Idea generation support method and system

Abstract

To provide an idea generation support method and a program which provide an idea generation support method.SOLUTION: An idea generation support method is executed by a system comprising: a generation AI server which uses a large scale language model, and executes natural language processing; and a terminal coupled to the generation AI server through a network. The method comprises: a step for sending by the terminal, an instruction for generating elements of two or more kinds of categories about a prescribed commodity, to the generation AI server; a step for generating elements of two or more kinds of categories about the prescribed commodity by the generation AI server, and sending elements of the two or more kinds of categories to a terminal; a step for sending by the terminal, an instruction for generating a concept of the commodity in which the elements of two or more kinds of categories are combined, to the generation AI server; and a step for generating by the generation AI server, the concept of the commodity including the elements of two or more kinds of categories assembled thereto, then sending the concept of the commodity in which the two or more kinds of elements are assembled, to the terminal.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to an idea generation support method and system. [Background technology]

[0002] Patent Document 1 discloses an idea generation support method. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7117044 Summary of the Invention [Problem to be solved by the invention]

[0004] In Patent Document 1, idea generation support is performed by performing morphological analysis of natural language sentences. However, when performing morphological analysis, words are separated from their context, so the context must be reconstructed by a human being after that.

[0005] The present invention has been made to solve such conventional problems, and has an object to provide idea support. [Means for solving the problem]

[0006] The present invention is an idea generation support method executed in a system including a generation AI server that performs natural language processing using a large-scale language model and a terminal connected to the generation AI server via a network, and includes the steps of: the terminal sending an instruction to the generation AI server to generate elements of two or more categories for a specified product; the generation AI server generating elements of two or more categories for the specified product and transmitting the elements of the two or more categories to the terminal; the terminal sending an instruction to the generation AI server to generate a product concept that combines elements of the two or more categories; and the generation AI server generating a product concept that combines the two or more elements and transmitting the product concept that combines the two or more elements to the terminal. Effect of the Invention

[0007] According to the idea generation support method and program of the present invention, it is possible to support idea generation. [Brief description of the drawings]

[0008] [Figure 1] Schematic diagram of a system for executing an idea support method [Diagram 2] Terminal block diagram [Diagram 3] Flowchart of the idea generation support method [Figure 4] Flowchart of the idea support program DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an idea generation support method according to an embodiment will be described in detail with reference to the drawings.

[0010] 1 is a schematic diagram of a system for executing the idea generation support method. In order to execute the idea generation support method, a terminal 1 is connected to a generation AI server 2 via a network.

[0011] The generation AI server 2 is a computer that executes processing of character strings made of input natural language (in the embodiment, element generation processing, concept generation processing, and content generation processing). The generation AI server 2 in the embodiment is a generation AI server that provides a cloud-based service incorporating large-scale language models such as ChatGPT (above, conversational service), GPT-4 Turbo, GPT-4, GPT-3.5 Turbo, GPT-3.5, and GPT-3 (above, API service) from OpenAI. Note that the generation AI server 2 is not limited to this, and may be a generation AI server that executes natural language processing incorporating a large-scale language model that provides similar functions (for example, Bard (above, conversational service) and Gemini (above, API service) developed by Google, etc.) or Claude3.

[0012] The generation AI server 2 in the embodiment has a CPU, memory, input / output devices, and an external interface, and performs natural language processing incorporating a large-scale language model in response to input from an external device (in the embodiment, element generation processing, concept generation processing, and content generation processing), and outputs the processing.

[0013] 2 is a block diagram of a terminal 1 in a system for executing an idea generation support method according to an embodiment. The terminal is, for example, a personal computer, tablet, smartphone, or the like owned by a user.

[0014] A CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a HDD (Hard Disk Drive) 105, an external I / F (Interface) 106, and an input unit 107 are connected via a system bus 108. The CPU 101, the ROM 102, and the RAM 103 constitute a control unit 104.

[0015] The ROM 102 prestores programs and thresholds executed by the CPU 101. The RAM 103 has various memory areas, such as an area for loading the programs executed by the CPU 101 and a work area that serves as a work area for data processing by the programs.

[0016] The HDD 105 stores patent data (natural language sentence data) and the like input from the input unit 107. The external I / F 106 is an interface for communicating with an external device such as an external server (PC), for example.

[0017] The external I / F 106 may be any interface that performs data communication with an external device, and may be, for example, a device (such as a USB memory) that connects locally to the external device, or may be a network interface for communication via a wired or wireless network.

[0018] The control unit 104 transmits instruction information, generates elements, generates concepts, and receives content generation results by exchanging data with an external device (a generation AI server) via the external I / F 106.

[0019] The external I / F 106 is connected to a display device (not shown) such as a liquid crystal display, etc. The input unit 107 is an input device such as a keyboard, a mouse, a scanner (reading device), etc.

[0020] (First embodiment) Next, a description will be given of a processing procedure of the idea support method according to the first embodiment. Note that, in the embodiment, idea support is performed for a vacuum cleaner, but the target product is not limited to this.

[0021] ChatGPT was used to implement the idea generation support method. ChatGPT is a system in which, when a prompt is entered into a window, the generation AI server generates an answer by executing natural language processing incorporating a large-scale language model and displays it in the window. In the following explanation, the content entered into the window is referred to as (prompt), and the output from the generation AI server to the window is referred to as (output of the generation AI). Note that other similar systems besides ChatGPT, such as Bard or Bing AI chat, may also be used.

[0022] 3 is a flowchart of the idea generation support method according to the embodiment. In STEP 1, an element group is generated, in STEP 2, a product concept is generated, in STEP 3, element contents are generated, and in STEP 4, structure contents are generated.

[0023] (STEP 1: Element generation step) First, the terminal 1 sends element generation instruction information (hereinafter also referred to as a prompt) to the generation AI server 2. In this embodiment, element groups are generated in three categories: benefit, quality, and technology. The number of categories of the element groups to be generated is not limited to this and may be two or more. Also, in this embodiment, 10 elements are generated as element groups for each category, but the number of elements is not limited to this and may be more or less than this.

[0024] (Generating a group of benefit factors) (prompt) Create 10 vacuum cleaner benefit elements.

[0025] (Generative AI output) The benefits of a vacuum cleaner include: 1. A comfortable feeling of cleanliness: By using the vacuum cleaner's performance to clean a room, users can experience fresh air and a clean space. 2. Reduced Effort: Compared to traditional cleaning methods, using these vacuum cleaners reduces physical stress and effort to a great extent. 3. Improved housework efficiency: Using a high-performance vacuum cleaner reduces cleaning time, thereby improving the overall efficiency of housework. 4. Worry-free hygiene: These vacuum cleaners effectively remove fine dust particles and allergens, allowing users to maintain good hygiene at home. 5. Stress-free operation: Eliminating unnecessary cords and hassle allows users to enjoy cleaning without stress. 6. Pride in your home: Keeping your home clean will give you a sense of pride when guests visit your home. 7. Satisfaction with Usability: The ease of use and functionality of the vacuum cleaner makes the user feel satisfied with their daily cleaning activities. 8. Comfortable living environment: Regular cleaning improves the quality of your living space and helps maintain a comfortable living environment. 9. Time-saving fulfillment: The efficient features of the vacuum cleaner reduce the time spent on cleaning, which can be used for other meaningful activities. 10. Confidence in a Smart Choice: By choosing these vacuum cleaners, you can feel confident that you have made a smart choice by taking advantage of the latest technology.

[0026] (Quality element group generation) (prompt) Create 10 vacuum cleaner quality elements.

[0027] (Generative AI output) The quality factors of a vacuum cleaner are as follows: 1. Suction: It has strong suction power and can efficiently suck up dust and debris. 2. Operability: Easy to use, allowing for smooth cleaning in a variety of situations. 3. Durability: It is hard to break even with prolonged or extended use, and will last a long time. 4. Maintenance: Regular maintenance and filter replacement are easy to perform. 5. Energy-saving: Low power consumption with high performance, energy efficient. 6. Quiet operation: Quiet operation so as not to disturb family or neighbors. 7. Lightweight: Lightweight and easy to carry, it is also easy to move up stairs. 8. Compactness: It has a compact design so that it doesn't take up much space when stored. 9. Safety: It has a safety design to prevent accidents and breakdowns during use. 10.Environmental friendliness: Use of recyclable materials and low environmental impact of waste.

[0028] (Technical element group generation) (prompt) Craft 10 vacuum cleaner tech elements.

[0029] (Generative AI output) The technical elements of a vacuum cleaner are as follows: 1. Motor: The central part that generates suction power. 2. Battery: Rechargeable battery as power source. 3. Dust bag / paper pack: A bag to store the sucked-up dust and debris. 4. Filter system: The part that captures tiny particles and allergens in the air. 5. Suction port / brush unit: A part for effectively sucking up dirt and dust. 6. Sensor: Sensors that detect obstacles and recognize the shape of the room. 7. Operation Panel & Switches: The interface through which the user operates the functions of the vacuum cleaner. 8. Control unit: The electronic circuits and programs that control the operation of the vacuum cleaner. 9. Dust box: The part that stores the sucked-up garbage and dust. 10. Exterior & Main Frame: Casing that maintains the overall shape and protects the components.

[0030] In this way, the generation AI server 2 is able to generate a group of elements with few omissions for the categories of benefit, quality, and technology for the vacuum cleaner. The generation AI server 2 generates 10 elements for the category of benefit, 10 elements for the category of quality, and 10 elements for the category of technology. Then, it transmits these elements to the terminal 1.

[0031] (STEP 2: Concept generation step) Next, the terminal 1 transmits concept generation instruction information to the generation AI server 2. In the embodiment, a vacuum cleaner concept is generated by combining element groups in three categories: benefit, quality, and technology.

[0032] (prompt) You are a consultant and have been asked to come up with a new vacuum cleaner concept. Below is an analysis of the benefits, quality, and technology of vacuum cleaners. Benefits are the essential requirements for a vacuum cleaner that users want. The quality is what the vacuum cleaner needs to have in order to realize that benefit. The technology would be the mechanism and other technology required for a vacuum cleaner to achieve that quality. The components of benefits and their explanations are as follows: A pleasant feeling of cleanliness: By using the vacuum cleaner's performance to clean the room, users can experience fresh air and a clean space. Reduced Effort: Compared to traditional cleaning methods, using these vacuum cleaners reduces physical stress and effort to a great extent. Improved household efficiency: Using a high-performance vacuum cleaner reduces cleaning time, thereby improving the overall efficiency of household chores. Worry-free hygiene: These vacuums effectively remove fine dust particles and allergens, allowing users to maintain good hygiene in their homes. Stress-free operation: Eliminating unnecessary cords and hassle allows users to enjoy cleaning without stress. Pride in your home: Keeping your home clean will give you confidence when guests visit. Satisfaction with Usability: The ease of use and functionality of the vacuum cleaner makes users feel satisfied with their daily cleaning activities. Comfortable living environment: Regular cleaning improves the quality of your living space and helps maintain a comfortable living environment. Time-saving fulfillment: The efficient features of the vacuum cleaner reduce the time spent cleaning, which can be spent on other worthwhile activities. Confidence in a Smart Choice: By choosing these vacuums, you can feel confident that you have made a smart choice by taking advantage of the latest technology. The quality elements and their explanations are as follows: Suction: It has a strong suction power and can efficiently pick up dust and debris. Operability: Easy to use, allowing for smooth cleaning in a variety of situations. Durability: It is hard to break even with prolonged or extended use and will last a long time. Maintenance: Regular maintenance and filter replacement are easy to perform. Energy Efficiency: Energy efficient with low power consumption and high performance. Quiet operation: Quiet operation so it won't disturb your family or neighbors. Lightweight: Lightweight and easy to carry, it is also easy to move up and down stairs. Compactness: Compact design that does not take up much space when stored. Safety: It is designed to be safe to prevent accidents and breakdowns during use. Environmental friendliness: Use of recyclable materials and low environmental impact of waste. The technical elements and their contents are explained below. Motor: The central part that generates suction power. Battery: Rechargeable battery as power source. Dust bag / paper pack: A bag to store sucked-up dust and debris. Filter system: The part that captures tiny particles and allergens in the air. Suction port / brush unit: A part for effectively sucking up dirt and dust. Sensors: Sensors that detect obstacles and recognize the shape of the room. Control Panel & Switches: The interface through which the user operates the vacuum cleaner's functions. Control unit: The electronic circuitry and programs that control the operation of the vacuum cleaner. Dust box: The part that stores sucked-up dirt and dust. Exterior & Main Frame: The casing that maintains the overall shape and protects the components. Please propose a new vacuum cleaner concept that combines the above benefits, quality, and technology.

[0033] (Generative AI output) Below we present five new vacuum cleaner concepts that combine benefit, quality and technology. 1. Smart Eco Vacuum Cleaner - Benefits: Comfortable living environment, confidence in making smart choices - Quality: Energy-saving and environmentally friendly - Technology: sensors, control units - Concept: Uses sensor technology to use the optimal amount of energy depending on how dirty the room is and how long it is being used. Eco-friendly and energy-saving. 2. Ultra-quiet design vacuum cleaner - Benefits: Stress-free operation, improved efficiency of housework - Quality: Quiet, compact - Technology: Motor, Exterior & Body Frame - Concept: Uses a high-performance motor while significantly reducing noise through a special exterior design. 3. Healthcare Vacuum Cleaner - Benefits: Comfortable cleanliness, worry-free hygiene management - Quality: suction and retention - Technology: Filter system, dust box - Concept: The cutting-edge filter system removes 99.9% of fine dust and allergens. The dust box can be easily removed without getting your hands dirty. 4. Usability-focused vacuum cleaner - Benefits: Reduced effort, satisfaction with ease of use - Quality: Easy to use, lightweight - Technology: Suction port & brush unit, operation panel & switch - Concept: Lightweight and intuitive operation panel, easy replacement of suction nozzles and brushes. Even beginners can use it intuitively. 5. Long-life total care vacuum cleaner - Benefits: Increased efficiency of housework, pride in home - Quality: Durable, safe - Technology: Battery, dust bag & paper carton - Concept: Long-life battery and sturdy design. Enhanced safety design for peace of mind for the whole family. These concepts are original ideas based on the above elements. Further detailed research and consideration is required for the actual product design and development.

[0034] In this way, the generation AI server 2 generates a concept proposal for a new vacuum cleaner by combining the elements of benefit, quality, and technology. These concepts are then sent to the terminal 1. Compared to generating a concept proposal without providing any elements, it is possible to generate a highly valid concept that takes benefit, quality, and technology into consideration. The generation AI server 2 can then propose a specific concept and generate product ideas.

[0035] In an embodiment, the elements of benefit, quality, and technology are combined to generate a concept proposal for a new vacuum cleaner, making it possible to come up with a product concept that meets user needs as well as a technically concrete product concept.

[0036] (STEP 3: Content generation step) The above output clarifies the concept of the product, but it is important in product development to also clarify the technical content that realizes that concept. Therefore, when realizing a specific concept, the necessary technical content is generated using the generated technical elements.

[0037] The terminal 1 transmits content generation instruction information (hereinafter, also referred to as a prompt) to the generation AI server 2. In the embodiment, the technical content of a specific concept (here, an ultra-quiet design vacuum cleaner) among the above five cleaning concepts is confirmed.

[0038] (prompt) 2. Please explain the structure of an ultra-quiet vacuum cleaner in terms of the following items. ·motor ·battery ·Dust bag ·Paper carton Filter system ·Suction port·Brush unit ·sensor ·Operation panel & switches Control unit Dust box Exterior & main frame

[0039] (Generative AI output) Understood. I will now explain the structure of each part of the "Ultra Quiet Design Vacuum Cleaner". 1. Motor: Highly efficient motor with low noise and strong suction. Special acoustic design minimizes vibration and noise during operation. 2. Battery: Uses a long-life, high-capacity lithium-ion battery, suitable for continuous use and with quick-charge function. 3. Dust bag / paper pack: Made of high-density material to prevent fine dust and dirt from escaping. Also contributes to quiet design. 4. Filter system: Equipped with a multi-layer filtering mechanism, it efficiently captures allergens and fine dust particles, ensuring clean exhaust. 5. Suction port and brush unit: Flexible brush design adapts to various floor textures. Special material reduces friction noise. 6. Sensor: Detects obstacles and the level of dirt in the room and automatically adjusts the motor output, preventing unnecessary energy consumption and keeping the machine quiet. 7. Operation panel and switches: Simple and intuitive design with the minimum number of buttons and quiet switches. 8. Control section: Using advanced electronic control technology, the operation of each part is optimized, especially the operation of parts that cause noise is precisely controlled. 9. Dust Box: Seamless design minimizes noise when opening and closing, and improves airtightness to contain internal noise. 10. Exterior & Main Frame: Robust exterior with built-in sound-absorbing material. Precision assembly down to the smallest detail eliminates unnecessary gaps and vibrations. As its name suggests, the "Ultra Quiet Design Vacuum Cleaner" is designed with quietness as a top priority. Each part is optimized to minimize noise.

[0040] In this way, the generation AI server 2 can generate a structure corresponding to each element contained in the technical elements. The generated configuration is then sent to the terminal 1. Because technical elements are highly comprehensive, it is possible to generate a structure with few omissions that covers the configuration of all vacuum cleaners. This allows ideas for technological development (such as which configuration to proceed with development) to be obtained.

[0041] (STEP 4: Detailed technical considerations) Next, narrow down the structures to one (e.g., a motor) and have the AI ​​propose a more detailed structure. Note that the AI ​​may propose multiple detailed structures.

[0042] (prompt) Motor: A highly efficient motor is used, providing powerful suction while producing little noise. Special acoustic design minimizes vibration and noise during operation. Could you please tell me about the special acoustic design?

[0043] (Generative AI output) Based on the term "special acoustic design", the specific acoustic design ideas for reducing motor noise are listed below: Installation of sound absorbing material: Installing high performance sound absorbing material around the motor and inside the casing absorbs generated noise and reduces sound emission to the outside. Anti-vibration mounts: Special vibration dampening mounts are used to mount the motors, reducing vibration and noise transmitted to the structure. Optimal speed control: By optimizing the motor speed, noise in a specific frequency band can be reduced, which can avoid the frequency band that is most unpleasant to the human ear. Airflow Optimization: The motor's inlet and exhaust are designed to smooth the airflow and reduce wind noise. Use of silent bearings: The motor bearings are made of special materials and have a structure that minimizes noise generation. Motor isolation design: The motor is physically isolated from the main body and connected with specific materials to block the transmission of noise and vibration from the motor. Resonance reduction: Noise caused by resonance is reduced by using special processing and materials to reduce the resonance of metal parts and casings. By adopting these acoustic design ideas, the motor of the "ultra-quiet design vacuum cleaner" produces significantly less noise than other conventional vacuum cleaners, providing a comfortable user experience.

[0044] In this way, by performing a more detailed analysis, the generation AI server 2 can propose a more specific configuration and transmit it to the terminal 1. This can provide ideas for technology development (e.g., installing sound-absorbing materials, anti-vibration mounts, controlling motor speed, improving materials, etc.), which is useful for determining the direction of technology development. Furthermore, by repeating the same prompt, more detailed content can be obtained.

[0045] In the embodiment, in STEPs 3 and 4, the content is generated and detailed examination is performed for technical elements, but the content may be generated and detailed examination is performed for benefit elements or quality elements in STEPs 3 and 4.

[0046] In the embodiment, the element categories are three: benefit, quality, and technology. However, this is not limited to these, and concepts may be generated by using and combining two or more categories such as use, effect, problem, solution, need, function, configuration, mechanism, and parts.

[0047] Second embodiment Next, the processing procedure of the program of the idea support method of the second embodiment will be explained. In the embodiment, the idea support is performed for beer, but the target product is not limited to this. The series of code blocks 1 to 13 below is the program and method of the embodiment. However, for ease of explanation, the code blocks 1 to 13 are divided and explained.

[0048] 4 is a flowchart of the process of the idea generation support processing program of the embodiment. In STEP 1, multiple problem (first category in natural language) summaries and multiple solution (second category in natural language) summaries are generated from multiple abstracts (character string information in natural language) of patents related to a predetermined product, in STEP 2, a problem element group (first category element group) is generated from the multiple problem summaries, a solution element group (second category element group) is generated from the multiple solution summaries, and in STEP 3, the problem element group and the solution element group are combined to generate a new beer concept.

[0049] In the embodiment, the abstract of patent data on beer is used as the character string in natural language to be processed, but the character string is not limited to this and may be character strings in the main text of the specification or claims. Furthermore, character strings in natural language from questionnaires, user reviews, papers, etc. other than patent data may also be processed.

[0050] (STEP 1: Summarizing the problem and solutions) First, the control unit 104 extracts character strings of the problem and character strings of the solution from the abstracts of multiple patent data. The program is as follows. The following program is a Python program stored in the control unit of the terminal 1. However, other programming tools and programming languages ​​(VBA, GAS, etc.) may also be used. The following program is merely an example, and the processing order and the libraries, functions, and variable names used may be changed.

[0051] (Code Block 1) import pandas as pd # Loading data # Using Google Drive from google.colab import drive drive.mount(' / content / drive') # Load data (from Google Drive) df = pd.read_excel(' / content / drive / MyDrive / beer_patent.xlsx') # Separating the problem from the solution # Extract the strings between [Problem] and [Solution], and between [Solution] and [Selection diagram], and add them as new columns (problem,solution) df['problem'] = df['summary'].str.extract('[problem](.+?)[solution]', expand=False) # Create a 'solution' column df['solution'] = df['Summary'].str.extract('[Solution](.+?)(?:[Choice]|$)', expand=False)

[0052] This program will be explained as follows. First, the control unit 104 imports a module called pandas. Pandas is a tool for performing data analysis in Python. Next, a function called drive is imported from a module called google.colab. Drive is a function for accessing Google Drive. Note that Google is a registered trademark.

[0053] The control unit 104 executes the drive function to mount Google Drive to the path ' / content / drive'. Mounting means that files and folders in Google Drive can be operated on Google Colab.

[0054] The control unit 104 uses the pd.read_excel function to read the Excel file beer_patent.xlsx located in the path ' / content / drive / MyDrive / beer_patent.xlsx' (note that the file format is not limited to Excel, and CSV format is also possible if other functions are used). This Excel file stores patent data that contains multiple abstract data (character string data in natural language). This patent data is patent data related to beer. When generating new beer concepts, patent data related to beer is used. A portion of the summary column of the patent data converted into a data frame is shown below.

[0055] (summary column data) 0 [Summary][Problem] Achieving a beer-like flavor and rich taste while reducing the purine concentration... 1 [Abstract][Problem] Achieving a beer-like flavor and rich taste while reducing the purine concentration... 2 [Abstract][Problem] To provide a beer-flavored beverage with reduced residual flavors. 3 [Summary][Problem] A beer that contains 50% or more malt by mass, but has no off-flavors derived from barley... 4 [Summary][Problem] Malt usage ratio is 50% or more and sugar content is 0.5g / 100... .. ... ... ... 91 [Abstract][Problem] To provide a beer-flavored beverage with an excellent balance of richness and sharpness. 92 [Abstract][Problem] A method for producing a non-fermented beer-flavored beverage, comprising: 93 [Abstract][Problem] The present invention provides a means for reducing the astringency of beer-flavored beverages,... 94 [Abstract][Problem] To provide a non-alcoholic beer-flavored beverage with a firm flavor... 95 [Abstract][Problem] To provide a beer-like sparkling beverage in which carbon dioxide loss is suppressed.

[0056] The contents of the patent abstracts are stored in the summary column of the data frame. Note that in the above example, due to space limitations, only the first five and a portion of the last five are shown, but in the embodiment, a data frame of 96 items (96 rows) is used. Of course, more or less than this number is possible. Also, in the above example, due to space limitations, the full text of the abstract is not displayed in the summary column, but in reality the full text of the abstract is stored in one cell in Excel. Note that Excel is a registered trademark. Note that columns other than the summary column will be added to the data frame by the processing in the following steps.

[0057] The control unit 104 assigns the read file to a variable called df. df is a table-format data structure called a data frame. By specifying df['summary'], only the column called summary is extracted from df. The summary column stores the contents of the patent abstract written in natural language.

[0058] The control unit 104 uses the str.extract function to extract the string from "Problem" to "Solution" from the summary column. This string represents the patent problem (problem string information). The extracted substring is added to a new column called problem. A new column problem is created in df by setting df['problem'] = ...

[0059] Similarly, the control unit 104 uses the str.extract function to extract the character string from the summary column, from "Solution" to "Selection diagram". This character string represents the solution of the patent (this is called solution string information). The extracted character string is added to a new column called solution. A new column "solution" is created in df by setting df['solution'] = .... A part of the problem column and solution column converted into a data frame is shown below. Note that, due to space restrictions, only the first 5 cases and a part of the last 5 cases are shown below, but in the embodiment, a data frame of 96 cases (96 rows) is used. Also, in the above, due to space restrictions, the problem column and solution column do not display the full text, but in reality, the full text of the problem and solution are each stored in one cell in Excel.

[0060] (Problem column data) 0 A beer-flavored fermented alcoholic beverage that has a reduced purine concentration while still retaining the richness and flavor of beer... 1 A beer-flavored fermented alcoholic beverage that has a reduced purine concentration while still retaining the richness and flavor of beer... 2. To provide a beer-flavored beverage with reduced residual unpleasant flavors. 3. A low-carb beer that uses 50% or more malt by mass, yet has improved harshness from barley... 4 The malt content is 50% or more, the sugar content is 0.5g / 100ml or less, and yet the sweetness is... .. ... 91. To provide a beer-flavored beverage with an excellent balance of richness and sharpness. 92 A manufacturing method for a non-fermented beer-taste beverage that can reliably reduce the concentration of DMTS, and the manufacturing method thereof 93 The present invention provides a means for reducing the astringency of beer-flavored beverages and for improving their mildness... 94. Providing a non-alcoholic beer-flavored beverage with a firm flavor. 95 To provide a beer-like sparkling beverage in which carbon dioxide loss is suppressed.

[0061] (solution column data) 0 A beer-flavored fermented alcoholic beverage with a reduced purine concentration, in which the original extract concentration in the beverage is... 1 A beer-flavored fermented alcoholic beverage with a reduced purine concentration, in which the molecular weight of the beverage is 20 to 100... 2 The ratio of malt in the raw materials is 45% by mass or more, and the concentration of isoamyl acetate in the beer-flavored beverage is 2 mg / l... 3 The ratio of malt in the raw materials is 50% by mass or more, sugar is included as an ingredient, and the sugar content of the beer-flavored beverage is... 4 The ratio of malt in the raw materials is 50% by mass or more, and the alcohol content of the beer-flavored beverage is 3.7v / v%... .. ... 91 Beer-flavored beverages contain grain-derived ingredients, have an apparent final fermentation degree of 89% or more, and have an amino acid concentration of... 92 A method for producing a non-fermented beer-taste beverage, in which a sugar solution with a pH of 4.0 or higher is poured into a copper-containing vessel in the heating section... 93 The present invention relates to an agent for improving the astringency of beer-flavored beverages, which contains lipoxygenase-1-deficient barley as an active ingredient, and 94 Weight ratio of polyphenols to the total amount of extract (weight % of polyphenols / weight % of total amount of extract) 95 A beer-like sparkling beverage, polyglycerol fatty acid ester and linalool, characterized by the above.

[0062] It should be noted that the process of extracting the character strings "problem" and "solution" from the summary is not essential. In other words, the entire summary may be sent as is to the generation AI server as character string information, and the element extraction process for the problem and solution (first and second categories) may be performed. However, by extracting and processing the character strings "problem" and "solution" separately, it is possible to reduce the usage fee for the generation AI and improve the classification accuracy by the generation AI server 2, so it is preferable to provide a process of extracting the character strings "problem" and "solution".

[0063] (Summary of the project) Next, the control unit 104 transmits the assignment string information (first category string information) and the assignment summary instruction information (first category string summary instruction information) to the generation AI server 2, and receives the assignment summary information from the generation AI server 2. The program is as follows.

[0064] (Code Block 2) # Installing packages !pip install openai import openai

[0065] This command is to install the OpenAI Python library. The ! indicates that the command should be interpreted as a shell command. pip is a Python package manager, and install is the command used to install libraries.

[0066] The control unit 104 imports a Python library called openai. The openai library is for executing various natural language processing tasks using the OpenAI API. Note that, in order to use the openai library, it is actually necessary to input an API key, but this is omitted from the description of the program because it would be difficult to make it public.

[0067] Next, the control unit 104 transmits the assignment string information and the assignment summary instruction information to the generation AI server 2, and receives the assignment summary information (first category string summary result information) from the generation AI server 2. The program is as follows.

[0068] (Code Block 3) # Summary of the issue def generate_p_summary(text): response = openai.ChatCompletion.create( model="gpt-4 ", messages=[ {"role": "system", "content": "Please answer in English within 20 words what are the main issues to be improved in the beer's technological development and design indicated by the following text."}, {"role": "user", "content": text}], temperature=0, max_tokens=100, frequency_penalty=0, presence_penalty=0, ) p_summary = response["choices"][0]["message"]["content"] return p_summary

[0069] This program uses OpenAI's language model "GPT-4" to provide the function of summarizing a given sentence. Note that the language model is not limited to "GPT-4", but may be "GPT-4 Turbo" or "GPT-3.5 Turbo", or the next version of the GPT series. These are known to demonstrate high accuracy in natural language processing tasks.

[0070] The generate_p_summary(text) function receives one text as an argument, and the control unit 104 calls the Chat Completion API of OpenAI to summarize the text. The API sends a message consisting of two roles, the system and the user, and the system sends a prompt saying, "Please answer in English within 20 words what are the main issues to be improved in the beer's technological development and design indicated by the following text." This prompt is called the issue summary prompt. The number of characters to be summarized is not limited to 20 words, and may be more or less than this. It is preferable to adjust the number of characters according to the upper limit of the number of tokens processed by the generation AI server. In the embodiment, the prompt is in English to reduce the number of tokens. However, it may be in Japanese, of course (the same applies below).

[0071] The generation AI server 2 summarizes the given text (task string information) based on the task summary instruction information and returns it as task summary information. The response from the generation AI server 2 contains the summarized text (task summary information). The task summary information is stored in the p_summary variable and returned as the output of the function.

[0072] (Code Block 4) # Add the result of the issue summary process to a new column (p_summary) df['p_summary'] = df['problem'].apply(lambda x: generate_p_summary(x))

[0073] This part of the program is designed to summarize the text of each row stored in the 'problem' column of the Pandas data frame df using the generate_p_summary function (problem summary information) and add the results to a new column 'p_summary' in df.

[0074] The generate_p_summary function takes the formatted text and uses the GPT-4 model to summarize the text. The summarized results are stored in a new column, 'p_summary', in the data frame df. A portion of the p_summary column converted into a data frame is shown below. Note that, due to space restrictions, only the first 5 cases and a portion of the last 5 cases are shown below, but in the embodiment, a data frame of 96 cases (96 rows) is used. Of course, more or less cases are possible. Also, in the above, due to space restrictions, the full text is not displayed in the p_summary column, but in reality, the full text of the issue summary is stored in one cell in Excel.

[0075] (p_summary column data) 0 Reducing purine levels while maintaining beer ... 1 Reducing purine levels while maintaining beer ... 2 Reducing off-flavors in beer-style beverages. 3 Improve malt-derived off-flavors in sugar-free... 4 Improve malt ratio, reduce sugar content, enhance... .. ... 91 Balancing richness and sharpness in beer taste... 92 Reducing DMTS concentration in non-fermented b... 93 Reducing astringency and enhancing mildness in... 94 Enhancing flavor and mouthfeel in non-alcohol... 95 carbon Improvement stability in beer-like car...

[0076] (Solution Summary) Next, the control unit 104 transmits the solution means string information (second category string information) and the solution means summary instruction information (second category string summary instruction information) to the generation AI server 2, and receives the solution means summary information (second category string summary result information) from the generation AI server 2. The program is as follows. Note that some code explanations will be omitted for parts common to the above processing.

[0077] (Code Block 5) # Solution Summary def generate_s_summary(text): response = openai.ChatCompletion.create( model="gpt-4", messages=[ {"role": "system", "content": "Please respond in English, using no more than 20 words, to describe the unique technological features of beer technology as outlined in the following beer technology solutions text."}, {"role": "user", "content": text}], temperature=0, max_tokens=100, frequency_penalty=0, presence_penalty=0, ) s_summary = response["choices"][0]["message"]["content"] return s_summary

[0078] The program uses OpenAI's language model GPT-4 to provide the ability to summarize a given sentence.

[0079] The generate_s_summary(text) function receives one text as an argument, and the control unit 104 calls the Chat Completion API of OpenAI to summarize the text. The API sends a message consisting of two roles, the system and the user, and the system sends a prompt saying, "Please respond in English, using no more than 20 words, to describe the unique technological features of beer technology as outlined in the following beer technology solutions text." This prompt is called the solution summary prompt (second category character string summary prompt). Note that the number of characters to be summarized is not limited to 20 words, and may be more or less than this. It is advisable to adjust the number of characters according to the upper limit of the number of tokens processed by the generation AI server.

[0080] The generation AI server 2 summarizes the given text (solution means string information) based on the solution means summary instruction information and returns it as solution means summary information (second category string summary result information). The response from the generation AI server 2 includes the summarized text (solution means summary information). The solution means summary information is stored in the s_summary variable and returned as the output of the function.

[0081] (Code Block 6) # Add the result of the solution summary process to a new column (s_summary) df['s_summary'] = df['solution'].apply(lambda x: generate_s_summary(x))

[0082] This part of the program is for adding the results (solution summary information) of the summary of each row of text stored in the 'solution' column of the Pandas data frame df using the generate_s_summary function to a new column 's_summary' of df. A part of the s_summary column converted into a data frame is shown below. Note that, due to space restrictions, only the first 5 cases and a part of the last 5 cases are shown below, but in the embodiment, a data frame of 96 cases (96 rows) is used. Of course, more or less cases are possible. Also, in the above, due to space restrictions, the full text is not displayed in the s_summary column, but in reality, the full text of each solution summary is stored in one cell in Excel.

[0083] (s_summary column data) 0 Beer technology offers reduced purine levels, ... 1 Beer technology offers reduced purine levels, ... 2 Beer technology solutions include high malt ra... 3 Beer technology with over 50% malt ratio, cont... 4 Beer technology with over 50% malt ratio, alco... .. ... 91 Beer-flavored beverages with grain-derived... 92 Unique features include boiling sugar solution... 93 This invention offers beer taste beverages wit... 94 Non-alcoholic beer-like beverages with polyphe... 95 Beer technology with polyglycerol fatty acid e...

[0084] In the embodiment, a step of generating a summary of the problem and the solution is provided due to the upper limit of the number of tokens for processing by the generation AI server, but if there is no upper limit on the number of tokens (or if the upper limit is large), the step of summarizing the problem and the solution may be omitted. In other words, the entire text of the problem and the solution (or the entire text of the abstract) may be sent to the generation AI server 2, and the subsequent element generation processing may be performed. However, from the viewpoint of processing speed and the cost of using the generation AI, it is preferable to perform summary processing.

[0085] (STEP 2: Generate elements of the problem and solution) (Task element generation) Next, the control unit transmits multiple pieces of task summary information (first category string summary result information) and task element generation instruction information (first category string element generation instruction information) to the generation AI server 2, and receives task element information including a task element group (first category element group) from the generation AI server 2. The program is as follows.

[0086] (Code Block 7) # A culture of issues # Extract the data from the 'p_summary' column of the DataFrame and store it in a variable called p_summaries. p_summaries = df['p_summary'].values # Combine all issue summaries into one string p_summaries_text = ', '.join(p_summaries)

[0087] This part of the program gets all the values ​​of the 'p_summary' column from the Pandas data frame df and stores them in a variable called p_summaries. Specifically, df['p_summary'].values ​​gets all the values ​​of the 'p_summary' column of the df data frame.

[0088] Next, each element of the 'p_summaries' variable (the summary string for each task) is concatenated with a comma and a space (', ') and converted into one large task summary string (p_summaries_text). This operation combines the list of task summaries into a single string that can be used in subsequent processing. In other words, this process combines the summarized strings of 20 words or less into a single string. (Note that this string is quite long, so we will not write it here.)

[0089] (Code Block 8) # Generation of task elements def generate_p_element(text): response = openai.ChatCompletion.create( model="gpt-4 ", messages=[ {"role": "system", "content": "Classify the numerous technical issues of the beers indicated by the following text into five categories, assign a name to each category, and output the five category names and a description of each category within 50 words."}, {"role": "user", "content": text}], temperature=0, max_tokens=4000, frequency_penalty=0, presence_penalty=0, ) p_element = response["choices"][0]["message"]["content"] return p_element

[0090] The program uses OpenAI's language model "GPT-4" to provide the ability to generate a set of task elements from a given sentence.

[0091] The generate_p_element(text) function receives one text (text) as an argument, and the control unit 104 calls the Chat Completion API of OpenAI to generate an element group from that text (task summary character string). The API sends a message consisting of two roles, that of the system and that of the user, and the system sends instruction information (prompt) such as "Classify the numerous technical issues of the beers indicated by the following text into five categories, assign a name to each category, and output the five category names and a description of each category within 50 words." This instruction information is set as task element group generation instruction information (first category element group generation instruction information). Note that the number of elements in the task element group is not limited to five, and may be more or less than five. Also, the content of the prompt is not limited to this, and may be a more detailed instruction or a prompt in Japanese.

[0092] The generation AI server 2 generates an element group based on the given text (task summary string) and the task element group generation instruction information, and replies. The response from the generation AI server 2 contains the text of the task element group (task element group information). The task element group information is stored in the p_element variable and returned as the output of the function.

[0093] (Code Block 9) p_element = generate_p_element(p_summaries_text)

[0094] This program calls the generate_p_element function with the generated p_summaries_text (all assignment summaries combined into one string) as an argument.

[0095] The generate_p_element function is responsible for generating an element of text (in this case, the assignment summary) using OpenAI's GPT-4 model. Specifically, based on the prompt, GPT-4 generates five categories:

[0096] When this code is executed, the task summary (p_summaries_text) is classified into five categories, and the results (element names and their descriptions) are stored in the p_element variable. In other words, the p_classification variable stores the following five task element groups (1. Flavor and Aroma Enhancement, 2. Health and Dietary Adjustments, 3. Technological and Production Innovations, 4. Ingredient and Recipe Development, 5. Quality and Stability Improvements) and their descriptions.

[0097] (Issue elements and their explanations) 1. Flavor and Aroma Enhancement - Focuses on improving the taste, aroma, and overall sensory experience of beer and beer-like beverages. This includes enhancing fruit flavors, reducing off-flavors, balancing bitterness and sweetness, and incorporating distinctive hop aromas. 2. Health and Dietary Adjustments - Addresses modifications to beer and beer-like beverages to meet health and dietary preferences, such as reducing sugar, purine, and alcohol content, while maintaining or enhancing taste and mouthfeel. This category also includes the development of low-carb and non-alcoholic options. 3. Technological and Production Innovations - Encompasses improvements in the manufacturing process, equipment, and materials used in brewing and serving beer. This includes enhancing foam stability, preventing flavor deterioration, improving fermentation processes, and developing methods for better aroma infusion and foam creation. 4. Ingredient and Recipe Development - Involves discovering new ingredients, adjusting malt ratios, and developing recipes to create beer-like beverages with improved taste, aroma, and health profiles. This includes creating hop-free options, balancing malt-derived flavors, and enhancing the richness and traditional flavor profiles. 5. Quality and Stability Improvements - Focuses on enhancing the physical and chemical stability of beer and beer-like beverages, including improving foam quality, preventing microbial contamination, and ensuring aroma stability over time. This category also addresses the challenge of maintaining flavor and quality in non-fermented and low-alcohol options.

[0098] (Create solution element) Next, the control unit transmits multiple pieces of solution means summary information (second category string summary result information) and solution means element generation instruction information (second category element generation instruction information) to the generation AI server 2, and receives solution means element information (second category element result information) from the generation AI server 2. The program is as follows.

[0099] (Code Block 10) # A culture of solutions # Extract the data from the 's_summary' column of the DataFrame and store it in a variable called s_summaries. s_summaries = df['s_summary'].values # Combine all issue summaries into one string s_summaries_text = ', '.join(s_summaries)

[0100] This part of the program gets all values ​​of the 's_summary' column from the Pandas data frame df and stores them in a variable called s_summaries. Specifically, df['s_summary'].values ​​gets all values ​​of the 's_summary' column of the df data frame.

[0101] Next, each element of the 's_summaries' variable (the summary of each solution) is concatenated with a comma and a space (',') and converted into one large solution summary string (s_summaries_text). This operation combines the list of solution summaries into a single string, which can be used in subsequent processing. In other words, this is a process of combining the summarized 20-word strings into a single string. (Note that this string is quite long, so we will not write it here.)

[0102] (Code Block 11) # Generate solution element group def generate_s_element(text): response = openai.ChatCompletion.create( model="gpt-4", messages=[ {"role": "system", "content": "Classify the numerous unique technological features of beer production indicated by the following text into five categories based on components, materials, or compounds, give each category a name based on components, materials, or compounds, and provide the names and a brief description (within 50 words) for each of the five categories."}, {"role": "user", "content": text}], temperature=0, max_tokens=4000, frequency_penalty=0, presence_penalty=0, ) s_element = response["choices"][0]["message"]["content"] return s_element

[0103] The program uses OpenAI's language model "GPT-4" to provide the ability to generate a set of elements from a given sentence.

[0104] The generate_s_element(text) function receives one text as an argument, and the control unit 104 calls the Chat Completion API of OpenAI to generate an element group from that text (solution summary character string). The API sends a message consisting of two roles, the system and the user, and sends instruction information (prompt) from the system side, "Classify the numerous unique technological features of beer production indicated by the following text into five categories based on components, materials, or compounds, give each category a name based on components, materials, or compounds, and provide the names and a brief description (within 50 words) for each of the five categories." This instruction information is the solution element group generation instruction information. Note that the number of elements in the solution element group is not limited to five, and may be more or less than five. Also, the content of the prompt is not limited to this, and may be a more detailed instruction or may be in Japanese.

[0105] The generation AI server 2 generates an element group based on the given text (solution means summary string) and solution means element group generation instruction information, and returns it as solution means element group generation result information (second category element group generation result information). The response from the generation AI server 2 includes the text of the solution means element group (solution means element group information). The solution means element group information is stored in the s_element variable and returned as the output of the function.

[0106] (Code Block 12) # Generate solution elements s_element = generate_s_element(s_summaries_text)

[0107] This program calls the generate_s_element function with the generated s_summaries_text (all solution summaries combined into one string) as an argument.

[0108] The generate_s_element function is responsible for generating a set of text elements (in this case, a summary of the solution) using OpenAI's GPT-4 model.

[0109] When this code is executed, the solution summary (s_summaries_text) is classified into five categories, and the results (element names) are stored in the s_element variable. That is, the following five solution element groups (1. Grain and Malt Composition, 2. Flavor and Aroma Enhancement, 3. Fermentation and Alcohol Content, 4. Health and Dietary Adjustments, 5. Process and Quality Control) and their descriptions are stored in the s_element variable.

[0110] (Solution elements and their explanations) 1. Grain and Malt Composition - High Malt Ratio: Technologies focusing on a high percentage of malt in the beer, affecting taste and quality. - Seed-Infused Flavors: Utilizing seeds in raw materials for unique beer flavors through fermentation or extraction processes. - Barley-Derived Components: Incorporating specific barley traits, like lipoxygenase-1 deficiency, to influence the final beverage profile. 2. Flavor and Aroma Enhancement - Unique Aroma Compounds: Adjusting specific compounds like 4-vinylguaiacol, ethylpyrazine, and linalool to enhance beer's aroma profile. - Fruit Peel Infusion: Using fruit peels in the brewing process to introduce unique flavor notes. - Flavor Stabilizers and Enhancers: Incorporating substances like quinine, α,β-unsaturated aldehydes, and specific acids to improve taste and aroma. 3. Fermentation and Alcohol Content - Controlled Fermentation: Techniques to manage fermentation processes for unique flavor profiles and alcohol levels. - Low-Alcohol and Non-Alcoholic Options: Technologies aimed at producing beer-like beverages with minimal or no alcohol content. - Alcohol and Sugar Content Regulation: Adjusting the balance of alcohol and sugar to meet specific dietary preferences and regulations. 4. Health and Dietary Adjustments - Reduced Purine Levels: Offering beer options with lower purine content for health-conscious consumers. - Low-Carb and High-Protein Options: Developing beers with specific nutritional profiles, including low carbohydrates and higher protein content. - Polyphenol and Acid Adjustments: Modifying polyphenol and acid levels for enhanced flavor and potential health benefits. 5. Process and Quality Control - Advanced Filtration Techniques: Using innovative filtration methods, like porous membranes, for improved quality control. - Foam and Carbonation Control: Technologies to stabilize foam and optimize carbonation for a better sensory experience. - Color and Turbidity Measurement: Implementing color calibration and turbidity measurement for consistent appearance and quality.

[0111] (STEP 3: Concept generation step) Next, the control unit transmits the problem element group information (first category element group information), the solution element group information (second category element group information), and the concept generation instruction information to the generation AI server 2, and receives the concept generation result information from the generation AI server 2. The program is as follows.

[0112] (Code Block 13) # Function to generate concepts response = openai.ChatCompletion.create( model="gpt-4", messages=[ {"role": "user", "content": f"You are an excellent consultant. We have received a request to come up with a new beer concept. Below are the results of the analysis on the problems and solutions for the beer. The element and description of the beer problems are as follows: '{p_element}'. The element and description of the solutions for the beer are as follows: '{s_element}'. Based on the above, please propose five new beer concepts that combine these problems and solutions."}], temperature=0, max_tokens=4000, frequency_penalty=0, presence_penalty=0, ) concept_text = response["choices"][0]["message"]["content"] print(concept_text)

[0113] This code is part of a program that uses OpenAI's API to generate new beer concepts. Each part is explained below. openai.ChatCompletion.create() is a function for generating text-based dialogue using OpenAI's GPT-4 model. model="gpt-4" specifies the model to be used. Here, we specify that the GPT-4 model is used. The messages argument defines a list of messages to be passed to the model. This list contains messages from the user, and generates the AI's response to them. {"role": "user", "content": ...} specifies the content of the message that is actually sent to the AI. In this example, the prompt (concept generation instruction information) is "You are an excellent consultant. We have received a request to come up with a new beer concept. Below are the results of the analysis on the problems and solutions for the beer. The element and description of the beer problems are as follows: '{p_element}' (problem element group information). The element and description of the solutions for the beer are as follows: '{s_element}' (solution element group information). Based on the above, please propose five new beer concepts that combine these problems and solutions." The AI ​​is asked to propose five new beer concepts based on the analysis results of the problem element group information and solution element group information about beer. temperature=0 controls the predictability of the generated text. When set to 0, the model selects the most confident response.max_tokens=4000 specifies the maximum number of tokens in the generated response. Here, 4000 tokens is the maximum value. frequency_penalty=0 and presence_penalty=0 are parameters to avoid repetition of certain words and increase diversity. Here, both are set to 0. response["choices"][0]["message"]["content"] gets the message content of the first option from the response from the API. Finally, print(concept_text) outputs the generated concept text. Below is the generated concept text.

[0114] (Generated concepts and their explanations) Given the detailed analysis of both the problems and solutions in beer production and enhancement, I propose the following five innovative beer concepts that address the identified issues while leveraging the suggested technological and ingredient solutions: 1. The Wellness Brew Concept Overview: A low-alcohol, high-protein beer with reduced purine levels, catering to health-conscious consumers who don't want to compromise on taste. This beer combines the health and dietary adjustments with advanced fermentation and alcohol content regulation. Key Features: - Low-Alcohol and Non-Alcoholic Options: Utilizes controlled fermentation techniques to offer a refreshing beer experience with minimal alcohol content. - Reduced Purine Levels & Low-Carb, High-Protein Options: Crafted for health-conscious drinkers, this beer reduces purine and carb content while boosting protein, using specific grain and malt compositions. - Polyphenol and Acid Adjustments: Adjusts polyphenol and acid levels to not only enhance flavor but also potentially offer health benefits. 2. The Aromatic Orchard Concept Overview: A fruit peel-infused beer that emphasizes unique aroma compounds and flavor stabilizers to create a sensory explosion reminiscent of walking through an orchard. This concept focuses on flavor and aroma enhancement through innovative ingredient use. Key Features: - Fruit Peel Infusion: Incorporates peels from exotic fruits during the brewing process, introducing unique, refreshing flavor notes. - Unique Aroma Compounds: Adjusts specific aroma-enhancing compounds to create a distinctive smell that complements the fruit flavors. - Flavor Stabilizers and Enhancers: Ensures the robustness of the fruit flavors and aromas over time, maintaining quality and enjoyment. 3. The Golden Barley Concept Overview: A premium beer that highlights the unique characteristics of barley, including barley-derived components and a high malt ratio, to offer a rich, traditional beer taste with a modern twist. Key Features: - Barley-Derived Components: Utilizes specific barley traits to influence the beer's flavor profile, focusing on richness and depth. - High Malt Ratio: Ensures a high percentage of malt in the beer, affecting taste and quality for a more premium experience. - Advanced Filtration Techniques: Implements innovative filtration methods to enhance the clarity and purity of the beer, showcasing the quality of the ingredients. 4. The Eco Craft Concept Overview: A sustainable beer option that focuses on technological and production innovations to minimize environmental impact while enhancing the beer's sensory experience. This concept integrates process and quality control with ingredient and recipe development. Key Features: - Seed-Infused Flavors: Utilizes sustainable seeds in raw materials for unique beer flavors, promoting biodiversity. - Foam and Carbonation Control: Employs technologies to stabilize foam and optimize carbonation, enhancing the sensory experience in an eco-friendly manner. - Advanced Filtration Techniques: Uses less energy-intensive filtration methods, contributing to a lower carbon footprint without compromising on quality. 5. The Heritage Blend Concept Overview: A beer that revives ancient brewing traditions with modern technology, focusing on ingredient and recipe development to offer a hop-free option that balances malt-derived flavors with richness and traditional profiles. Key Features: - Hop-Free Options: Provides an alternative to hop-centric beers by focusing on malt and other ingredients for flavoring, appealing to those looking for something different. - Balancing Malt-Derived Flavors: Carefully adjusts malt ratios and incorporates traditional brewing ingredients to create a rich, complex flavor profile. - Color and Turbidity Measurement: Ensures the beer maintains a consistent appearance and quality, honoring traditional recipes with modern quality control techniques. Each of these concepts addresses specific consumer needs and preferences, leveraging technological advancements and innovative ingredients to create unique beer experiences.

[0115] In this way, Generative AI Server 2 generates five new beer concept proposals (here, 1. The Wellness Brew, 2. The Aromatic Orchard, 3. The Golden Barley, 4. The Eco Craft, and 5. The Heritage Blend) by combining the issues extracted from a large amount of patent information and each element of the solution. Compared to generating concept proposals without providing any information, it is possible to generate highly valid concepts that take into account the issues extracted from a large amount of patents and the element groups of the solution. Generative AI Server 2 can then propose specific concepts and obtain product ideas.

[0116] In an embodiment, the problems extracted from a large number of patents and each element of the solution are combined to generate a new beer concept proposal, which makes it possible to come up with a product concept that is technically concrete.

[0117] In the embodiment, the element categories are divided into two, namely, problems and solutions, but this is not limited to this. Concepts may be generated by using and combining two or more categories, such as benefit, quality, use, effect, problem, solution, needs, function, configuration, mechanism, parts, etc.

[0118] (program) A process of transmitting element generation instruction information to a generation AI server that provides natural language processing using a large-scale language model, the element generation instruction information including character string information in multiple natural languages ​​related to a specific product and an instruction to generate a first category element in multiple natural languages ​​and a second category element in multiple natural languages ​​based on the character string information in multiple natural languages, to a computer connected to the generation AI server via a network; and a process of receiving element generation result information from the generation AI server, the element generation result information including the first category element in multiple natural languages ​​and the second category element in multiple natural languages ​​generated by the generation AI server based on the element generation instruction information. An idea generation support program comprising: a process of sending concept generation instruction information to the generation AI server, the concept generation instruction information including an instruction to generate a concept combining a first category element in the multiple natural languages ​​and a second category element in the multiple natural languages; and a process of receiving from the generation AI server concept information that combines a first category element in the multiple natural languages ​​and a second category element in the multiple natural languages, the concept information being generated by the generation AI server based on the concept generation instruction information.

[0119] (system) An idea generation support system in which a generation AI server that provides natural language processing using a large-scale language model and a terminal are connected via a network, the idea generation support system sending element generation instruction information to the generation AI server, the element generation instruction information including string information in multiple natural languages ​​related to a specific product and instructions to generate a first category element in multiple natural languages ​​and a second category element in multiple natural languages ​​based on the string information in the multiple natural languages, the generation AI server generating the first category elements in the multiple natural languages ​​and the second category elements in the multiple natural languages ​​based on the element generation instruction information, the terminal sending instructions to the generation AI server to generate a concept combining the first category elements in the multiple natural languages ​​and the second category elements in the multiple natural languages, the generation AI server generating concept information combining the first category elements in the multiple natural languages ​​and the second category elements in the multiple natural languages, and sending the concept information to the terminal.

[0120] (method) A method for supporting idea generation in which a generation AI server that provides natural language processing using a large-scale language model and a terminal are connected via a network, the method comprising the steps of: transmitting element generation instruction information to the generation AI server, the element generation instruction information including string information in multiple natural languages ​​related to a specific product and instructions for generating a first category element in multiple natural languages ​​and a second category element in multiple natural languages ​​based on the string information in the multiple natural languages; the generation AI server generates the first category elements in the multiple natural languages ​​and the second category elements in the multiple natural languages ​​based on the element generation instruction information; the terminal transmitting an instruction to the generation AI server to generate a concept combining the first category elements in the multiple natural languages ​​and the second category elements in the multiple natural languages; the generation AI server generating concept information combining the first category elements in the multiple natural languages ​​and the second category elements in the multiple natural languages, and transmitting the concept information to the terminal.

[0121] Although the embodiment has been described above, this embodiment is presented as an example and is not intended to limit the scope of the invention. This new embodiment can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the gist of the invention. This embodiment and its modifications are included in the scope and gist of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0122] 101 CPU, 102 ROM, 103 RAM, 104 control unit, 105 HDD, 106 external I / F, 107 input unit, 108 system bus

Claims

1. A concept support system including a generation AI server that uses a large-scale language model to perform natural language processing, and a terminal connected to the generation AI server via a network, A step of transmitting an instruction from the terminal to the generation AI server to generate element groups of two or more categories for a predetermined product; The generation AI server generates a group of elements of two or more categories for the predetermined product and transmits the group of elements of the two or more categories to the terminal; A step of transmitting an instruction from the terminal to the generation AI server to generate a product concept combining elements of the two or more categories; a step of the generation AI server generating a product concept combining elements of the two or more categories and transmitting the product concept to the terminal; An idea support system including:

2. A method for supporting ideas is provided in a system in which a generative AI server that provides natural language processing using a large-scale language model and a terminal are connected via a network, the method comprising: The terminal transmits to the generation AI server character string information in a plurality of natural languages ​​related to a specific product and an instruction to generate a first category element group in a natural language and a second category element group in a natural language based on the character string information in a plurality of natural languages; the generation AI server generates a first category element group in a natural language and a second category element group in a natural language based on character string information in the plurality of natural languages ​​and an instruction to generate a first category element group in a natural language and a second category element group in a natural language based on the character string information in the plurality of natural languages; The terminal transmits to the generation AI server an instruction to generate a concept combining a first group of category elements in the natural language and a second group of category elements in the natural language; The idea generation support method, in which the generation AI server generates concept information by combining a first group of category elements in the natural language and a second group of category elements in the natural language, and transmits the concept information to the terminal.

Images