[0799] The server evaluates and proposes ideas using the evaluation and proposal means. The server evaluates the generated ideas and proposes the most useful ideas to the user. Based on the evaluation results, the most highly rated ideas are presented to the user.

[0800] 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.

[0801] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) 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.

[0802] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0803] 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.

[0804] [Second embodiment]

[0805] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0806] 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.

[0807] 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).

[0808] 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.

[0809] 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.

[0810] 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).

[0811] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] In the smart glasses 214, the 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.

[0816] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0817] "Example 1"

[0818] The brainstreaming support system of the present invention uses generative AI to generate related ideas and questions based on a theme input by the user. Specifically, when a user inputs "new business development" as a theme, the generative AI generates questions such as "What are the market needs for new business development?" and "What resources are needed for new business development?", as well as ideas such as "Leverage the existing customer base for new business development" and "Consider introducing new technology for new business development."

[0819] "Example 2"

[0820] For the generated ideas, evaluation buttons such as "Be original," "Be realistic," and "Review from a management perspective" are provided to support the expansion of the ideas. Specifically, when a user presses the "Be original" evaluation button for the generated idea "Consider introducing new technology to develop new businesses," the generative AI will generate new ideas such as "What kind of original businesses will become possible by introducing new technology?"

[0821] "Example 3"

[0822] The system of the present invention not only utilizes input from the WebUI, but also utilizes information from meeting minutes by linking with web conferencing tools. Specifically, minutes from meetings held using web conferencing tools such as Zoom are imported, and the generative AI generates new ideas based on the information contained in the minutes. For example, if the minutes contain information such as "new technology needs to be introduced to develop new businesses," the generative AI can use this information to generate new ideas such as "what kind of new businesses can be developed by introducing new technology?"

[0823] The processing flow of each embodiment will be described below.

[0824] "Example 1"

[0825] Step 1: The user accesses the Web UI of the brainstorming support system.

[0826] Enter "New Business Development" as the theme.

[0827] Step 2: The system's generative AI receives topic input from the user and generates related ideas and questions. Specifically, it generates questions such as "What are the market needs for new business development?" and "What resources are needed for new business development?", as well as ideas such as "Leverage the existing customer base for new business development" and "Consider introducing new technology for new business development."

[0828] Step 3: The generated ideas and questions are presented to the user, who can then add their own thoughts or rate the presented ideas.

[0829] "Example 2"

[0830] Step 1: The user clicks the "Be original" rating button for the generated idea, "Consider introducing new technology to develop new businesses."

[0831] Step 2: The system's generative AI receives user evaluation input and generates new ideas based on the evaluation. Specifically, it generates new ideas such as "What kind of original business will become possible by introducing new technology?"

[0832] Step 3: The generated new ideas are presented to the user, who can then add their own thoughts or rate the presented ideas.

[0833] "Example 3"

[0834] Step 1: Users hold meetings using web conferencing tools such as Zoom and import the minutes into the system.

[0835] Step 2: The system's generative AI analyzes the information from the minutes and generates new ideas based on that information. For example, if the minutes contain information such as "new technology needs to be introduced to develop new businesses," the generative AI will use this information to generate new ideas such as "what kind of new businesses can be developed by introducing new technology?"

[0836] Step 3: The generated new ideas are presented to the user, who can then add their own thoughts or rate the presented ideas.

[0837] Example 1

[0838] Next, a description will be given of Example 1 of Form 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."

[0839] Conventional brainstreaming support systems lack the ability to automatically generate specific ideas and questions related to a topic when the user inputs it. They also lack the means to evaluate and further expand on the generated ideas and questions. Furthermore, they lack integration with web conferencing tools, making it difficult to effectively utilize information obtained during meetings.

[0840] 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.

[0841] In this invention, the server includes a means for inputting a theme from a user, a means for converting the theme into a prompt, a means for transmitting the prompt to a generative AI model, a means for receiving output from the generative AI model, a means for displaying generated ideas and questions to the user, and a means for input from a Web UI and a means for linking with a web conferencing tool. This makes it possible to automatically generate specific ideas and questions based on the theme input by the user, and to evaluate and expand them. Furthermore, linking with a web conferencing tool makes it possible to effectively utilize information obtained during a conference.

[0842] The "means for user theme input" is a means for providing an interface for the user to input a brainstorming theme.

[0843] The "means for converting the theme into a prompt sentence" refers to a means for converting the theme entered by the user into a prompt sentence in a format suitable for the generative AI model.

[0844] The "means for transmitting the prompt sentence to the generative AI model" refers to a means for transmitting the generated prompt sentence to the generative AI model.

[0845] "Means for receiving output from the generative AI model" refers to means for receiving ideas or questions returned from the generative AI model.

[0846] "Means for displaying generated ideas and questions to the user" means means for displaying ideas and questions received from the generative AI model to the user.

[0847] "Means for input from WebUI" refers to the means by which a user can input information through a web interface.

[0848] "Means of integration with web conferencing tools" refers to means of integrating with web conferencing tools to obtain information and utilize it within the system.

[0849] MODE FOR CARRYING OUT THE INVENTION

[0850] This invention is a brainstreaming support system that uses a generative AI model to generate related ideas and questions based on a user-input topic. Specific embodiments of this system are described below.

[0851] System configuration

[0852] The system consists of the following main components:

[0853] 1. User theme input method

[0854] 2. A means of converting the theme into a prompt sentence

[0855] 3. Means for sending the prompt sentence to the generative AI model

[0856] 4. A means of receiving output from a generative AI model

[0857] 5. A way to display generated ideas and questions to users

[0858] 6. Input method from WebUI

[0859] 7. How to integrate with web conferencing tools

[0860] Hardware and software used

[0861] Hardware: Servers, devices (users' PCs and smartphones)

[0862] Software: Generative AI models (e.g., GPT-4), web browsers, HTML, JavaScript, Python

[0863] Program processing

[0864] The user inputs a theme through a web browser. For example, the theme is "new business development." The device sends this theme to the server. The server converts the received theme into a prompt. Specifically, it generates the prompt, "Please generate questions or ideas related to 'new business development.'"

[0865] The server sends this prompt to a generative AI model (GPT-4), which generates relevant questions and ideas based on the prompt. For example, it generates content such as "What are the market needs for new business development?" or "Leverage the existing customer base to develop new businesses."

[0866] The generated questions and ideas are sent to the device via the server, and the device displays this information in a web browser, allowing users to brainstorm based on this information.

[0867] Specific examples

[0868] The user inputs the theme "new business development." The device sends this theme to the server. The server generates a prompt message saying, "Generate questions and ideas related to 'new business development,'" and sends this to the generative AI model (GPT-4). The generative AI model generates questions and ideas such as, "What are the market needs for new business development?" and "Leverage the existing customer base to develop new businesses." The server receives these generated results and sends them to the device. The device displays the received questions and ideas on the browser, and the user uses them to brainstorm.

[0869] In this way, users can get diverse perspectives and ideas related to the topic and receive brainstorming support.

[0870] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0871] Step 1:

[0872] The user inputs a theme.

[0873] The user accesses the interface on a web browser and enters the theme they want to brainstream into the theme input field. For example, they might enter "new business development." The entered theme is temporarily stored in the device's memory.

[0874] Step 2:

[0875] The device sends the theme to the server.

[0876] The terminal sends the theme entered by the user to the server as an HTTP request. This request is made using the JavaScript fetch function. The input data is the theme "New Business Development", and the output is a request sent to the server.

[0877] Step 3:

[0878] The server converts the theme into a prompt.

[0879] The server generates a prompt based on the received theme. For example, for the theme "New Business Development," it creates the prompt "Please generate questions and ideas related to 'New Business Development'." The input data is the theme "New Business Development," and the output is the prompt "Please generate questions and ideas related to 'New Business Development'."

[0880] Step 4:

[0881] The server sends the prompt to the generative AI model.

[0882] The server sends the generated prompt sentence to the generative AI model (GPT-4). This communication is performed using an API request. The input data is the prompt sentence, and the output is a request sent to the generative AI model.

[0883] Step 5:

[0884] Generative AI models generate questions and ideas.

[0885] The generative AI model generates relevant questions and ideas based on the prompt it receives, such as "What are the market needs for new business development?" or "Leverage the existing customer base to develop new businesses." The input data is the prompt, and the output is the generated questions and ideas.

[0886] Step 6:

[0887] The server receives the generated questions and ideas.

[0888] The server receives the questions and ideas returned by the generative AI model. This data is received in JSON format. The input data is the output from the generative AI model, and the output is the data received by the server.

[0889] Step 7:

[0890] The server sends questions and ideas to the device.

[0891] The server sends the received questions and ideas to the terminal as an HTTP response. This response is also in JSON format. The input data is the generated questions and ideas, and the output is the data sent to the terminal.

[0892] Step 8:

[0893] The device displays questions and ideas to the user.

[0894] The device displays the questions and ideas received from the server on the browser. Users can brainstorm based on this information. The input data is the response from the server, and the output is what is displayed on the browser.

[0895] (Application example 1)

[0896] Next, a description will be given of Application Example 1 of Form 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."

[0897] Conventional brainstreaming support systems have the ability to generate ideas and questions based on themes entered by users, but they lack support specialized for specific industries or applications. In particular, they lack the ability to generate specific ideas and questions to improve production efficiency within factories, making it difficult for factory managers and engineers to efficiently find ways to improve production lines.

[0898] 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.

[0899] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conference tool, a means for generating ideas and questions for improving production efficiency in a factory, and a learning means for providing feedback on the generated ideas and questions and reflecting the feedback in future generation. This enables factory managers and engineers to efficiently generate specific ideas and questions for improving production efficiency and find improvement measures.

[0900] The "user topic input means" is an interface that allows the user to input a specific topic or problem.

[0901] "Generative AI methods" are artificial intelligence functions that generate related ideas and questions based on an input topic.

[0902] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion and improvement of the ideas based on the evaluation results.

[0903] "WebUI input means" means a means by which a user inputs information through a web user interface.

[0904] "Means for linking with web conferencing tools" refers to a function that links with web conferencing tools to share information and utilize data such as minutes.

[0905] The "means for generating ideas and questions to improve production efficiency in a factory" is a function for generating ideas and questions specialized for improving production efficiency in a factory.

[0906] "Learning means that provides feedback on generated ideas and questions and reflects it in future generations" is a function that collects feedback from users and allows the generative AI to reflect that feedback in the generation of future ideas and questions.

[0907] As an embodiment of the present invention, a brainstreaming support system for improving production efficiency within a factory will be specifically described.

[0908] System Configuration

[0909] The system includes the following major hardware and software components:

[0910] Server: Hosts the generative AI model, receives thematic input from users, and generates relevant ideas and questions.

[0911] User terminal: A device (e.g., PC, tablet) where factory managers and engineers can input topics and review generated ideas and questions.

[0912] Web User Interface (WebUI): The interface through which users can enter topics and view generated ideas and questions.

[0913] Web conferencing tools: Tools to capture meeting minutes and integrate with systems.

[0914] Program processing

[0915] The server processes and calculates data using the following means:

[0916] 1. Theme input method: The user inputs a theme through the Web UI. For example, the user inputs the theme "improving production line efficiency."

[0917] 2. Generative AI methods: Generative AI models such as OpenAI's GPT-3 are used to generate relevant ideas and questions based on the input topic. These ideas and questions are then processed on the server and sent to the user's device.

[0918] 3. Evaluation method: Users evaluate the generated ideas and questions. The evaluation results are sent to the server and reflected in future generation.

[0919] 4. Input from WebUI: Users provide feedback through the WebUI and evaluate the generated ideas and questions.

[0920] 5. Means of integration with web conferencing tools: Information is obtained from the minutes of web conferencing tools and used as training data for generative AI models.

[0921] 6. Learning method: The generative AI model is updated based on user feedback and reflected in the generation of ideas and questions from the next time onwards.

[0922] Specific examples

[0923] For example, if a factory manager inputs the theme "improving production line efficiency," the generative AI model will generate ideas and questions like the following:

[0924] "Where is the bottleneck on the production line?"

[0925] "What processes can be automated?"

[0926] "Would changing the layout of the production line improve efficiency?"

[0927] These ideas and questions are displayed on the user's device's WebUI, where users can rate and provide feedback.

[0928] Prompt Sentence Examples

[0929] Theme: Improving production line efficiency

[0930] Generate relevant ideas and questions.

[0931] In this way, specific ideas and questions for improving production efficiency within the factory can be efficiently generated, enabling managers and engineers to find improvement measures.

[0932] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0933] Step 1:

[0934] The user enters the theme through the WebUI.

[0935] Input: The user inputs a theme such as "improving production line efficiency."

[0936] Output: The input theme is sent to the server.

[0937] Specific operation: The user enters a theme into the input field of the WebUI and clicks the "Submit" button.

[0938] Step 2:

[0939] The server uses a generative AI model to generate relevant ideas and questions based on the input topic.

[0940] Input: The server receives the theme submitted by the user.

[0941] Output: A list of ideas and questions generated by the generative AI model.

[0942] How it works: The server sends a theme as a prompt to a generative AI model such as OpenAI's GPT-3, and receives the generated ideas and questions.

[0943] Step 3:

[0944] The server transmits the generated ideas and questions to the user terminal.

[0945] Input: A list of ideas or questions generated by a generative AI model.

[0946] Output: Ideas and questions displayed on the user's terminal.

[0947] Specific operation: The server sends the generated ideas and questions to the WebUI on the user's device and displays them.

[0948] Step 4:

[0949] Users rate the generated ideas and questions.

[0950] Input: Users rate the ideas and questions displayed.

[0951] Output: The evaluation result is sent to the server.

[0952] Specific operation: The user clicks on an evaluation button on the Web UI, such as "Be original," "Be realistic," or "Review from a management perspective."

[0953] Step 5:

[0954] The server receives the evaluation results from the user and saves them as learning data to be reflected in future generations.

[0955] Input: The evaluation results submitted by the user.

[0956] Output: The evaluation results are saved and used as training data for the generative AI model.

[0957] Specific operation: The server stores the evaluation results in a database and provides them as feedback to the learning algorithm of the generative AI model.

[0958] Step 6:

[0959] The server obtains information from the minutes of the web conferencing tool and uses it as learning data for the generative AI model.

[0960] Input: Minutes data from a web conferencing tool.

[0961] Output: The minutes data is used as training data for the generative AI model.

[0962] Specific operation: The server obtains the minutes data through the API of the web conferencing tool and provides it to the learning algorithm of the generative AI model.

[0963] In this way, specific ideas and questions for improving production efficiency within the factory can be efficiently generated, enabling managers and engineers to find improvement measures.

[0964] Example 2

[0965] Next, a description will be given of Example 2 of Form 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."

[0966] Conventional brainstorming support systems have had the problem of not being able to provide appropriate feedback or expansion on the ideas entered by users. Furthermore, the evaluation criteria are limited, making it difficult to expand on ideas from multiple perspectives. Furthermore, there is a lack of concrete methods for improving the quality and relevance of generated ideas.

[0967] 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.

[0968] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, a means for generating a prompt sentence based on the evaluation, a means for sending the generated prompt sentence to a generative AI model, a means for returning a response from the generative AI model to the user, and a means for input from a Web UI and a means for linking with a Web conferencing tool. This enables the ideas input by the user to be evaluated and expanded from multiple perspectives, thereby improving the quality and relevance of the generated ideas.

[0969] The "means for user theme input" is an interface that allows users to input ideas and themes into the system.

[0970] "Generative AI methods" are artificial intelligence functions that generate relevant ideas and questions based on a topic entered by the user.

[0971] The "evaluation means" is an interface that allows users to evaluate the generated ideas, and includes evaluation buttons such as "original," "realistic," and "review from a management perspective."

[0972] The "means for generating prompt sentences" is a function that creates prompt sentences to be sent to the generative AI model based on the user's evaluation.

[0973] "Means for sending to the generative AI model" refers to a communication means for sending the generated prompt sentence to the generative AI model.

[0974] "Means for returning responses from the generative AI model to the user" refers to a function for returning new ideas and answers received from the generative AI model to the user.

[0975] "Input means from WebUI" means a means by which a user inputs information into the system through a web interface.

[0976] "Means of integration with web conferencing tools" refers to a function that allows you to utilize information such as minutes by integrating with web conferencing tools.

[0977] This invention is a system that utilizes a generative AI model based on a theme entered by a user to support the evaluation and expansion of ideas. Specific embodiments of this system are described below.

[0978] First, the user uses a device (such as a PC or smartphone) to input a theme into the system's Web UI. For example, the user might input "Consider introducing new technology for new business development."

[0979] Next, the user presses one of the evaluation buttons for the entered theme, such as "creative," "realistic," or "review from a management perspective." For example, the user presses the "creative" button.

[0980] The server generates an appropriate prompt based on the evaluation button pressed by the user. For example, if the "Be creative" button is pressed, the server generates the prompt "What kind of creative business will become possible with the introduction of new technology?"

[0981] Next, the server sends the generated prompt to a generative AI model (e.g., OpenAI's GPT-4) via an API.

[0982] The generative AI model generates new ideas based on the prompt it receives. For example, in response to the prompt, "What kind of unique business will become possible with the introduction of new technology?", it generates ideas such as "A new logistics service that utilizes AI-powered autonomous driving technology."

[0983] Finally, the server returns the new ideas received from the generative AI model to the user by displaying them on the device screen.

[0984] The system allows users to evaluate and expand on ideas from multiple perspectives, improving the quality and relevance of the generated ideas. It can also utilize information from meeting minutes by linking with web conferencing tools.

[0985] As a concrete example, consider the case where a user inputs "Consider introducing new technology for new business development" and presses the evaluation button for "Review from the perspective of management." In this case, the server generates a prompt message asking, "What are the advantages and risks of introducing new technology from the perspective of management?" The generative AI model generates new ideas and reviews based on this prompt message, and the server returns the results to the user.

[0986] Examples of prompts include:

[0987] "What kind of creative business will become possible with the introduction of new technology?"

[0988] "What are the benefits and risks of introducing new technology from a management perspective?"

[0989] "What practical impact will the introduction of new technologies have?"

[0990] In this way, users can evaluate and further expand their ideas using generative AI models.

[0991] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0992] Step 1:

[0993] The user inputs a theme into the input form on the terminal.

[0994] Input: Theme entered by the user (e.g., "Consider introducing new technology for new business development")

[0995] Output: The input theme is sent to the server.

[0996] Specific operation: The user uses the device's WebUI to enter a theme and press the send button.

[0997] Step 2:

[0998] The user presses the rating button.

[0999] Input: A rating button that the user selects (e.g., "Creatively").

[1000] Output: The selected rating is sent to the server.

[1001] Specific operation: The user presses one of the evaluation buttons for the entered theme, such as "original," "realistic," or "review from a management perspective."

[1002] Step 3:

[1003] The server generates a prompt.

[1004] Input: User-entered theme and rating button selection information

[1005] Output: Generated prompt (e.g., "What creative ventures will become possible with the introduction of new technology?")

[1006] Specific operation: The server generates an appropriate prompt sentence based on the rating button pressed by the user.

[1007] Step 4:

[1008] The server sends a prompt to the generative AI model.

[1009] Input: Generated prompt text

[1010] Output: The prompt sent to the generative AI model

[1011] Specific operation: The server sends the generated prompt sentence to the generative AI model (e.g., OpenAI's GPT-4) via an API.

[1012] Step 5:

[1013] Generative AI models generate new ideas.

[1014] Input: The prompt sent to the generative AI model

[1015] Output: Generated new ideas (e.g., "A new logistics service utilizing AI-based autonomous driving technology")

[1016] Specific operation: The generative AI model generates new ideas based on the received prompt.

[1017] Step 6:

[1018] The server returns the generated ideas to the user.

[1019] Input: New ideas received from the generative AI model

[1020] Output: The new idea displayed on the user's terminal

[1021] Specific operation: The server sends new ideas received from the generative AI model to the user's device and displays them on the screen.

[1022] (Application example 2)

[1023] Next, a description will be given of Application Example 2 of Form 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."

[1024] Conventional brainstorming support systems lacked specific means for users to further expand on the ideas they generated. They also lacked functionality to help content creators generate new content ideas and further expand them using a rating button. This made it difficult to improve creativity and generate ideas efficiently.

[1025] 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.

[1026] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conference tool, a means for supporting content creators in generating new content ideas and further expanding them using a rating button, and an application means installed on a smartphone or a head-mounted display. This allows users to further expand on their generated ideas using the rating button, thereby improving creativity and realizing efficient idea generation.

[1027] The "user theme input means" is an interface that allows a user to input a specific theme or topic into the system.

[1028] "Generative AI methods" are artificial intelligence functions that automatically generate related ideas and questions based on an input topic.

[1029] The "evaluation tool" is an interface that allows users to evaluate the generated ideas, such as "originality," "realism," and "review from a management perspective."

[1030] "WebUI input means" means a means by which a user inputs information through a web user interface.

[1031] "Means for linking with web conferencing tools" refers to a function that links with web conferencing tools to utilize information such as minutes.

[1032] "A means to assist content creators in generating new content ideas and further developing them using the rating button" is a support function that enables content creators to generate new ideas and further develop them using the rating button.

[1033] "Application means installed on a smartphone or head-mounted display" refers to a means for using the system through an application installed on a smartphone or head-mounted display.

[1034] A system for implementing this invention includes a means for user theme input, a generative AI means, an evaluation means, an input means from a Web UI, a means for linking with a Web conferencing tool, a means for supporting content creators in generating new content ideas and further expanding them using evaluation buttons, and an application means to be installed on a smartphone or head-mounted display.

[1035] System program processing explanation

[1036] Hardware and Software Use

[1037] Hardware:

[1038] Smartphone

[1039] head-mounted display

[1040] server

[1041] software:

[1042] OpenAI API

[1043] Python Program

[1044] WebUI

[1045] Web conferencing tools

[1046] Data processing and calculation

[1047] User Action:

[1048] Users use a smartphone or head-mounted display to input a theme, such as "Consider introducing new technology to develop new businesses."

[1049] Generative AI processing:

[1050] The server uses generative AI (e.g., GPT-3) to generate related ideas and questions based on the input topic. Generated ideas might include, for example, "What kind of creative business will become possible with the introduction of new technology?"

[1051] Operation of the assessment instrument:

[1052] For each generated idea, users can rate it with buttons such as "original," "realistic," or "review from a management perspective." For example, if users press the "original" rating button, the generative AI will generate a new idea such as "By introducing new technology, we will provide a personalized content distribution service using AI."

[1053] Integration with WebUI and web conferencing tools:

[1054] Users can input information through the WebUI and utilize information from the minutes of the web conferencing tool, enabling more detailed idea generation.

[1055] Supporting content creators:

[1056] Content creators can further expand on generated ideas using the rating button and generate new content ideas, which will improve creativity and make idea generation more efficient.

[1057] Examples and prompts

[1058] Examples:

[1059] Initial idea: "Consider introducing new technology to develop new businesses."

[1060] User rating: "Ingenious"

[1061] Generated idea: "By introducing new technology, we will provide a personalized content delivery service using AI."

[1062] Example prompt sentence:

[1063] "When developing new businesses, it is important to think creatively about introducing new technologies."

[1064] In this way, the generative AI generates new ideas based on user evaluations, supporting the creativity of content creators.

[1065] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1066] Step 1:

[1067] The user inputs a theme using a smartphone or head-mounted display. For example, they input a theme such as "Consider introducing new technology for new business development." The input theme is sent to the server.

[1068] Input: The theme entered by the user

[1069] Output: The theme sent to the server

[1070] Step 2:

[1071] The server sends the received theme to a generative AI model (e.g., GPT-3) to generate related ideas and questions. The generative AI model generates prompts based on the theme and outputs corresponding ideas.

[1072] Input: The theme sent to the server

[1073] Output: Ideas and questions generated by the generative AI model

[1074] Step 3:

[1075] The server sends the generated ideas and questions to the user's device, where the user can view the generated ideas via a smartphone or head-mounted display.

[1076] Input: Ideas or questions generated by a generative AI model

[1077] Output: Ideas and questions sent to the user's device

[1078] Step 4:

[1079] The user presses evaluation buttons for the generated ideas, such as "original," "realistic," and "review from a managerial perspective." The information selected by the evaluation button is sent to the server.

[1080] Input: User's rating button selection information

[1081] Output: Rating button selection information sent to the server

[1082] Step 5:

[1083] The server generates a new prompt sentence based on the selection information of the rating button and sends it to the generative AI model again. The generative AI model generates further expanded ideas based on the new prompt sentence.

[1084] Input: Rating button selection information sent to the server

[1085] Output: Augmented ideas generated by the generative AI model

[1086] Step 6:

[1087] The server sends the augmented ideas to the user's device, where the user can view the augmented ideas via a smartphone or head-mounted display.

[1088] Input: Augmented ideas generated by a generative AI model

[1089] Output: The extension idea sent to the user's device

[1090] Step 7:

[1091] The user can continue to hit the rating button and expand on the idea as needed, and the process repeats until the user is satisfied.

[1092] Input: User's rating button selection information

[1093] Output: Further expanded ideas generated by the generative AI model

[1094] In this way, the user can further expand on the generated ideas using the rating buttons, which improves creativity and allows for more efficient idea generation.

[1095] Example 3

[1096] Next, a description will be given of Example 3 of Form Example 3. 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."

[1097] Conventional brainstreaming support systems allow users to input topics and generate ideas using generative AI, but they lack sufficient integration with web conferencing tools, making it difficult to effectively utilize information obtained from meeting minutes. Furthermore, support for evaluating and expanding on generated ideas is limited, making it difficult for users to obtain the specific, practical ideas they desire. This poses a challenge, reducing the efficiency and effectiveness of brainstreaming.

[1098] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1099] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from a Web UI and a means for linking with a Web conferencing tool, a means for analyzing minutes of the Web conferencing tool and extracting important information, a means for creating and sending prompts to the generative AI model based on the extracted information, and a means for displaying ideas generated by the generative AI model to the user. This makes it possible to effectively utilize information obtained from minutes of the Web conferencing tool to generate specific and practical ideas that users desire.

[1100] The "means for user theme input" refers to a means for providing an interface for users to input specific themes or topics to the system.

[1101] "Generative AI methods" are methods that use artificial intelligence technology to generate related ideas and questions based on an input topic.

[1102] The "evaluation means" is a means for users to evaluate and provide feedback on the generated ideas.

[1103] "Input means from WebUI" refers to the means by which a user inputs information into the system via a web browser.

[1104] "Means for linking with web conferencing tools" refers to the means for linking the system with web conferencing tools and importing meeting minutes and other information into the system.

[1105] "Means for analyzing minutes from a web conferencing tool and extracting important information" refers to means for analyzing minutes obtained from a web conferencing tool and extracting important information from them.

[1106] "Means for creating and sending prompt sentences to a generative AI model" refers to means for creating appropriate prompt sentences for a generative AI model based on extracted information and sending them.

[1107] "Means for displaying ideas generated from a generative AI model to a user" refers to means for displaying ideas generated from a generative AI model to a user.

[1108] The present invention is a brainstreaming support system in which a user, a terminal, and a server work together. A specific embodiment of this system will be described below.

[1109] User Actions

[1110] Users access the system's WebUI using a web browser. The WebUI has input fields such as text boxes and drop-down menus, where users can enter information such as "I want to generate ideas for new business development."

[1111] Device operation

[1112] Users use devices (PCs or smartphones) to launch a web conferencing tool and hold a meeting. The content discussed during the meeting is recorded using the conferencing tool's recording and minutes-creation functions. After the meeting ends, the device uploads the meeting minutes to the server, either automatically or via user operation. The minutes are saved as text files or PDF format.

[1113] Server Processing

[1114] The server receives the uploaded minutes and analyzes them using natural language processing (NLP) technology. Specifically, it uses tools such as Python's NLTK library and SpaCy to extract important information from the minutes, such as "New business development requires the introduction of new technology."

[1115] Based on the extracted information, the server creates a prompt to send to the generative AI model. For example, it creates a prompt such as, "What new businesses can be developed by introducing new technology?" The created prompt is sent to the generative AI model via an API.

[1116] A generative AI model (e.g., OpenAI's GPT-3) generates new ideas based on the prompt it receives, and the generated ideas are returned to the server in text format.

[1117] The server receives the ideas returned by the generative AI model and sends them to the device using communication protocols such as HTTP requests or WebSockets.

[1118] Terminal display

[1119] The terminal displays the ideas received from the server to the user. The generated ideas are displayed on the Web UI, allowing the user to review them. The user can provide feedback and request the idea generation again if necessary.

[1120] Specific examples

[1121] 1. The user enters through the WebUI, "I would like you to generate ideas for new business development."

[1122] 2. A user holds a meeting using a web conferencing tool and uploads the minutes to the system.

[1123] 3. The server analyzes the minutes and extracts the information that "new technology needs to be introduced to develop new businesses."

[1124] 4. The server creates a prompt for the generative AI model: "What new businesses can be developed by introducing new technology?"

[1125] 5. The generative AI model generates new ideas and displays them to the user via their device.

[1126] Prompt Sentence Examples

[1127] "Generate ideas about what new businesses can be developed with the introduction of new technologies."

[1128] In this way, the system of the present invention utilizes information obtained from minutes by linking the Web UI and the web conferencing tool, and generates new ideas using the generative AI model. This allows users to obtain specific and practical ideas. The flow of the identification process in Example 3 will be described with reference to Figure 15.

[1129] Step 1:

[1130] The user enters information through the WebUI.

[1131] The user opens a web browser and accesses the system's WebUI. The WebUI has input fields such as text boxes and drop-down menus, where the user enters information such as "I would like you to generate ideas for new business development." The entered information is sent to the server, where the server receives the input data in text format.

[1132] Step 2:

[1133] The device will hold the meeting using a web conferencing tool.

[1134] Users use their devices (PCs or smartphones) to launch a web conferencing tool and hold a meeting. The content discussed during the meeting is recorded using the recording and minutes-creation functions of the conferencing tool. After the meeting ends, the device uploads the minutes to the server, either automatically or via user operation. The minutes are saved as text files or PDF format. The input data is the minutes file, which is received by the server.

[1135] Step 3:

[1136] The server analyzes the minutes and extracts important information.

[1137] The server receives the uploaded minutes and analyzes them using natural language processing (NLP) technology. Specifically, it uses tools such as Python's NLTK library and SpaCy to extract important information from the minutes, such as "New technology needs to be introduced for new business development." The input data is the text of the minutes, and the output data is the extracted important information.

[1138] Step 4:

[1139] The server creates and sends a prompt to the generative AI model.

[1140] The server creates a prompt to be sent to the generative AI model based on the extracted information. For example, it creates a prompt such as, "What new businesses can be developed by introducing new technology?" The created prompt is sent to the generative AI model via an API. The input data is the extracted information, and the output data is the prompt.

[1141] Step 5:

[1142] Generative AI models generate new ideas.

[1143] A generative AI model (e.g., OpenAI's GPT-3) generates new ideas based on the received prompt. The generated ideas are returned to the server in text format. The input data is the prompt, and the output data is the generated ideas.

[1144] Step 6:

[1145] The server transmits the generated ideas to the terminal.

[1146] The server receives the ideas returned by the generative AI model and sends them to the device. For transmission, communication protocols such as HTTP requests and WebSockets are used. The input data are the generated ideas, and the output data are the ideas sent to the device.

[1147] Step 7:

[1148] The terminal displays the generated ideas to the user.

[1149] The terminal displays the ideas received from the server to the user. The generated ideas are displayed on the WebUI, allowing the user to review them. The user can provide feedback and request the idea to be generated again if necessary. The input data are the ideas sent from the server, and the output data are the ideas displayed to the user.

[1150] (Application example 3)

[1151] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1152] Conventional brainstorming support systems utilize themes input by users and minutes of meetings linked to web conferencing tools, but they do not support the generation of ideas for specific manufacturing processes or efficiency improvements within factories. Therefore, there is a need for a system that can generate ideas for new manufacturing processes and efficiency improvements based on meeting minutes within factories.

[1153] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for inputting a theme from the user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from the Web UI and a linking means with a Web conferencing tool, and a means for importing minutes of meetings held in the factory and generating ideas for new manufacturing processes and efficiency improvements based on that information. This makes it possible to generate ideas for new manufacturing processes and efficiency improvements based on the minutes of meetings held in the factory.

[1154] The "means for user topic input" is an interface that allows users to input topics for discussion and idea generation into the system.

[1155] "Generative AI methods" are artificial intelligence functions that generate related ideas and questions based on an input topic.

[1156] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion and improvement of the ideas based on the evaluation results.

[1157] "WebUI input means" means a user inputting information into the system through a web user interface.

[1158] "Means for linking with web conferencing tools" refers to the means for linking the system with web conferencing tools and importing meeting minutes and other information into the system.

[1159] "A means of importing minutes from meetings held within the factory and generating ideas for new manufacturing processes and efficiency improvements based on that information" is a function that imports minutes from meetings held within the factory into the system and generates ideas for new manufacturing processes and efficiency improvements based on those minutes.

[1160] The system for implementing this invention includes a means for user input of themes, a generative AI means, an evaluation means, an input means from a Web UI, a means for linking with a Web conferencing tool, and a means for capturing minutes of meetings held within a factory and generating ideas for new manufacturing processes and efficiency improvements based on that information.

[1161] The server provides an interface for users to input a theme. The theme input by the user is sent to the generative AI means, which generates related ideas and questions. The generated ideas are evaluated by the user through the evaluation means, and the ideas are expanded or improved based on the evaluation results.

[1162] The WebUI input method allows users to input information into the system through a web user interface, allowing users to easily input themes and evaluation results.

[1163] The means of linking with web conferencing tools is a means of linking the system with web conferencing tools and incorporating meeting minutes and other information into the system. For example, minutes can be obtained from web conferencing tools such as Zoom, and generative AI can generate new ideas based on that information.

[1164] The means for importing minutes of meetings held within the factory and generating ideas for new manufacturing processes and efficiency improvements based on that information is a function for importing minutes of meetings held within the factory into the system and generating ideas for new manufacturing processes and efficiency improvements based on those minutes. This makes it possible to generate ideas for new manufacturing processes and efficiency improvements based on the minutes of meetings held within the factory.

[1165] For example, the following prompts can be fed to a generative AI model:

[1166] Example prompt sentence:

[1167] Minutes: The production line needs to be made more efficient. In particular, there is a bottleneck in the assembly process. Please propose ideas for solving this problem by introducing new technologies or methods.

[1168] Based on this prompt, a generative AI might generate ideas like:

[1169] 1. The introduction of robotic arms will advance automation of the assembly process.

[1170] 2. Introduce a quality inspection system using AI to enable early detection of defective products.

[1171] 3. Redesign the production line layout to improve work efficiency.

[1172] In this way, ideas for new manufacturing processes and efficiency improvements can be generated based on the minutes of meetings held within the factory.

[1173] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1174] Step 1:

[1175] The user inputs a topic. The user inputs a topic for discussion or idea generation through a web user interface. The input topic is sent to the server. The input data is in text format, and the server receives it and passes it on to the next process.

[1176] Step 2:

[1177] The server generates ideas and questions using generative AI means. The server inputs the theme received in step 1 into the generative AI model to generate related ideas and questions. The generative AI model processes the data based on the theme and outputs related ideas and questions in text format.

[1178] Step 3:

[1179] The server sends the generated ideas to the evaluation means. The server then sends the ideas and questions output from the generative AI model to the evaluation means. The evaluation means provides an interface for users to evaluate the ideas. Users evaluate the ideas using evaluation buttons such as "Be original," "Be realistic," and "Review from a management perspective."

[1180] Step 4:

[1181] The user evaluates the ideas. The user evaluates the generated ideas through the evaluation means. The evaluation results are sent to the server and used for the next process. The evaluation data is in numerical or text format, and the server receives it and passes it on to the next process.

[1182] Step 5:

[1183] The server expands or improves the idea based on the evaluation results. The server expands or improves the idea again using the generative AI model based on the evaluation results received from the user. The generative AI model uses the evaluation results as input data to expand or improve the idea.

[1184] Step 6:

[1185] The server retrieves the minutes using a means of linking with the web conferencing tool. The server retrieves the minutes of the meeting from the web conferencing tool (for example, Zoom). The retrieved minutes are in text format, and the server passes them on to the next process.

[1186] Step 7:

[1187] The server inputs the minutes into a generative AI means to generate ideas for new manufacturing processes and efficiency improvements. The server inputs the acquired minutes into a generative AI model to generate ideas for new manufacturing processes and efficiency improvements based on the minutes. The generative AI model analyzes the contents of the minutes and outputs related ideas in text format.

[1188] Step 8:

[1189] The server provides the generated ideas to the user. The server provides ideas for new manufacturing processes and efficiency improvements output from the generative AI model to the user. The user can review these ideas through a web user interface and provide evaluations and feedback as necessary.

[1190] 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.

[1191] "Example 1"

[1192] One embodiment of the present invention is a brainstreaming assistance system that includes an emotion engine that recognizes a user's emotions. The system receives a topic input from the user and generates ideas and questions related to the topic. The generated ideas are evaluated based on the user's emotions, and new ideas are generated based on the evaluation results. Specifically, if the user expresses joy, positive ideas that match the emotion are generated. Conversely, if the user expresses sadness, ideas that propose solutions corresponding to the emotion are generated.

[1193] "Example 2"

[1194] Another embodiment of the present invention is a brainstreaming support system in which an emotion engine adjusts the evaluation criteria of an evaluation means. In this system, the evaluation criteria are adjusted based on the user's emotions. Specifically, when the user is in an excited state, the evaluation criteria are set high to match the user's emotions, making it easier to evaluate more challenging ideas. Conversely, when the user is in a calm state, the evaluation criteria are set low to match the user's emotions, making it easier to evaluate more realistic ideas.

[1195] "Example 3"

[1196] Another embodiment of the present invention is a brainstreaming support system that utilizes information from minutes of a web conferencing tool. In this system, new ideas are generated based on information obtained from the minutes of a web conferencing tool. Specifically, an emotion engine analyzes the user's emotional information recorded in the minutes, and idea generation and evaluation adjustments are performed based on the results. For example, if the minutes record "expectations for new business development," positive ideas that match those expectations are generated based on that information.

[1197] The processing flow of each embodiment will be described below.

[1198] "Example 1"

[1199] Step 1: Receive theme input from the user.

[1200] Step 2: Generate ideas and questions related to the theme.

[1201] Step 3: Recognize the user's emotions with the emotion engine.

[1202] Step 4: Evaluate the generated ideas based on the perceived emotions.

[1203] Step 5: Generate new ideas based on the evaluation results.

[1204] "Example 2"

[1205] Step 1: Recognize the user's emotions with the emotion engine.

[1206] Step 2: Adjust the rating scale of the assessment instrument based on the perceived emotions.

[1207] Step 3: Evaluate the ideas based on the adjusted evaluation criteria.

[1208] Step 4: Generate new ideas based on the evaluation results.

[1209] "Example 3"

[1210] Step 1: Get information from the meeting minutes in your web conferencing tool.

[1211] Step 2: Generate new ideas based on the information obtained.

[1212] Step 3: Analyze the user's emotional information recorded in the minutes using the emotion engine.

[1213] Step 4: Adjust idea generation and evaluation based on the analysis results.

[1214] Example 1

[1215] Next, a description will be given of Example 1 of Form 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."

[1216] Conventional brainstorming support systems generate ideas and questions without considering the user's emotions, making it difficult to provide appropriate ideas and questions that reflect the user's emotional state. Furthermore, the generated ideas and questions are not evaluated based on the user's emotions, which can lead to a decrease in user satisfaction. Furthermore, there is a problem of insufficient integration with meeting tools and the inability to utilize information from meeting minutes, which reduces the efficiency of brainstorming.

[1217] 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.

[1218] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an emotion recognition means for recognizing the user's emotions, a means for evaluating ideas and questions based on the emotion information and generating new ideas and questions, and a means for linking the input means with the conference tool. This makes it possible to provide appropriate ideas and questions according to the user's emotional state, thereby improving user satisfaction. Furthermore, by utilizing information from the minutes of the conference tool, the efficiency of brainstorming can be improved.

[1219] The "means for user theme input" is an interface that allows the user to input the brainstorming theme.

[1220] A "generative AI method" is an artificial intelligence mechanism that generates related ideas and questions based on a topic entered by the user.

[1221] The "evaluation means" is a function for evaluating the generated ideas and questions and providing feedback to the user.

[1222] "Emotion recognition means" is a technology for recognizing a user's emotional state by analyzing their facial expressions and tone of voice.

[1223] The "means for evaluating ideas and questions based on emotional information and generating new ideas and questions" is a function for evaluating generated ideas and questions based on the recognized emotional information of the user, and further generating new ideas and questions.

[1224] "Input means" refers to an interface through which a user inputs information into the system.

[1225] "Means of collaboration with conference tools" refers to a function that allows collaboration with conference tools to utilize information such as minutes.

[1226] This invention is a brainstreaming support system that generates related ideas and questions based on a topic input from a user, and evaluates and expands them according to the user's emotional state. Specific embodiments of this system are described below.

[1227] First, the user enters a topic into the device's input field. For example, they might enter "new business development." The device then sends this topic to the server. The server then uses a generative AI model (for example, a general natural language processing model) to generate ideas and questions related to the topic. Examples of generated ideas and questions include the following:

[1228] Example questions:

[1229] "What are the market needs for new business development?"

[1230] "What resources are needed for new business development?"

[1231] Example ideas:

[1232] "We will utilize our existing customer base to develop new businesses."

[1233] "When developing new businesses, we consider introducing new technologies."

[1234] The generated ideas and questions are sent from the server to the device. The device recognizes the user's emotions using emotion recognition means (e.g., general emotion recognition software). It analyzes the user's facial expressions and tone of voice to determine their emotional state. For example, if the user is smiling, it recognizes the emotion of joy.

[1235] The device sends the recognized emotional information to the server. The server evaluates the generated ideas and questions based on the emotional information and generates new ideas and questions. For example, if the user expresses joy, the server generates positive ideas that match that emotion. Conversely, if the user expresses sadness, the server generates ideas that propose solutions that correspond to that emotion.

[1236] Finally, the server sends the evaluated ideas and questions to the device, which displays them to the user, who can use them to further their brainstorming.

[1237] As a concrete example, if a user inputs the topic "new business development," the generative AI model will generate questions and ideas such as the following:

[1238] Example questions:

[1239] "What are the market needs for new business development?"

[1240] "What resources are needed for new business development?"

[1241] Example ideas:

[1242] "We will utilize our existing customer base to develop new businesses."

[1243] "When developing new businesses, we consider introducing new technologies."

[1244] An example of a prompt sentence might be:

[1245] "Generate ideas for new business development."

[1246] "Generate questions about market needs for new business development."

[1247] In this way, a system is realized in which the server, terminals, and users work together to support brainstorming.

[1248] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1249] Step 1:

[1250] The user inputs a theme.

[1251] The user inputs a theme into the input field of the terminal and clicks the send button. For example, the user inputs "New Business Development." The input data is the theme text.

[1252] Step 2:

[1253] The device sends the theme to the server.

[1254] The terminal uses an HTTP POST request to send the input theme "New Business Development" to the server. The input data is the theme text, and the output data is the request to the server.

[1255] Step 3:

[1256] The server uses a generative AI model to generate relevant ideas and questions.

[1257] The server inputs the received theme into a generative AI model to generate related ideas and questions. For example, it generates questions such as "What are the market needs for new business development?" and "What resources are needed for new business development?", as well as ideas such as "Leverage the existing customer base for new business development" and "Consider introducing new technology for new business development." The input data is the theme text, and the output data is a list of generated ideas and questions.

[1258] Step 4:

[1259] The server sends generated ideas and questions to the device.

[1260] The server sends the generated ideas and questions to the terminal in JSON format. The input data is the list of generated ideas and questions, and the output data is the response to the terminal.

[1261] Step 5:

[1262] The terminal recognizes the user's emotions using an emotion engine.

[1263] The device uses the emotion engine to analyze the user's facial expression and tone of voice to recognize their emotional state. For example, if the user is smiling, the emotion of joy is recognized. The input data is the user's facial expression and tone of voice, and the output data is the recognized emotional information.

[1264] Step 6:

[1265] The device transmits the recognized emotion information to the server.

[1266] The device sends the recognized emotion information to the server in JSON format. The input data is the recognized emotion information, and the output data is the request to the server.

[1267] Step 7:

[1268] The server evaluates ideas and questions based on the emotional information and generates new ideas and questions.

[1269] The server evaluates the generated ideas and questions based on the received emotional information. For example, if the user expresses happiness, it generates positive ideas that match that emotion. Conversely, if the user expresses sadness, it generates ideas that propose solutions that correspond to that emotion. The input data is the emotional information and a list of generated ideas and questions, and the output data is a list of evaluated ideas and questions.

[1270] Step 8:

[1271] The server sends the final ideas and questions to the device.

[1272] The server finally sends the evaluated ideas and questions to the terminal in JSON format. The input data is the list of evaluated ideas and questions, and the output data is the response to the terminal.

[1273] Step 9:

[1274] The device displays the final ideas and questions to the user.

[1275] The terminal displays the final ideas and questions it receives to the user, who can then use these ideas and questions to further their brainstorming. The input data is the list of evaluated ideas and questions, and the output data is what is displayed to the user.

[1276] (Application example 1)

[1277] Next, a description will be given of Application Example 1 of Form 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."

[1278] Conventional brainstreaming support systems can generate ideas and questions based on user input, but they do not take user emotions into account when generating or evaluating ideas, making it difficult to provide appropriate ideas that reflect the user's emotions. Furthermore, there is a lack of concrete means for generating ideas for new production processes and efficiency improvements within factories, making them less practical for on-site use.

[1279] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conferencing tool, an emotion recognition means for recognizing the user's emotions, a means for evaluating the generated ideas based on the emotions and generating new ideas, and a means installed in a robot for generating ideas for new production processes and efficiency improvements in a factory. This makes it possible to provide appropriate ideas according to the user's emotions, thereby increasing practicality in a factory.

[1280] The "user theme input means" is an interface that allows a user to input a specific theme or topic.

[1281] "Generative AI methods" are artificial intelligence functions that generate relevant ideas and questions based on a topic entered by the user.

[1282] The "evaluation means" is a function for expanding and evaluating the generated ideas.

[1283] "Input means from WebUI" means a means for a user to enter input through a web user interface.

[1284] "Means for linking with web conferencing tools" refers to means for linking with web conferencing tools to share information and utilize information from meeting minutes.

[1285] "Emotion recognition means" is a function for recognizing the user's emotions.

[1286] The "means for evaluating ideas generated based on emotions and generating new ideas" is a function for evaluating ideas generated based on the user's emotions and generating new ideas based on the results.

[1287] "Means installed in robots to generate ideas for new production processes and efficiency improvements within factories" refers to functions installed in robots to generate ideas for new production processes and efficiency improvements within factories.

[1288] The system for implementing this invention includes a means for inputting a theme from a user, a generative AI means, an evaluation means, an input means from a Web UI, a means for linking with a Web conferencing tool, an emotion recognition means, a means for evaluating ideas generated based on emotions and generating new ideas, and a means installed on a robot for generating ideas for new production processes and efficiency improvements within a factory.

[1289] Program processing explanation

[1290] The server provides an interface for receiving topic input from a user. Once the user inputs a topic, the server uses a generative AI mechanism to generate ideas and questions related to the topic. The generative AI mechanism utilizes a generative AI model, such as the OpenAI API, to generate relevant ideas and questions based on the topic.

[1291] The generated ideas are expanded and evaluated using an evaluation tool that provides evaluation buttons such as "original," "realistic," and "review from a management perspective," allowing users to evaluate the generated ideas.

[1292] Furthermore, the system uses an emotion recognition mechanism to recognize the user's emotions. The emotion recognition mechanism analyzes the user's emotions using the Emotion Recognition library and the camera. Based on the recognized emotions, the generated ideas are evaluated and a mechanism for generating new ideas is activated. For example, if the user shows an emotion of joy, a positive idea is added.

[1293] This also includes a means installed on the robot to generate ideas for new production processes and efficiency improvements within the factory. The robot patrols the factory, receives topic input from workers, and uses generative AI means to generate related ideas and questions. The generated ideas are evaluated based on the workers' sentiment, and new ideas are added as needed.

[1294] Specific examples

[1295] For example, if a user inputs the theme "improving the efficiency of a new production line," the generative AI method will generate ideas and questions such as the following:

[1296] Example prompt sentence:

[1297] Theme: Improving efficiency of new production lines

[1298] Generate relevant ideas and questions.

[1299] Ideas and questions generated:

[1300] Where are the bottlenecks on the production line?

[1301] What technologies are needed to advance automation?

[1302] How can you reduce the burden on workers?

[1303] Add positive ideas.

[1304] Introducing a new robotic arm to improve work efficiency.

[1305] Increase worker motivation by increasing break time.

[1306] In this way, it becomes possible to provide appropriate ideas that correspond to the user's emotions, increasing practicality within the factory.

[1307] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1308] Step 1:

[1309] The user inputs a theme. The user inputs a theme through a web user interface (WebUI). The input theme is sent to the server. The input data is text information of the theme.

[1310] Step 2:

[1311] The server receives the input theme and passes it to the generative AI means. The generative AI means uses a generative AI model such as the OpenAI API to generate ideas and questions related to the theme. The input data is text information about the theme, and the output data is text information about the generated ideas and questions.

[1312] Step 3:

[1313] The server passes the generated ideas and questions to the evaluation means. The evaluation means provides evaluation buttons such as "original," "realistic," and "review from a managerial perspective," allowing users to evaluate the generated ideas. The input data is the text information of the generated ideas and questions, and the output data is the evaluation results by the users.

[1314] Step 4:

[1315] The server uses an emotion recognition means to recognize the user's emotions. The emotion recognition means analyzes the user's emotions using the Emotion Recognition library and a camera. The input data is the user's facial image and voice data, and the output data is information on the recognized emotions.

[1316] Step 5:

[1317] The server evaluates the generated ideas based on the recognized emotions and uses a means to generate new ideas. For example, if the user expresses joy, a positive idea is added. The input data is the recognized emotion information and text information of the generated ideas or questions, and the output data is text information of the new ideas evaluated based on the emotions.

[1318] Step 6:

[1319] The server uses the means installed on the robot to generate ideas for new production processes and efficiency improvements within the factory. The robot patrols the factory, receives topic input from workers, and generates related ideas and questions using generative AI means. The input data is text information on the topic from the workers, and the output data is text information of the generated ideas and questions.

[1320] Step 7:

[1321] The server presents the generated ideas and questions to the workers, who can then consider new production processes and ways to improve efficiency based on the presented ideas and questions. The input data is the text information of the generated ideas and questions, and the output data is the feedback and new suggestions from the workers.

[1322] Example 2

[1323] Next, a description will be given of Example 2 of Form 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."

[1324] Conventional brainstreaming support systems have had problems with providing appropriate feedback and expansion to ideas generated by users, resulting in insufficient improvement in the quality and creativity of ideas. Furthermore, because evaluation criteria are set without taking the user's emotional state into account, there is also the issue of not being able to appropriately evaluate ideas according to the user's state. Furthermore, there is also the issue of insufficient integration with web conferencing tools, making it difficult to effectively utilize ideas generated during meetings and meeting minutes.

[1325] 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.

[1326] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, a means for generating a prompt sentence based on the type of evaluation button, a means for sending the generated prompt sentence to the generative AI means, a means for displaying new ideas returned by the generative AI means to the user, an emotion engine means for analyzing the user's emotional state, a means for adjusting evaluation criteria based on the analysis results of the emotion engine means, and a means for inputting from a Web UI and for linking with a Web conferencing tool. This enables the setting of appropriate evaluation criteria according to the user's emotional state and the generation and expansion of high-quality ideas by the generative AI. Furthermore, linking with a Web conferencing tool allows for the effective use of ideas and minutes generated during meetings.

[1327] "User theme input means" is an interface that allows users to input themes such as new business development into the system.

[1328] "Generative AI methods" are artificial intelligence functions that generate relevant ideas and questions based on a topic entered by the user.

[1329] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion of the ideas based on the evaluation.

[1330] The "evaluation button" is a button for making evaluations such as "creative," "realistic," and "review from a management perspective."

[1331] The "means for generating a prompt sentence" is a function that generates a prompt sentence to be sent to the generative AI means based on the type of evaluation button pressed by the user.

[1332] The "means for sending to the generative AI means" is a function for sending the generated prompt sentence to the generative AI means.

[1333] "Means for displaying new ideas returned by the generative AI means to the user" refers to a function that receives new ideas returned by the generative AI means and displays them on the user's device.

[1334] The "emotion engine means" is a function for analyzing the user's emotional state.

[1335] The "means for adjusting the evaluation criteria" is a function for adjusting the evaluation criteria based on the analysis results of the emotion engine means.

[1336] "Input means from WebUI" is a function that allows users to input information into the system through a web interface.

[1337] "Means for linking with web conferencing tools" refers to a function that links with web conferencing tools and allows ideas and minutes raised during meetings to be imported into the system.

[1338] This invention is a system that uses a generative AI means to generate ideas and questions related to a theme input by a user, such as new business development, and supports the expansion of the generated ideas. Specific embodiments of this system are described below.

[1339] Hardware and software used

[1340] Server: The central processing unit of the system, running the generative AI model, storing data, and providing the user interface.

[1341] Terminal: A device operated by a user, such as a PC or smartphone.

[1342] Generative AI models: Use generative AI models such as OpenAI's GPT-4.

[1343] Emotion engine: Software for analyzing the user's emotional state, for example, using the emotion recognition API from Microsoft's Azure Cognitive Services.

[1344] System processing flow

[1345] 1. Users enter their ideas

[1346] The user uses a terminal to input ideas for new business development into the system's input form. For example, the user might input, "We are considering introducing new technology to develop new businesses."

[1347] 2. The user presses the rating button

[1348] For the ideas entered by the user, they press one of the evaluation buttons, such as "Be original," "Be realistic," or "Review from a management perspective."

[1349] 3. The server generates a prompt

[1350] The server generates a prompt to send to the generative AI model based on the type of evaluation button pressed by the user. For example, if the "Be creative" button is pressed, the server generates a prompt such as "What kind of creative business will become possible with the introduction of new technology?"

[1351] 4. The server sends a prompt to the generative AI model

[1352] The server sends the generated prompt to the generative AI model, which runs on the cloud.

[1353] 5. Generative AI models generate new ideas

[1354] The generative AI model generates new ideas based on the prompt, such as "The introduction of new technology will enable personalized marketing using AI."

[1355] 6. The server displays the generated ideas to the user

[1356] The server receives new ideas returned by the generative AI model and displays them on the user's device.

[1357] 7. Emotion Engine Analyzes User Emotions (Alternative Embodiment)

[1358] While the user is typing their idea, the emotion engine analyzes their facial expressions and voice to determine whether they are excited or calm.

[1359] 8. Server Adjusts Evaluation Criteria (Alternative Embodiment)

[1360] The server receives the analysis results of the emotion engine, and if the user is in an excited state, it sets the evaluation criteria high, making it easier for challenging ideas to be evaluated. Conversely, if the user is in a calm state, it sets the evaluation criteria low, making it easier for realistic ideas to be evaluated.

[1361] Specific examples

[1362] Example 1: Expanding an idea

[1363] User action: The user enters the idea "Consider introducing new technology to develop new businesses" and presses the "Be original" rating button.

[1364] Server processing: The server sends a prompt to the generative AI model: "What kind of creative business will become possible with the introduction of new technology?"

[1365] Response of the generative AI model: The generative AI model generates a new idea, such as "The introduction of new technology will make personalized marketing using AI possible."

[1366] Displaying the results: The server displays the generated ideas on the user's device.

[1367] Example 2: Using the Emotion Engine

[1368] User action: The user inputs the idea, "Consider introducing new technology to develop new businesses," and the emotion engine detects the user's state of excitement.

[1369] Server processing: The server sets the evaluation criteria high based on the analysis results of the emotion engine and sends a prompt to the generative AI model asking, "What challenging business will become possible with the introduction of new technology?"

[1370] Response from the generative AI model: The generative AI model generates challenging ideas such as "The introduction of new technologies will make it possible to build fully automated smart cities."

[1371] Displaying the results: The server displays the generated ideas on the user's device.

[1372] Prompt Sentence Examples

[1373] "What kind of creative business will become possible with the introduction of new technology?"

[1374] "What practical businesses will become possible with the introduction of new technologies?"

[1375] "What benefits does the introduction of new technology bring from the perspective of management?"

[1376] The above is a specific embodiment of this system.

[1377] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1378] Step 1:

[1379] The user inputs an idea.

[1380] The user opens a browser on their device and accesses the system's web page. They enter "We are considering introducing new technology for new business development" into the input form. The entered data is sent from the device to the server.

[1381] Input: User-entered ideas

[1382] Output: Idea data sent to the server

[1383] Step 2:

[1384] The user presses the rating button.

[1385] The user clicks one of the rating buttons, such as "Be original," "Be realistic," or "Review from a management perspective." When the button is clicked, the information is sent from the terminal to the server.

[1386] Input: Information about the rating button pressed by the user

[1387] Output: Rating button information sent to the server

[1388] Step 3:

[1389] The server generates a prompt.

[1390] Based on the information on the evaluation buttons received by the server, the server generates a prompt to send to the generative AI model. For example, if the "Be creative" button is pressed, the server generates a prompt such as "What kind of creative business will become possible with the introduction of new technology?"

[1391] Input: Rating button information

[1392] Output: Generated prompt statement

[1393] Step 4:

[1394] The server sends a prompt to the generative AI model.

[1395] The server sends the generated prompt to the generative AI model, which runs on the cloud.

[1396] Input: Generated prompt statement

[1397] Output: The prompt sent to the generative AI model

[1398] Step 5:

[1399] Generative AI models generate new ideas.

[1400] The generative AI model analyzes the prompt and generates new ideas, such as "The introduction of new technology will enable personalized marketing using AI." The generated ideas are returned to the server.

[1401] Input: prompt statement

[1402] Output: New ideas generated

[1403] Step 6:

[1404] The server displays the generated ideas to the user.

[1405] The server receives the new ideas returned by the generative AI model and sends them to the user's device, which then displays the new ideas on its screen.

[1406] Input: Generated new ideas

[1407] Output: The idea displayed on the user's device

[1408] Step 7:

[1409] An emotion engine analyzes the user's emotions (another embodiment).

[1410] While the user is inputting their idea, the emotion engine analyzes their facial expressions and voice to determine whether they are excited or calm, and the analysis results are sent to the server.

[1411] Input: User facial and voice data

[1412] Output: Analysis results by the emotion engine

[1413] Step 8:

[1414] The server adjusts the evaluation criteria (alternative embodiment).

[1415] The server receives the analysis results of the emotion engine, and if the user is in an excited state, it sets the evaluation criteria high, making it easier for challenging ideas to be evaluated. Conversely, if the user is in a calm state, it sets the evaluation criteria low, making it easier for realistic ideas to be evaluated.

[1416] Input: Analysis results of emotion engine

[1417] Output: adjusted metrics

[1418] (Application example 2)

[1419] Next, a description will be given of Application Example 2 of Form 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."

[1420] Conventional brainstorming support systems evaluate ideas without considering the user's emotional state, making it difficult to generate appropriate ideas that reflect the user's emotions. Furthermore, since the system does not take into consideration use on mobile devices such as smartphones, users are unable to easily generate ideas anywhere.

[1421] 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.

[1422] In this invention, the server includes a means for inputting a theme from the user, a generative AI means for generating ideas and questions related to the theme, and an evaluation means for supporting the expansion of the generated ideas. This makes it possible to detect the emotional state of the user and adjust the evaluation criteria based on that. In addition, by including an application means to be installed on a smartphone, users can easily generate ideas anywhere.

[1423] The "theme input means" is an interface that allows users to input brainstorming themes or topics.

[1424] "Generative AI means" is an artificial intelligence function that automatically generates ideas and questions related to an input topic.

[1425] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion of the ideas based on the evaluation.

[1426] "WebUI input means" means a means by which a user inputs information through a web user interface.

[1427] "Means of integration with web conferencing tools" refers to means of integrating with web conferencing tools to share information and utilize data such as minutes.

[1428] The "emotion engine means" is a function for detecting the user's emotional state and adjusting the system's operation based on that information.

[1429] The "means for adjusting evaluation criteria" is a function that dynamically changes the evaluation criteria for ideas based on the user's emotional state.

[1430] The "application means installed on a smartphone" refers to the application functions that are installed on a smartphone and that can be used by the user anywhere.

[1431] As an embodiment of the present invention, the following system can be constructed.

[1432] First, the user inputs a brainstorming theme using an application installed on the smartphone. The theme input unit receives the theme input by the user and transmits it to the server.

[1433] The server uses a generative AI means to generate ideas and questions related to the input topic. This generative AI means can use a generative AI model such as GPT-3. The generated ideas are displayed on the user's smartphone.

[1434] Next, the user presses rating buttons for the displayed ideas, such as "original," "realistic," and "review from a management perspective." The rating tool receives the user's rating and helps expand the idea based on it.

[1435] Furthermore, an emotion engine means detects the user's emotional state. An emotion detection library such as Affectiva can be used as the emotion engine means. Based on the emotional state, an evaluation criterion adjustment means operates to set an appropriate evaluation criterion according to the user's emotion.

[1436] The system also includes a means for inputting information from a Web UI and a means for linking with a web conferencing tool, which can extract information from meeting minutes and use it for idea generation.

[1437] As a concrete example, if a user inputs the theme "Consider introducing new technologies for new business development," the generative AI means can generate the following prompt sentence:

[1438] Example prompt sentence:

[1439] "When developing a new business, we consider introducing new technologies. What kind of technologies should we introduce as a creative approach?"

[1440] Based on this prompt, the generative AI model generates new ideas and provides them to the user. When the user presses the "Be creative" evaluation button, the generative AI means generates new ideas such as "What kind of creative business can be made possible by introducing new technology?"

[1441] In this way, a system is realized in which generative AI provides new ideas based on the user's emotional state and evaluation criteria.

[1442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1443] Step 1:

[1444] The user launches the application installed on their smartphone and enters the brainstorming topic.

[1445] Input: Theme entered by the user (e.g., "Consider introducing new technology for new business development")

[1446] Output: The input theme is sent to the server.

[1447] Specific behavior: The user enters a theme into the application's input field and presses the "Submit" button.

[1448] Step 2:

[1449] The server uses generative AI tools to generate ideas and questions related to the input topic.

[1450] Input: The theme entered by the user

[1451] Output: Generated ideas and questions (e.g., "What unique business ventures will be made possible by introducing new technologies?")

[1452] How it works: The server inputs a theme as a prompt into a generative AI model such as GPT-3 and obtains the generated ideas.

[1453] Step 3:

[1454] The generated ideas are displayed on the user's smartphone.

[1455] Input: Generated ideas and questions

[1456] Output: Ideas and questions displayed on the smartphone screen

[1457] How it works: The server sends the generated ideas to the smartphone, where the application displays them.

[1458] Step 4:

[1459] Users can press rating buttons for the displayed ideas, such as "original," "realistic," and "review from a management perspective."

[1460] Input: User rating (e.g., "creatively")

[1461] Output: The evaluation result is sent to the server.

[1462] Specific behavior: The user selects a rating button and presses the "Submit" button.

[1463] Step 5:

[1464] The server uses an emotion engine means to detect the user's emotional state.

[1465] Input: User emotion data (e.g., input from camera or microphone)

[1466] Output: Detected emotional state (e.g., "excited")

[1467] What it does: The server uses an emotion detection library such as Affectiva to analyze the user's emotional state.

[1468] Step 6:

[1469] A means operates to adjust the evaluation criteria based on the emotional state.

[1470] Input: Detected emotional state

[1471] Output: Adjusted evaluation criteria (e.g., "creatively")

[1472] Specific operation: The server resets the evaluation criteria according to the emotional state.

[1473] Step 7:

[1474] The server generates new ideas based on the evaluation criteria.

[1475] Input: Adjusted criteria, initial ideas

[1476] Output: New ideas (e.g., "What unique business ventures can be made possible by introducing new technology?")

[1477] Specific operation: The server again inputs the prompt into the generative AI model to generate new ideas.

[1478] Step 8:

[1479] New ideas are displayed on the user's smartphone.

[1480] Input: Newly generated ideas

[1481] Output: New ideas displayed on a smartphone screen

[1482] What it does: The server sends new ideas to the smartphone, and the application displays them.

[1483] Example 3

[1484] Next, a description will be given of Example 3 of Form Example 3. 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."

[1485] Conventional brainstreaming support systems primarily generate ideas based on user input and are unable to utilize meeting minutes from web conferencing tools. As a result, important information and ideas discussed during meetings are not fully utilized, making efficient idea generation difficult. Furthermore, support for evaluating and expanding on generated ideas is insufficient, making it difficult for users to effectively utilize the generated ideas.

[1486] The identification process by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means. In this invention, the server includes a theme input means from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conference tool, a means for acquiring minutes data from the Web conference tool, a means for analyzing the acquired minutes data and extracting important information, a means for generating and sending prompt sentences to the generative AI model based on the extracted information, and a means for saving the generated ideas. This makes it possible to efficiently generate new ideas by utilizing the minutes data of the Web conference tool and support evaluation and expansion of the generated ideas.

[1487] The "user topic input means" is an interface that allows a user to input information about a particular topic or theme.

[1488] "Generative AI methods" are artificial intelligence functions that generate related ideas and questions based on an input topic.

[1489] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion and improvement of the ideas based on the evaluation results.

[1490] "WebUI input means" means a user inputting information through a web user interface.

[1491] "Means of linking with web conferencing tools" refers to a function that links the system with web conferencing tools to acquire and utilize information during meetings.

[1492] "Means for obtaining meeting minutes data from a web conferencing tool" refers to a function for automatically obtaining meeting minutes data from a web conferencing tool.

[1493] The "means for analyzing the acquired minutes data and extracting important information" is a function for analyzing the acquired minutes data and extracting important information that was discussed during the meeting.

[1494] "Means for generating and sending prompt sentences to a generative AI model based on extracted information" refers to a function for generating and sending prompt sentences to a generative AI model based on extracted information.

[1495] "Means for saving generated ideas" refers to a function for saving ideas generated from a generative AI model in a database, etc.

[1496] This invention is a system that includes a means for user theme input, a generative AI means, an evaluation means, an input means from a Web UI, a means for linking with a web conferencing tool, a means for acquiring minutes data from the web conferencing tool, a means for analyzing the acquired minutes data and extracting important information, a means for generating and sending a prompt sentence to a generative AI model based on the extracted information, and a means for saving the generated ideas.

[1497] Server Operation

[1498] The server first obtains the minutes data from the web conferencing tool (e.g., a general web conferencing tool). To do this, it uses the web conferencing tool's API. The obtained minutes data is then analyzed using a natural language processing library (e.g., NLTK or SpaCy). As a result of the analysis, important keywords and phrases are extracted.

[1499] Next, the server generates a prompt to be sent to a generative AI model (such as OpenAI's GPT-3) based on the extracted information. For example, if the minutes contain the information that "new technology needs to be introduced to develop new businesses," the server generates a prompt that asks, "What new businesses can be developed by introducing new technologies?"

[1500] The generated prompt sentences are sent to a generative AI model to generate new ideas, which are then stored in a database by the server and later provided to the user.

[1501] Device behavior

[1502] The device sends information entered by the user through the WebUI to the server. For example, the user enters specific questions or requests regarding new business development. The device also receives ideas generated by the server and displays them to the user. The user can then provide further feedback based on the displayed ideas, which is also sent from the device to the server.

[1503] User Actions

[1504] Users input information about new business development through the Web UI. For example, they can enter specific questions such as, "I'm looking for ideas for introducing new technology." Users also hold meetings using a web conferencing tool, and the minutes of those meetings are imported into the system. Users can then review the generated ideas and provide feedback as needed.

[1505] Specific examples

[1506] 1. Minutes: "New business development requires the introduction of new technology."

[1507] 2. Prompt for the generative AI model: "What new businesses can be developed by introducing new technologies?"

[1508] A generative AI model might generate ideas like the following based on this prompt:

[1509] "Development of a customer support system using AI"

[1510] "Building a supply chain management system using blockchain technology"

[1511] In this way, the system of the present invention utilizes the minutes data of the web conference tool and generates new ideas using the generative AI model. This allows users to efficiently obtain ideas for new businesses. The flow of the identification process in Example 3 will be described with reference to Figure 21.

[1512] Step 1:

[1513] The server obtains the minutes data from the web conferencing tool. Specifically, it downloads the minutes data of the meeting using the web conferencing tool's API. The input is authentication information such as the meeting ID and API key, and the output is the obtained minutes data.

[1514] Step 2:

[1515] The server analyzes the acquired minutes data. Specifically, it performs text analysis using a natural language processing library (e.g., NLTK or SpaCy). The input is the minutes data, and the output is the extracted important keywords and phrases.

[1516] Step 3:

[1517] The server generates a prompt to send to the generative AI model based on the analysis results. For example, if the information includes the message, "New business development requires the introduction of new technology," it generates a prompt such as, "What kind of new business can be developed by introducing new technology?" The input is the extracted keywords and phrases, and the output is the generated prompt.

[1518] Step 4:

[1519] The server sends the generated prompt to a generative AI model (e.g., OpenAI's GPT-3) via an API request. The input is the prompt, and the output is the generated idea.

[1520] Step 5:

[1521] The server stores the ideas returned by the generative AI model in a database by executing an INSERT query against the database. The input is the generated idea, and the output is confirmation of the stored idea.

[1522] Step 6:

[1523] The terminal sends the information entered by the user through the WebUI to the server. Specifically, the user enters information into an input form and presses the send button. The input is the information entered by the user, and the output is the information sent to the server.

[1524] Step 7:

[1525] The terminal receives the generated ideas from the server and displays them to the user. Specifically, it receives the response from the server and displays it on the WebUI. The input is the idea received from the server, and the output is the idea displayed to the user.

[1526] Step 8:

[1527] The terminal sends the feedback provided by the user to the server. Specifically, the user enters information into the feedback form and presses the send button. The input is the feedback entered by the user, and the output is the feedback sent to the server.

[1528] Step 9:

[1529] The user inputs information about new business development through the WebUI. Specifically, the user enters information into an input form and presses the send button. The input is the information entered by the user, and the output is the information sent to the terminal.

[1530] Step 10:

[1531] A user holds a meeting using a web conferencing tool. Specifically, the user starts a meeting and minutes are automatically recorded. The input is the audio and text of the meeting, and the output is the recorded minutes data.

[1532] Step 11:

[1533] The user reviews the generated ideas displayed on the terminal and provides feedback. Specifically, the user evaluates the displayed ideas, enters information in a feedback form, and presses the submit button. The input is the displayed idea and the user's feedback, and the output is the feedback sent to the terminal.

[1534] (Application example 3)

[1535] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1536] Conventional brainstreaming support systems rely on user input of themes and the generation of ideas using generative AI, but they do not fully utilize the content of discussions in meetings or the emotional information of participants, which limits the quality and realism of the generated ideas. Furthermore, evaluations and proposals of generated ideas tend to be subjective, making it difficult to efficiently select the most useful ideas.

[1537] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conferencing tool, an analysis means for analyzing the contents of the minutes and extracting keywords and emotional information, an idea generation means for generating new ideas based on the extracted information, and an evaluation and proposal means for evaluating the generated ideas and proposing the most useful ideas. This enables the generation of high-quality, realistic ideas based on the contents of discussions in meetings and the emotional information of participants, and the efficient evaluation and proposal of ideas.

[1538] The "means for user topic input" is an interface that allows users to input topics for discussion and idea generation into the system.

[1539] "Generative AI methods" are artificial intelligence functions that generate related ideas and questions based on an input topic.

[1540] The "evaluation means" is a function for expanding and evaluating the generated ideas.

[1541] "WebUI input means" means a means for receiving input from a user through a web user interface.

[1542] "Means for linking with web conferencing tools" refers to the means for linking the system with web conferencing tools and importing meeting minutes and other information.

[1543] The "analysis means for analyzing the contents of minutes" is a function for analyzing the contents of minutes imported from a web conferencing tool and extracting important keywords and emotional information.

[1544] The "idea generation means" is a function for generating new ideas based on the information extracted by the analysis means.

[1545] The "evaluation and suggestion means" is a function for evaluating the generated ideas and proposing the most useful ideas.

[1546] The following system configuration will be described as an embodiment of the present invention.

[1547] System Configuration

[1548] This system includes a means for users to input themes, a generative AI means, an evaluation means, an input means from the Web UI, a means for linking with web conferencing tools, an analysis means for analyzing the contents of minutes, a means for generating ideas, and a means for evaluation and proposal.

[1549] Program processing

[1550] The server performs the following process.

[1551] 1. User theme input method:

[1552] It provides an interface for users to input topics for discussion and idea generation into the system, for example, using a form that runs on a web browser.

[1553] 2. Generative AI means:

[1554] It generates relevant ideas and questions based on the input topic, using a generative AI model such as OpenAI's GPT-3.

[1555] 3. Evaluation method:

[1556] The generated ideas can be expanded and evaluated using evaluation buttons such as "Be original," "Be realistic," and "Review from a management perspective."

[1557] 4. Input method from WebUI:

[1558] It receives input from users through a web user interface, for example, by users clicking on rating buttons to enter a rating.

[1559] 5. Integration with web conferencing tools:

[1560] Integrate the system with web conferencing tools (e.g., Zoom) to capture meeting minutes and other information. Automatically obtain meeting minutes using API.

[1561] 6. Analysis methods for analyzing the contents of the minutes:

[1562] Analyze the contents of minutes imported from web conferencing tools and extract important keywords and sentiment information. Here, use a natural language processing library such as TextBlob.

[1563] 7. Idea generation methods:

[1564] New ideas are generated based on the information extracted by the analytical method. A generative AI model is used to generate prompt sentences and generate ideas.

[1565] 8. Evaluation proposal method:

[1566] Evaluate the generated ideas and suggest the most useful ones. Based on the evaluation results, present the most highly rated ideas to the user.

[1567] Specific examples

[1568] For example, if the Zoom minutes state that "a new robotic arm is needed," the analytics tool will extract this information and send a prompt to the generative AI model, such as:

[1569] Example prompt sentence:

[1570] Minutes Keywords: New robotic arm, introduction, production efficiency

[1571] Emotional information: Positive

[1572] Use this information to generate ideas for new manufacturing techniques and production line improvements.

[1573] Based on this prompt, the generative AI model generates ideas on how the introduction of a new robotic arm can improve production efficiency. The generated ideas are evaluated by an evaluation tool, and the most useful ideas are suggested to the user.

[1574] In this way, it becomes possible to generate high-quality, realistic ideas based on the content of discussions in meetings and the emotional information of participants, and to efficiently evaluate and propose ideas.

[1575] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1576] Step 1:

[1577] The user inputs the topic. The user inputs the topic for discussion or idea generation using a form on a web browser. The input topic is sent to the server and stored in a database.

[1578] Step 2:

[1579] The server generates ideas using generative AI methods. Based on the saved themes, the server sends prompts to a generative AI model (e.g., OpenAI's GPT-3) to generate related ideas and questions. The generated ideas are returned to the server and stored in a database.

[1580] Step 3:

[1581] The server provides the evaluation method. Users can review the generated ideas through the web UI and enter their evaluation by clicking evaluation buttons such as "original," "realistic," and "review from a management perspective." The evaluation results are sent to the server and stored in a database.

[1582] Step 4:

[1583] The server retrieves the minutes using a method linked to the web conferencing tool. The server automatically retrieves the minutes of the meeting using the API of the web conferencing tool (e.g., Zoom). The retrieved minutes are stored on the server.

[1584] Step 5:

[1585] The server analyzes the contents of the minutes. The server analyzes the saved minutes and extracts important keywords and sentiment information using a natural language processing library such as TextBlob. The extracted information is stored on the server.

[1586] Step 6:

[1587] The server generates new ideas using the idea generation means. The server sends prompts to the generative AI model based on the extracted keywords and emotional information to generate new ideas. The generated ideas are returned to the server and stored in a database.

[1588] Step 7:

[1589] The server evaluates and proposes ideas using the evaluation and proposal means. The server evaluates the generated ideas and proposes the most useful ideas to the user. Based on the evaluation results, the most highly rated ideas are presented to the user.

[1590] 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.

[1591] 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> ) 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.

[1592] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1593] 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.

[1594] [Third embodiment]

[1595] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1596] 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.

[1597] 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).

[1598] 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.

[1599] 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.

[1600] 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).

[1601] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1602] 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.

[1603] 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.

[1604] 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.

[1605] 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.

[1606] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1607] "Example 1"

[1608] The brainstreaming support system of the present invention uses generative AI to generate related ideas and questions based on a theme input by the user. Specifically, when a user inputs "new business development" as a theme, the generative AI generates questions such as "What are the market needs for new business development?" and "What resources are needed for new business development?", as well as ideas such as "Leverage the existing customer base for new business development" and "Consider introducing new technology for new business development."

[1609] "Example 2"

[1610] For the generated ideas, evaluation buttons such as "Be original," "Be realistic," and "Review from a management perspective" are provided to support the expansion of the ideas. Specifically, when a user presses the "Be original" evaluation button for the generated idea "Consider introducing new technology to develop new businesses," the generative AI will generate new ideas such as "What kind of original businesses will become possible by introducing new technology?"

[1611] "Example 3"

[1612] The system of the present invention not only utilizes input from the WebUI, but also utilizes information from meeting minutes by linking with web conferencing tools. Specifically, minutes from meetings held using web conferencing tools such as Zoom are imported, and the generative AI generates new ideas based on the information contained in the minutes. For example, if the minutes contain information such as "new technology needs to be introduced to develop new businesses," the generative AI can use this information to generate new ideas such as "what kind of new businesses can be developed by introducing new technology?"

[1613] The processing flow of each embodiment will be described below.

[1614] "Example 1"

[1615] Step 1: The user accesses the brainstorming support system's Web UI and enters "new business development" as the theme.

[1616] Step 2: The system's generative AI receives topic input from the user and generates related ideas and questions. Specifically, it generates questions such as "What are the market needs for new business development?" and "What resources are needed for new business development?", as well as ideas such as "Leverage the existing customer base for new business development" and "Consider introducing new technology for new business development."

[1617] Step 3: The generated ideas and questions are presented to the user, who can then add their own thoughts or rate the presented ideas.

[1618] "Example 2"

[1619] Step 1: The user clicks the "Be original" rating button for the generated idea, "Consider introducing new technology to develop new businesses."

[1620] Step 2: The system's generative AI receives user evaluation input and generates new ideas based on the evaluation. Specifically, it generates new ideas such as "What kind of original business will become possible by introducing new technology?"

[1621] Step 3: The generated new ideas are presented to the user, who can then add their own thoughts or rate the presented ideas.

[1622] "Example 3"

[1623] Step 1: Users hold meetings using web conferencing tools such as Zoom and import the minutes into the system.

[1624] Step 2: The system's generative AI analyzes the information from the minutes and generates new ideas based on that information. For example, if the minutes contain information such as "new technology needs to be introduced to develop new businesses," the generative AI will use this information to generate new ideas such as "what kind of new businesses can be developed by introducing new technology?"

[1625] Step 3: The generated new ideas are presented to the user, who can then add their own thoughts or rate the presented ideas.

[1626] Example 1

[1627] Next, a description will be given of Example 1 of Form 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."

[1628] Conventional brainstreaming support systems lack the ability to automatically generate specific ideas and questions related to a topic when the user inputs it. They also lack the means to evaluate and further expand on the generated ideas and questions. Furthermore, they lack integration with web conferencing tools, making it difficult to effectively utilize information obtained during meetings.

[1629] 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.

[1630] In this invention, the server includes a means for inputting a theme from a user, a means for converting the theme into a prompt, a means for transmitting the prompt to a generative AI model, a means for receiving output from the generative AI model, a means for displaying generated ideas and questions to the user, and a means for input from a Web UI and a means for linking with a web conferencing tool. This makes it possible to automatically generate specific ideas and questions based on the theme input by the user, and to evaluate and expand them. Furthermore, linking with a web conferencing tool makes it possible to effectively utilize information obtained during a conference.

[1631] The "means for user theme input" is a means for providing an interface for the user to input a brainstorming theme.

[1632] The "means for converting the theme into a prompt sentence" refers to a means for converting the theme entered by the user into a prompt sentence in a format suitable for the generative AI model.

[1633] The "means for transmitting the prompt sentence to the generative AI model" refers to a means for transmitting the generated prompt sentence to the generative AI model.

[1634] "Means for receiving output from the generative AI model" refers to means for receiving ideas or questions returned from the generative AI model.

[1635] "Means for displaying generated ideas and questions to a user" means means for displaying ideas and questions received from a generative AI model to a user.

[1636] "Means for input from WebUI" refers to the means by which a user can input information through a web interface.

[1637] "Means of integration with web conferencing tools" refers to means of integrating with web conferencing tools to obtain information and utilize it within the system.

[1638] MODE FOR CARRYING OUT THE INVENTION

[1639] This invention is a brainstreaming support system that uses a generative AI model to generate related ideas and questions based on a user-input topic. Specific embodiments of this system are described below.

[1640] System configuration

[1641] The system consists of the following main components:

[1642] 1. User theme input method

[1643] 2. A means of converting the theme into a prompt sentence

[1644] 3. Means for sending the prompt sentence to the generative AI model

[1645] 4. A means of receiving output from a generative AI model

[1646] 5. A way to display generated ideas and questions to users

[1647] 6. Input method from WebUI

[1648] 7. How to integrate with web conferencing tools

[1649] Hardware and software used

[1650] Hardware: Servers, devices (users' PCs and smartphones)

[1651] Software: Generative AI models (e.g., GPT-4), web browsers, HTML, JavaScript, Python

[1652] Program processing

[1653] The user inputs a theme through a web browser. For example, the theme is "new business development." The device sends this theme to the server. The server converts the received theme into a prompt. Specifically, it generates the prompt, "Please generate questions or ideas related to 'new business development.'"

[1654] The server sends this prompt to a generative AI model (GPT-4), which generates relevant questions and ideas based on the prompt. For example, it generates content such as "What are the market needs for new business development?" or "Leverage the existing customer base to develop new businesses."

[1655] The generated questions and ideas are sent to the device via the server, and the device displays this information in a web browser, allowing users to brainstorm based on this information.

[1656] Specific examples

[1657] The user inputs the theme "new business development." The device sends this theme to the server. The server generates a prompt message saying, "Generate questions and ideas related to 'new business development,'" and sends this to the generative AI model (GPT-4). The generative AI model generates questions and ideas such as, "What are the market needs for new business development?" and "Leverage the existing customer base to develop new businesses." The server receives these generated results and sends them to the device. The device displays the received questions and ideas on the browser, and the user uses them to brainstorm.

[1658] In this way, users can get diverse perspectives and ideas related to the topic and receive brainstorming support.

[1659] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1660] Step 1:

[1661] The user inputs a theme.

[1662] The user accesses the interface on a web browser and enters the theme they want to brainstream into the theme input field. For example, they might enter "new business development." The entered theme is temporarily stored in the device's memory.

[1663] Step 2:

[1664] The device sends the theme to the server.

[1665] The terminal sends the theme entered by the user to the server as an HTTP request. This request is made using the JavaScript fetch function. The input data is the theme "New Business Development", and the output is a request sent to the server.

[1666] Step 3:

[1667] The server converts the theme into a prompt.

[1668] The server generates a prompt based on the received theme. For example, for the theme "New Business Development," it creates the prompt "Please generate questions and ideas related to 'New Business Development'." The input data is the theme "New Business Development," and the output is the prompt "Please generate questions and ideas related to 'New Business Development'."

[1669] Step 4:

[1670] The server sends the prompt to the generative AI model.

[1671] The server sends the generated prompt sentence to the generative AI model (GPT-4). This communication is performed using an API request. The input data is the prompt sentence, and the output is a request sent to the generative AI model.

[1672] Step 5:

[1673] Generative AI models generate questions and ideas.

[1674] The generative AI model generates relevant questions and ideas based on the prompt it receives, such as "What are the market needs for new business development?" or "Leverage the existing customer base to develop new businesses." The input data is the prompt, and the output is the generated questions and ideas.

[1675] Step 6:

[1676] The server receives the generated questions and ideas.

[1677] The server receives the questions and ideas returned by the generative AI model. This data is received in JSON format. The input data is the output from the generative AI model, and the output is the data received by the server.

[1678] Step 7:

[1679] The server sends questions and ideas to the device.

[1680] The server sends the received questions and ideas to the terminal as an HTTP response. This response is also in JSON format. The input data is the generated questions and ideas, and the output is the data sent to the terminal.

[1681] Step 8:

[1682] The device displays questions and ideas to the user.

[1683] The device displays the questions and ideas received from the server on the browser. Users can brainstorm based on this information. The input data is the response from the server, and the output is what is displayed on the browser.

[1684] (Application example 1)

[1685] Next, a description will be given of Application Example 1 of Form 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."

[1686] Conventional brainstreaming support systems have the ability to generate ideas and questions based on themes entered by users, but they lack support specialized for specific industries or applications. In particular, they lack the ability to generate specific ideas and questions to improve production efficiency within factories, making it difficult for factory managers and engineers to efficiently find ways to improve production lines.

[1687] 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.

[1688] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conference tool, a means for generating ideas and questions for improving production efficiency in a factory, and a learning means for providing feedback on the generated ideas and questions and reflecting the feedback in future generation. This enables factory managers and engineers to efficiently generate specific ideas and questions for improving production efficiency and find improvement measures.

[1689] The "user topic input means" is an interface that allows the user to input a specific topic or problem.

[1690] "Generative AI methods" are artificial intelligence functions that generate related ideas and questions based on an input topic.

[1691] The "evaluation means" is a function that allows users to evaluate the generated ideas and supports the expansion and improvement of the ideas based on the evaluation results.

[1692] "WebUI input means" means a means by which a user inputs information through a web user interface.

[1693] "Means for linking with web conferencing tools" refers to a function that links with web conferencing tools to share information and utilize data such as minutes.

[1694] The "means for generating ideas and questions to improve production efficiency in a factory" is a function for generating ideas and questions specialized for improving production efficiency in a factory.

[1695] "Learning means that provides feedback on generated ideas and questions and reflects it in future generations" is a function that collects feedback from users and allows the generative AI to reflect that feedback in the generation of future ideas and questions.

[1696] As an embodiment of the present invention, a brainstreaming support system for improving production efficiency within a factory will be specifically described.

[1697] System Configuration

[1698] The system includes the following major hardware and software components:

[1699] Server: Hosts the generative AI model, receives thematic input from users, and generates relevant ideas and questions.

[1700] User terminal: A device (e.g., PC, tablet) where factory managers and engineers can input topics and review generated ideas and questions.

[1701] Web User Interface (WebUI): The interface through which users can enter topics and view generated ideas and questions.

[1702] Web conferencing tools: Tools to capture meeting minutes and integrate with systems.

[1703] Program processing

[1704] The server processes and calculates data using the following means:

[1705] 1. Theme input method: The user inputs a theme through the Web UI. For example, the user inputs the theme "improving production line efficiency."

[1706] 2. Generative AI methods: Generative AI models such as OpenAI's GPT-3 are used to generate relevant ideas and questions based on the input topic. These ideas and questions are then processed on the server and sent to the user's device.

[1707] 3. Evaluation method: Users evaluate the generated ideas and questions. The evaluation results are sent to the server and reflected in future generation.

[1708] 4. Input from WebUI: Users provide feedback through the WebUI and evaluate the generated ideas and questions.

[1709] 5. Means of integration with web conferencing tools: Information is obtained from the minutes of web conferencing tools and used as training data for generative AI models.

[1710] 6. Learning method: The generative AI model is updated based on user feedback and reflected in the generation of ideas and questions from the next time onwards.

[1711] Specific examples

[1712] For example, if a factory manager inputs the theme "improving production line efficiency," the generative AI model will generate ideas and questions like the following:

[1713] "Where is the bottleneck on the production line?"

[1714] "What processes can be automated?"

[1715] "Would changing the layout of the production line improve efficiency?"

[1716] These ideas and questions are displayed on the user's device's WebUI, where users can rate and provide feedback.

[1717] Prompt Sentence Examples

[1718] Theme: Improving production line efficiency

[1719] Generate relevant ideas and questions.

[1720] In this way, specific ideas and questions for improving production efficiency within the factory can be efficiently generated, enabling managers and engineers to find improvement measures.

[1721] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1722] Step 1:

[1723] The user enters the theme through the WebUI.

[1724] Input: The user inputs a theme such as "improving production line efficiency."

[1725] Output: The input theme is sent to the server.

[1726] Specific operation: The user enters a theme into the input field of the WebUI and clicks the "Submit" button.

[1727] Step 2:

[1728] The server uses a generative AI model to generate relevant ideas and questions based on the input topic.

[1729] Input: The server receives the theme submitted by the user.

[1730] Output: A list of ideas and questions generated by the generative AI model.

[1731] How it works: The server sends a theme as a prompt to a generative AI model such as OpenAI's GPT-3, and receives the generated ideas and questions.

[1732] Step 3:

[1733] The server transmits the generated ideas and questions to the user terminal.

[1734] Input: A list of ideas or questions generated by a generative AI model.

[1735] Output: Ideas and questions displayed on the user's terminal.

[1736] Specific operation: The server sends the generated ideas and questions to the WebUI on the user's device and displays them.

[1737] Step 4:

[1738] Users rate the generated ideas and questions.

[1739] Input: Users rate the ideas and questions displayed.

[1740] Output: The evaluation result is sent to the server.

[1741] Specific operation: The user clicks an evaluation button on the Web UI, such as "Be original," "Be realistic," or "Review from a management perspective."

[1742] Step 5:

[1743] The server receives the evaluation results from the user and saves them as learning data to be reflected in future generations.

[1744] Input: The evaluation results submitted by the user.

[1745] Output: The evaluation results are saved and used as training data for the generative AI model.

[1746] Specific operation: The server stores the evaluation results in a database and provides them as feedback to the learning algorithm of the generative AI model.

[1747] Step 6:

[1748] The server obtains information from the minutes of the web conferencing tool and uses it as learning data for the generative AI model.

[1749] Input: Minutes data from a web conferencing tool.

[1750] Output: The minutes data is used as training data for the generative AI model.

[1751] Specific operation: The server obtains the minutes data through the API of the web conferencing tool and provides it to the learning algorithm of the generative AI model.

[1752] In this way, specific ideas and questions for improving production efficiency within the factory can be efficiently generated, enabling managers and engineers to find improvement measures.

[1753] Example 2

[1754] Next, a description will be given of Example 2 of Form 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."

[1755] Conventional brainstorming support systems have had the problem of not being able to provide appropriate feedback or expansion on the ideas entered by users. Furthermore, the evaluation criteria are limited, making it difficult to expand on ideas from multiple perspectives. Furthermore, there is a lack of concrete methods for improving the quality and relevance of generated ideas.

[1756] 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.

[1757] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, a means for generating a prompt sentence based on the evaluation, a means for sending the generated prompt sentence to a generative AI model, a means for returning a response from the generative AI model to the user, and a means for input from a Web UI and a means for linking with a Web conferencing tool. This enables the ideas input by the user to be evaluated and expanded from multiple perspectives, thereby improving the quality and relevance of the generated ideas.

[1758] The "means for user theme input" is an interface that allows users to input ideas and themes into the system.

[1759] "Generative AI methods" are artificial intelligence functions that generate relevant ideas and questions based on a topic entered by the user.

[1760] The "evaluation means" is an interface that allows users to evaluate the generated ideas, and includes evaluation buttons such as "original," "realistic," and "review from a management perspective."

[1761] The "means for generating prompt sentences" is a function that creates prompt sentences to be sent to the generative AI model based on the user's evaluation.

[1762] "Means for sending to the generative AI model" refers to a communication means for sending the generated prompt sentence to the generative AI model.

[1763] "Means for returning responses from the generative AI model to the user" refers to a function for returning new ideas and answers received from the generative AI model to the user.

[1764] "Input means from WebUI" means a means by which a user inputs information into the system through a web interface.

[1765] "Means of integration with web conferencing tools" refers to a function that allows you to utilize information such as minutes by integrating with web conferencing tools.

[1766] This invention is a system that utilizes a generative AI model based on a theme entered by a user to support the evaluation and expansion of ideas. Specific embodiments of this system are described below.

[1767] First, the user uses a device (such as a PC or smartphone) to input a theme into the system's Web UI. For example, the user might input "Consider introducing new technology for new business development."

[1768] Next, the user presses one of the evaluation buttons for the entered theme, such as "creative," "realistic," or "review from a management perspective." For example, the user presses the "creative" button.

[1769] The server generates an appropriate prompt based on the evaluation button pressed by the user. For example, if the "Be creative" button is pressed, the server generates the prompt "What kind of creative business will become possible with the introduction of new technology?"

[1770] Next, the server sends the generated prompt to a generative AI model (e.g., OpenAI's GPT-4) via an API.

[1771] The generative AI model generates new ideas based on the prompt it receives. For example, in response to the prompt, "What kind of unique business will become possible with the introduction of new technology?", it generates ideas such as "A new logistics service that utilizes AI-powered autonomous driving technology."

[1772] Finally, the server returns the new ideas received from the generative AI model to the user by displaying them on the device screen.

[1773] The system allows users to evaluate and expand on ideas from multiple perspectives, improving the quality and relevance of the generated ideas. It can also utilize information from meeting minutes by linking with web conferencing tools.

[1774] As a concrete example, consider the case where a user inputs "Consider introducing new technology for new business development" and presses the evaluation button for "Review from the perspective of management." In this case, the server generates a prompt message asking, "What are the advantages and risks of introducing new technology from the perspective of management?" The generative AI model generates new ideas and reviews based on this prompt message, and the server returns the results to the user.

[1775] Examples of prompts include:

[1776] "What kind of creative business will become possible with the introduction of new technology?"

[1777] "What are the benefits and risks of introducing new technology from a management perspective?"

[1778] "What practical impact will the introduction of new technologies have?"

[1779] In this way, users can evaluate and further expand their ideas using generative AI models.

[1780] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1781] Step 1:

[1782] The user inputs a theme into the input form on the terminal.

[1783] Input: Theme entered by the user (e.g., "Consider introducing new technology for new business development")

[1784] Output: The input theme is sent to the server.

[1785] Specific operation: The user uses the device's WebUI to enter a theme and press the send button.

[1786] Step 2:

[1787] The user presses the rating button.

[1788] Input: A rating button that the user selects (e.g., "Creatively").

[1789] Output: The selected rating is sent to the server.

[1790] Specific operation: The user presses one of the evaluation buttons for the entered theme, such as "original," "realistic," or "review from a management perspective."

[1791] Step 3:

[1792] The server generates a prompt.

[1793] Input: User-entered theme and rating button selection information

[1794] Output: Generated prompt (e.g., "What creative ventures will become possible with the introduction of new technology?")

[1795] Specific operation: The server generates an appropriate prompt sentence based on the rating button pressed by the user.

[1796] Step 4:

[1797] The server sends a prompt to the generative AI model.

[1798] Input: Generated prompt text

[1799] Output: The prompt sent to the generative AI model

[1800] Specific operation: The server sends the generated prompt sentence to the generative AI model (e.g., OpenAI's GPT-4) via an API.

[1801] Step 5:

[1802] Generative AI models generate new ideas.

[1803] Input: The prompt sent to the generative AI model

[1804] Output: Generated new ideas (e.g., "A new logistics service utilizing AI-based autonomous driving technology")

[1805] Specific operation: The generative AI model generates new ideas based on the received prompt.

[1806] Step 6:

[1807] The server returns the generated ideas to the user.

[1808] Input: New ideas received from the generative AI model

[1809] Output: The new idea displayed on the user's terminal

[1810] Specific operation: The server sends new ideas received from the generative AI model to the user's device and displays them on the screen.

[1811] (Application example 2)

[1812] Next, a description will be given of Application Example 2 of Form 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."

[1813] Conventional brainstorming support systems lacked specific means for users to further expand on the ideas they generated. They also lacked functionality to help content creators generate new content ideas and further expand them using a rating button. This made it difficult to improve creativity and generate ideas efficiently.

[1814] 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.

[1815] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting expansion of the generated ideas, an input means from a Web UI and a linking means with a Web conference tool, a means for supporting content creators in generating new content ideas and further expanding them using a rating button, and an application means installed on a smartphone or a head-mounted display. This allows users to further expand on their generated ideas using the rating button, thereby improving creativity and realizing efficient idea generation.

[1816] The "user theme input means" is an interface that allows a user to input a specific theme or topic into the system.

[1817] "Generative AI methods" are artificial intelligence functions that automatically generate related ideas and questions based on an input topic.

[1818] The "evaluation tool" is an interface that allows users to evaluate the generated ideas, such as "originality," "realism," and "review from a management perspective."

[1819] "WebUI input means" means a means by which a user inputs information through a web user interface.

[1820] "Means for linking with web conferencing tools" refers to a function that links with web conferencing tools to utilize information such as minutes.

[1821] "A means to assist content creators in generating new content ideas and further developing them using the rating button" is a support function that enables content creators to generate new ideas and further develop them using the rating button.

[1822] "Application means installed on a smartphone or head-mounted display" refers to a means for using the system through an application installed on a smartphone or head-mounted display.

[1823] A system for implementing this invention includes a means for user theme input, a generative AI means, an evaluation means, an input means from a Web UI, a means for linking with a Web conferencing tool, a means for supporting content creators in generating new content ideas and further expanding them using evaluation buttons, and an application means to be installed on a smartphone or head-mounted display.

[1824] System program processing explanation

[1825] Hardware and Software Use

[1826] Hardware:

[1827] Smartphone

[1828] head-mounted display

[1829] server

[1830] software:

[1831] OpenAI API

[1832] Python Program

[1833] WebUI

[1834] Web conferencing tools

[1835] Data processing and calculation

[1836] User Action:

[1837] Users use a smartphone or head-mounted display to input a theme, such as "Consider introducing new technology to develop new businesses."

[1838] Generative AI processing:

[1839] The server uses generative AI (e.g., GPT-3) to generate related ideas and questions based on the input topic. Generated ideas might include, for example, "What unique business ventures will become possible with the introduction of new technology?"

[1840] Operation of the assessment instrument:

[1841] For each generated idea, users can rate it with buttons such as "original," "realistic," or "review from a management perspective." For example, if users press the "original" rating button, the generative AI will generate a new idea such as "By introducing new technology, we will provide a personalized content distribution service using AI."

[1842] Integration with WebUI and web conferencing tools:

[1843] Users can input information through the WebUI and utilize information from the minutes of the web conferencing tool, enabling more detailed idea generation.

[1844] Supporting content creators:

[1845] Content creators can further expand on generated ideas using the rating button and generate new content ideas, which will improve creativity and make idea generation more efficient.

[1846] Examples and prompts

[1847] Examples:

[1848] Initial idea: "Consider introducing new technology to develop new businesses."

[1849] User rating: "Ingenious"

[1850] Generated idea: "By introducing new technology, we will provide a personalized content delivery service using AI."

[1851] Example prompt sentence:

[1852] "When developing new businesses, it is important to think creatively about introducing new technologies."

[1853] In this way, the generative AI generates new ideas based on user evaluations, supporting the creativity of content creators.

[1854] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1855] Step 1:

[1856] The user inputs a theme using a smartphone or head-mounted display. For example, they input a theme such as "Consider introducing new technology for new business development." The input theme is sent to the server.

[1857] Input: The theme entered by the user

[1858] Output: The theme sent to the server

[1859] Step 2:

[1860] The server sends the received theme to a generative AI model (e.g., GPT-3) to generate related ideas and questions. The generative AI model generates prompts based on the theme and outputs corresponding ideas.

[1861] Input: The theme sent to the server

[1862] Output: Ideas and questions generated by the generative AI model

[1863] Step 3:

[1864] The server sends the generated ideas and questions to the user's device, where the user can view the generated ideas via a smartphone or head-mounted display.

[1865] Input: Ideas or questions generated by a generative AI model

[1866] Output: Ideas and questions sent to the user's device

[1867] Step 4:

[1868] The user presses evaluation buttons for the generated ideas, such as "original," "realistic," and "review from a managerial perspective." The information selected by the evaluation button is sent to the server.

[1869] Input: User's rating button selection information

[1870] Output: Rating button selection information sent to the server

[1871] Step 5:

[1872] The server generates a new prompt sentence based on the selection information of the rating button and sends it to the generative AI model again. The generative AI model generates further expanded ideas based on the new prompt sentence.

[1873] Input: Rating button selection information sent to the server

[1874] Output: Augmented ideas generated by the generative AI model

[1875] Step 6:

[1876] The server sends the augmented ideas to the user's device, where the user can view the augmented ideas via a smartphone or head-mounted display.

[1877] Input: Augmented ideas generated by a generative AI model

[1878] Output: The extension idea sent to the user's device

[1879] Step 7:

[1880] The user can continue to hit the rating button and expand on the idea as needed, and the process repeats until the user is satisfied.

[1881] Input: User's rating button selection information

[1882] Output: Further expanded ideas generated by the generative AI model

[1883] In this way, the user can further expand on the generated ideas using the rating buttons, which improves creativity and allows for more efficient idea generation.

[1884] Example 3

[1885] Next, a third embodiment of the third embodiment will be described. 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."

[1886] Conventional brainstreaming support systems allow users to input topics and generate ideas using generative AI, but they lack sufficient integration with web conferencing tools, making it difficult to effectively utilize information obtained from meeting minutes. Furthermore, support for evaluating and expanding on generated ideas is limited, making it difficult for users to obtain the specific, practical ideas they desire. This poses a challenge, reducing the efficiency and effectiveness of brainstreaming.

[1887] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1888] In this invention, the server includes a means for inputting a theme from a user, a generative AI means for generating ideas and questions related to the theme, an evaluation means for supporting the expansion of the generated ideas, an input means from a Web UI and a means for linking with a Web conferencing tool, a means for analyzing minutes of the Web conferencing tool and extracting important information, a means for creating and sending prompts to the generative AI model based on the extracted information, and a means for displaying ideas generated by the generative AI model to the user. This makes it possible to effectively utilize information obtained from minutes of the Web conferencing tool to generate specific and practical ideas that users desire.

[1889] The "means for user theme input" refers to a means for providing an interface for users to input specific themes or topics to the system.

[1890] "Generative AI methods" are methods that use artificial intelligence technology to generate related ideas and questions based on an input topic.

[1891] The "evaluation means" is a means for users to evaluate and provide feedback on the generated ideas.

[1892] "Input means from WebUI" refers to the means by which a user inputs information into the system via a web browser.

[1893] "Means for linking with web conferencing tools" refers to the means for linking the system with web conferencing tools and importing meeting minutes and other information into the system.

[1894] "Means for analyzing minutes from a web conferencing tool and extracting important information" refers to means for analyzing minutes obtained from a web conferencing tool and extracting important information from them.

[1895] "Means for creating and sending prompt sentences to a generative AI model" refers to means for creating appropriate prompt sentences for a generative AI model based on extracted information and sending them.

[1896] "Means for displaying ideas generated from a generative AI model to a user" refers to means for displaying ideas generated from a generative AI model to a user.

[1897] The present invention is a brainstreaming support system in which a user, a terminal, and a server work together. A specific embodiment of this system will be described below.

[1898] User Actions

[1899] Users access the system's WebUI using a web browser. The WebUI has input fields such as text boxes and drop-down menus, where users can enter information such as "I want to generate ideas for new business development."

[1900] Device operation

[1901] Users use devices (PCs or smartphones) to launch a web conferencing tool and hold a meeting. The content discussed during the meeting is recorded using the conferencing tool's recording and minutes-creation functions. After the meeting ends, the device uploads the meeting minutes to the server, either automatically or via user operation. The minutes are saved as text files or PDF format.

[1902] Server Processing

[1903] The server receives the uploaded minutes and analyzes them using natural language processing (NLP) technology. Specifically, it uses tools such as Python's NLTK library and SpaCy to extract important information from the minutes, such as "New business development requires the introduction of new technology."

[1904] Based on the extracted information, the server creates a prompt to be sent to the generative AI model. For example, it creates a prompt such as, "What new businesses can be developed by introducing new technology?" The created prompt is sent to the generative AI model via an API.

[1905] A generative AI model (e.g., OpenAI's GPT-3) generates new ideas based on the prompt it receives, and the generated ideas are returned to the server in text format.

[1906] The server receives the ideas returned by the generative AI model and sends them to the device using communication protocols such as HTTP requests or WebSockets.

[1907] Terminal display

[1908] The terminal displays the ideas received from the server to the user. The generated ideas are displayed on the Web UI, allowing the user to review them. The user can provide feedback and request the idea generation again if necessary.

[1909] Specific examples

[1910] 1. The user enters through the WebUI, "I would like you to generate ideas for new business development."

[1911] 2. A user holds a meeting using a web conferencing tool and uploads the minutes to the system.

[1912] 3. The server analyzes the minutes and extracts the information that "new technology needs to be introduced to develop new businesses."

[1913] 4. The server creates a prompt for the generative AI model: "What new businesses can be developed by introducing new technology?"

[1914] 5. The generative AI model generates new ideas and displays them to the user via their device.

[1915] Prompt Sentence Examples

[1916] "Generate ideas about what new businesses can be developed with the introduction of new technologies."

[1917] In this way, the system of the present invention utilizes information obtained from minutes by linking the Web UI and the web conferencing tool, and generates new ideas using the generative AI model. This allows users to obtain specific and practical ideas. The flow of the identification process in Example 3 will be described with reference to Figure 15.

[1918] Step 1:

[1919] The user enters information through the WebUI.

[1920] The user opens a web browser and accesses the system's WebUI. The WebUI has input fields such as text boxes and drop-down menus, where the user enters information such as "I would like you to generate ideas for new business development." The entered information is sent to the server, where the server receives the input data in text format.

[1921] Step 2:

[1922] The device will hold the meeting using a web conferencing tool.

[1923] Users use their devices (PCs or smartphones) to launch a web conferencing tool and hold a meeting. The content discussed during the meeting is recorded using the recording and minutes-creation functions of the conferencing tool. After the meeting ends, the device uploads the minutes to the server, either automatically or via user operation. The minutes are saved as text files or PDF format. The input data is the minutes file, which is received by the server.

[1924] Step 3:

[1925] The server analyzes the minutes and extracts important information.

[1926] The server receives the uploaded minutes and analyzes them using natural language processing (NLP) technology. Specifically, it uses tools such as Python's NLTK library and SpaCy to extract important information from the minutes, such as "New technology needs to be introduced for new business development." The input data is the text of the minutes, and the output data is the extracted important information.

[1927] Step 4:

[1928] The server creates and sends a prompt to the generative AI model.

[1929] The server creates a prompt to be sent to the generative AI model based on the extracted information. For example, it creates a prompt such as, "What new businesses can be developed by introducing new technology?" The created prompt is sent to the generative AI model via an API. The input data is the extracted information, and the output data is the prompt.

[1930] Step 5:

[1931] Generative AI models generate new ideas.

[1932] A generative AI model (e.g., OpenAI's GPT-3) generates new ideas based on the received prompt. The generated ideas are returned to the server in text format. The input data is the prompt, and the output data is the generated ideas...

Claims

1. a theme input means for receiving a theme input from a user; A generative AI means for generating ideas and questions related to the theme; An evaluation means for supporting the expansion of the ideas generated by the generative AI means; An emotion recognition means for recognizing an emotion of the user; a means for evaluating ideas and questions based on the emotions recognized by the emotion recognition means and generating new ideas and questions; An input means and a means for linking with a conference tool; A system including:

2. 2. The system according to claim 1, wherein the evaluation means provides an interface for a user to evaluate the ideas generated by the generative AI means.

3. The system according to claim 1 , wherein the linking means utilizes information from minutes of a Web conference tool.

Images