System

Abstract

To provide a system.SOLUTION: A system includes means for: providing a prompt sentence instructing a generative AI model to perform market research; collecting market data output from the generative AI model; analyzing competitive products using the market data; generating a new product concept based on the competitive products; and evaluating the new product concept.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] By their very nature, creative work, especially product planning, relies heavily on human intuition and experience, making it difficult to streamline. Furthermore, in order to quickly respond to market changes and user needs, product plans must be generated and evaluated quickly. However, when these tasks are performed by humans, they are time-consuming and costly, making them difficult to carry out efficiently. [Means for solving the problem]

[0005] This invention utilizes generative AI to automate creative tasks and streamline the generation and evaluation of product plans. Specifically, it provides a system that includes a means for automating creative tasks using generative AI, a means for generating product plans using generative AI, and a means for evaluating product plans using generative AI. This makes it possible to streamline product planning tasks and quickly respond to market changes and user needs. [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. DETAILED DESCRIPTION OF THE INVENTION

[0007] An example of an embodiment of a system according to the disclosed technique will be described below with reference to the accompanying drawings.

[0008] do.

[0009] First, the terms used in the following description will be explained.

[0010] 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)).

[0011] 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.

[0012] 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.

[0013] 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.

[0014] 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."

[0015] [First embodiment]

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0028] "Example 1"

[0029] One embodiment of the present invention is a system for improving the efficiency of product planning work using generative AI. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, and a means for evaluating product plans using generative AI. Specifically, the generative AI automates creative work based on a specific workflow. For example, it can automate tasks such as market research, competitive analysis, and product concept generation. The generative AI also generates product plans based on market data and user feedback. For example, it can analyze user purchase data and review data and generate new product plans based on that data. Furthermore, the generative AI evaluates the generated product plans. For example, it can evaluate whether the product plans meet market needs and whether they have an advantage over competitors. These means enable the efficiency of product planning work to be improved, enabling quick responses to market changes and user needs.

[0030] "Example 2"

[0031] One embodiment of the present invention is a system for improving the efficiency of product planning work using generative AI. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, and a means for evaluating product plans using generative AI. Specifically, the generative AI automates creative work based on a specific workflow. For example, it can automate tasks such as market research, competitive analysis, and product concept generation. The generative AI also generates product plans based on market data and user feedback. For example, it can analyze user purchase data and review data and generate new product plans based on that data. Furthermore, the generative AI evaluates the generated product plans. For example, it can evaluate whether the product plans meet market needs and whether they have an advantage over competitors. These means enable the efficiency of product planning work to be improved, enabling quick responses to market changes and user needs.

[0032] The processing flow of each embodiment will be described below.

[0033] "Example 1"

[0034] Step 1: Generative AI automates creative tasks such as market research and competitive analysis. Specifically, it collects publicly available information on the Internet and extracts information on market trends and competing products.

[0035] Step 2: Next, the generative AI analyzes the collected market data and user feedback. This analysis uses machine learning algorithms and natural language processing technology to understand user purchasing trends, product evaluations, market needs, and more.

[0036] Step 3: Generative AI generates new product plans based on the analysis results. For example, it proposes new product concepts and features based on user purchasing trends. It also devise product pricing and sales strategies based on market needs.

[0037] Step 4: Finally, the generative AI evaluates the generated product plan. Specifically, it evaluates whether the product plan meets market needs and whether it has an advantage over competitors. The results of this evaluation are used to improve the product plan and make a final decision.

[0038] "Example 2"

[0039] Step 1: Generative AI automates creative tasks such as market research and competitive analysis. Specifically, it collects publicly available information on the Internet and extracts information on market trends and competing products.

[0040] Step 2: Next, the generative AI analyzes the collected market data and user feedback. This analysis uses machine learning algorithms and natural language processing technology to understand user purchasing trends, product evaluations, market needs, and more.

[0041] Step 3: Generative AI generates new product plans based on the analysis results. For example, it proposes new product concepts and features based on user purchasing trends. It also devise product pricing and sales strategies based on market needs.

[0042] Step 4: Finally, the generative AI evaluates the generated product plan. Specifically, it evaluates whether the product plan meets market needs and whether it has an advantage over competitors. The results of this evaluation are used to improve the product plan and make a final decision.

[0043] Example 1

[0044] 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."

[0045] Traditional product planning work required a lot of manual work and time, resulting in inefficiency. It was also difficult to respond quickly to market changes and user needs, so rapid product planning was required to maintain competitiveness. Furthermore, traditional methods had limitations when it came to automating creative tasks and evaluating product plans.

[0046] 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.

[0047] In this invention, the server includes means for automating creative tasks using a generative AI model, means for generating product plans using the generative AI model, means for evaluating product plans using the generative AI model, means for collecting market data and user data, means for preprocessing the collected data, means for inputting data into the generative AI model, and means for outputting evaluation results of the generated product plans. This makes it possible to improve the efficiency of product planning tasks and quickly respond to changes in the market and user needs.

[0048] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to generate new information or ideas from data.

[0049] "Means for automating creative tasks" refers to means for automating creative tasks such as market research, competitive analysis, and product concept generation using generative AI models.

[0050] "Means for generating product plans" refers to the means for generating new product plans based on market data and user feedback.

[0051] "Means for evaluating product plans" refers to means for evaluating whether the generated product plans meet market needs and whether they have an advantage over competitors.

[0052] "Market Data" means information and statistics about a particular market, including market trends and competitor information.

[0053] "User Data" refers to information about users, such as their purchasing history, reviews, and feedback.

[0054] "Data preprocessing measures" refer to measures used to clean and normalize collected data in order to convert it into a format suitable for generative AI models.

[0055] "Data Input Means" refers to the means for inputting pre-processed data into a generative AI model.

[0056] "Means for outputting evaluation results" refers to a means for providing users with the results of product planning evaluated by the generative AI model.

[0057] MODE FOR CARRYING OUT THE INVENTION

[0058] This invention is a system for improving the efficiency of product planning work by utilizing a generative AI model. Specific embodiments of this system are described below.

[0059] Hardware and software used

[0060] The server uses high-performance hardware, specifically a high-performance server equipped with an NVIDIA GPU. The software uses a generative AI model (e.g., OpenAI (registered trademark) GPT-4 (registered trademark)), and BeautifulSoup and Scrapy are used as data collection tools.

[0061] System configuration

[0062] The system includes the following main means:

[0063] 1. Means of automating creative tasks: The server uses generative AI models to automate creative tasks such as market research, competitive analysis, and product concept generation.

[0064] 2. Means for generating product plans: The server generates new product plans based on market data and user data.

[0065] 3. Product plan evaluation means: The server evaluates whether the generated product plan meets market needs and whether it has an advantage over competitors.

[0066] 4. Means of collecting market data and user data: The server collects market data and user data from public databases and APIs on the Internet.

[0067] 5. Data preprocessing: The server cleans and normalizes the collected data and converts it into a format suitable for the generative AI model.

[0068] 6. Means for inputting data into the generative AI model: The server inputs the preprocessed data into the generative AI model.

[0069] 7. Output means for evaluation results: The server provides the user with the results of the product plans evaluated by the generative AI model.

[0070] Specific examples

[0071] The server collects market research data from public databases on the Internet. For example, it uses BeautifulSoup to access specific websites, parse the HTML structure, and extract the necessary data. It then cleans the collected data, imputes missing values, removes outliers, and converts the data into CSV format.

[0072] The server then inputs the following prompt into the generative AI model:

[0073] "Analyze the latest market trends and identify your competitors' strengths and weaknesses."

[0074] To collect user data, we call the API of an online shopping site to obtain user purchase history and reviews. We clean the collected data and tokenize the review text data to convert it into vector format. Next, we input the following prompt sentence into the generative AI model:

[0075] "Please propose new product ideas based on user purchasing data and reviews."

[0076] Finally, to evaluate the generated product ideas, we input the following prompt into the generative AI model:

[0077] "Please evaluate whether this product plan meets market needs and whether it has an advantage over competitors."

[0078] The evaluation results are visualized in graphs and tables by the server and displayed on a dashboard that users can access.

[0079] In this way, a system for improving the efficiency of product planning work using generative AI models can consistently perform everything from automating creative work to generating and evaluating product plans, making it possible to quickly respond to changes in the market and user needs.

[0080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0081] Step 1:

[0082] The server collects market data. Specifically, it retrieves market data from public databases and APIs on the Internet. For example, it uses BeautifulSoup or Scrapy to access specific websites and parse the HTML structure to extract the required data. The input is the website URL or API endpoint, and the output is the collected market data.

[0083] Step 2:

[0084] The server preprocesses the collected market data. Specifically, it cleans and normalizes the data and converts it into a format suitable for the generative AI model. For example, it imputes missing values, removes outliers, and converts the data into CSV format. The input is the collected market data, and the output is the preprocessed data.

[0085] Step 3:

[0086] The server inputs the preprocessed market data into the generative AI model. Specifically, it uses a prompt to instruct the generative AI model on a specific task. For example, the prompt might say, "Analyze the latest market trends and identify the strengths and weaknesses of competitors." The inputs are the preprocessed market data and the prompt, and the output is the analysis results from the generative AI model.

[0087] Step 4:

[0088] The server collects user data. Specifically, it obtains user purchase data and review data from online shopping sites and social media. It collects data using APIs and web scraping tools. The inputs include API endpoints and website URLs, and the output is the collected user data.

[0089] Step 5:

[0090] The server preprocesses the collected user data. Specifically, it cleans and tokenizes the text data and converts it into a format suitable for the generative AI model. For example, it cleans the text data of reviews, tokenizes it, and converts it into vector format. The input is the collected user data, and the output is the preprocessed data.

[0091] Step 6:

[0092] The server inputs the preprocessed user data into the generative AI model. Specifically, it instructs the model to generate a new product proposal using a prompt. For example, the prompt might read, "Please propose a new product proposal based on the user's purchasing data and reviews." The inputs are the preprocessed user data and the prompt, and the output is a new product proposal from the generative AI model.

[0093] Step 7:

[0094] The server evaluates the generated product proposal. Specifically, it uses a generative AI model to evaluate whether the product proposal meets market needs and whether it has an advantage over competitors. For example, a prompt such as "Please evaluate whether this product proposal meets market needs and whether it has an advantage over competitors" is input. The inputs are the generated product proposal and the prompt, and the output is the evaluation result.

[0095] Step 8:

[0096] The server outputs the evaluation results and provides them to the user. Specifically, the evaluation results are visualized in graphs and tables and displayed on a dashboard that the user can access. The input is the evaluation results, and the output is the visualized evaluation results.

[0097] (Application example 1)

[0098] 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."

[0099] Traditional product planning requires a wide range of manual tasks, such as market research, competitive analysis, and product concept generation and evaluation. This is time-consuming and labor-intensive, and there is a high possibility of human error. It is also difficult to effectively utilize user purchase data and review data, making it difficult to quickly respond to market changes and user needs.

[0100] 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 means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, means for collecting market data and analyzing trends and competing products, means for generating new product concepts based on user purchase data and review data, and means for evaluating whether the generated product plans meet market needs and have an advantage over competitors. This makes it possible to improve the efficiency of product planning tasks and quickly respond to changes in the market and user needs.

[0101] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[0102] A "means for automating creative tasks" is a means for automatically executing creative tasks based on a specific workflow.

[0103] "Means for generating product plans" are means for generating new product plans based on market data and user feedback.

[0104] The "means for evaluating a product plan" is a means for evaluating whether the generated product plan meets market needs and whether it has an advantage over competitors.

[0105] "Market Data" is data containing information about a specific market, used to analyze trends, competing products, etc.

[0106] "User Data" refers to data that includes information about a user, such as the user's purchasing history and reviews.

[0107] A "trend" is information that indicates market or consumer trends or tendencies over a specific period of time.

[0108] "Competitive products" are products sold by other companies in the same market and are the products to be compared.

[0109] A "product concept" is a concept that indicates the basic idea and design policy of a new product.

[0110] "Market needs" refer to the demands and expectations of consumers in a particular market.

[0111] "Advantages" refer to the superior features or benefits of a particular product compared to competing products.

[0112] A system for carrying out the present invention utilizes generative AI to improve the efficiency of product planning work. A specific embodiment of this system will be described below.

[0113] System configuration

[0114] The system includes the following main components:

[0115] 1. Automating creative tasks with generative AI

[0116] 2. How to generate product plans using generative AI

[0117] 3. Evaluation method for product planning using generative AI

[0118] 4. A means of gathering market data and analyzing trends and competitor products

[0119] 5. A means of generating new product concepts based on user purchase and review data

[0120] 6. A means of evaluating whether the generated product plan meets market needs and has an advantage over competitors.

[0121] Hardware and software used

[0122] Hardware: Smartphones, servers

[0123] Software: Python, OpenAI API, Pandas

[0124] Data processing and calculation

[0125] 1. Automated Market Research

[0126] The server collects market data and analyzes trends and competitors using a generative AI model (e.g., OpenAI's GPT-4), specifically using the following prompt:

[0127] Example prompt sentence:

[0128] Analyze the market data below to identify trends and competing products.

[0129] Fashion market data for 2023

[0130] 2. Product concept generation

[0131] The server collects user data and generates new product concepts using a generative AI model, specifically using the following prompt:

[0132] Example prompt sentence:

[0133] Generate a new product concept based on the following user data:

[0134] User purchase and review data for 2023

[0135] 3. Product Planning Evaluation

[0136] The server uses a generative AI model to evaluate the generated product concept and market data, using the following prompt:

[0137] Example prompt sentence:

[0138] Please rate the following product concepts:

[0139] Product Concept: A new eco-friendly fashion line

[0140] Market Data: Fashion Market Data for 2023

[0141] Specific examples

[0142] For example, when planning a new eco-friendly fashion line in the fashion market, the server first collects market data and uses a generative AI model to analyze trends and competing products, then generates a new product concept based on user purchase and review data, and finally evaluates whether the generated product concept meets market needs and has an advantage over competitors.

[0143] In this way, a system for improving the efficiency of product planning work that utilizes generative AI can automate product planning work and respond quickly and accurately to changes in the market and user needs.

[0144] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0145] Step 1:

[0146] The server collects market data. Specifically, the server obtains market data from public databases on the Internet and from internal company databases. This market data includes trend information and information on competing products. The input is market data, and the output is the collected market data.

[0147] Step 2:

[0148] The server inputs the collected market data into the generative AI model to analyze trends and competing products. Specifically, the server sends the following prompt to the generative AI model:

[0149] Analyze the market data below to identify trends and competing products.

[0150] Fashion market data for 2023

[0151] The generative AI model analyzes data based on this prompt and outputs trend information and competitive product information. The input is market data and the prompt, and the output is trend information and competitive product information.

[0152] Step 3:

[0153] The server collects user data. Specifically, the server obtains data including user purchase history and reviews. This data reflects user behavior and preferences. The input is user data, and the output is the collected user data.

[0154] Step 4:

[0155] The server inputs the collected user data into the generative AI model to generate a new product concept. Specifically, the server sends the following prompt to the generative AI model:

[0156] Generate a new product concept based on the following user data:

[0157] User purchase and review data for 2023

[0158] The generative AI model analyzes data based on this prompt and outputs a new product concept. The input is user data and the prompt, and the output is a new product concept.

[0159] Step 5:

[0160] The server inputs the generated product concept and market data into the generative AI model for evaluation. Specifically, the server sends the following prompt to the generative AI model:

[0161] Please rate the following product concepts:

[0162] Product Concept: A new eco-friendly fashion line

[0163] Market Data: Fashion Market Data for 2023

[0164] The generative AI model analyzes data based on this prompt and outputs the evaluation results of the product concept. The input is the product concept, market data, and the prompt, and the output is the evaluation results of the product concept.

[0165] Step 6:

[0166] The server determines the final product plan based on the evaluation results. Specifically, the server analyzes the evaluation results and determines whether the product concept meets market needs and has an advantage over competitors. The input is the evaluation results, and the output is the final product plan.

[0167] In this way, a system for improving the efficiency of product planning work that utilizes generative AI can automate product planning work and respond quickly and accurately to changes in the market and user needs.

[0168] Example 2

[0169] 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."

[0170] Traditional product planning work required manual market research, competitive analysis, and the collection and analysis of user data, which was time-consuming and labor-intensive. Furthermore, these tasks required specialized knowledge and were difficult to perform efficiently, making it difficult to respond to the market quickly. Furthermore, evaluation of the resulting product plans often relied on subjective judgment, making objective evaluation difficult.

[0171] 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. In this invention, the server includes a means for automating creative tasks using a generation AI, a means for generating product plans using the generation AI, a means for evaluating product plans using the generation AI, a means for collecting market research data, a means for performing competitive analysis, and a means for collecting and analyzing user data. This makes it possible to improve the efficiency of product planning tasks and quickly respond to changes in the market and user needs.

[0172] "Generative AI" is a system that uses artificial intelligence technology to generate new data and information.

[0173] "Means for automating creative tasks" are means for automatically performing creative tasks such as market research and competitive analysis based on a specific workflow.

[0174] "Means for generating product plans" refers to means for generating new product plans based on market data and user feedback.

[0175] The "means for evaluating a product plan" is a means for evaluating whether the generated product plan meets market needs and whether it has an advantage over competitors.

[0176] "Means for collecting market research data" means means for collecting market data from the internet and other sources.

[0177] "Methods for conducting competitive analysis" are methods for analyzing the strengths and weaknesses of competitors based on collected market research data.

[0178] "Means for collecting and analyzing user data" refers to means for collecting and analyzing user purchasing data and review data.

[0179] The present invention relates to a system for improving the efficiency of product planning work using generative AI. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, a means for evaluating product plans using generative AI, a means for collecting market research data, a means for conducting competitive analysis, and a means for collecting and analyzing user data.

[0180] System configuration

[0181] 1. Hardware and Software Use

[0182] The server provides the computational resources to run the generative AI model. Specifically, a server equipped with a high-performance CPU and GPU is required.

[0183] A terminal is a device for collecting and analyzing user data, and includes software for accessing a database (e.g., MySQL (registered trademark)).

[0184] Generative AI models are built using machine learning frameworks such as TENSORFLOW® and PyTorch.

[0185] Program processing

[0186] 1. Collecting market research data

[0187] The server uses a web scraping tool (e.g., BeautifulSoup) to collect market research data from the Internet by crawling a specified list of URLs and parsing the HTML data to extract the required information.

[0188] 2. Conduct a competitive analysis

[0189] The server performs competitive analysis based on the collected market research data. It uses a natural language processing library (e.g., NLTK) to extract the strengths and weaknesses of competitors. Specifically, it tokenizes the text data and extracts frequently occurring words and phrases to analyze the characteristics of competitors.

[0190] 3. Product concept generation

[0191] The generative AI model generates new product concepts based on the results of competitive analysis. It uses a generative AI model (e.g., GPT-3 (registered trademark)) to propose product concepts that include points of differentiation from competitors. Specifically, it receives the prompt "Please propose a new product concept that includes points of differentiation from competitors" as input and outputs the generated text.

[0192] 4. Collection and analysis of user data

[0193] The device collects user purchase data and review data by retrieving user data from a database (e.g., MySQL) and executing SQL queries to extract purchase history and review comments within a specific period.

[0194] 5. Product planning

[0195] The generative AI model generates new product ideas based on collected user data. It uses machine learning algorithms (e.g., TensorFlow) to analyze user preferences and suggest product ideas based on them.

[0196] 6. Product Planning Evaluation

[0197] The generative AI model evaluates the generated product plans. Based on evaluation indicators (e.g., market suitability, competitive advantage), it evaluates whether the generated product plans meet market needs. Specifically, it uses the evaluation indicators to score the product plans and determine their merits.

[0198] Specific examples

[0199] Automated market research: "Analyze the latest market trends and learn what your competitors are doing."

[0200] Product planning generation: "Please propose new product concepts based on user purchasing data."

[0201] Product Plan Evaluation: "Evaluate whether the generated product plan meets market needs."

[0202] This system will improve the efficiency of product planning operations and enable quick responses to market changes and user needs.

[0203] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0204] Step 1:

[0205] Market research data collection

[0206] The server collects market research data from the Internet by using a web scraping tool (e.g., BeautifulSoup) to crawl a specified list of URLs and parse the HTML data to extract the required information.

[0207] Input: URL list

[0208] Output: Market research data (text format)

[0209] Specific operation: The server accesses the specified URL and retrieves the HTML content. It then uses BeautifulSoup to parse the HTML and extract the necessary text data.

[0210] Step 2:

[0211] Conducting a competitive analysis

[0212] The server performs competitive analysis based on the collected market research data, using natural language processing libraries (e.g., NLTK) to extract competitor strengths and weaknesses.

[0213] Input: Market research data (text format)

[0214] Output: Competitive analysis results (text format)

[0215] Specific operation: The server tokenizes the collected market research data and extracts frequently occurring words and phrases, which are then used to analyze the strengths and weaknesses of competitors, and outputs the results in text format.

[0216] Step 3:

[0217] Product concept generation

[0218] Generative AI models generate new product concepts based on the results of competitive analysis. Generative AI models (e.g., GPT-3) are used to propose product concepts that include points of differentiation from competitors.

[0219] Input: Competitive analysis results (text format)

[0220] Output: Product concept (text format)

[0221] How it works: The generative AI model takes the prompt "Please propose a new product concept that differentiates it from competitors" as input and outputs the generated text.

[0222] Step 4:

[0223] User data collection and analysis

[0224] The device collects user purchase data and review data by retrieving user data from a database (e.g., MySQL) and executing SQL queries to extract purchase history and review comments within a specific period.

[0225] Input: SQL query

[0226] Output: User data (text format)

[0227] Specific operation: The device connects to the database, executes SQL queries to retrieve user data, and outputs the retrieved data in text format.

[0228] Step 5:

[0229] Product planning generation

[0230] The generative AI model generates new product ideas based on collected user data. It uses machine learning algorithms (e.g., TensorFlow) to analyze user preferences and suggest product ideas based on them.

[0231] Input: User data (text format)

[0232] Output: Product planning (text format)

[0233] How it works: The generative AI model takes user data as input and uses a neural network to generate new product ideas.

[0234] Step 6:

[0235] Product planning evaluation

[0236] The generative AI model evaluates the generated product plans, assessing whether the generated product plans fit market needs based on evaluation indicators (e.g., market fit, competitive advantage).

[0237] Input: Product plan (text format)

[0238] Output: Evaluation results (text format)

[0239] Specific operation: The generative AI model uses evaluation indicators to score and judge the merits of product plans. The evaluation results are output in text format.

[0240] (Application example 2)

[0241] 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."

[0242] Traditional product planning work requires a wide range of manual tasks, such as market research, competitive analysis, product concept generation, user feedback analysis, and product plan evaluation, which is time-consuming and labor-intensive. Furthermore, these tasks require specialized knowledge and are difficult to perform efficiently, which poses a major challenge in today's world, where rapid market response is required. Furthermore, there is a lack of efficient ways to automate product planning work using smart devices, making it necessary to solve these issues.

[0243] 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.

[0244] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, means for automating market research using a smart device, means for automating competitive analysis using a smart device, means for generating product concepts using a smart device, and means for evaluating product plans using a smart device, thereby making it possible to improve the efficiency of product planning tasks.

[0245] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[0246] "Product planning" involves coming up with ideas for new products and services and putting them together into concrete plans.

[0247] "Means for automating creative tasks" are means for automating creative tasks such as market research and competitive analysis using generative AI.

[0248] "Product planning generation means" is a means of generating new product plans based on market data and user feedback using generative AI.

[0249] "Product planning evaluation means" is a means of evaluating whether product planning generated using generative AI meets market needs and has an advantage over competitors.

[0250] "Smart devices" are portable electronic devices with advanced functions, such as smartphones and tablets.

[0251] "Market research automation methods" are methods that use smart devices to collect market data and use generative AI to analyze that data.

[0252] "Automated competitive analysis methods" are methods that use smart devices to collect competitor data and analyze that data using generative AI.

[0253] "Product concept generation means" refers to a means of collecting market data and user feedback using smart devices and generating new product concepts using generative AI.

[0254] The "product plan evaluation means" is a means for evaluating a product plan created using a smart device and displaying the results.

[0255] As an embodiment of the present invention, a method for implementing a system for improving the efficiency of product planning work using generative AI on a smart device will be described. This system includes means for automating creative work using generative AI, means for generating product plans, means for evaluating product plans, means for automating market research using a smart device, means for automating competitive analysis, means for generating product concepts, and means for evaluating product plans.

[0256] Hardware and software used

[0257] Hardware: Smartphone (iOS or ANDROID (registered trademark))

[0258] software:

[0259] Generative AI models (e.g., OpenAI GPT-4)

[0260] Database (e.g. Firebase Firestore)

[0261] Front-end frameworks (e.g. React Native)

[0262] Backend framework (e.g. Node.js)

[0263] System configuration

[0264] 1. Automated means of market research:

[0265] A user starts the application using a smartphone and taps the "Market Research" button.

[0266] The server sends market research prompts to the generative AI model.

[0267] The generative AI model collects market data and generates analytical results.

[0268] The server displays the analysis results on the smartphone screen.

[0269] 2. Automated Competitive Analysis Methods:

[0270] User taps the "Competitor Analysis" button.

[0271] The server sends competitive analysis prompts to the generative AI model.

[0272] The generative AI model collects competitor data and generates analytical results.

[0273] The server displays the analysis results on the smartphone screen.

[0274] 3. Product concept generation methods:

[0275] The user taps the "Generate Product Concept" button.

[0276] The server sends a prompt to the generative AI model to generate a product concept.

[0277] Generative AI models generate new product concepts based on market data and user feedback.

[0278] The server displays the generated product concept on the smartphone screen.

[0279] 4. Product planning evaluation methods:

[0280] The user taps the "Product Planning Evaluation" button.

[0281] The server sends a prompt for product planning evaluation to the generative AI model.

[0282] The generative AI model evaluates the generated product proposals and generates evaluation results.

[0283] The server displays the evaluation results on the smartphone screen.

[0284] Examples and prompts

[0285] Specific examples

[0286] For example, when planning a new smartphone case, the following prompt sentence can be sent to the generative AI model:

[0287] Prompt Sentence Examples

[0288] 1. Market research:

[0289] "What are the latest trends in the smartphone case market? Could you please tell us more about the most popular designs and features?"

[0290] 2. Competitive analysis:

[0291] "What are the main competitors in the current smartphone case market and what are the features of their products?"

[0292] 3. Product concept generation:

[0293] "Propose a new smartphone case concept based on user feedback and market data, taking into account user demand for functionality and design."

[0294] 4. Product Planning Evaluation:

[0295] "Please evaluate the following smartphone case proposal. Please tell us whether this proposal meets market needs and whether it has an advantage over competitors. Proposal content: [Specific proposal content]"

[0296] In this way, a system for streamlining product planning work using generative AI can be realized on smart devices, enabling fast and effective product planning.

[0297] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0298] Step 1:

[0299] A user starts the application on their smartphone and taps the "Market Research" button. This causes the application to generate a market research prompt and send it to the server. The input is the user's operation, and the output is the market research prompt.

[0300] Step 2:

[0301] The server sends a market research prompt to the generative AI model. The input is the market research prompt, and the output is a request to the generative AI model.

[0302] Step 3:

[0303] The generative AI model collects market data and generates analysis results. The input is a market research prompt, and the output is the analysis results of the market data. Specifically, the generative AI model collects market data from public databases and news sites on the Internet and performs analysis using natural language processing techniques.

[0304] Step 4:

[0305] The server receives the analysis results from the generative AI model and sends them to the smartphone. The input is the analysis results from the generative AI model, and the output is data sent to the smartphone.

[0306] Step 5:

[0307] The smartphone displays the analysis results received from the server on its screen. The input is the analysis results from the server, and the output is what is displayed to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[0308] Step 6:

[0309] The user taps the "Competitor Analysis" button. This causes the application to generate a prompt for competitor analysis and send it to the server. The input is the user's operation, and the output is the prompt for competitor analysis.

[0310] Step 7:

[0311] The server sends a competitive analysis prompt to the generative AI model. The input is the competitive analysis prompt, and the output is a request to the generative AI model.

[0312] Step 8:

[0313] The generative AI model collects competitor data and generates analysis results. The input is the competitor analysis prompt, and the output is the analysis results of the competitor data. Specifically, the generative AI model collects data from competitor websites and review sites and performs analysis using natural language processing techniques.

[0314] Step 9:

[0315] The server receives the analysis results from the generative AI model and sends them to the smartphone. The input is the analysis results from the generative AI model, and the output is data sent to the smartphone.

[0316] Step 10:

[0317] The smartphone displays the analysis results received from the server on its screen. The input is the analysis results from the server, and the output is what is displayed to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[0318] Step 11:

[0319] The user taps the "Generate Product Concept" button. This causes the application to generate a prompt for generating a product concept and send it to the server. The input is the user's operation, and the output is the prompt for generating a product concept.

[0320] Step 12:

[0321] The server sends a prompt for product concept generation to the generative AI model. The input is the prompt for product concept generation, and the output is a request to the generative AI model.

[0322] Step 13:

[0323] The generative AI model generates new product concepts based on market data and user feedback. The input is a product concept generation prompt, and the output is a new product concept. Specifically, the generative AI model collects data from market databases and user review sites, and uses natural language processing technology to generate new product concepts.

[0324] Step 14:

[0325] The server receives new product concepts from the generative AI model and sends them to the smartphone. The input is the new product concept from the generative AI model, and the output is data transmission to the smartphone.

[0326] Step 15:

[0327] The smartphone displays the new product concept received from the server on its screen. The input is the new product concept from the server, and the output is the display to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[0328] Step 16:

[0329] The user taps the "Product Planning Evaluation" button. This causes the application to generate a prompt for product planning evaluation and send it to the server. The input is the user's operation, and the output is the prompt for product planning evaluation.

[0330] Step 17:

[0331] The server sends a prompt for product planning evaluation to the generative AI model. The input is the prompt for product planning evaluation, and the output is a request to the generative AI model.

[0332] Step 18:

[0333] The generative AI model evaluates the generated product plans and generates evaluation results. The input is the product plan evaluation prompt, and the output is the evaluation results. Specifically, the generative AI model evaluates product plans based on market data and competitor data.

[0334] Step 19:

[0335] The server receives the evaluation results from the generative AI model and sends them to the smartphone. The input is the evaluation results from the generative AI model, and the output is data sent to the smartphone.

[0336] Step 20:

[0337] The smartphone displays the evaluation results received from the server on its screen. The input is the evaluation result from the server, and the output is the display to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[0338] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0339] "Example 1"

[0340] As one embodiment of the present invention, a system for improving the efficiency of product planning work that combines an emotion engine is provided. This system includes a means for automating creative work using a generative AI, a means for generating product plans using the generative AI, a means for evaluating product plans using the generative AI, and an emotion engine that recognizes user emotions.

[0341] Specifically, the emotion engine recognizes the user's emotions and provides that information to the generative AI. The generative AI uses this emotional information to automate creative tasks. For example, it understands how the user feels about a product and generates a new product proposal based on that emotion. The generative AI also uses the emotional information to evaluate the product proposal. Specifically, it evaluates how well the product proposal responds to the user's emotions.

[0342] As a specific example, if a user expresses joy toward a certain product, the emotion engine provides that information to the generation AI. The generation AI then generates a new product plan that includes elements that will delight the user. The generation AI also evaluates the extent to which the product plan responds to the user's joy. In this way, a system for improving the efficiency of product planning work that combines an emotion engine can deeply understand user emotions and efficiently plan products based on those emotions.

[0343] "Example 2"

[0344] As one embodiment of the present invention, a system for improving the efficiency of product planning work that combines an emotion engine is provided. This system includes a means for automating creative work using a generative AI, a means for generating product plans using the generative AI, a means for evaluating product plans using the generative AI, and an emotion engine that recognizes user emotions.

[0345] Specifically, the emotion engine recognizes the user's emotions and provides that information to the generative AI. The generative AI uses this emotional information to automate creative tasks. For example, it understands how the user feels about a product and generates a new product proposal based on that emotion. The generative AI also uses the emotional information to evaluate the product proposal. Specifically, it evaluates how well the product proposal responds to the user's emotions.

[0346] As a specific example, if a user expresses joy toward a certain product, the emotion engine provides that information to the generation AI. The generation AI then generates a new product plan that includes elements that will delight the user. The generation AI also evaluates the extent to which the product plan responds to the user's joy. In this way, a system for improving the efficiency of product planning work that combines an emotion engine can deeply understand user emotions and efficiently plan products based on those emotions.

[0347] The processing flow of each embodiment will be described below.

[0348] "Example 1"

[0349] Step 1: The emotion engine recognizes the user's emotions. In this step, emotions are analyzed from the user's actions, comments, facial expressions, etc., and the results are generated as emotional information.

[0350] Step 2: Generative AI receives the emotion information and uses it to automate creative tasks. Specifically, it generates new product plans based on the user's emotions.

[0351] Step 3: The generative AI evaluates the product plan. Specifically, it evaluates how well the product plan responds to user emotions. The results of this evaluation are used to improve the product plan or generate new product plans.

[0352] Step 4: The generative AI improves the product plans based on the evaluation results. Specifically, for product plans with low evaluation results, it improves them to better match user emotions. For product plans with high evaluation results, it uses the success factors to generate new product plans.

[0353] "Example 2"

[0354] Step 1: The emotion engine recognizes the user's emotions. In this step, emotions are analyzed from the user's actions, comments, facial expressions, etc., and the results are generated as emotional information.

[0355] Step 2: Generative AI receives the emotion information and uses it to automate creative tasks. Specifically, it generates new product plans based on the user's emotions.

[0356] Step 3: The generative AI evaluates the product plan. Specifically, it evaluates how well the product plan responds to user emotions. The results of this evaluation are used to improve the product plan or generate new product plans.

[0357] Step 4: The generative AI improves the product plans based on the evaluation results. Specifically, for product plans with low evaluation results, it improves them to better match user emotions. For product plans with high evaluation results, it uses the success factors to generate new product plans.

[0358] Example 1

[0359] 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."

[0360] Traditional product planning requires a lot of time and effort due to manual market research, competitive analysis, and the collection and analysis of user feedback. It is also difficult to generate and evaluate product plans that take user sentiment into account, making it difficult to respond quickly to user needs. This has led to a demand for improved efficiency and accuracy in product planning.

[0361] 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.

[0362] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, an emotion engine for recognizing user emotions, means for providing emotion information obtained from the emotion engine to the generation AI, means for generating product plans using the emotion information, and means for evaluating product plans using the emotion information, thereby enabling the efficiency and accuracy of product planning tasks to be improved.

[0363] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[0364] "Means for automating creative tasks" are means for automatically performing creative tasks such as market research and competitive analysis based on a specific workflow.

[0365] "Means for generating product plans" refers to means for generating new product plans based on market data and user feedback.

[0366] The "means for evaluating product plans" is a means for evaluating whether the generated product plans are compatible with market needs and whether they have an advantage over competitors.

[0367] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, etc. and analyzes that information.

[0368] "Means for providing emotional information to the generation AI" refers to means for inputting the user's emotional data obtained from the emotion engine into the generation AI.

[0369] The "means for generating a product plan using emotion information" is a means for generating a new product plan based on the emotion data of the user.

[0370] The "means for evaluating a product plan using emotional information" is a means for evaluating to what extent a generated product plan responds to the user's emotions.

[0371] This invention is a system that utilizes generative AI and an emotion engine to improve the efficiency of product planning work. This system includes a means for automating creative work using generative AI, a means for generating product plans, a means for evaluating product plans, and an emotion engine that recognizes user emotions.

[0372] Hardware and software used

[0373] Server: Use a server with high-performance computing capabilities. Specifically, use a cloud-based server (e.g., Amazon Web Services, Google (registered trademark) Cloud Platform).

[0374] Generative AI models: Use advanced generative AI models such as OpenAI's GPT-4.

[0375] Emotion Engine: Uses Affectiva's emotion recognition software to recognize the user's emotions.

[0376] Device: To collect user emotion data, we use devices equipped with cameras and microphones (e.g., smartphones, tablets).

[0377] Program processing

[0378] 1. Automating creative tasks

[0379] The server collects market data from public databases and APIs on the internet, specifically from data sources such as Google Trends and Statista.

[0380] Example: A server calls the Google Trends API and sends a request to "get data about the latest market trends."

[0381] 2. Conduct a competitive analysis

[0382] The server inputs the collected market data into a generative AI model to perform competitive analysis. The generative AI model used is OpenAI's GPT-4.

[0383] Example: The server inputs the prompt "Please evaluate the strengths and weaknesses of your competitors" into the generation AI and retrieves the results.

[0384] 3. Product planning

[0385] The server collects user purchase and review data and provides it to the generative AI model, which then generates new product plans based on this data.

[0386] Example: The server inputs the following prompt into the generation AI: "Analyze user purchasing data from the past year and suggest a product concept that is likely to be the next hit."

[0387] 4. Product Planning Evaluation

[0388] The server inputs the generated product plans into a generative AI model and evaluates whether they meet market needs.

[0389] Example: The server inputs the prompt statement "Please rate how well this product proposal meets market needs" into the generation AI.

[0390] 5. Collecting User Emotion Data

[0391] The device analyzes the user's facial expressions and voice to collect emotional data using an emotion engine powered by Affectiva's emotion recognition software.

[0392] Example: The device captures the user's facial expressions with a camera and analyzes them using Affectiva's emotion recognition software.

[0393] 6. Sending Emotional Data

[0394] The terminal transmits the analysis results to the server.

[0395] Example: The device sends the analysis result that "the user is expressing feelings of joy toward the product" to the server.

[0396] 7. Product Planning Using Emotional Information

[0397] The server inputs the emotional information obtained from the emotion engine into a generative AI model and generates product plans based on the user's emotions.

[0398] Example: The server inputs the prompt statement "Generate a product proposal that includes elements that the user expresses feelings of joy" into the generation AI.

[0399] 8. Product Planning Evaluation Using Emotional Information

[0400] The server evaluates to what extent the generated product plan responds to the user's feelings.

[0401] Example: The server inputs the prompt statement "Please rate the extent to which this product proposal responds to the user's feelings of joy" into the generation AI.

[0402] In this way, by combining a generative AI and an emotion engine, the system of the present invention can streamline product planning operations and quickly carry out product planning based on user emotions.

[0403] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0404] Step 1:

[0405] Market Data Collection

[0406] The server collects market data from public databases and APIs on the internet, specifically from data sources such as Google Trends and Statista.

[0407] Input: A request to the Google Trends API

[0408] Output: Latest market trend data

[0409] What happens: The server calls the Google Trends API and sends a request to get data about the latest market trends. The server then parses the data returned by the API and extracts the required information.

[0410] Step 2:

[0411] Conducting a competitive analysis

[0412] The server inputs the collected market data into a generative AI model to perform competitive analysis. The generative AI model used is OpenAI's GPT-4.

[0413] Input: Market data, prompt: "Evaluate your competitors' strengths and weaknesses."

[0414] Output: Competitive analysis results

[0415] Specific operation: The server inputs market data into the generation AI and sends a prompt to the generation AI saying, "Please evaluate the strengths and weaknesses of your competitors." The generation AI analyzes the market data and returns the results of its evaluation of the strengths and weaknesses of your competitors.

[0416] Step 3:

[0417] User Data Collection

[0418] The server collects user purchase data and review data, specifically using the database of the e-commerce site and the API of the social networking site.

[0419] Input: E-commerce site database, SNS API

[0420] Output: User purchase data, review data

[0421] Specific operation: The server retrieves the user's purchasing history for the past year from the e-commerce site's database and collects user review data through the SNS API.

[0422] Step 4:

[0423] Product planning generation

[0424] The server inputs the collected user data into a generative AI model to generate new product plans.

[0425] Input: User data, prompt: "Analyze user purchasing data from the past year and suggest product concepts that are likely to be the next hit."

[0426] Output: New product planning

[0427] Specific operation: The server inputs user data into the generation AI and sends it a prompt saying, "Analyze user purchasing data from the past year and propose a product concept that is likely to be the next hit." The generation AI analyzes the data and generates a new product plan.

[0428] Step 5:

[0429] Product planning evaluation

[0430] The server inputs the generated product plans into a generative AI model and evaluates whether they meet market needs.

[0431] Input: Product proposal, prompt: "Please rate how well this product proposal meets market needs."

[0432] Output: Product planning evaluation results

[0433] Specific operation: The server inputs the product plan into the generation AI and sends a prompt to the generation AI saying, "Please evaluate how well this product plan meets market needs." The generation AI analyzes the product plan and evaluates whether it meets market needs.

[0434] Step 6:

[0435] Collecting user emotion data

[0436] The device analyzes the user's facial expressions and voice to collect emotional data using an emotion engine powered by Affectiva's emotion recognition software.

[0437] Input: User's facial expression data, voice data

[0438] Output: Emotion data

[0439] How it works: The device captures the user's facial expressions with a camera and analyzes them using Affectiva's emotion recognition software, generating emotional data as a result of the analysis.

[0440] Step 7:

[0441] Sending emotional data

[0442] The terminal transmits the analysis results to the server.

[0443] Input: Emotion data

[0444] Output: Data sent to the server

[0445] Specific operation: The device sends the analysis result that "the user is expressing feelings of joy toward the product" to the server.

[0446] Step 8:

[0447] Product planning generation using emotional information

[0448] The server inputs the emotional information obtained from the emotion engine into a generative AI model and generates product plans based on the user's emotions.

[0449] Input: Emotion information, prompt "Generate product proposals that include elements that the user finds pleasing"

[0450] Output: Emotion-based product planning

[0451] Specific operation: The server inputs the emotion information into the generation AI and sends a prompt message to the generation AI saying, "Please generate a product proposal that includes elements that show the user's emotion of joy." The generation AI analyzes the emotion information and generates a product proposal based on the user's emotion.

[0452] Step 9:

[0453] Evaluating product planning using emotional information

[0454] The server evaluates to what extent the generated product plan responds to the user's feelings.

[0455] Input: Product proposal, prompt: "Please rate how well this product proposal responds to users' feelings of delight."

[0456] Output: Evaluation results of product planning based on emotions

[0457] Specific operation: The server inputs the product proposal into the generation AI and sends a prompt message to the generation AI saying, "Please rate how well this product proposal responds to the user's feelings of joy." The generation AI analyzes the product proposal and evaluates how well it responds to the user's feelings.

[0458] (Application example 1)

[0459] 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."

[0460] Conventional systems for improving the efficiency of product planning work using generative AI do not take user emotions into consideration when proposing products, making it difficult to increase user satisfaction. Furthermore, by proposing products based on user emotions, more personalized proposals would be possible, which would be expected to increase purchasing motivation, but no such system exists.

[0461] 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.

[0462] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product proposals using the generation AI, means for evaluating the product proposals using the generation AI, means for recognizing emotions, means for providing emotion information to the generation AI, means for generating product proposals based on the emotion information, and means for evaluating the product proposals based on the emotion information. This makes it possible to recognize user emotions in real time and make product proposals based on those emotions.

[0463] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[0464] A "means for automating creative tasks" is a means for automatically executing creative tasks based on a specific workflow.

[0465] The "means for generating product plans" is a means for generating new product plans based on market data and user feedback.

[0466] The "means for evaluating a product plan" is a means for evaluating the extent to which the generated product plan is superior to market needs and competitors.

[0467] The "emotion recognition means" is a means for recognizing the user's emotions from facial expressions, voice, etc.

[0468] "Means for providing emotional information to the generating AI" refers to means for transmitting the recognized emotional information to the generating AI.

[0469] The "means for generating a product proposal based on emotion information" is a means for generating a new product proposal based on emotion information of a user.

[0470] The "means for evaluating product proposals based on emotion information" is a means for evaluating to what extent the generated product proposals respond to the emotions of the user.

[0471] The system for implementing this invention combines a generative AI model and an emotion recognition means. A specific embodiment of the system will be described below.

[0472] System Configuration

[0473] Hardware

[0474] Smartphone: Equipped with a camera and microphone to capture the user's facial expressions and voice.

[0475] Server: Provides the computational resources to run the generative AI model and emotion recognition software.

[0476] software

[0477] Emotion recognition software: As an example, we will use the Microsoft® Azure® Emotion API, which is software for analyzing emotions from a user's facial expressions and voice.

[0478] Generative AI models: As an example, we will use OpenAI GPT-4, a model for generating new product recommendations based on sentiment information, market data, and user feedback.

[0479] Mail order site API: Used to obtain product data and user purchasing history.

[0480] Data processing and calculation

[0481] emotion recognition

[0482] The smartphone's camera and microphone are used to capture the user's facial expressions and voice in real time, and emotion recognition software is used to analyze the user's emotions from the captured data and send the results to a server.

[0483] Generate product suggestions

[0484] The server generates prompts based on the emotion recognition results and the user's past purchase data and browsing history. The generated prompts are then used by the generative AI model to generate new product suggestions.

[0485] Product proposal evaluation

[0486] The system evaluates how well the generated product suggestions respond to the user's emotions, and presents the optimal product suggestions to the user based on the evaluation results.

[0487] Specific examples

[0488] When a user browses a shopping site on their smartphone, the camera and microphone capture their facial expressions and voice. If the user smiles when looking at a particular product, emotion recognition software interprets the smile as "joy." This information is sent to a server, and a generative AI model generates prompts suggesting "products that will make the user happy."

[0489] Prompt Sentence Examples

[0490] Based on the products for which the user expresses joy, generate new product suggestions that satisfy the following criteria:

[0491] 1. The product is similar to a product the user has purchased in the past.

[0492] 2. Products that may be of interest to you based on your browsing history.

[0493] 3. It is in line with current market trends.

[0494] In this way, a product recommendation app that utilizes emotional feedback can make optimal product recommendations based on the user's emotions.

[0495] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0496] Step 1:

[0497] A user browses a shopping site on a smartphone. The smartphone's camera and microphone capture the user's facial expressions and voice in real time. The input is the user's facial expression and voice data, and the output is the captured raw data.

[0498] Step 2:

[0499] The smartphone sends the captured facial and voice data to emotion recognition software, which analyzes the data and identifies the user's emotions. The input is the captured facial and voice data, and the output is the analyzed emotion information.

[0500] Step 3:

[0501] The emotion recognition software sends the analyzed emotion information to the server, which receives the emotion information and provides it to the generative AI model. The input is the analyzed emotion information, and the output is the emotion information provided to the generative AI model.

[0502] Step 4:

[0503] The server generates prompts based on emotional information and the user's past purchasing data and browsing history. The input is emotional information, purchasing data, and browsing history, and the output is the generated prompt. Specifically, the server integrates this data and creates prompts in a format suitable for the generative AI model.

[0504] Step 5:

[0505] The generative AI model generates new product suggestions based on the generated prompt. The input is the prompt, and the output is the generated product suggestions. Specifically, the generative AI model analyzes the prompt and generates appropriate product suggestions.

[0506] Step 6:

[0507] The server evaluates the generated product proposals. The evaluation checks the extent to which the emotional information is reflected. The inputs are the generated product proposals and the emotional information, and the output is the evaluation results. Specifically, the server executes an algorithm to evaluate the extent to which the product proposals respond to the user's emotions.

[0508] Step 7:

[0509] The server presents optimal product suggestions to the user based on the evaluation results. The input is the evaluation results, and the output is the product suggestions presented to the user. Specifically, the server considers the evaluation results, selects the most appropriate product suggestions, and sends them to the user's smartphone.

[0510] In this way, a product recommendation app that utilizes emotional feedback can make optimal product recommendations based on the user's emotions.

[0511] Example 2

[0512] 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."

[0513] Traditional product planning requires manual market research, competitive analysis, and the collection and analysis of user feedback, which takes time and effort. It is also difficult to generate and evaluate product plans that take user sentiment into account, making it difficult to respond quickly to user needs. This has led to a demand for improved efficiency and accuracy in product planning.

[0514] 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.

[0515] In this invention, the server includes a means for automating creative tasks using a generation AI, a means for generating product plans using the generation AI, a means for evaluating product plans using the generation AI, a means for collecting emotion data using an emotion engine that recognizes user emotions, and a means for analyzing the emotion data and providing it to the generation AI, thereby enabling the efficiency and accuracy of product planning tasks to be improved.

[0516] "Generative AI" is a system that uses artificial intelligence technology to generate data and automate specific tasks.

[0517] "Means for automating creative tasks" refers to means for automating creative tasks such as market research, competitive analysis, and product concept generation using generative AI.

[0518] "Product planning generation means" refers to a means of generating new product plans based on market data and user feedback using generative AI.

[0519] "Product planning evaluation means" is a means of evaluating whether product planning generated using generative AI meets market needs and has an advantage over competitors.

[0520] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, etc. and analyzes that information.

[0521] The "emotion data collection means" is a means for collecting user emotions using an emotion engine.

[0522] "Means for analyzing emotional data and providing it to the generative AI" refers to means for analyzing collected emotional data and providing the results as input data to the generative AI.

[0523] The present invention relates to a system for improving the efficiency of product planning work by utilizing generative AI and an emotion engine. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, a means for evaluating product plans using generative AI, a means for collecting emotion data using an emotion engine that recognizes user emotions, and a means for analyzing the emotion data and providing it to the generative AI.

[0524] Hardware and software used

[0525] Server: Executes the generative AI model, analyzes data, and generates and evaluates product plans.

[0526] Device: Equipped with a camera and microphone to collect user emotions and runs the emotion engine.

[0527] Generative AI model: An artificial intelligence model that analyzes market data and user feedback to generate and evaluate product proposals.

[0528] Emotion engine: Software that recognizes emotions from the user's facial expressions and voice and analyzes the data.

[0529] Program processing

[0530] 1. Collecting user emotion data

[0531] The device uses a camera and microphone to collect the user's emotions toward the product, for example by detecting facial expressions and voices while the user is using a smartphone.

[0532] The device uses an emotion engine to analyze the user's emotions from their facial expressions and voice. For example, if the user smiles, it will recognize this as "happiness."

[0533] 2. Emotion data analysis and transmission

[0534] The device sends the analyzed emotion data to the server. For example, it sends data indicating that the user is expressing joy toward the smartphone.

[0535] The server provides the received emotion data to the generation AI, for example, using the emotion data as input data for the generation AI.

[0536] 3. Automating creative tasks

[0537] The server uses generative AI to automate market research and competitive analysis. For example, the server collects market data from the internet and analyzes competitor product information.

[0538] The server generates a product concept based on the collected data, for example, a "new smartphone concept that includes elements that will delight users."

[0539] 4. Product planning

[0540] The server uses generative AI to generate specific product plans, for example, by analyzing user purchase and review data and proposing specifications and designs for new smartphones.

[0541] The server adjusts the product proposal by taking the emotion data into account, for example, by generating a product proposal that emphasizes elements that indicate the user's emotion of joy.

[0542] 5. Product Planning Evaluation

[0543] The server evaluates the product plans generated using generative AI, for example, whether the product plans meet market needs and whether they have an advantage over competitors.

[0544] The server evaluates the degree to which the product plan responds to the user's emotions based on the emotion data, for example, "the degree to which the product plan responds to the user's emotion of joy."

[0545] Specific examples

[0546] For example, if a user expresses joy over a new smartphone, the emotion engine sends that information to the server. The server then uses generative AI to generate a new smartphone proposal that includes elements that the user will be happy about. The server also evaluates how well the proposal responds to the user's joy.

[0547] Prompt Sentence Examples

[0548] "Use generative AI to generate a new smartphone design based on the emotional data users have shown about their new smartphone. Also, evaluate how well that design responds to the user's emotions."

[0549] In this way, the system of the present invention can deeply understand the emotions of users and efficiently carry out product planning based on those emotions.

[0550] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0551] Step 1:

[0552] Collecting user emotion data

[0553] The device uses a camera and microphone to collect the user's emotions toward the product, for example by detecting facial expressions and voices while the user is using a smartphone.

[0554] Input: User's facial expression data, voice data

[0555] Data processing: Using an emotion engine, the collected facial expression and voice data is analyzed to recognize emotions. For example, a smile can be recognized as "joy."

[0556] Output: Parsed emotion data (e.g., happiness, surprise, dissatisfaction, etc.)

[0557] Step 2:

[0558] Emotional data analysis and transmission

[0559] The device sends the analyzed emotion data to the server. For example, it sends data indicating that the user is expressing joy toward the smartphone.

[0560] Input: Parsed emotion data

[0561] Data processing: Emotion data is encrypted and sent to the server using a secure communication protocol.

[0562] Output: Emotion data sent to the server

[0563] Step 3:

[0564] Automating creative tasks

[0565] The server uses generative AI to automate market research and competitive analysis. For example, the server collects market data from the internet and analyzes competitor product information.

[0566] Input: Market data, competitive data

[0567] Data processing: Using generative AI models, collected data is analyzed to extract trends and competitive strengths and weaknesses.

[0568] Output: Analysis results (e.g. market trend reports, competitive analysis reports)

[0569] Step 4:

[0570] Product planning generation

[0571] The server uses generative AI to generate specific product plans, for example, by analyzing user purchase and review data and proposing specifications and designs for new smartphones.

[0572] Inputs: Market data, user feedback, sentiment data

[0573] Data processing: Using a generative AI model, input data is analyzed to generate new product ideas. Emotional data is taken into account to highlight elements that will delight users.

[0574] Output: New product planning (e.g., specifications and design proposals for a new smartphone)

[0575] Step 5:

[0576] Product planning evaluation

[0577] The server evaluates the product plans generated using generative AI, for example, whether the product plans meet market needs and whether they have an advantage over competitors.

[0578] Input: Generated product plans, sentiment data, competitor data

[0579] Data processing: Using generative AI models, we evaluate product planning. Based on emotional data, we evaluate how well it responds to user emotions.

[0580] Output: Evaluation results (e.g., market fit evaluation, competitive advantage evaluation)

[0581] In this way, by clarifying the specific operations and data input / output at each step, the processing flow of the system can be understood more concretely.

[0582] (Application example 2)

[0583] 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."

[0584] Traditional product planning tasks required manual market research, competitive analysis, and the collection and analysis of user feedback, which was extremely time-consuming and labor-intensive. It was also difficult to generate and evaluate product plans that took user sentiment into account, making it difficult to respond quickly to user needs. This made it challenging to improve the efficiency of product planning and user satisfaction.

[0585] 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.

[0586] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, means for recognizing user emotions using an emotion engine, means for providing prompt sentences to the generation AI based on user emotion data, and means for evaluating the product plans generated by the generation AI based on the user's emotions. This makes it possible to improve the efficiency of product planning tasks and generate and evaluate product plans based on user emotions.

[0587] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[0588] A "means for automating creative tasks" is a means for automatically executing creative tasks based on a specific workflow.

[0589] "Means for generating product plans" are means for generating new product plans based on market data and user feedback.

[0590] The "means for evaluating a product plan" is a means for evaluating whether the generated product plan meets market needs and whether it has an advantage over competitors.

[0591] An "emotion engine" is a technology that recognizes a user's emotions and provides that information to other systems.

[0592] The "user emotion recognition means" is a means for analyzing the user's emotions and collecting the emotion data.

[0593] A "prompt sentence" is an input sentence that gives specific instructions or asks questions to the generating AI.

[0594] "Means for providing prompt sentences to the generation AI based on the user's emotional data" refers to means for generating and providing appropriate prompt sentences to the generation AI based on the collected user's emotional data.

[0595] "Means for evaluating product proposals generated by a generative AI based on user emotions" refers to means for evaluating product proposals generated by a generative AI based on user emotional data.

[0596] A system for implementing the present invention uses hardware and software such as a generative AI, an emotion engine, a user terminal, a server, etc. Specific embodiments will be described below.

[0597] System Configuration

[0598] 1. Generation AI

[0599] Generative AI is a system that uses artificial intelligence techniques to generate new information or content from data, specifically using generative AI models such as OpenAI's GPT-3.

[0600] 2. Emotion Engine

[0601] An emotion engine is a technology that recognizes user emotions and provides that information to generative AI. For example, it uses an emotion analysis library such as TextBlob.

[0602] 3. User Device

[0603] A user terminal is a device that users use to enter reviews and feedback, such as a smartphone or PC.

[0604] 4. Server

[0605] The server integrates the generative AI and the emotion engine, and processes and stores data. The server includes a means for automating creative tasks using the generative AI, a means for generating product plans, a means for evaluating product plans, a means for recognizing user emotions using the emotion engine, a means for providing prompt sentences to the generative AI based on user emotion data, and a means for evaluating the product plans generated by the generative AI based on user emotions.

[0606] Data processing and calculation

[0607] 1. Emotion analysis

[0608] Reviews and feedback sent from user devices are sent to a server, which uses a sentiment analysis library such as TextBlob to analyze the user's sentiment and quantify its positive / negative rating.

[0609] 2. Prompt generation

[0610] Based on the collected emotional data, the server generates and provides appropriate prompts to the AI. For example, it generates prompts like the following:

[0611] User sentiment data: [0.8, 0.2, -0.1]

[0612] Please propose a new product concept based on this.

[0613] 3. Product planning

[0614] The generation AI generates a new product plan based on the provided prompt sentence, and the generated product plan is sent to the server.

[0615] 4. Product Planning Evaluation

[0616] The generated product plans are evaluated again using the emotion engine based on the user's emotion data. The evaluation results are stored on the server and fed back to the user's terminal as needed.

[0617] Specific examples

[0618] For example, if a user review reads, "This product is very easy to use!", "The design is great, but the functionality is a bit lacking," or "I think the price is too high, but the quality is good," the results of sentiment analysis will reveal that there are many positive sentiments, but also dissatisfaction with the functionality and price. Based on this sentiment data, the following prompt sentences will be generated:

[0619] User sentiment data: [0.8, 0.2, -0.1]

[0620] Please propose a new product concept based on this.

[0621] The generative AI generates new product concepts based on the prompts and sends them to the server. The generated product concepts are evaluated using an emotion engine, and feedback based on the user's emotions is provided.

[0622] In this way, it becomes possible to improve the efficiency of product planning work and to generate and evaluate product plans based on user emotions.

[0623] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0624] Step 1:

[0625] The user uses the device to enter reviews and feedback.

[0626] Input: User review or feedback text

[0627] Output: User reviews and feedback data

[0628] Specific actions: The user uses a smartphone or computer to enter a review or feedback about a product and press the submit button.

[0629] Step 2:

[0630] The device sends reviews and feedback data to the server.

[0631] Input: User reviews and feedback data

[0632] Output: Review and feedback data sent to the server

[0633] Specific operation: The device transmits the reviews and feedback data entered by the user to a server via the Internet.

[0634] Step 3:

[0635] The server uses an emotion engine to analyze the reviews and feedback data and generate emotion data.

[0636] Input: Review and feedback data

[0637] Output: Emotion data (positive / negative)

[0638] What it does: The server uses a sentiment analysis library such as TextBlob to analyze the reviews and feedback data and quantify the positive / negative ratings.

[0639] Step 4:

[0640] The server generates and provides prompt sentences to the generation AI based on the emotional data.

[0641] Input: Emotion data

[0642] Output: prompt statement

[0643] Specific operation: The server generates and provides appropriate prompts to the generation AI based on the collected emotion data. For example, it generates a prompt such as, "User emotion data: [0.8, 0.2, -0.1] Please propose a new product concept based on this."

[0644] Step 5:

[0645] The generation AI generates a new product plan based on the prompt text and sends it to the server.

[0646] Input: prompt statement

[0647] Output: New product planning

[0648] Specific operation: The generation AI generates a new product proposal based on the provided prompt sentence and sends the result to the server.

[0649] Step 6:

[0650] The server evaluates the generated product plan using an emotion engine.

[0651] Input: New product plan

[0652] Output: Evaluation result

[0653] Specific operation: The server evaluates the generated product proposal again using the emotion engine based on the user's emotion data, and generates the evaluation results.

[0654] Step 7:

[0655] The server feeds back the evaluation results to the user terminal.

[0656] Input: Evaluation result

[0657] Output: Evaluation results displayed on the user's terminal

[0658] Specific operation: The server sends the evaluation results to the user's terminal, and the user can check the results on the terminal.

[0659] 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.

[0660] 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.

[0661] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0662] 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.

[0663] [Second embodiment]

[0664] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0665] 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.

[0666] 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).

[0667] 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.

[0668] 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.

[0669] 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).

[0670] 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.

[0671] 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.

[0672] 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.

[0673] 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.

[0674] 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.

[0675] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0676] "Example 1"

[0677] One embodiment of the present invention is a system for improving the efficiency of product planning work using generative AI. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, and a means for evaluating product plans using generative AI. Specifically, the generative AI automates creative work based on a specific workflow. For example, it can automate tasks such as market research, competitive analysis, and product concept generation. The generative AI also generates product plans based on market data and user feedback. For example, it can analyze user purchase data and review data and generate new product plans based on that data. Furthermore, the generative AI evaluates the generated product plans. For example, it can evaluate whether the product plans meet market needs and whether they have an advantage over competitors. These means enable the efficiency of product planning work to be improved, enabling quick responses to market changes and user needs.

[0678] "Example 2"

[0679] One embodiment of the present invention is a system for improving the efficiency of product planning work using generative AI. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, and a means for evaluating product plans using generative AI. Specifically, the generative AI automates creative work based on a specific workflow. For example, it can automate tasks such as market research, competitive analysis, and product concept generation. The generative AI also generates product plans based on market data and user feedback. For example, it can analyze user purchase data and review data and generate new product plans based on that data. Furthermore, the generative AI evaluates the generated product plans. For example, it can evaluate whether the product plans meet market needs and whether they have an advantage over competitors. These means enable the efficiency of product planning work to be improved, enabling quick responses to market changes and user needs.

[0680] The processing flow of each embodiment will be described below.

[0681] "Example 1"

[0682] Step 1: Generative AI automates creative tasks such as market research and competitive analysis. Specifically, it collects publicly available information on the Internet and extracts information on market trends and competing products.

[0683] Step 2: Next, the generative AI analyzes the collected market data and user feedback. This analysis uses machine learning algorithms and natural language processing technology to understand user purchasing trends, product evaluations, market needs, and more.

[0684] Step 3: Generative AI generates new product plans based on the analysis results. For example, it proposes new product concepts and features based on user purchasing trends. It also devise product pricing and sales strategies based on market needs.

[0685] Step 4: Finally, the generative AI evaluates the generated product plan. Specifically, it evaluates whether the product plan meets market needs and whether it has an advantage over competitors. The results of this evaluation are used to improve the product plan and make a final decision.

[0686] "Example 2"

[0687] Step 1: Generative AI automates creative tasks such as market research and competitive analysis. Specifically, it collects publicly available information on the Internet and extracts information on market trends and competing products.

[0688] Step 2: Next, the generative AI analyzes the collected market data and user feedback. This analysis uses machine learning algorithms and natural language processing technology to understand user purchasing trends, product evaluations, market needs, and more.

[0689] Step 3: Generative AI generates new product plans based on the analysis results. For example, it proposes new product concepts and features based on user purchasing trends. It also devise product pricing and sales strategies based on market needs.

[0690] Step 4: Finally, the generative AI evaluates the generated product plan. Specifically, it evaluates whether the product plan meets market needs and whether it has an advantage over competitors. The results of this evaluation are used to improve the product plan and make a final decision.

[0691] Example 1

[0692] 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."

[0693] Traditional product planning work required a lot of manual work and time, resulting in inefficiency. It was also difficult to respond quickly to market changes and user needs, so rapid product planning was required to maintain competitiveness. Furthermore, traditional methods had limitations when it came to automating creative tasks and evaluating product plans.

[0694] 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.

[0695] In this invention, the server includes means for automating creative tasks using a generative AI model, means for generating product plans using the generative AI model, means for evaluating product plans using the generative AI model, means for collecting market data and user data, means for preprocessing the collected data, means for inputting data into the generative AI model, and means for outputting evaluation results of the generated product plans. This makes it possible to improve the efficiency of product planning tasks and quickly respond to changes in the market and user needs.

[0696] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to generate new information or ideas from data.

[0697] "Means for automating creative tasks" refers to means for automating creative tasks such as market research, competitive analysis, and product concept generation using generative AI models.

[0698] "Means for generating product plans" refers to the means for generating new product plans based on market data and user feedback.

[0699] "Means for evaluating product plans" refers to means for evaluating whether the generated product plans meet market needs and whether they have an advantage over competitors.

[0700] "Market Data" means information and statistics about a particular market, including market trends and competitor information.

[0701] "User Data" refers to information about users, such as their purchasing history, reviews, and feedback.

[0702] "Data preprocessing measures" refer to measures used to clean and normalize collected data in order to convert it into a format suitable for generative AI models.

[0703] "Data Input Means" refers to the means for inputting pre-processed data into a generative AI model.

[0704] "Means for outputting evaluation results" refers to a means for providing users with the results of product planning evaluated by the generative AI model.

[0705] MODE FOR CARRYING OUT THE INVENTION

[0706] This invention is a system for improving the efficiency of product planning work by utilizing a generative AI model. Specific embodiments of this system are described below.

[0707] Hardware and software used

[0708] The server uses high-performance hardware, specifically a high-performance server equipped with an NVIDIA GPU, and uses a generative AI model (e.g., OpenAI GPT-4) as software, and BeautifulSoup and Scrapy as data collection tools.

[0709] System configuration

[0710] The system includes the following main means:

[0711] 1. Means of automating creative tasks: The server uses generative AI models to automate creative tasks such as market research, competitive analysis, and product concept generation.

[0712] 2. Means for generating product plans: The server generates new product plans based on market data and user data.

[0713] 3. Product plan evaluation means: The server evaluates whether the generated product plan meets market needs and whether it has an advantage over competitors.

[0714] 4. Means of collecting market data and user data: The server collects market data and user data from public databases and APIs on the Internet.

[0715] 5. Data preprocessing: The server cleans and normalizes the collected data and converts it into a format suitable for the generative AI model.

[0716] 6. Means for inputting data into the generative AI model: The server inputs the preprocessed data into the generative AI model.

[0717] 7. Output means for evaluation results: The server provides the user with the results of the product plans evaluated by the generative AI model.

[0718] Specific examples

[0719] The server collects market research data from public databases on the Internet. For example, it uses BeautifulSoup to access specific websites, parse the HTML structure, and extract the necessary data. It then cleans the collected data, imputes missing values, removes outliers, and converts the data into CSV format.

[0720] The server then inputs the following prompt into the generative AI model:

[0721] "Analyze the latest market trends and identify your competitors' strengths and weaknesses."

[0722] To collect user data, we call the API of an online shopping site to obtain user purchase history and reviews. We clean the collected data and tokenize the review text data to convert it into vector format. Next, we input the following prompt sentence into the generative AI model:

[0723] "Please propose new product ideas based on user purchasing data and reviews."

[0724] Finally, to evaluate the generated product ideas, we input the following prompt into the generative AI model:

[0725] "Please evaluate whether this product plan meets market needs and whether it has an advantage over competitors."

[0726] The evaluation results are visualized in graphs and tables by the server and displayed on a dashboard that users can access.

[0727] In this way, a system for improving the efficiency of product planning work using generative AI models can consistently perform everything from automating creative work to generating and evaluating product plans, making it possible to quickly respond to changes in the market and user needs.

[0728] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0729] Step 1:

[0730] The server collects market data. Specifically, it retrieves market data from public databases and APIs on the Internet. For example, it uses BeautifulSoup or Scrapy to access specific websites and parse the HTML structure to extract the required data. The input is the website URL or API endpoint, and the output is the collected market data.

[0731] Step 2:

[0732] The server preprocesses the collected market data. Specifically, it cleans and normalizes the data and converts it into a format suitable for the generative AI model. For example, it imputes missing values, removes outliers, and converts the data into CSV format. The input is the collected market data, and the output is the preprocessed data.

[0733] Step 3:

[0734] The server inputs the preprocessed market data into the generative AI model. Specifically, it uses a prompt to instruct the generative AI model on a specific task. For example, the prompt might say, "Analyze the latest market trends and identify the strengths and weaknesses of competitors." The inputs are the preprocessed market data and the prompt, and the output is the analysis results from the generative AI model.

[0735] Step 4:

[0736] The server collects user data. Specifically, it obtains user purchase data and review data from online shopping sites and social media. It collects data using APIs and web scraping tools. The inputs include API endpoints and website URLs, and the output is the collected user data.

[0737] Step 5:

[0738] The server preprocesses the collected user data. Specifically, it cleans and tokenizes the text data and converts it into a format suitable for the generative AI model. For example, it cleans the text data of reviews, tokenizes it, and converts it into vector format. The input is the collected user data, and the output is the preprocessed data.

[0739] Step 6:

[0740] The server inputs the preprocessed user data into the generative AI model. Specifically, it instructs the model to generate a new product proposal using a prompt. For example, the prompt might read, "Please propose a new product proposal based on the user's purchasing data and reviews." The inputs are the preprocessed user data and the prompt, and the output is a new product proposal from the generative AI model.

[0741] Step 7:

[0742] The server evaluates the generated product proposal. Specifically, it uses a generative AI model to evaluate whether the product proposal meets market needs and whether it has an advantage over competitors. For example, a prompt such as "Please evaluate whether this product proposal meets market needs and whether it has an advantage over competitors" is input. The inputs are the generated product proposal and the prompt, and the output is the evaluation result.

[0743] Step 8:

[0744] The server outputs the evaluation results and provides them to the user. Specifically, the evaluation results are visualized in graphs and tables and displayed on a dashboard that the user can access. The input is the evaluation results, and the output is the visualized evaluation results.

[0745] (Application example 1)

[0746] 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."

[0747] Traditional product planning requires a wide range of manual tasks, such as market research, competitive analysis, and product concept generation and evaluation. This is time-consuming and labor-intensive, and there is a high possibility of human error. It is also difficult to effectively utilize user purchase data and review data, making it difficult to quickly respond to market changes and user needs.

[0748] 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 means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, means for collecting market data and analyzing trends and competing products, means for generating new product concepts based on user purchase data and review data, and means for evaluating whether the generated product plans meet market needs and have an advantage over competitors. This makes it possible to improve the efficiency of product planning tasks and quickly respond to changes in the market and user needs.

[0749] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[0750] A "means for automating creative tasks" is a means for automatically executing creative tasks based on a specific workflow.

[0751] "Means for generating product plans" are means for generating new product plans based on market data and user feedback.

[0752] The "means for evaluating a product plan" is a means for evaluating whether the generated product plan meets market needs and whether it has an advantage over competitors.

[0753] "Market Data" is data containing information about a specific market, used to analyze trends, competing products, etc.

[0754] "User Data" refers to data that includes information about a user, such as the user's purchasing history and reviews.

[0755] A "trend" is information that indicates market or consumer trends or tendencies over a specific period of time.

[0756] "Competitive products" are products sold by other companies in the same market and are the products to be compared.

[0757] A "product concept" is a concept that indicates the basic idea and design policy of a new product.

[0758] "Market needs" refer to the demands and expectations of consumers in a particular market.

[0759] "Advantages" refer to the superior features or benefits of a particular product compared to competing products.

[0760] A system for carrying out the present invention utilizes generative AI to improve the efficiency of product planning work. A specific embodiment of this system will be described below.

[0761] System configuration

[0762] The system includes the following main components:

[0763] 1. Automating creative tasks with generative AI

[0764] 2. How to generate product plans using generative AI

[0765] 3. Evaluation method for product planning using generative AI

[0766] 4. A means of gathering market data and analyzing trends and competitor products

[0767] 5. A means of generating new product concepts based on user purchase and review data

[0768] 6. A means of evaluating whether the generated product plan meets market needs and has an advantage over competitors.

[0769] Hardware and software used

[0770] Hardware: Smartphones, servers

[0771] Software: Python, OpenAI API, Pandas

[0772] Data processing and calculation

[0773] 1. Automated Market Research

[0774] The server collects market data and analyzes trends and competitors using a generative AI model (e.g., OpenAI's GPT-4), using the following prompt:

[0775] Example prompt sentence:

[0776] Analyze the market data below to identify trends and competing products.

[0777] Fashion market data for 2023

[0778] 2. Product concept generation

[0779] The server collects user data and generates new product concepts using a generative AI model, specifically using the following prompt:

[0780] Example prompt sentence:

[0781] Generate a new product concept based on the following user data:

[0782] User purchase and review data for 2023

[0783] 3. Product Planning Evaluation

[0784] The server uses a generative AI model to evaluate the generated product concept and market data, using the following prompt:

[0785] Example prompt sentence:

[0786] Please rate the following product concepts:

[0787] Product Concept: A new eco-friendly fashion line

[0788] Market Data: Fashion Market Data for 2023

[0789] Specific examples

[0790] For example, when planning a new eco-friendly fashion line in the fashion market, the server first collects market data and uses a generative AI model to analyze trends and competing products, then generates a new product concept based on user purchase and review data, and finally evaluates whether the generated product concept meets market needs and has an advantage over competitors.

[0791] In this way, a system for improving the efficiency of product planning work that utilizes generative AI can automate product planning work and respond quickly and accurately to changes in the market and user needs.

[0792] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0793] Step 1:

[0794] The server collects market data. Specifically, the server obtains market data from public databases on the Internet and from internal company databases. This market data includes trend information and information on competing products. The input is market data, and the output is the collected market data.

[0795] Step 2:

[0796] The server inputs the collected market data into the generative AI model to analyze trends and competing products. Specifically, the server sends the following prompt to the generative AI model:

[0797] Analyze the market data below to identify trends and competing products.

[0798] Fashion market data for 2023

[0799] The generative AI model analyzes data based on this prompt and outputs trend information and competitive product information. The input is market data and the prompt, and the output is trend information and competitive product information.

[0800] Step 3:

[0801] The server collects user data. Specifically, the server obtains data including user purchase history and reviews. This data reflects user behavior and preferences. The input is user data, and the output is the collected user data.

[0802] Step 4:

[0803] The server inputs the collected user data into the generative AI model to generate a new product concept. Specifically, the server sends the following prompt to the generative AI model:

[0804] Generate a new product concept based on the following user data:

[0805] User purchase and review data for 2023

[0806] The generative AI model analyzes data based on this prompt and outputs a new product concept. The input is user data and the prompt, and the output is a new product concept.

[0807] Step 5:

[0808] The server inputs the generated product concept and market data into the generative AI model for evaluation. Specifically, the server sends the following prompt to the generative AI model:

[0809] Please rate the following product concepts:

[0810] Product Concept: A new eco-friendly fashion line

[0811] Market Data: Fashion Market Data for 2023

[0812] The generative AI model analyzes data based on this prompt and outputs the evaluation results of the product concept. The input is the product concept, market data, and the prompt, and the output is the evaluation results of the product concept.

[0813] Step 6:

[0814] The server determines the final product plan based on the evaluation results. Specifically, the server analyzes the evaluation results and determines whether the product concept meets market needs and has an advantage over competitors. The input is the evaluation results, and the output is the final product plan.

[0815] In this way, a system for improving the efficiency of product planning work that utilizes generative AI can automate product planning work and respond quickly and accurately to changes in the market and user needs.

[0816] Example 2

[0817] 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."

[0818] Traditional product planning work required manual market research, competitive analysis, and the collection and analysis of user data, which was time-consuming and labor-intensive. Furthermore, these tasks required specialized knowledge and were difficult to perform efficiently, making it difficult to respond to the market quickly. Furthermore, evaluation of the resulting product plans often relied on subjective judgment, making objective evaluation difficult.

[0819] 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. In this invention, the server includes a means for automating creative tasks using a generation AI, a means for generating product plans using the generation AI, a means for evaluating product plans using the generation AI, a means for collecting market research data, a means for performing competitive analysis, and a means for collecting and analyzing user data. This makes it possible to improve the efficiency of product planning tasks and quickly respond to changes in the market and user needs.

[0820] "Generative AI" is a system that uses artificial intelligence technology to generate new data and information.

[0821] "Means for automating creative tasks" are means for automatically performing creative tasks such as market research and competitive analysis based on a specific workflow.

[0822] "Means for generating product plans" refers to means for generating new product plans based on market data and user feedback.

[0823] The "means for evaluating a product plan" is a means for evaluating whether the generated product plan meets market needs and whether it has an advantage over competitors.

[0824] "Means for collecting market research data" means means for collecting market data from the internet and other sources.

[0825] "Methods for conducting competitive analysis" are methods for analyzing the strengths and weaknesses of competitors based on collected market research data.

[0826] "Means for collecting and analyzing user data" refers to means for collecting and analyzing user purchasing data and review data.

[0827] The present invention relates to a system for improving the efficiency of product planning work using generative AI. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, a means for evaluating product plans using generative AI, a means for collecting market research data, a means for conducting competitive analysis, and a means for collecting and analyzing user data.

[0828] System configuration

[0829] 1. Hardware and Software Use

[0830] The server provides the computational resources to run the generative AI model. Specifically, a server equipped with a high-performance CPU and GPU is required.

[0831] A terminal is a device for collecting and analyzing user data, including software for accessing a database (e.g., MySQL).

[0832] Generative AI models are built using machine learning frameworks such as TensorFlow and PyTorch.

[0833] Program processing

[0834] 1. Collecting market research data

[0835] The server uses a web scraping tool (e.g., BeautifulSoup) to collect market research data from the Internet by crawling a specified list of URLs and parsing the HTML data to extract the required information.

[0836] 2. Conduct a competitive analysis

[0837] The server performs competitive analysis based on the collected market research data. It uses a natural language processing library (e.g., NLTK) to extract the strengths and weaknesses of competitors. Specifically, it tokenizes the text data and extracts frequently occurring words and phrases to analyze the characteristics of competitors.

[0838] 3. Product concept generation

[0839] The generative AI model generates new product concepts based on the results of competitive analysis. A generative AI model (e.g., GPT-3) is used to propose product concepts that include points of differentiation from competitors. Specifically, it receives the prompt "Please propose a new product concept that includes points of differentiation from competitors" as input and outputs the generated text.

[0840] 4. Collection and analysis of user data

[0841] The device collects user purchase data and review data by retrieving user data from a database (e.g., MySQL) and executing SQL queries to extract purchase history and review comments within a specific period.

[0842] 5. Product planning

[0843] The generative AI model generates new product ideas based on collected user data. It uses machine learning algorithms (e.g., TensorFlow) to analyze user preferences and suggest product ideas based on them.

[0844] 6. Product Planning Evaluation

[0845] The generative AI model evaluates the generated product plans. Based on evaluation indicators (e.g., market suitability, competitive advantage), it evaluates whether the generated product plans meet market needs. Specifically, it uses the evaluation indicators to score the product plans and determine their merits.

[0846] Specific examples

[0847] Automated market research: "Analyze the latest market trends and learn what your competitors are doing."

[0848] Product planning generation: "Please propose new product concepts based on user purchasing data."

[0849] Product Plan Evaluation: "Evaluate whether the generated product plan meets market needs."

[0850] This system will improve the efficiency of product planning operations and enable quick responses to market changes and user needs.

[0851] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0852] Step 1:

[0853] Market research data collection

[0854] The server collects market research data from the Internet by using a web scraping tool (e.g., BeautifulSoup) to crawl a specified list of URLs and parse the HTML data to extract the required information.

[0855] Input: URL list

[0856] Output: Market research data (text format)

[0857] Specific operation: The server accesses the specified URL and retrieves the HTML content. It then uses BeautifulSoup to parse the HTML and extract the necessary text data.

[0858] Step 2:

[0859] Conducting a competitive analysis

[0860] The server performs competitive analysis based on the collected market research data, using natural language processing libraries (e.g., NLTK) to extract competitor strengths and weaknesses.

[0861] Input: Market research data (text format)

[0862] Output: Competitive analysis results (text format)

[0863] Specific operation: The server tokenizes the collected market research data and extracts frequently occurring words and phrases, which are then used to analyze the strengths and weaknesses of competitors, and outputs the results in text format.

[0864] Step 3:

[0865] Product concept generation

[0866] Generative AI models generate new product concepts based on the results of competitive analysis. Generative AI models (e.g., GPT-3) are used to propose product concepts that include points of differentiation from competitors.

[0867] Input: Competitive analysis results (text format)

[0868] Output: Product concept (text format)

[0869] How it works: The generative AI model takes the prompt "Please propose a new product concept that differentiates it from competitors" as input and outputs the generated text.

[0870] Step 4:

[0871] User data collection and analysis

[0872] The device collects user purchase data and review data by retrieving user data from a database (e.g., MySQL) and executing SQL queries to extract purchase history and review comments within a specific period.

[0873] Input: SQL query

[0874] Output: User data (text format)

[0875] Specific operation: The device connects to the database, executes SQL queries to retrieve user data, and outputs the retrieved data in text format.

[0876] Step 5:

[0877] Product planning generation

[0878] The generative AI model generates new product ideas based on collected user data. It uses machine learning algorithms (e.g., TensorFlow) to analyze user preferences and suggest product ideas based on them.

[0879] Input: User data (text format)

[0880] Output: Product planning (text format)

[0881] How it works: The generative AI model takes user data as input and uses a neural network to generate new product ideas.

[0882] Step 6:

[0883] Product planning evaluation

[0884] The generative AI model evaluates the generated product plans, assessing whether the generated product plans fit market needs based on evaluation indicators (e.g., market fit, competitive advantage).

[0885] Input: Product plan (text format)

[0886] Output: Evaluation results (text format)

[0887] Specific operation: The generative AI model uses evaluation indicators to score and judge the merits of product plans. The evaluation results are output in text format.

[0888] (Application example 2)

[0889] 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."

[0890] Traditional product planning work requires a wide range of manual tasks, such as market research, competitive analysis, product concept generation, user feedback analysis, and product plan evaluation, which is time-consuming and labor-intensive. Furthermore, these tasks require specialized knowledge and are difficult to perform efficiently, which poses a major challenge in today's world, where rapid market response is required. Furthermore, there is a lack of efficient ways to automate product planning work using smart devices, making it necessary to solve these issues.

[0891] 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.

[0892] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, means for automating market research using a smart device, means for automating competitive analysis using a smart device, means for generating product concepts using a smart device, and means for evaluating product plans using a smart device, thereby making it possible to improve the efficiency of product planning tasks.

[0893] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[0894] "Product planning" involves coming up with ideas for new products and services and putting them together into concrete plans.

[0895] "Means for automating creative tasks" are means for automating creative tasks such as market research and competitive analysis using generative AI.

[0896] "Product planning generation means" is a means of generating new product plans based on market data and user feedback using generative AI.

[0897] "Product planning evaluation means" is a means of evaluating whether product planning generated using generative AI meets market needs and has an advantage over competitors.

[0898] "Smart devices" are portable electronic devices with advanced functions, such as smartphones and tablets.

[0899] "Market research automation methods" are methods that use smart devices to collect market data and use generative AI to analyze that data.

[0900] "Automated competitive analysis methods" are methods that use smart devices to collect competitor data and analyze that data using generative AI.

[0901] "Product concept generation means" refers to a means of collecting market data and user feedback using smart devices and generating new product concepts using generative AI.

[0902] The "product plan evaluation means" is a means for evaluating a product plan created using a smart device and displaying the results.

[0903] As an embodiment of the present invention, a method for implementing a system for improving the efficiency of product planning work using generative AI on a smart device will be described. This system includes means for automating creative work using generative AI, means for generating product plans, means for evaluating product plans, means for automating market research using a smart device, means for automating competitive analysis, means for generating product concepts, and means for evaluating product plans.

[0904] Hardware and software used

[0905] Hardware: Smartphone (iOS or Android)

[0906] software:

[0907] Generative AI models (e.g., OpenAI GPT-4)

[0908] Database (e.g. Firebase Firestore)

[0909] Front-end frameworks (e.g. React Native)

[0910] Backend framework (e.g. Node.js)

[0911] System configuration

[0912] 1. Automated means of market research:

[0913] A user starts the application using a smartphone and taps the "Market Research" button.

[0914] The server sends market research prompts to the generative AI model.

[0915] The generative AI model collects market data and generates analytical results.

[0916] The server displays the analysis results on the smartphone screen.

[0917] 2. Automated Competitive Analysis Methods:

[0918] User taps the "Competitor Analysis" button.

[0919] The server sends competitive analysis prompts to the generative AI model.

[0920] The generative AI model collects competitor data and generates analytical results.

[0921] The server displays the analysis results on the smartphone screen.

[0922] 3. Product concept generation methods:

[0923] The user taps the "Generate Product Concept" button.

[0924] The server sends a prompt to the generative AI model to generate a product concept.

[0925] Generative AI models generate new product concepts based on market data and user feedback.

[0926] The server displays the generated product concept on the smartphone screen.

[0927] 4. Product planning evaluation methods:

[0928] The user taps the "Product Planning Evaluation" button.

[0929] The server sends a prompt for product planning evaluation to the generative AI model.

[0930] The generative AI model evaluates the generated product proposals and generates evaluation results.

[0931] The server displays the evaluation results on the smartphone screen.

[0932] Examples and prompts

[0933] Specific examples

[0934] For example, when planning a new smartphone case, the following prompt sentence can be sent to the generative AI model:

[0935] Prompt Sentence Examples

[0936] 1. Market research:

[0937] "What are the latest trends in the smartphone case market? Could you please tell us more about the most popular designs and features?"

[0938] 2. Competitive analysis:

[0939] "What are the main competitors in the current smartphone case market and what are the features of their products?"

[0940] 3. Product concept generation:

[0941] "Propose a new smartphone case concept based on user feedback and market data, taking into account user demand for functionality and design."

[0942] 4. Product Planning Evaluation:

[0943] "Please evaluate the following smartphone case proposal. Please tell us whether this proposal meets market needs and whether it has an advantage over competitors. Proposal content: [Specific proposal content]"

[0944] In this way, a system for streamlining product planning work using generative AI can be realized on smart devices, enabling fast and effective product planning.

[0945] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0946] Step 1:

[0947] A user starts the application on their smartphone and taps the "Market Research" button. This causes the application to generate a market research prompt and send it to the server. The input is the user's operation, and the output is the market research prompt.

[0948] Step 2:

[0949] The server sends a market research prompt to the generative AI model. The input is the market research prompt, and the output is a request to the generative AI model.

[0950] Step 3:

[0951] The generative AI model collects market data and generates analysis results. The input is a market research prompt, and the output is the analysis results of the market data. Specifically, the generative AI model collects market data from public databases and news sites on the Internet and performs analysis using natural language processing techniques.

[0952] Step 4:

[0953] The server receives the analysis results from the generative AI model and sends them to the smartphone. The input is the analysis results from the generative AI model, and the output is data sent to the smartphone.

[0954] Step 5:

[0955] The smartphone displays the analysis results received from the server on its screen. The input is the analysis results from the server, and the output is what is displayed to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[0956] Step 6:

[0957] The user taps the "Competitor Analysis" button. This causes the application to generate a prompt for competitor analysis and send it to the server. The input is the user's operation, and the output is the prompt for competitor analysis.

[0958] Step 7:

[0959] The server sends a competitive analysis prompt to the generative AI model. The input is the competitive analysis prompt, and the output is a request to the generative AI model.

[0960] Step 8:

[0961] The generative AI model collects competitor data and generates analysis results. The input is the competitor analysis prompt, and the output is the analysis results of the competitor data. Specifically, the generative AI model collects data from competitor websites and review sites and performs analysis using natural language processing techniques.

[0962] Step 9:

[0963] The server receives the analysis results from the generative AI model and sends them to the smartphone. The input is the analysis results from the generative AI model, and the output is data sent to the smartphone.

[0964] Step 10:

[0965] The smartphone displays the analysis results received from the server on its screen. The input is the analysis results from the server, and the output is what is displayed to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[0966] Step 11:

[0967] The user taps the "Generate Product Concept" button. This causes the application to generate a prompt for generating a product concept and send it to the server. The input is the user's operation, and the output is the prompt for generating a product concept.

[0968] Step 12:

[0969] The server sends a prompt for product concept generation to the generative AI model. The input is the prompt for product concept generation, and the output is a request to the generative AI model.

[0970] Step 13:

[0971] The generative AI model generates new product concepts based on market data and user feedback. The input is a product concept generation prompt, and the output is a new product concept. Specifically, the generative AI model collects data from market databases and user review sites, and uses natural language processing technology to generate new product concepts.

[0972] Step 14:

[0973] The server receives new product concepts from the generative AI model and sends them to the smartphone. The input is the new product concept from the generative AI model, and the output is data transmission to the smartphone.

[0974] Step 15:

[0975] The smartphone displays the new product concept received from the server on its screen. The input is the new product concept from the server, and the output is the display to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[0976] Step 16:

[0977] The user taps the "Product Planning Evaluation" button. This causes the application to generate a prompt for product planning evaluation and send it to the server. The input is the user's operation, and the output is the prompt for product planning evaluation.

[0978] Step 17:

[0979] The server sends a prompt for product planning evaluation to the generative AI model. The input is the prompt for product planning evaluation, and the output is a request to the generative AI model.

[0980] Step 18:

[0981] The generative AI model evaluates the generated product plans and generates evaluation results. The input is the product plan evaluation prompt, and the output is the evaluation results. Specifically, the generative AI model evaluates product plans based on market data and competitor data.

[0982] Step 19:

[0983] The server receives the evaluation results from the generative AI model and sends them to the smartphone. The input is the evaluation results from the generative AI model, and the output is data sent to the smartphone.

[0984] Step 20:

[0985] The smartphone displays the evaluation results received from the server on its screen. The input is the evaluation result from the server, and the output is the display to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[0986] 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.

[0987] "Example 1"

[0988] As one embodiment of the present invention, a system for improving the efficiency of product planning work that combines an emotion engine is provided. This system includes a means for automating creative work using a generative AI, a means for generating product plans using the generative AI, a means for evaluating product plans using the generative AI, and an emotion engine that recognizes user emotions.

[0989] Specifically, the emotion engine recognizes the user's emotions and provides that information to the generative AI. The generative AI uses this emotional information to automate creative tasks. For example, it understands how the user feels about a product and generates a new product proposal based on that emotion. The generative AI also uses the emotional information to evaluate the product proposal. Specifically, it evaluates how well the product proposal responds to the user's emotions.

[0990] As a specific example, if a user expresses joy toward a certain product, the emotion engine provides that information to the generation AI. The generation AI then generates a new product plan that includes elements that will delight the user. The generation AI also evaluates the extent to which the product plan responds to the user's joy. In this way, a system for improving the efficiency of product planning work that combines an emotion engine can deeply understand user emotions and efficiently plan products based on those emotions.

[0991] "Example 2"

[0992] As one embodiment of the present invention, a system for improving the efficiency of product planning work that combines an emotion engine is provided. This system includes a means for automating creative work using a generative AI, a means for generating product plans using the generative AI, a means for evaluating product plans using the generative AI, and an emotion engine that recognizes user emotions.

[0993] Specifically, the emotion engine recognizes the user's emotions and provides that information to the generative AI. The generative AI uses this emotional information to automate creative tasks. For example, it understands how the user feels about a product and generates a new product proposal based on that emotion. The generative AI also uses the emotional information to evaluate the product proposal. Specifically, it evaluates how well the product proposal responds to the user's emotions.

[0994] As a specific example, if a user expresses joy toward a certain product, the emotion engine provides that information to the generation AI. The generation AI then generates a new product plan that includes elements that will delight the user. The generation AI also evaluates the extent to which the product plan responds to the user's joy. In this way, a system for improving the efficiency of product planning work that combines an emotion engine can deeply understand user emotions and efficiently plan products based on those emotions.

[0995] The processing flow of each embodiment will be described below.

[0996] "Example 1"

[0997] Step 1: The emotion engine recognizes the user's emotions. In this step, emotions are analyzed from the user's actions, comments, facial expressions, etc., and the results are generated as emotional information.

[0998] Step 2: Generative AI receives the emotion information and uses it to automate creative tasks. Specifically, it generates new product plans based on the user's emotions.

[0999] Step 3: The generative AI evaluates the product plan. Specifically, it evaluates how well the product plan responds to user emotions. The results of this evaluation are used to improve the product plan or generate new product plans.

[1000] Step 4: The generative AI improves the product plans based on the evaluation results. Specifically, for product plans with low evaluation results, it improves them to better match user emotions. For product plans with high evaluation results, it uses the success factors to generate new product plans.

[1001] "Example 2"

[1002] Step 1: The emotion engine recognizes the user's emotions. In this step, emotions are analyzed from the user's actions, comments, facial expressions, etc., and the results are generated as emotional information.

[1003] Step 2: Generative AI receives the emotion information and uses it to automate creative tasks. Specifically, it generates new product plans based on the user's emotions.

[1004] Step 3: The generative AI evaluates the product plan. Specifically, it evaluates how well the product plan responds to user emotions. The results of this evaluation are used to improve the product plan or generate new product plans.

[1005] Step 4: The generative AI improves the product plans based on the evaluation results. Specifically, for product plans with low evaluation results, it improves them to better match user emotions. For product plans with high evaluation results, it uses the success factors to generate new product plans.

[1006] Example 1

[1007] 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."

[1008] Traditional product planning requires a lot of time and effort due to manual market research, competitive analysis, and the collection and analysis of user feedback. It is also difficult to generate and evaluate product plans that take user sentiment into account, making it difficult to respond quickly to user needs. This has led to a demand for improved efficiency and accuracy in product planning.

[1009] 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.

[1010] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, an emotion engine for recognizing user emotions, means for providing emotion information obtained from the emotion engine to the generation AI, means for generating product plans using the emotion information, and means for evaluating product plans using the emotion information, thereby enabling the efficiency and accuracy of product planning tasks to be improved.

[1011] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[1012] "Means for automating creative tasks" are means for automatically performing creative tasks such as market research and competitive analysis based on a specific workflow.

[1013] "Means for generating product plans" refers to means for generating new product plans based on market data and user feedback.

[1014] The "means for evaluating product plans" is a means for evaluating whether the generated product plans are compatible with market needs and whether they have an advantage over competitors.

[1015] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, etc. and analyzes that information.

[1016] "Means for providing emotional information to the generation AI" refers to means for inputting the user's emotional data obtained from the emotion engine into the generation AI.

[1017] The "means for generating a product plan using emotion information" is a means for generating a new product plan based on the emotion data of the user.

[1018] The "means for evaluating a product plan using emotional information" is a means for evaluating to what extent a generated product plan responds to the user's emotions.

[1019] This invention is a system that utilizes generative AI and an emotion engine to improve the efficiency of product planning work. This system includes a means for automating creative work using generative AI, a means for generating product plans, a means for evaluating product plans, and an emotion engine that recognizes user emotions.

[1020] Hardware and software used

[1021] Server: Use a server with high-performance computing power. Specifically, use a cloud-based server (e.g., Amazon Web Services, Google Cloud Platform).

[1022] Generative AI models: Use advanced generative AI models such as OpenAI's GPT-4.

[1023] Emotion Engine: Uses Affectiva's emotion recognition software to recognize the user's emotions.

[1024] Device: To collect user emotion data, we use devices equipped with cameras and microphones (e.g., smartphones, tablets).

[1025] Program processing

[1026] 1. Automating creative tasks

[1027] The server collects market data from public databases and APIs on the internet, specifically from data sources such as Google Trends and Statista.

[1028] Example: A server calls the Google Trends API and sends a request to "get data about the latest market trends."

[1029] 2. Conduct a competitive analysis

[1030] The server inputs the collected market data into a generative AI model to perform competitive analysis. The generative AI model used is OpenAI's GPT-4.

[1031] Example: The server inputs the prompt "Please evaluate the strengths and weaknesses of your competitors" into the generation AI and retrieves the results.

[1032] 3. Product planning

[1033] The server collects user purchase and review data and provides it to the generative AI model, which then generates new product plans based on this data.

[1034] Example: The server inputs the following prompt into the generation AI: "Analyze user purchasing data from the past year and suggest a product concept that is likely to be the next hit."

[1035] 4. Product Planning Evaluation

[1036] The server inputs the generated product plans into a generative AI model and evaluates whether they meet market needs.

[1037] Example: The server inputs the prompt statement "Please rate how well this product proposal meets market needs" into the generation AI.

[1038] 5. Collecting User Emotion Data

[1039] The device analyzes the user's facial expressions and voice to collect emotional data using an emotion engine powered by Affectiva's emotion recognition software.

[1040] Example: The device captures the user's facial expressions with a camera and analyzes them using Affectiva's emotion recognition software.

[1041] 6. Sending Emotional Data

[1042] The terminal transmits the analysis results to the server.

[1043] Example: The device sends the analysis result that "the user is expressing feelings of joy toward the product" to the server.

[1044] 7. Product Planning Using Emotional Information

[1045] The server inputs the emotional information obtained from the emotion engine into a generative AI model and generates product plans based on the user's emotions.

[1046] Example: The server inputs the prompt statement "Generate a product proposal that includes elements that the user expresses feelings of joy" into the generation AI.

[1047] 8. Product Planning Evaluation Using Emotional Information

[1048] The server evaluates to what extent the generated product plan responds to the user's feelings.

[1049] Example: The server inputs the prompt statement "Please rate the extent to which this product proposal responds to the user's feelings of joy" into the generation AI.

[1050] In this way, by combining a generative AI and an emotion engine, the system of the present invention can streamline product planning operations and quickly carry out product planning based on user emotions.

[1051] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1052] Step 1:

[1053] Market Data Collection

[1054] The server collects market data from public databases and APIs on the internet, specifically from data sources such as Google Trends and Statista.

[1055] Input: A request to the Google Trends API

[1056] Output: Latest market trend data

[1057] What happens: The server calls the Google Trends API and sends a request to get data about the latest market trends. The server then parses the data returned by the API and extracts the required information.

[1058] Step 2:

[1059] Conducting a competitive analysis

[1060] The server inputs the collected market data into a generative AI model to perform competitive analysis. The generative AI model used is OpenAI's GPT-4.

[1061] Input: Market data, prompt: "Evaluate your competitors' strengths and weaknesses."

[1062] Output: Competitive analysis results

[1063] Specific operation: The server inputs market data into the generation AI and sends a prompt to the generation AI saying, "Please evaluate the strengths and weaknesses of your competitors." The generation AI analyzes the market data and returns the results of its evaluation of the strengths and weaknesses of your competitors.

[1064] Step 3:

[1065] User Data Collection

[1066] The server collects user purchase data and review data, specifically using the database of the e-commerce site and the API of the social networking site.

[1067] Input: E-commerce site database, SNS API

[1068] Output: User purchase data, review data

[1069] Specific operation: The server retrieves the user's purchasing history for the past year from the e-commerce site's database and collects user review data through the SNS API.

[1070] Step 4:

[1071] Product planning generation

[1072] The server inputs the collected user data into a generative AI model to generate new product plans.

[1073] Input: User data, prompt: "Analyze user purchasing data from the past year and suggest product concepts that are likely to be the next hit."

[1074] Output: New product planning

[1075] Specific operation: The server inputs user data into the generation AI and sends it a prompt saying, "Analyze user purchasing data from the past year and propose a product concept that is likely to be the next hit." The generation AI analyzes the data and generates a new product plan.

[1076] Step 5:

[1077] Product planning evaluation

[1078] The server inputs the generated product plans into a generative AI model and evaluates whether they meet market needs.

[1079] Input: Product proposal, prompt: "Please rate how well this product proposal meets market needs."

[1080] Output: Product planning evaluation results

[1081] Specific operation: The server inputs the product plan into the generation AI and sends a prompt to the generation AI saying, "Please evaluate how well this product plan meets market needs." The generation AI analyzes the product plan and evaluates whether it meets market needs.

[1082] Step 6:

[1083] Collecting user emotion data

[1084] The device analyzes the user's facial expressions and voice to collect emotional data using an emotion engine powered by Affectiva's emotion recognition software.

[1085] Input: User's facial expression data, voice data

[1086] Output: Emotion data

[1087] How it works: The device captures the user's facial expressions with a camera and analyzes them using Affectiva's emotion recognition software, generating emotional data as a result of the analysis.

[1088] Step 7:

[1089] Sending emotional data

[1090] The terminal transmits the analysis results to the server.

[1091] Input: Emotion data

[1092] Output: Data sent to the server

[1093] Specific operation: The device sends the analysis result that "the user is expressing feelings of joy toward the product" to the server.

[1094] Step 8:

[1095] Product planning generation using emotional information

[1096] The server inputs the emotional information obtained from the emotion engine into a generative AI model and generates product plans based on the user's emotions.

[1097] Input: Emotion information, prompt "Generate product proposals that include elements that the user finds pleasing"

[1098] Output: Emotion-based product planning

[1099] Specific operation: The server inputs the emotion information into the generation AI and sends a prompt message to the generation AI saying, "Please generate a product proposal that includes elements that show the user's emotion of joy." The generation AI analyzes the emotion information and generates a product proposal based on the user's emotion.

[1100] Step 9:

[1101] Evaluating product planning using emotional information

[1102] The server evaluates to what extent the generated product plan responds to the user's feelings.

[1103] Input: Product proposal, prompt: "Please rate how well this product proposal responds to users' feelings of delight."

[1104] Output: Evaluation results of product planning based on emotions

[1105] Specific operation: The server inputs the product proposal into the generation AI and sends a prompt message to the generation AI saying, "Please rate how well this product proposal responds to the user's feelings of joy." The generation AI analyzes the product proposal and evaluates how well it responds to the user's feelings.

[1106] (Application example 1)

[1107] 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."

[1108] Conventional systems for improving the efficiency of product planning work using generative AI do not take user emotions into consideration when proposing products, making it difficult to increase user satisfaction. Furthermore, by proposing products based on user emotions, more personalized proposals would be possible, which would be expected to increase purchasing motivation, but no such system exists.

[1109] 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.

[1110] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product proposals using the generation AI, means for evaluating the product proposals using the generation AI, means for recognizing emotions, means for providing emotion information to the generation AI, means for generating product proposals based on the emotion information, and means for evaluating the product proposals based on the emotion information. This makes it possible to recognize user emotions in real time and make product proposals based on those emotions.

[1111] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[1112] A "means for automating creative tasks" is a means for automatically executing creative tasks based on a specific workflow.

[1113] The "means for generating product plans" is a means for generating new product plans based on market data and user feedback.

[1114] The "means for evaluating a product plan" is a means for evaluating the extent to which the generated product plan is superior to market needs and competitors.

[1115] The "emotion recognition means" is a means for recognizing the user's emotions from facial expressions, voice, etc.

[1116] "Means for providing emotional information to the generating AI" refers to means for transmitting the recognized emotional information to the generating AI.

[1117] The "means for generating a product proposal based on emotion information" is a means for generating a new product proposal based on emotion information of a user.

[1118] The "means for evaluating product proposals based on emotion information" is a means for evaluating to what extent the generated product proposals respond to the emotions of the user.

[1119] The system for implementing this invention combines a generative AI model and an emotion recognition means. A specific embodiment of the system will be described below.

[1120] System Configuration

[1121] Hardware

[1122] Smartphone: Equipped with a camera and microphone to capture the user's facial expressions and voice.

[1123] Server: Provides the computational resources to run the generative AI model and emotion recognition software.

[1124] software

[1125] Emotion recognition software: As an example, we will use the Microsoft Azure Emotion API, which is software for analyzing emotions from a user's facial expressions and voice.

[1126] Generative AI models: As an example, we will use OpenAI GPT-4, a model for generating new product recommendations based on sentiment information, market data, and user feedback.

[1127] Mail order site API: Used to obtain product data and user purchasing history.

[1128] Data processing and calculation

[1129] emotion recognition

[1130] The smartphone's camera and microphone are used to capture the user's facial expressions and voice in real time, and emotion recognition software is used to analyze the user's emotions from the captured data and send the results to a server.

[1131] Generate product suggestions

[1132] The server generates prompts based on the emotion recognition results and the user's past purchase data and browsing history. The generated prompts are then used by the generative AI model to generate new product suggestions.

[1133] Product proposal evaluation

[1134] The system evaluates how well the generated product suggestions respond to the user's emotions, and presents the optimal product suggestions to the user based on the evaluation results.

[1135] Specific examples

[1136] When a user browses a shopping site on their smartphone, the camera and microphone capture their facial expressions and voice. If the user smiles when looking at a particular product, emotion recognition software interprets the smile as "joy." This information is sent to a server, and a generative AI model generates prompts suggesting "products that will make the user happy."

[1137] Prompt Sentence Examples

[1138] Based on the products for which the user expresses joy, generate new product suggestions that satisfy the following criteria:

[1139] 1. The product is similar to a product the user has purchased in the past.

[1140] 2. Products that may be of interest to you based on your browsing history.

[1141] 3. It is in line with current market trends.

[1142] In this way, a product recommendation app that utilizes emotional feedback can make optimal product recommendations based on the user's emotions.

[1143] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1144] Step 1:

[1145] A user browses a shopping site on a smartphone. The smartphone's camera and microphone capture the user's facial expressions and voice in real time. The input is the user's facial expression and voice data, and the output is the captured raw data.

[1146] Step 2:

[1147] The smartphone sends the captured facial and voice data to emotion recognition software, which analyzes the data and identifies the user's emotions. The input is the captured facial and voice data, and the output is the analyzed emotion information.

[1148] Step 3:

[1149] The emotion recognition software sends the analyzed emotion information to the server, which receives the emotion information and provides it to the generative AI model. The input is the analyzed emotion information, and the output is the emotion information provided to the generative AI model.

[1150] Step 4:

[1151] The server generates prompts based on emotional information and the user's past purchasing data and browsing history. The input is emotional information, purchasing data, and browsing history, and the output is the generated prompt. Specifically, the server integrates this data and creates prompts in a format suitable for the generative AI model.

[1152] Step 5:

[1153] The generative AI model generates new product suggestions based on the generated prompt. The input is the prompt, and the output is the generated product suggestions. Specifically, the generative AI model analyzes the prompt and generates appropriate product suggestions.

[1154] Step 6:

[1155] The server evaluates the generated product proposals. The evaluation checks the extent to which the emotional information is reflected. The inputs are the generated product proposals and the emotional information, and the output is the evaluation results. Specifically, the server executes an algorithm to evaluate the extent to which the product proposals respond to the user's emotions.

[1156] Step 7:

[1157] The server presents optimal product suggestions to the user based on the evaluation results. The input is the evaluation results, and the output is the product suggestions presented to the user. Specifically, the server considers the evaluation results, selects the most appropriate product suggestions, and sends them to the user's smartphone.

[1158] In this way, a product recommendation app that utilizes emotional feedback can make optimal product recommendations based on the user's emotions.

[1159] Example 2

[1160] 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."

[1161] Traditional product planning requires manual market research, competitive analysis, and the collection and analysis of user feedback, which takes time and effort. It is also difficult to generate and evaluate product plans that take user sentiment into account, making it difficult to respond quickly to user needs. This has led to a demand for improved efficiency and accuracy in product planning.

[1162] 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.

[1163] In this invention, the server includes a means for automating creative tasks using a generation AI, a means for generating product plans using the generation AI, a means for evaluating product plans using the generation AI, a means for collecting emotion data using an emotion engine that recognizes user emotions, and a means for analyzing the emotion data and providing it to the generation AI, thereby enabling the efficiency and accuracy of product planning tasks to be improved.

[1164] "Generative AI" is a system that uses artificial intelligence technology to generate data and automate specific tasks.

[1165] "Means for automating creative tasks" refers to means for automating creative tasks such as market research, competitive analysis, and product concept generation using generative AI.

[1166] "Product planning generation means" refers to a means of generating new product plans based on market data and user feedback using generative AI.

[1167] "Product planning evaluation means" is a means of evaluating whether product planning generated using generative AI meets market needs and has an advantage over competitors.

[1168] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, etc. and analyzes that information.

[1169] The "emotion data collection means" is a means for collecting user emotions using an emotion engine.

[1170] "Means for analyzing emotional data and providing it to the generative AI" refers to means for analyzing collected emotional data and providing the results as input data to the generative AI.

[1171] The present invention relates to a system for improving the efficiency of product planning work by utilizing generative AI and an emotion engine. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, a means for evaluating product plans using generative AI, a means for collecting emotion data using an emotion engine that recognizes user emotions, and a means for analyzing the emotion data and providing it to the generative AI.

[1172] Hardware and software used

[1173] Server: Executes the generative AI model, analyzes data, and generates and evaluates product plans.

[1174] Device: Equipped with a camera and microphone to collect user emotions and runs the emotion engine.

[1175] Generative AI model: An artificial intelligence model that analyzes market data and user feedback to generate and evaluate product proposals.

[1176] Emotion engine: Software that recognizes emotions from the user's facial expressions and voice and analyzes the data.

[1177] Program processing

[1178] 1. Collecting user emotion data

[1179] The device uses a camera and microphone to collect the user's emotions toward the product, for example by detecting facial expressions and voices while the user is using a smartphone.

[1180] The device uses an emotion engine to analyze the user's emotions from their facial expressions and voice. For example, if the user smiles, it will recognize this as "happiness."

[1181] 2. Emotion data analysis and transmission

[1182] The device sends the analyzed emotion data to the server. For example, it sends data indicating that the user is expressing joy toward the smartphone.

[1183] The server provides the received emotion data to the generation AI, for example, using the emotion data as input data for the generation AI.

[1184] 3. Automating creative tasks

[1185] The server uses generative AI to automate market research and competitive analysis. For example, the server collects market data from the internet and analyzes competitor product information.

[1186] The server generates a product concept based on the collected data, for example, a "new smartphone concept that includes elements that will delight users."

[1187] 4. Product planning

[1188] The server uses generative AI to generate specific product plans, for example, by analyzing user purchase and review data and proposing specifications and designs for new smartphones.

[1189] The server adjusts the product proposal by taking the emotion data into account, for example, by generating a product proposal that emphasizes elements that indicate the user's emotion of joy.

[1190] 5. Product Planning Evaluation

[1191] The server evaluates the product plans generated using generative AI, for example, whether the product plans meet market needs and whether they have an advantage over competitors.

[1192] The server evaluates the degree to which the product plan responds to the user's emotions based on the emotion data, for example, "the degree to which the product plan responds to the user's emotion of joy."

[1193] Specific examples

[1194] For example, if a user expresses joy over a new smartphone, the emotion engine sends that information to the server. The server then uses generative AI to generate a new smartphone proposal that includes elements that the user will be happy about. The server also evaluates how well the proposal responds to the user's joy.

[1195] Prompt Sentence Examples

[1196] "Use generative AI to generate a new smartphone design based on the emotional data users have shown about their new smartphone. Also, evaluate how well that design responds to the user's emotions."

[1197] In this way, the system of the present invention can deeply understand the emotions of users and efficiently carry out product planning based on those emotions.

[1198] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1199] Step 1:

[1200] Collecting user emotion data

[1201] The device uses a camera and microphone to collect the user's emotions toward the product, for example by detecting facial expressions and voices while the user is using a smartphone.

[1202] Input: User's facial expression data, voice data

[1203] Data processing: Using an emotion engine, the collected facial expression and voice data is analyzed to recognize emotions. For example, a smile can be recognized as "joy."

[1204] Output: Parsed emotion data (e.g., happiness, surprise, dissatisfaction, etc.)

[1205] Step 2:

[1206] Emotional data analysis and transmission

[1207] The device sends the analyzed emotion data to the server. For example, it sends data indicating that the user is expressing joy toward the smartphone.

[1208] Input: Parsed emotion data

[1209] Data processing: Emotion data is encrypted and sent to the server using a secure communication protocol.

[1210] Output: Emotion data sent to the server

[1211] Step 3:

[1212] Automating creative tasks

[1213] The server uses generative AI to automate market research and competitive analysis. For example, the server collects market data from the internet and analyzes competitor product information.

[1214] Input: Market data, competitive data

[1215] Data processing: Using generative AI models, collected data is analyzed to extract trends and competitive strengths and weaknesses.

[1216] Output: Analysis results (e.g. market trend reports, competitive analysis reports)

[1217] Step 4:

[1218] Product planning generation

[1219] The server uses generative AI to generate specific product plans, for example, by analyzing user purchase and review data and proposing specifications and designs for new smartphones.

[1220] Inputs: Market data, user feedback, sentiment data

[1221] Data processing: Using a generative AI model, input data is analyzed to generate new product ideas. Emotional data is taken into account to highlight elements that will delight users.

[1222] Output: New product planning (e.g., specifications and design proposals for a new smartphone)

[1223] Step 5:

[1224] Product planning evaluation

[1225] The server evaluates the product plans generated using generative AI, for example, whether the product plans meet market needs and whether they have an advantage over competitors.

[1226] Input: Generated product plans, sentiment data, competitor data

[1227] Data processing: Using generative AI models, we evaluate product planning. Based on emotional data, we evaluate how well it responds to user emotions.

[1228] Output: Evaluation results (e.g., market fit evaluation, competitive advantage evaluation)

[1229] In this way, by clarifying the specific operations and data input / output at each step, the processing flow of the system can be understood more concretely.

[1230] (Application example 2)

[1231] 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."

[1232] Traditional product planning tasks required manual market research, competitive analysis, and the collection and analysis of user feedback, which was extremely time-consuming and labor-intensive. It was also difficult to generate and evaluate product plans that took user sentiment into account, making it difficult to respond quickly to user needs. This made it challenging to improve the efficiency of product planning and user satisfaction.

[1233] 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.

[1234] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, means for recognizing user emotions using an emotion engine, means for providing prompt sentences to the generation AI based on user emotion data, and means for evaluating the product plans generated by the generation AI based on the user's emotions. This makes it possible to improve the efficiency of product planning tasks and generate and evaluate product plans based on user emotions.

[1235] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[1236] A "means for automating creative tasks" is a means for automatically executing creative tasks based on a specific workflow.

[1237] "Means for generating product plans" are means for generating new product plans based on market data and user feedback.

[1238] The "means for evaluating a product plan" is a means for evaluating whether the generated product plan meets market needs and whether it has an advantage over competitors.

[1239] An "emotion engine" is a technology that recognizes a user's emotions and provides that information to other systems.

[1240] The "user emotion recognition means" is a means for analyzing the user's emotions and collecting the emotion data.

[1241] A "prompt sentence" is an input sentence that gives specific instructions or asks questions to the generating AI.

[1242] "Means for providing prompt sentences to the generation AI based on the user's emotional data" refers to means for generating and providing appropriate prompt sentences to the generation AI based on the collected user's emotional data.

[1243] "Means for evaluating product proposals generated by a generative AI based on user emotions" refers to means for evaluating product proposals generated by a generative AI based on user emotional data.

[1244] A system for implementing the present invention uses hardware and software such as a generative AI, an emotion engine, a user terminal, a server, etc. Specific embodiments will be described below.

[1245] System Configuration

[1246] 1. Generation AI

[1247] Generative AI is a system that uses artificial intelligence techniques to generate new information or content from data, specifically using generative AI models such as OpenAI's GPT-3.

[1248] 2. Emotion Engine

[1249] An emotion engine is a technology that recognizes user emotions and provides that information to generative AI. For example, it uses an emotion analysis library such as TextBlob.

[1250] 3. User Device

[1251] A user terminal is a device that users use to enter reviews and feedback, such as a smartphone or PC.

[1252] 4. Server

[1253] The server integrates the generative AI and the emotion engine, and processes and stores data. The server includes a means for automating creative tasks using the generative AI, a means for generating product plans, a means for evaluating product plans, a means for recognizing user emotions using the emotion engine, a means for providing prompt sentences to the generative AI based on user emotion data, and a means for evaluating the product plans generated by the generative AI based on user emotions.

[1254] Data processing and calculation

[1255] 1. Emotion analysis

[1256] Reviews and feedback sent from user devices are sent to a server, which uses a sentiment analysis library such as TextBlob to analyze the user's sentiment and quantify its positive / negative rating.

[1257] 2. Prompt generation

[1258] Based on the collected emotional data, the server generates and provides appropriate prompts to the AI. For example, it generates prompts like the following:

[1259] User sentiment data: [0.8, 0.2, -0.1]

[1260] Please propose a new product concept based on this.

[1261] 3. Product planning

[1262] The generation AI generates a new product plan based on the provided prompt sentence, and the generated product plan is sent to the server.

[1263] 4. Product Planning Evaluation

[1264] The generated product plans are evaluated again using the emotion engine based on the user's emotion data. The evaluation results are stored on the server and fed back to the user's terminal as needed.

[1265] Specific examples

[1266] For example, if a user review reads, "This product is very easy to use!", "The design is great, but the functionality is a bit lacking," or "I think the price is too high, but the quality is good," the results of sentiment analysis will reveal that there are many positive sentiments, but also dissatisfaction with the functionality and price. Based on this sentiment data, the following prompt sentences will be generated:

[1267] User sentiment data: [0.8, 0.2, -0.1]

[1268] Please propose a new product concept based on this.

[1269] The generative AI generates new product concepts based on the prompts and sends them to the server. The generated product concepts are evaluated using an emotion engine, and feedback based on the user's emotions is provided.

[1270] In this way, it becomes possible to improve the efficiency of product planning work and to generate and evaluate product plans based on user emotions.

[1271] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1272] Step 1:

[1273] The user uses the device to enter reviews and feedback.

[1274] Input: User review or feedback text

[1275] Output: User reviews and feedback data

[1276] Specific actions: The user uses a smartphone or computer to enter a review or feedback about a product and press the submit button.

[1277] Step 2:

[1278] The device sends reviews and feedback data to the server.

[1279] Input: User reviews and feedback data

[1280] Output: Review and feedback data sent to the server

[1281] Specific operation: The device transmits the reviews and feedback data entered by the user to a server via the Internet.

[1282] Step 3:

[1283] The server uses an emotion engine to analyze the reviews and feedback data and generate emotion data.

[1284] Input: Review and feedback data

[1285] Output: Emotion data (positive / negative)

[1286] What it does: The server uses a sentiment analysis library such as TextBlob to analyze the reviews and feedback data and quantify the positive / negative ratings.

[1287] Step 4:

[1288] The server generates and provides prompt sentences to the generation AI based on the emotional data.

[1289] Input: Emotion data

[1290] Output: prompt statement

[1291] Specific operation: The server generates and provides appropriate prompts to the generation AI based on the collected emotion data. For example, it generates a prompt such as, "User emotion data: [0.8, 0.2, -0.1] Please propose a new product concept based on this."

[1292] Step 5:

[1293] The generation AI generates a new product plan based on the prompt text and sends it to the server.

[1294] Input: prompt statement

[1295] Output: New product planning

[1296] Specific operation: The generation AI generates a new product proposal based on the provided prompt sentence and sends the result to the server.

[1297] Step 6:

[1298] The server evaluates the generated product plan using an emotion engine.

[1299] Input: New product plan

[1300] Output: Evaluation result

[1301] Specific operation: The server evaluates the generated product proposal again using the emotion engine based on the user's emotion data, and generates the evaluation results.

[1302] Step 7:

[1303] The server feeds back the evaluation results to the user terminal.

[1304] Input: Evaluation result

[1305] Output: Evaluation results displayed on the user's terminal

[1306] Specific operation: The server sends the evaluation results to the user's terminal, and the user can check the results on the terminal.

[1307] 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.

[1308] 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.

[1309] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1310] 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.

[1311] [Third embodiment]

[1312] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1313] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1314] 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).

[1315] 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.

[1316] 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.

[1317] 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).

[1318] 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.

[1319] 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.

[1320] 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.

[1321] 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.

[1322] 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.

[1323] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1324] "Example 1"

[1325] One embodiment of the present invention is a system for improving the efficiency of product planning work using generative AI. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, and a means for evaluating product plans using generative AI. Specifically, the generative AI automates creative work based on a specific workflow. For example, it can automate tasks such as market research, competitive analysis, and product concept generation. The generative AI also generates product plans based on market data and user feedback. For example, it can analyze user purchase data and review data and generate new product plans based on that data. Furthermore, the generative AI evaluates the generated product plans. For example, it can evaluate whether the product plans meet market needs and whether they have an advantage over competitors. These means enable the efficiency of product planning work to be improved, enabling quick responses to market changes and user needs.

[1326] "Example 2"

[1327] One embodiment of the present invention is a system for improving the efficiency of product planning work using generative AI. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, and a means for evaluating product plans using generative AI. Specifically, the generative AI automates creative work based on a specific workflow. For example, it can automate tasks such as market research, competitive analysis, and product concept generation. The generative AI also generates product plans based on market data and user feedback. For example, it can analyze user purchase data and review data and generate new product plans based on that data. Furthermore, the generative AI evaluates the generated product plans. For example, it can evaluate whether the product plans meet market needs and whether they have an advantage over competitors. These means enable the efficiency of product planning work to be improved, enabling quick responses to market changes and user needs.

[1328] The processing flow of each embodiment will be described below.

[1329] "Example 1"

[1330] Step 1: Generative AI automates creative tasks such as market research and competitive analysis. Specifically, it collects publicly available information on the Internet and extracts information on market trends and competing products.

[1331] Step 2: Next, the generative AI analyzes the collected market data and user feedback. This analysis uses machine learning algorithms and natural language processing technology to understand user purchasing trends, product evaluations, market needs, and more.

[1332] Step 3: Generative AI generates new product plans based on the analysis results. For example, it proposes new product concepts and features based on user purchasing trends. It also devise product pricing and sales strategies based on market needs.

[1333] Step 4: Finally, the generative AI evaluates the generated product plan. Specifically, it evaluates whether the product plan meets market needs and whether it has an advantage over competitors. The results of this evaluation are used to improve the product plan and make a final decision.

[1334] "Example 2"

[1335] Step 1: Generative AI automates creative tasks such as market research and competitive analysis. Specifically, it collects publicly available information on the Internet and extracts information on market trends and competing products.

[1336] Step 2: Next, the generative AI analyzes the collected market data and user feedback. This analysis uses machine learning algorithms and natural language processing technology to understand user purchasing trends, product evaluations, market needs, and more.

[1337] Step 3: Generative AI generates new product plans based on the analysis results. For example, it proposes new product concepts and features based on user purchasing trends. It also devise product pricing and sales strategies based on market needs.

[1338] Step 4: Finally, the generative AI evaluates the generated product plan. Specifically, it evaluates whether the product plan meets market needs and whether it has an advantage over competitors. The results of this evaluation are used to improve the product plan and make a final decision.

[1339] Example 1

[1340] 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."

[1341] Traditional product planning work required a lot of manual work and time, resulting in inefficiency. It was also difficult to respond quickly to market changes and user needs, so rapid product planning was required to maintain competitiveness. Furthermore, traditional methods had limitations when it came to automating creative tasks and evaluating product plans.

[1342] 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.

[1343] In this invention, the server includes means for automating creative tasks using a generative AI model, means for generating product plans using the generative AI model, means for evaluating product plans using the generative AI model, means for collecting market data and user data, means for preprocessing the collected data, means for inputting data into the generative AI model, and means for outputting evaluation results of the generated product plans. This makes it possible to improve the efficiency of product planning tasks and quickly respond to changes in the market and user needs.

[1344] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to generate new information or ideas from data.

[1345] "Means for automating creative tasks" refers to means for automating creative tasks such as market research, competitive analysis, and product concept generation using generative AI models.

[1346] "Means for generating product plans" refers to the means for generating new product plans based on market data and user feedback.

[1347] "Means for evaluating product plans" refers to means for evaluating whether the generated product plans meet market needs and whether they have an advantage over competitors.

[1348] "Market Data" means information and statistics about a particular market, including market trends and competitor information.

[1349] "User Data" refers to information about users, such as their purchasing history, reviews, and feedback.

[1350] "Data preprocessing measures" refer to measures used to clean and normalize collected data in order to convert it into a format suitable for generative AI models.

[1351] "Data Input Means" refers to the means for inputting pre-processed data into a generative AI model.

[1352] "Means for outputting evaluation results" refers to a means for providing users with the results of product planning evaluated by the generative AI model.

[1353] MODE FOR CARRYING OUT THE INVENTION

[1354] This invention is a system for improving the efficiency of product planning work by utilizing a generative AI model. Specific embodiments of this system are described below.

[1355] Hardware and software used

[1356] The server uses high-performance hardware, specifically a high-performance server equipped with an NVIDIA GPU, and uses a generative AI model (e.g., OpenAI GPT-4) as software, and BeautifulSoup and Scrapy as data collection tools.

[1357] System configuration

[1358] The system includes the following main means:

[1359] 1. Means of automating creative tasks: The server uses generative AI models to automate creative tasks such as market research, competitive analysis, and product concept generation.

[1360] 2. Means for generating product plans: The server generates new product plans based on market data and user data.

[1361] 3. Product plan evaluation means: The server evaluates whether the generated product plan meets market needs and whether it has an advantage over competitors.

[1362] 4. Means of collecting market data and user data: The server collects market data and user data from public databases and APIs on the Internet.

[1363] 5. Data preprocessing: The server cleans and normalizes the collected data and converts it into a format suitable for the generative AI model.

[1364] 6. Means for inputting data into the generative AI model: The server inputs the preprocessed data into the generative AI model.

[1365] 7. Output means for evaluation results: The server provides the user with the results of the product plans evaluated by the generative AI model.

[1366] Specific examples

[1367] The server collects market research data from public databases on the Internet. For example, it uses BeautifulSoup to access specific websites, parse the HTML structure, and extract the necessary data. It then cleans the collected data, imputes missing values, removes outliers, and converts the data into CSV format.

[1368] The server then inputs the following prompt into the generative AI model:

[1369] "Analyze the latest market trends and identify your competitors' strengths and weaknesses."

[1370] To collect user data, we call the API of an online shopping site to obtain user purchase history and reviews. We clean the collected data and tokenize the review text data to convert it into vector format. Next, we input the following prompt sentence into the generative AI model:

[1371] "Please propose new product ideas based on user purchasing data and reviews."

[1372] Finally, to evaluate the generated product ideas, we input the following prompt into the generative AI model:

[1373] "Please evaluate whether this product plan meets market needs and whether it has an advantage over competitors."

[1374] The evaluation results are visualized in graphs and tables by the server and displayed on a dashboard that users can access.

[1375] In this way, a system for improving the efficiency of product planning work using generative AI models can consistently perform everything from automating creative work to generating and evaluating product plans, making it possible to quickly respond to changes in the market and user needs.

[1376] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1377] Step 1:

[1378] The server collects market data. Specifically, it retrieves market data from public databases and APIs on the Internet. For example, it uses BeautifulSoup or Scrapy to access specific websites and parse the HTML structure to extract the required data. The input is the website URL or API endpoint, and the output is the collected market data.

[1379] Step 2:

[1380] The server preprocesses the collected market data. Specifically, it cleans and normalizes the data and converts it into a format suitable for the generative AI model. For example, it imputes missing values, removes outliers, and converts the data into CSV format. The input is the collected market data, and the output is the preprocessed data.

[1381] Step 3:

[1382] The server inputs the preprocessed market data into the generative AI model. Specifically, it uses a prompt to instruct the generative AI model on a specific task. For example, the prompt might say, "Analyze the latest market trends and identify the strengths and weaknesses of competitors." The inputs are the preprocessed market data and the prompt, and the output is the analysis results from the generative AI model.

[1383] Step 4:

[1384] The server collects user data. Specifically, it obtains user purchase data and review data from online shopping sites and social media. It collects data using APIs and web scraping tools. The inputs include API endpoints and website URLs, and the output is the collected user data.

[1385] Step 5:

[1386] The server preprocesses the collected user data. Specifically, it cleans and tokenizes the text data and converts it into a format suitable for the generative AI model. For example, it cleans the text data of reviews, tokenizes it, and converts it into vector format. The input is the collected user data, and the output is the preprocessed data.

[1387] Step 6:

[1388] The server inputs the preprocessed user data into the generative AI model. Specifically, it instructs the model to generate a new product proposal using a prompt. For example, the prompt might read, "Please propose a new product proposal based on the user's purchasing data and reviews." The inputs are the preprocessed user data and the prompt, and the output is a new product proposal from the generative AI model.

[1389] Step 7:

[1390] The server evaluates the generated product proposal. Specifically, it uses a generative AI model to evaluate whether the product proposal meets market needs and whether it has an advantage over competitors. For example, a prompt such as "Please evaluate whether this product proposal meets market needs and whether it has an advantage over competitors" is input. The inputs are the generated product proposal and the prompt, and the output is the evaluation result.

[1391] Step 8:

[1392] The server outputs the evaluation results and provides them to the user. Specifically, the evaluation results are visualized in graphs and tables and displayed on a dashboard that the user can access. The input is the evaluation results, and the output is the visualized evaluation results.

[1393] (Application example 1)

[1394] 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."

[1395] Traditional product planning requires a wide range of manual tasks, such as market research, competitive analysis, and product concept generation and evaluation. This is time-consuming and labor-intensive, and there is a high possibility of human error. It is also difficult to effectively utilize user purchase data and review data, making it difficult to quickly respond to market changes and user needs.

[1396] 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 means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, means for collecting market data and analyzing trends and competing products, means for generating new product concepts based on user purchase data and review data, and means for evaluating whether the generated product plans meet market needs and have an advantage over competitors. This makes it possible to improve the efficiency of product planning tasks and quickly respond to changes in the market and user needs.

[1397] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[1398] A "means for automating creative tasks" is a means for automatically executing creative tasks based on a specific workflow.

[1399] "Means for generating product plans" are means for generating new product plans based on market data and user feedback.

[1400] The "means for evaluating a product plan" is a means for evaluating whether the generated product plan meets market needs and whether it has an advantage over competitors.

[1401] "Market Data" is data containing information about a specific market, used to analyze trends, competing products, etc.

[1402] "User Data" refers to data that includes information about a user, such as the user's purchasing history and reviews.

[1403] A "trend" is information that indicates market or consumer trends or tendencies over a specific period of time.

[1404] "Competitive products" are products sold by other companies in the same market and are the products to be compared.

[1405] A "product concept" is a concept that indicates the basic idea and design policy of a new product.

[1406] "Market needs" refer to the demands and expectations of consumers in a particular market.

[1407] "Advantages" refer to the superior features or benefits of a particular product compared to competing products.

[1408] A system for carrying out the present invention utilizes generative AI to improve the efficiency of product planning work. A specific embodiment of this system will be described below.

[1409] System configuration

[1410] The system includes the following main components:

[1411] 1. Automating creative tasks with generative AI

[1412] 2. How to generate product plans using generative AI

[1413] 3. Evaluation method for product planning using generative AI

[1414] 4. A means of gathering market data and analyzing trends and competitor products

[1415] 5. A means of generating new product concepts based on user purchase and review data

[1416] 6. A means of evaluating whether the generated product plan meets market needs and has an advantage over competitors.

[1417] Hardware and software used

[1418] Hardware: Smartphones, servers

[1419] Software: Python, OpenAI API, Pandas

[1420] Data processing and calculation

[1421] 1. Automated Market Research

[1422] The server collects market data and analyzes trends and competitors using a generative AI model (e.g., OpenAI's GPT-4), specifically using the following prompt:

[1423] Example prompt sentence:

[1424] Analyze the market data below to identify trends and competing products.

[1425] Fashion market data for 2023

[1426] 2. Product concept generation

[1427] The server collects user data and generates new product concepts using a generative AI model, specifically using the following prompt:

[1428] Example prompt sentence:

[1429] Generate a new product concept based on the following user data:

[1430] User purchase and review data for 2023

[1431] 3. Product Planning Evaluation

[1432] The server uses a generative AI model to evaluate the generated product concept and market data, using the following prompt:

[1433] Example prompt sentence:

[1434] Please rate the following product concepts:

[1435] Product Concept: A new eco-friendly fashion line

[1436] Market Data: Fashion Market Data for 2023

[1437] Specific examples

[1438] For example, when planning a new eco-friendly fashion line in the fashion market, the server first collects market data and uses a generative AI model to analyze trends and competing products, then generates a new product concept based on user purchase and review data, and finally evaluates whether the generated product concept meets market needs and has an advantage over competitors.

[1439] In this way, a system for improving the efficiency of product planning work that utilizes generative AI can automate product planning work and respond quickly and accurately to changes in the market and user needs.

[1440] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1441] Step 1:

[1442] The server collects market data. Specifically, the server obtains market data from public databases on the Internet and from internal company databases. This market data includes trend information and information on competing products. The input is market data, and the output is the collected market data.

[1443] Step 2:

[1444] The server inputs the collected market data into the generative AI model to analyze trends and competing products. Specifically, the server sends the following prompt to the generative AI model:

[1445] Analyze the market data below to identify trends and competing products.

[1446] Fashion market data for 2023

[1447] The generative AI model analyzes data based on this prompt and outputs trend information and competitive product information. The input is market data and the prompt, and the output is trend information and competitive product information.

[1448] Step 3:

[1449] The server collects user data. Specifically, the server obtains data including user purchase history and reviews. This data reflects user behavior and preferences. The input is user data, and the output is the collected user data.

[1450] Step 4:

[1451] The server inputs the collected user data into the generative AI model to generate a new product concept. Specifically, the server sends the following prompt to the generative AI model:

[1452] Generate a new product concept based on the following user data:

[1453] User purchase and review data for 2023

[1454] The generative AI model analyzes data based on this prompt and outputs a new product concept. The input is user data and the prompt, and the output is a new product concept.

[1455] Step 5:

[1456] The server inputs the generated product concept and market data into the generative AI model for evaluation. Specifically, the server sends the following prompt to the generative AI model:

[1457] Please rate the following product concepts:

[1458] Product Concept: A new eco-friendly fashion line

[1459] Market Data: Fashion Market Data for 2023

[1460] The generative AI model analyzes data based on this prompt and outputs the evaluation results of the product concept. The input is the product concept, market data, and the prompt, and the output is the evaluation results of the product concept.

[1461] Step 6:

[1462] The server determines the final product plan based on the evaluation results. Specifically, the server analyzes the evaluation results and determines whether the product concept meets market needs and has an advantage over competitors. The input is the evaluation results, and the output is the final product plan.

[1463] In this way, a system for improving the efficiency of product planning work that utilizes generative AI can automate product planning work and respond quickly and accurately to changes in the market and user needs.

[1464] Example 2

[1465] 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."

[1466] Traditional product planning work required manual market research, competitive analysis, and the collection and analysis of user data, which was time-consuming and labor-intensive. Furthermore, these tasks required specialized knowledge and were difficult to perform efficiently, making it difficult to respond to the market quickly. Furthermore, evaluation of the resulting product plans often relied on subjective judgment, making objective evaluation difficult.

[1467] 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. In this invention, the server includes a means for automating creative tasks using a generation AI, a means for generating product plans using the generation AI, a means for evaluating product plans using the generation AI, a means for collecting market research data, a means for performing competitive analysis, and a means for collecting and analyzing user data. This makes it possible to improve the efficiency of product planning tasks and quickly respond to changes in the market and user needs.

[1468] "Generative AI" is a system that uses artificial intelligence technology to generate new data and information.

[1469] "Means for automating creative tasks" are means for automatically performing creative tasks such as market research and competitive analysis based on a specific workflow.

[1470] "Means for generating product plans" refers to means for generating new product plans based on market data and user feedback.

[1471] The "means for evaluating a product plan" is a means for evaluating whether the generated product plan meets market needs and whether it has an advantage over competitors.

[1472] "Means for collecting market research data" means means for collecting market data from the internet and other sources.

[1473] "Methods for conducting competitive analysis" are methods for analyzing the strengths and weaknesses of competitors based on collected market research data.

[1474] "Means for collecting and analyzing user data" refers to means for collecting and analyzing user purchasing data and review data.

[1475] The present invention relates to a system for improving the efficiency of product planning work using generative AI. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, a means for evaluating product plans using generative AI, a means for collecting market research data, a means for conducting competitive analysis, and a means for collecting and analyzing user data.

[1476] System configuration

[1477] 1. Hardware and Software Use

[1478] The server provides the computational resources to run the generative AI model. Specifically, a server equipped with a high-performance CPU and GPU is required.

[1479] A terminal is a device for collecting and analyzing user data, including software for accessing a database (e.g., MySQL).

[1480] Generative AI models are built using machine learning frameworks such as TensorFlow and PyTorch.

[1481] Program processing

[1482] 1. Collecting market research data

[1483] The server uses a web scraping tool (e.g., BeautifulSoup) to collect market research data from the Internet by crawling a specified list of URLs and parsing the HTML data to extract the required information.

[1484] 2. Conduct a competitive analysis

[1485] The server performs competitive analysis based on the collected market research data. It uses a natural language processing library (e.g., NLTK) to extract the strengths and weaknesses of competitors. Specifically, it tokenizes the text data and extracts frequently occurring words and phrases to analyze the characteristics of competitors.

[1486] 3. Product concept generation

[1487] The generative AI model generates new product concepts based on the results of competitive analysis. A generative AI model (e.g., GPT-3) is used to propose product concepts that include points of differentiation from competitors. Specifically, it receives the prompt "Please propose a new product concept that includes points of differentiation from competitors" as input and outputs the generated text.

[1488] 4. Collection and analysis of user data

[1489] The device collects user purchase data and review data by retrieving user data from a database (e.g., MySQL) and executing SQL queries to extract purchase history and review comments within a specific period.

[1490] 5. Product planning

[1491] The generative AI model generates new product ideas based on collected user data. It uses machine learning algorithms (e.g., TensorFlow) to analyze user preferences and suggest product ideas based on them.

[1492] 6. Product Planning Evaluation

[1493] The generative AI model evaluates the generated product plans. Based on evaluation indicators (e.g., market suitability, competitive advantage), it evaluates whether the generated product plans meet market needs. Specifically, it uses the evaluation indicators to score the product plans and determine their merits.

[1494] Specific examples

[1495] Automated market research: "Analyze the latest market trends and learn what your competitors are doing."

[1496] Product planning generation: "Please propose new product concepts based on user purchasing data."

[1497] Product Plan Evaluation: "Evaluate whether the generated product plan meets market needs."

[1498] This system will improve the efficiency of product planning operations and enable quick responses to market changes and user needs.

[1499] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1500] Step 1:

[1501] Market research data collection

[1502] The server collects market research data from the Internet by using a web scraping tool (e.g., BeautifulSoup) to crawl a specified list of URLs and parse the HTML data to extract the required information.

[1503] Input: URL list

[1504] Output: Market research data (text format)

[1505] Specific operation: The server accesses the specified URL and retrieves the HTML content. It then uses BeautifulSoup to parse the HTML and extract the necessary text data.

[1506] Step 2:

[1507] Conducting a competitive analysis

[1508] The server performs competitive analysis based on the collected market research data, using natural language processing libraries (e.g., NLTK) to extract competitor strengths and weaknesses.

[1509] Input: Market research data (text format)

[1510] Output: Competitive analysis results (text format)

[1511] Specific operation: The server tokenizes the collected market research data and extracts frequently occurring words and phrases, which are then used to analyze the strengths and weaknesses of competitors, and outputs the results in text format.

[1512] Step 3:

[1513] Product concept generation

[1514] Generative AI models generate new product concepts based on the results of competitive analysis. Generative AI models (e.g., GPT-3) are used to propose product concepts that include points of differentiation from competitors.

[1515] Input: Competitive analysis results (text format)

[1516] Output: Product concept (text format)

[1517] How it works: The generative AI model takes the prompt "Please propose a new product concept that differentiates it from competitors" as input and outputs the generated text.

[1518] Step 4:

[1519] User data collection and analysis

[1520] The device collects user purchase data and review data by retrieving user data from a database (e.g., MySQL) and executing SQL queries to extract purchase history and review comments within a specific period.

[1521] Input: SQL query

[1522] Output: User data (text format)

[1523] Specific operation: The device connects to the database, executes SQL queries to retrieve user data, and outputs the retrieved data in text format.

[1524] Step 5:

[1525] Product planning generation

[1526] The generative AI model generates new product ideas based on collected user data. It uses machine learning algorithms (e.g., TensorFlow) to analyze user preferences and suggest product ideas based on them.

[1527] Input: User data (text format)

[1528] Output: Product planning (text format)

[1529] How it works: The generative AI model takes user data as input and uses a neural network to generate new product ideas.

[1530] Step 6:

[1531] Product planning evaluation

[1532] The generative AI model evaluates the generated product plans, assessing whether the generated product plans fit market needs based on evaluation indicators (e.g., market fit, competitive advantage).

[1533] Input: Product plan (text format)

[1534] Output: Evaluation results (text format)

[1535] Specific operation: The generative AI model uses evaluation indicators to score and judge the merits of product plans. The evaluation results are output in text format.

[1536] (Application example 2)

[1537] 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."

[1538] Traditional product planning work requires a wide range of manual tasks, such as market research, competitive analysis, product concept generation, user feedback analysis, and product plan evaluation, which is time-consuming and labor-intensive. Furthermore, these tasks require specialized knowledge and are difficult to perform efficiently, which poses a major challenge in today's world, where rapid market response is required. Furthermore, there is a lack of efficient ways to automate product planning work using smart devices, making it necessary to solve these issues.

[1539] 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.

[1540] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, means for automating market research using a smart device, means for automating competitive analysis using a smart device, means for generating product concepts using a smart device, and means for evaluating product plans using a smart device, thereby making it possible to improve the efficiency of product planning tasks.

[1541] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[1542] "Product planning" involves coming up with ideas for new products and services and putting them together into concrete plans.

[1543] "Means for automating creative tasks" are means for automating creative tasks such as market research and competitive analysis using generative AI.

[1544] "Product planning generation means" is a means of generating new product plans based on market data and user feedback using generative AI.

[1545] "Product planning evaluation means" is a means of evaluating whether product planning generated using generative AI meets market needs and has an advantage over competitors.

[1546] "Smart devices" are portable electronic devices with advanced functions, such as smartphones and tablets.

[1547] "Market research automation methods" are methods that use smart devices to collect market data and use generative AI to analyze that data.

[1548] "Automated competitive analysis methods" are methods that use smart devices to collect competitor data and analyze that data using generative AI.

[1549] "Product concept generation means" refers to a means of collecting market data and user feedback using smart devices and generating new product concepts using generative AI.

[1550] The "product plan evaluation means" is a means for evaluating a product plan created using a smart device and displaying the results.

[1551] As an embodiment of the present invention, a method for implementing a system for improving the efficiency of product planning work using generative AI on a smart device will be described. This system includes means for automating creative work using generative AI, means for generating product plans, means for evaluating product plans, means for automating market research using a smart device, means for automating competitive analysis, means for generating product concepts, and means for evaluating product plans.

[1552] Hardware and software used

[1553] Hardware: Smartphone (iOS or Android)

[1554] software:

[1555] Generative AI models (e.g., OpenAI GPT-4)

[1556] Database (e.g. Firebase Firestore)

[1557] Front-end frameworks (e.g. React Native)

[1558] Backend framework (e.g. Node.js)

[1559] System configuration

[1560] 1. Automated means of market research:

[1561] A user starts the application using a smartphone and taps the "Market Research" button.

[1562] The server sends market research prompts to the generative AI model.

[1563] The generative AI model collects market data and generates analytical results.

[1564] The server displays the analysis results on the smartphone screen.

[1565] 2. Automated Competitive Analysis Methods:

[1566] User taps the "Competitor Analysis" button.

[1567] The server sends competitive analysis prompts to the generative AI model.

[1568] The generative AI model collects competitor data and generates analytical results.

[1569] The server displays the analysis results on the smartphone screen.

[1570] 3. Product concept generation methods:

[1571] The user taps the "Generate Product Concept" button.

[1572] The server sends a prompt to the generative AI model to generate a product concept.

[1573] Generative AI models generate new product concepts based on market data and user feedback.

[1574] The server displays the generated product concept on the smartphone screen.

[1575] 4. Product planning evaluation methods:

[1576] The user taps the "Product Planning Evaluation" button.

[1577] The server sends a prompt for product planning evaluation to the generative AI model.

[1578] The generative AI model evaluates the generated product proposals and generates evaluation results.

[1579] The server displays the evaluation results on the smartphone screen.

[1580] Examples and prompts

[1581] Specific examples

[1582] For example, when planning a new smartphone case, the following prompt sentence can be sent to the generative AI model:

[1583] Prompt Sentence Examples

[1584] 1. Market research:

[1585] "What are the latest trends in the smartphone case market? Could you please tell us more about the most popular designs and features?"

[1586] 2. Competitive analysis:

[1587] "What are the main competitors in the current smartphone case market and what are the features of their products?"

[1588] 3. Product concept generation:

[1589] "Propose a new smartphone case concept based on user feedback and market data, taking into account user demand for functionality and design."

[1590] 4. Product Planning Evaluation:

[1591] "Please evaluate the following smartphone case proposal. Please tell us whether this proposal meets market needs and whether it has an advantage over competitors. Proposal content: [Specific proposal content]"

[1592] In this way, a system for streamlining product planning work using generative AI can be realized on smart devices, enabling fast and effective product planning.

[1593] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1594] Step 1:

[1595] A user starts the application on their smartphone and taps the "Market Research" button. This causes the application to generate a market research prompt and send it to the server. The input is the user's operation, and the output is the market research prompt.

[1596] Step 2:

[1597] The server sends a market research prompt to the generative AI model. The input is the market research prompt, and the output is a request to the generative AI model.

[1598] Step 3:

[1599] The generative AI model collects market data and generates analysis results. The input is a market research prompt, and the output is the analysis results of the market data. Specifically, the generative AI model collects market data from public databases and news sites on the Internet and performs analysis using natural language processing techniques.

[1600] Step 4:

[1601] The server receives the analysis results from the generative AI model and sends them to the smartphone. The input is the analysis results from the generative AI model, and the output is data sent to the smartphone.

[1602] Step 5:

[1603] The smartphone displays the analysis results received from the server on its screen. The input is the analysis results from the server, and the output is what is displayed to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[1604] Step 6:

[1605] The user taps the "Competitor Analysis" button. This causes the application to generate a prompt for competitor analysis and send it to the server. The input is the user's operation, and the output is the prompt for competitor analysis.

[1606] Step 7:

[1607] The server sends a competitive analysis prompt to the generative AI model. The input is the competitive analysis prompt, and the output is a request to the generative AI model.

[1608] Step 8:

[1609] The generative AI model collects competitor data and generates analysis results. The input is the competitor analysis prompt, and the output is the analysis results of the competitor data. Specifically, the generative AI model collects data from competitor websites and review sites and performs analysis using natural language processing techniques.

[1610] Step 9:

[1611] The server receives the analysis results from the generative AI model and sends them to the smartphone. The input is the analysis results from the generative AI model, and the output is data sent to the smartphone.

[1612] Step 10:

[1613] The smartphone displays the analysis results received from the server on its screen. The input is the analysis results from the server, and the output is what is displayed to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[1614] Step 11:

[1615] The user taps the "Generate Product Concept" button. This causes the application to generate a prompt for generating a product concept and send it to the server. The input is the user's operation, and the output is the prompt for generating a product concept.

[1616] Step 12:

[1617] The server sends a prompt for product concept generation to the generative AI model. The input is the prompt for product concept generation, and the output is a request to the generative AI model.

[1618] Step 13:

[1619] The generative AI model generates new product concepts based on market data and user feedback. The input is a product concept generation prompt, and the output is a new product concept. Specifically, the generative AI model collects data from market databases and user review sites, and uses natural language processing technology to generate new product concepts.

[1620] Step 14:

[1621] The server receives new product concepts from the generative AI model and sends them to the smartphone. The input is the new product concept from the generative AI model, and the output is data transmission to the smartphone.

[1622] Step 15:

[1623] The smartphone displays the new product concept received from the server on its screen. The input is the new product concept from the server, and the output is the display to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[1624] Step 16:

[1625] The user taps the "Product Planning Evaluation" button. This causes the application to generate a prompt for product planning evaluation and send it to the server. The input is the user's operation, and the output is the prompt for product planning evaluation.

[1626] Step 17:

[1627] The server sends a prompt for product planning evaluation to the generative AI model. The input is the prompt for product planning evaluation, and the output is a request to the generative AI model.

[1628] Step 18:

[1629] The generative AI model evaluates the generated product plans and generates evaluation results. The input is the product plan evaluation prompt, and the output is the evaluation results. Specifically, the generative AI model evaluates product plans based on market data and competitor data.

[1630] Step 19:

[1631] The server receives the evaluation results from the generative AI model and sends them to the smartphone. The input is the evaluation results from the generative AI model, and the output is data sent to the smartphone.

[1632] Step 20:

[1633] The smartphone displays the evaluation results received from the server on its screen. The input is the evaluation result from the server, and the output is the display to the user. Specifically, the smartphone application analyzes the received data and displays it in a format that is easy for the user to understand.

[1634] 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.

[1635] "Example 1"

[1636] As one embodiment of the present invention, a system for improving the efficiency of product planning work that combines an emotion engine is provided. This system includes a means for automating creative work using a generative AI, a means for generating product plans using the generative AI, a means for evaluating product plans using the generative AI, and an emotion engine that recognizes user emotions.

[1637] Specifically, the emotion engine recognizes the user's emotions and provides that information to the generative AI. The generative AI uses this emotional information to automate creative tasks. For example, it understands how the user feels about a product and generates a new product proposal based on that emotion. The generative AI also uses the emotional information to evaluate the product proposal. Specifically, it evaluates how well the product proposal responds to the user's emotions.

[1638] As a specific example, if a user expresses joy toward a certain product, the emotion engine provides that information to the generation AI. The generation AI then generates a new product plan that includes elements that will delight the user. The generation AI also evaluates the extent to which the product plan responds to the user's joy. In this way, a system for improving the efficiency of product planning work that combines an emotion engine can deeply understand user emotions and efficiently plan products based on those emotions.

[1639] "Example 2"

[1640] As one embodiment of the present invention, a system for improving the efficiency of product planning work that combines an emotion engine is provided. This system includes a means for automating creative work using a generative AI, a means for generating product plans using the generative AI, a means for evaluating product plans using the generative AI, and an emotion engine that recognizes user emotions.

[1641] Specifically, the emotion engine recognizes the user's emotions and provides that information to the generative AI. The generative AI uses this emotional information to automate creative tasks. For example, it understands how the user feels about a product and generates a new product proposal based on that emotion. The generative AI also uses the emotional information to evaluate the product proposal. Specifically, it evaluates how well the product proposal responds to the user's emotions.

[1642] As a specific example, if a user expresses joy toward a certain product, the emotion engine provides that information to the generation AI. The generation AI then generates a new product plan that includes elements that will delight the user. The generation AI also evaluates the extent to which the product plan responds to the user's joy. In this way, a system for improving the efficiency of product planning work that combines an emotion engine can deeply understand user emotions and efficiently plan products based on those emotions.

[1643] The processing flow of each embodiment will be described below.

[1644] "Example 1"

[1645] Step 1: The emotion engine recognizes the user's emotions. In this step, emotions are analyzed from the user's actions, comments, facial expressions, etc., and the results are generated as emotional information.

[1646] Step 2: Generative AI receives the emotion information and uses it to automate creative tasks. Specifically, it generates new product plans based on the user's emotions.

[1647] Step 3: The generative AI evaluates the product plan. Specifically, it evaluates how well the product plan responds to user emotions. The results of this evaluation are used to improve the product plan or generate new product plans.

[1648] Step 4: The generative AI improves the product plans based on the evaluation results. Specifically, for product plans with low evaluation results, it improves them to better match user emotions. For product plans with high evaluation results, it uses the success factors to generate new product plans.

[1649] "Example 2"

[1650] Step 1: The emotion engine recognizes the user's emotions. In this step, emotions are analyzed from the user's actions, comments, facial expressions, etc., and the results are generated as emotional information.

[1651] Step 2: Generative AI receives the emotion information and uses it to automate creative tasks. Specifically, it generates new product plans based on the user's emotions.

[1652] Step 3: The generative AI evaluates the product plan. Specifically, it evaluates how well the product plan responds to user emotions. The results of this evaluation are used to improve the product plan or generate new product plans.

[1653] Step 4: Generative AI improves product planning based on the evaluation results.

[1654] For product plans with low evaluation results, we improve them to better match user emotions. For product plans with high evaluation results, we use the success factors to create new product plans.

[1655] Example 1

[1656] 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."

[1657] Traditional product planning requires a lot of time and effort due to manual market research, competitive analysis, and the collection and analysis of user feedback. It is also difficult to generate and evaluate product plans that take user sentiment into account, making it difficult to respond quickly to user needs. This has led to a demand for improved efficiency and accuracy in product planning.

[1658] 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.

[1659] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, an emotion engine for recognizing user emotions, means for providing emotion information obtained from the emotion engine to the generation AI, means for generating product plans using the emotion information, and means for evaluating product plans using the emotion information, thereby enabling the efficiency and accuracy of product planning tasks to be improved.

[1660] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[1661] "Means for automating creative tasks" are means for automatically performing creative tasks such as market research and competitive analysis based on a specific workflow.

[1662] "Means for generating product plans" refers to means for generating new product plans based on market data and user feedback.

[1663] The "means for evaluating product plans" is a means for evaluating whether the generated product plans are compatible with market needs and whether they have an advantage over competitors.

[1664] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, etc. and analyzes that information.

[1665] "Means for providing emotional information to the generation AI" refers to means for inputting the user's emotional data obtained from the emotion engine into the generation AI.

[1666] The "means for generating a product plan using emotion information" is a means for generating a new product plan based on the emotion data of the user.

[1667] The "means for evaluating a product plan using emotional information" is a means for evaluating to what extent a generated product plan responds to the user's emotions.

[1668] This invention is a system that utilizes generative AI and an emotion engine to improve the efficiency of product planning work. This system includes a means for automating creative work using generative AI, a means for generating product plans, a means for evaluating product plans, and an emotion engine that recognizes user emotions.

[1669] Hardware and software used

[1670] Server: Use a server with high-performance computing power. Specifically, use a cloud-based server (e.g., Amazon Web Services, Google Cloud Platform).

[1671] Generative AI models: Use advanced generative AI models such as OpenAI's GPT-4.

[1672] Emotion Engine: Uses Affectiva's emotion recognition software to recognize the user's emotions.

[1673] Device: To collect user emotion data, we use devices equipped with cameras and microphones (e.g., smartphones, tablets).

[1674] Program processing

[1675] 1. Automating creative tasks

[1676] The server collects market data from public databases and APIs on the internet, specifically from data sources such as Google Trends and Statista.

[1677] Example: A server calls the Google Trends API and sends a request to "get data about the latest market trends."

[1678] 2. Conduct a competitive analysis

[1679] The server inputs the collected market data into a generative AI model to perform competitive analysis. The generative AI model used is OpenAI's GPT-4.

[1680] Example: The server inputs the prompt "Please evaluate the strengths and weaknesses of your competitors" into the generation AI and retrieves the results.

[1681] 3. Product planning

[1682] The server collects user purchase and review data and provides it to the generative AI model, which then generates new product plans based on this data.

[1683] Example: The server inputs the following prompt into the generation AI: "Analyze user purchasing data from the past year and suggest a product concept that is likely to be the next hit."

[1684] 4. Product Planning Evaluation

[1685] The server inputs the generated product plans into a generative AI model and evaluates whether they meet market needs.

[1686] Example: The server inputs the prompt statement "Please rate how well this product proposal meets market needs" into the generation AI.

[1687] 5. Collecting User Emotion Data

[1688] The device analyzes the user's facial expressions and voice to collect emotional data using an emotion engine powered by Affectiva's emotion recognition software.

[1689] Example: The device captures the user's facial expressions with a camera and analyzes them using Affectiva's emotion recognition software.

[1690] 6. Sending Emotional Data

[1691] The terminal transmits the analysis results to the server.

[1692] Example: The device sends the analysis result that "the user is expressing feelings of joy toward the product" to the server.

[1693] 7. Product Planning Using Emotional Information

[1694] The server inputs the emotional information obtained from the emotion engine into a generative AI model and generates product plans based on the user's emotions.

[1695] Example: The server inputs the prompt statement "Generate a product proposal that includes elements that the user expresses feelings of joy" into the generation AI.

[1696] 8. Product Planning Evaluation Using Emotional Information

[1697] The server evaluates to what extent the generated product plan responds to the user's feelings.

[1698] Example: The server inputs the prompt statement "Please rate the extent to which this product proposal responds to the user's feelings of joy" into the generation AI.

[1699] In this way, by combining a generative AI and an emotion engine, the system of the present invention can streamline product planning operations and quickly carry out product planning based on user emotions.

[1700] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1701] Step 1:

[1702] Market Data Collection

[1703] The server collects market data from public databases and APIs on the internet, specifically from data sources such as Google Trends and Statista.

[1704] Input: A request to the Google Trends API

[1705] Output: Latest market trend data

[1706] What happens: The server calls the Google Trends API and sends a request to get data about the latest market trends. The server then parses the data returned by the API and extracts the required information.

[1707] Step 2:

[1708] Conducting a competitive analysis

[1709] The server inputs the collected market data into a generative AI model to perform competitive analysis. The generative AI model used is OpenAI's GPT-4.

[1710] Input: Market data, prompt: "Evaluate your competitors' strengths and weaknesses."

[1711] Output: Competitive analysis results

[1712] Specific operation: The server inputs market data into the generation AI and sends a prompt to the generation AI saying, "Please evaluate the strengths and weaknesses of your competitors." The generation AI analyzes the market data and returns the results of its evaluation of the strengths and weaknesses of your competitors.

[1713] Step 3:

[1714] User Data Collection

[1715] The server collects user purchase data and review data, specifically using the database of the e-commerce site and the API of the social networking site.

[1716] Input: E-commerce site database, SNS API

[1717] Output: User purchase data, review data

[1718] Specific operation: The server retrieves the user's purchasing history for the past year from the e-commerce site's database and collects user review data through the SNS API.

[1719] Step 4:

[1720] Product planning generation

[1721] The server inputs the collected user data into a generative AI model to generate new product plans.

[1722] Input: User data, prompt: "Analyze user purchasing data from the past year and suggest product concepts that are likely to be the next hit."

[1723] Output: New product planning

[1724] Specific operation: The server inputs user data into the generation AI and sends it a prompt saying, "Analyze user purchasing data from the past year and propose a product concept that is likely to be the next hit." The generation AI analyzes the data and generates a new product plan.

[1725] Step 5:

[1726] Product planning evaluation

[1727] The server inputs the generated product plans into a generative AI model and evaluates whether they meet market needs.

[1728] Input: Product proposal, prompt: "Please rate how well this product proposal meets market needs."

[1729] Output: Product planning evaluation results

[1730] Specific operation: The server inputs the product plan into the generation AI and sends a prompt to the generation AI saying, "Please evaluate how well this product plan meets market needs." The generation AI analyzes the product plan and evaluates whether it meets market needs.

[1731] Step 6:

[1732] Collecting user emotion data

[1733] The device analyzes the user's facial expressions and voice to collect emotional data using an emotion engine powered by Affectiva's emotion recognition software.

[1734] Input: User's facial expression data, voice data

[1735] Output: Emotion data

[1736] How it works: The device captures the user's facial expressions with a camera and analyzes them using Affectiva's emotion recognition software, generating emotional data as a result of the analysis.

[1737] Step 7:

[1738] Sending emotional data

[1739] The terminal transmits the analysis results to the server.

[1740] Input: Emotion data

[1741] Output: Data sent to the server

[1742] Specific operation: The device sends the analysis result that "the user is expressing feelings of joy toward the product" to the server.

[1743] Step 8:

[1744] Product planning generation using emotional information

[1745] The server inputs the emotional information obtained from the emotion engine into a generative AI model and generates product plans based on the user's emotions.

[1746] Input: Emotion information, prompt "Generate product proposals that include elements that the user finds pleasing"

[1747] Output: Emotion-based product planning

[1748] Specific operation: The server inputs the emotion information into the generation AI and sends a prompt message to the generation AI saying, "Please generate a product proposal that includes elements that show the user's emotion of joy." The generation AI analyzes the emotion information and generates a product proposal based on the user's emotion.

[1749] Step 9:

[1750] Evaluating product planning using emotional information

[1751] The server evaluates to what extent the generated product plan responds to the user's feelings.

[1752] Input: Product proposal, prompt: "Please rate how well this product proposal responds to users' feelings of delight."

[1753] Output: Evaluation results of product planning based on emotions

[1754] Specific operation: The server inputs the product proposal into the generation AI and sends a prompt message to the generation AI saying, "Please rate how well this product proposal responds to the user's feelings of joy." The generation AI analyzes the product proposal and evaluates how well it responds to the user's feelings.

[1755] (Application example 1)

[1756] 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."

[1757] Conventional systems for improving the efficiency of product planning work using generative AI do not take user emotions into consideration when proposing products, making it difficult to increase user satisfaction. Furthermore, by proposing products based on user emotions, more personalized proposals would be possible, which would be expected to increase purchasing motivation, but no such system exists.

[1758] 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.

[1759] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product proposals using the generation AI, means for evaluating the product proposals using the generation AI, means for recognizing emotions, means for providing emotion information to the generation AI, means for generating product proposals based on the emotion information, and means for evaluating the product proposals based on the emotion information. This makes it possible to recognize user emotions in real time and make product proposals based on those emotions.

[1760] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[1761] A "means for automating creative tasks" is a means for automatically executing creative tasks based on a specific workflow.

[1762] The "means for generating product plans" is a means for generating new product plans based on market data and user feedback.

[1763] The "means for evaluating a product plan" is a means for evaluating the extent to which the generated product plan is superior to market needs and competitors.

[1764] The "emotion recognition means" is a means for recognizing the user's emotions from facial expressions, voice, etc.

[1765] "Means for providing emotional information to the generating AI" refers to means for transmitting the recognized emotional information to the generating AI.

[1766] The "means for generating a product proposal based on emotion information" is a means for generating a new product proposal based on emotion information of a user.

[1767] The "means for evaluating product proposals based on emotion information" is a means for evaluating to what extent the generated product proposals respond to the emotions of the user.

[1768] The system for implementing this invention combines a generative AI model and an emotion recognition means. A specific embodiment of the system will be described below.

[1769] System Configuration

[1770] Hardware

[1771] Smartphone: Equipped with a camera and microphone to capture the user's facial expressions and voice.

[1772] Server: Provides the computational resources to run the generative AI model and emotion recognition software.

[1773] software

[1774] Emotion recognition software: As an example, we will use the Microsoft Azure Emotion API, which is software for analyzing emotions from a user's facial expressions and voice.

[1775] Generative AI models: As an example, we will use OpenAI GPT-4, a model for generating new product recommendations based on sentiment information, market data, and user feedback.

[1776] Mail order site API: Used to obtain product data and user purchasing history.

[1777] Data processing and calculation

[1778] emotion recognition

[1779] The smartphone's camera and microphone are used to capture the user's facial expressions and voice in real time, and emotion recognition software is used to analyze the user's emotions from the captured data and send the results to a server.

[1780] Generate product suggestions

[1781] The server generates prompts based on the emotion recognition results and the user's past purchase data and browsing history. The generated prompts are then used by the generative AI model to generate new product suggestions.

[1782] Product proposal evaluation

[1783] The system evaluates how well the generated product suggestions respond to the user's emotions, and presents the optimal product suggestions to the user based on the evaluation results.

[1784] Specific examples

[1785] When a user browses a shopping site on their smartphone, the camera and microphone capture their facial expressions and voice. If the user smiles when looking at a particular product, emotion recognition software interprets the smile as "joy." This information is sent to a server, and a generative AI model generates prompts suggesting "products that will make the user happy."

[1786] Prompt Sentence Examples

[1787] Based on the products for which the user expresses joy, generate new product suggestions that satisfy the following criteria:

[1788] 1. The product is similar to a product the user has purchased in the past.

[1789] 2. Products that may be of interest to you based on your browsing history.

[1790] 3. It is in line with current market trends.

[1791] In this way, a product recommendation app that utilizes emotional feedback can make optimal product recommendations based on the user's emotions.

[1792] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1793] Step 1:

[1794] A user browses a shopping site on a smartphone. The smartphone's camera and microphone capture the user's facial expressions and voice in real time. The input is the user's facial expression and voice data, and the output is the captured raw data.

[1795] Step 2:

[1796] The smartphone sends the captured facial and voice data to emotion recognition software, which analyzes the data and identifies the user's emotions. The input is the captured facial and voice data, and the output is the analyzed emotion information.

[1797] Step 3:

[1798] The emotion recognition software sends the analyzed emotion information to the server, which receives the emotion information and provides it to the generative AI model. The input is the analyzed emotion information, and the output is the emotion information provided to the generative AI model.

[1799] Step 4:

[1800] The server generates prompts based on emotional information and the user's past purchasing data and browsing history. The input is emotional information, purchasing data, and browsing history, and the output is the generated prompt. Specifically, the server integrates this data and creates prompts in a format suitable for the generative AI model.

[1801] Step 5:

[1802] The generative AI model generates new product suggestions based on the generated prompt. The input is the prompt, and the output is the generated product suggestions. Specifically, the generative AI model analyzes the prompt and generates appropriate product suggestions.

[1803] Step 6:

[1804] The server evaluates the generated product proposals. The evaluation checks the extent to which the emotional information is reflected. The inputs are the generated product proposals and the emotional information, and the output is the evaluation results. Specifically, the server executes an algorithm to evaluate the extent to which the product proposals respond to the user's emotions.

[1805] Step 7:

[1806] The server presents optimal product suggestions to the user based on the evaluation results. The input is the evaluation results, and the output is the product suggestions presented to the user. Specifically, the server considers the evaluation results, selects the most appropriate product suggestions, and sends them to the user's smartphone.

[1807] In this way, a product recommendation app that utilizes emotional feedback can make optimal product recommendations based on the user's emotions.

[1808] Example 2

[1809] 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."

[1810] Traditional product planning requires manual market research, competitive analysis, and the collection and analysis of user feedback, which takes time and effort. It is also difficult to generate and evaluate product plans that take user sentiment into account, making it difficult to respond quickly to user needs. This has led to a demand for improved efficiency and accuracy in product planning.

[1811] 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.

[1812] In this invention, the server includes a means for automating creative tasks using a generation AI, a means for generating product plans using the generation AI, a means for evaluating product plans using the generation AI, a means for collecting emotion data using an emotion engine that recognizes user emotions, and a means for analyzing the emotion data and providing it to the generation AI, thereby enabling the efficiency and accuracy of product planning tasks to be improved.

[1813] "Generative AI" is a system that uses artificial intelligence technology to generate data and automate specific tasks.

[1814] "Means for automating creative tasks" refers to means for automating creative tasks such as market research, competitive analysis, and product concept generation using generative AI.

[1815] "Product planning generation means" refers to a means of generating new product plans based on market data and user feedback using generative AI.

[1816] "Product planning evaluation means" is a means of evaluating whether product planning generated using generative AI meets market needs and has an advantage over competitors.

[1817] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, etc. and analyzes that information.

[1818] The "emotion data collection means" is a means for collecting user emotions using an emotion engine.

[1819] "Means for analyzing emotional data and providing it to the generative AI" refers to means for analyzing collected emotional data and providing the results as input data to the generative AI.

[1820] The present invention relates to a system for improving the efficiency of product planning work by utilizing generative AI and an emotion engine. This system includes a means for automating creative work using generative AI, a means for generating product plans using generative AI, a means for evaluating product plans using generative AI, a means for collecting emotion data using an emotion engine that recognizes user emotions, and a means for analyzing the emotion data and providing it to the generative AI.

[1821] Hardware and software used

[1822] Server: Executes the generative AI model, analyzes data, and generates and evaluates product plans.

[1823] Device: Equipped with a camera and microphone to collect user emotions and runs the emotion engine.

[1824] Generative AI model: An artificial intelligence model that analyzes market data and user feedback to generate and evaluate product proposals.

[1825] Emotion engine: Software that recognizes emotions from the user's facial expressions and voice and analyzes the data.

[1826] Program processing

[1827] 1. Collecting user emotion data

[1828] The device uses a camera and microphone to collect the user's emotions toward the product, for example by detecting facial expressions and voices while the user is using a smartphone.

[1829] The device uses an emotion engine to analyze the user's emotions from their facial expressions and voice. For example, if the user smiles, it will recognize this as "happiness."

[1830] 2. Emotion data analysis and transmission

[1831] The device sends the analyzed emotion data to the server. For example, it sends data indicating that the user is expressing joy toward the smartphone.

[1832] The server provides the received emotion data to the generation AI, for example, using the emotion data as input data for the generation AI.

[1833] 3. Automating creative tasks

[1834] The server uses generative AI to automate market research and competitive analysis. For example, the server collects market data from the internet and analyzes competitor product information.

[1835] The server generates a product concept based on the collected data, for example, a "new smartphone concept that includes elements that will delight users."

[1836] 4. Product planning

[1837] The server uses generative AI to generate specific product plans, for example, by analyzing user purchase and review data and proposing specifications and designs for new smartphones.

[1838] The server adjusts the product proposal by taking the emotion data into account, for example, by generating a product proposal that emphasizes elements that indicate the user's emotion of joy.

[1839] 5. Product Planning Evaluation

[1840] The server evaluates the product plans generated using generative AI, for example, whether the product plans meet market needs and whether they have an advantage over competitors.

[1841] The server evaluates the degree to which the product plan responds to the user's emotions based on the emotion data, for example, "the degree to which the product plan responds to the user's emotion of joy."

[1842] Specific examples

[1843] For example, if a user expresses joy over a new smartphone, the emotion engine sends that information to the server. The server then uses generative AI to generate a new smartphone proposal that includes elements that the user will be happy about. The server also evaluates how well the proposal responds to the user's joy.

[1844] Prompt Sentence Examples

[1845] "Use generative AI to generate a new smartphone design based on the emotional data users have shown about their new smartphone. Also, evaluate how well that design responds to the user's emotions."

[1846] In this way, the system of the present invention can deeply understand the emotions of users and efficiently carry out product planning based on those emotions.

[1847] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1848] Step 1:

[1849] Collecting user emotion data

[1850] The device uses a camera and microphone to collect the user's emotions toward the product, for example by detecting facial expressions and voices while the user is using a smartphone.

[1851] Input: User's facial expression data, voice data

[1852] Data processing: Using an emotion engine, the collected facial expression and voice data is analyzed to recognize emotions. For example, a smile can be recognized as "joy."

[1853] Output: Parsed emotion data (e.g., happiness, surprise, dissatisfaction, etc.)

[1854] Step 2:

[1855] Emotional data analysis and transmission

[1856] The device sends the analyzed emotion data to the server. For example, it sends data indicating that the user is expressing joy toward the smartphone.

[1857] Input: Parsed emotion data

[1858] Data processing: Emotion data is encrypted and sent to the server using a secure communication protocol.

[1859] Output: Emotion data sent to the server

[1860] Step 3:

[1861] Automating creative tasks

[1862] The server uses generative AI to automate market research and competitive analysis. For example, the server collects market data from the internet and analyzes competitor product information.

[1863] Input: Market data, competitive data

[1864] Data processing: Using generative AI models, collected data is analyzed to extract trends and competitive strengths and weaknesses.

[1865] Output: Analysis results (e.g. market trend reports, competitive analysis reports)

[1866] Step 4:

[1867] Product planning generation

[1868] The server uses generative AI to generate specific product plans, for example, by analyzing user purchase and review data and proposing specifications and designs for new smartphones.

[1869] Inputs: Market data, user feedback, sentiment data

[1870] Data processing: Using a generative AI model, input data is analyzed to generate new product ideas. Emotional data is taken into account to highlight elements that will delight users.

[1871] Output: New product planning (e.g., specifications and design proposals for a new smartphone)

[1872] Step 5:

[1873] Product planning evaluation

[1874] The server evaluates the product plans generated using generative AI, for example, whether the product plans meet market needs and whether they have an advantage over competitors.

[1875] Input: Generated product plans, sentiment data, competitor data

[1876] Data processing: Using generative AI models, we evaluate product planning. Based on emotional data, we evaluate how well it responds to user emotions.

[1877] Output: Evaluation results (e.g., market fit evaluation, competitive advantage evaluation)

[1878] In this way, by clarifying the specific operations and data input / output at each step, the processing flow of the system can be understood more concretely.

[1879] (Application example 2)

[1880] 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."

[1881] Traditional product planning tasks required manual market research, competitive analysis, and the collection and analysis of user feedback, which was extremely time-consuming and labor-intensive. It was also difficult to generate and evaluate product plans that took user sentiment into account, making it difficult to respond quickly to user needs. This made it challenging to improve the efficiency of product planning and user satisfaction.

[1882] 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.

[1883] In this invention, the server includes means for automating creative tasks using a generation AI, means for generating product plans using the generation AI, means for evaluating product plans using the generation AI, means for recognizing user emotions using an emotion engine, means for providing prompt sentences to the generation AI based on user emotion data, and means for evaluating the product plans generated by the generation AI based on the user's emotions. This makes it possible to improve the efficiency of product planning tasks and generate and evaluate product plans based on user emotions.

[1884] "Generative AI" is a system that uses artificial intelligence technology to generate new information and content from data.

[1885] A "means for automating creative tasks" is a means for automatically executing creative tasks based on a specific workflow.

[1886] "Means for generating product plans" are means for generating new product plans based on market data and user feedback.

[1887] The "means for evaluating a product plan" is a means for evaluating whether the generated product plan meets market needs and whether it has an advantage over competitors.

[1888] An "emotion engine" is a technology that recognizes a user's emotions and provides that information to other systems.

[1889] The "user emotion recognition means" is a means for analyzing the user's emotions and collecting the emotion data.

[1890] A "prompt sentence" is an input sentence that gives specific instructions or asks questions to the generating AI.

[1891] "Means for providing prompt sentences to the generation AI based on the user's emotional data" refers to means for generating and providing appropriate prompt sentences to the generation AI based on the collected user's emotional data.

[1892] "Means for evaluating product proposals generated by a generative AI based on user emotions" refers to means for evaluating product proposals generated by a generative AI based on user emotional data.

[1893] A system for implementing the present invention uses hardware and software such as a generative AI, an emotion engine, a user terminal, a server, etc. Specific embodiments will be described below.

[1894] System Configuration

[1895] 1. Generation AI

[1896] Generative AI is a system that uses artificial intelligence techniques to generate new information or content from data, specifically using generative AI models such as OpenAI's GPT-3.

[1897] 2. Emotion Engine

[1898] An emotion engine is a technology that recognizes user emotions and provides that information to generative AI. For example, it uses an emotion analysis library such as TextBlob.

[1899] 3. User Device

[1900] A user terminal is a device that users use to enter reviews and feedback, such as a smartphone or PC.

[1901] 4. Server

[1902] The server integrates the generative AI and the emotion engine, and processes and stores data. The server includes a means for automating creative tasks using the generative AI, a means for generating product plans, a means for evaluating product plans, a means for recognizing user emotions using the emotion engine, a means for providing prompt sentences to the generative AI based on user emotion data, and a means for evaluating the product plans generated by the generative AI based on user emotions.

[1903] Data processing and calculation

[1904] 1. Emotion analysis

[1905] Reviews and feedback sent from user devices are sent to a server, which uses a sentiment analysis library such as TextBlob to analyze the user's sentiment and quantify its positive / negative rating.

[1906] 2. Prompt generation

[1907] Based on the collected emotional data, the server generates and provides appropriate prompts to the AI. For example, it generates prompts like the following:

[1908] User sentiment data: [0.8, 0.2, -0.1]

[1909] Please propose a new product concept based on this.

[1910] 3. Product planning

[1911] The generation AI generates a new product plan based on the provided prompt sentence, and the generated product plan is sent to the server.

[1912] 4. Product Planning Evaluation

[1913] The generated product plans are evaluated again using the emotion engine based on the user's emotion data. The evaluation results are stored on the server and fed back to the user's terminal as needed.

[1914] Specific examples

[1915] For example, if a user review reads, "This product is very easy to use!", "The design is great, but the functionality is a bit lacking," or "I think the price is too high, but the quality is good," the results of sentiment analysis will reveal that there are many positive sentiments, but also dissatisfaction with the functionality and price. Based on this sentiment data, the following prompt sentences will be generated:

[1916] User sentiment data: [0.8, 0.2, -0.1]

[1917] Please propose a new product concept based on this.

[1918] The generative AI generates new product concepts based on the prompts and sends them to the server. The generated product concepts are evaluated using an emotion engine, and feedback based on the user's emotions is provided.

[1919] In this way, it becomes possible to improve the efficiency of product planning work and to generate and evaluate product plans based on user emotions.

[1920] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1921] Step 1:

[1922] The user uses the device to enter reviews and feedback.

[1923] Input: User review or feedback text

[1924] Output: User reviews and feedback data

[1925] Specific actions: The user uses a smartphone or computer to enter a review or feedback about a product and press the submit button.

[1926] Step 2:

[1927] The device sends reviews and feedback data to the server.

[1928] Input: User reviews and feedback data

[1929] Output: Review and feedback data sent to the server

[1930] Specific operation: The device transmits the reviews and feedback data entered by the user to a server via the Internet.

[1931] Step 3:

[1932] The server uses an emotion engine to analyze the reviews and feedback data and generate emotion data.

[1933] Input: Review and feedback data

[1934] Output: Emotion data (positive / negative)

[1935] What it does: The server uses a sentiment analysis library such as TextBlob to analyze the reviews and feedback data and quantify the positive / negative ratings.

[1936] Step 4:

[1937] The server generates and provides prompt sentences to the generation AI based on the emotional data.

[1938] Input: Emotion data

[1939] Output: prompt statement

[1940] Specific operation: The server generates and provides appropriate prompts to the generation AI based on the collected emotion data. For example, it generates a prompt such as, "User emotion data: [0.8, 0.2, -0.1] Please propose a new product concept based on this."

[1941] Step 5:

[1942] The generation AI generates a new product plan based on the prompt text and sends it to the server.

[1943] Input: prompt statement

[1944] Output: New product planning

[1945] Specific operation: The generation AI generates a new product proposal based on the provided prompt sentence and sends the result to the server.

[1946] Step 6:

[1947] The server evaluates the generated product plan using an emotion engine.

[1948] Input: New product plan

[1949] Output: Evaluation result

[1950] Specific operation: The server evaluates the generated product proposal again using the emotion engine based on the user's emotion data, and generates the evaluation results.

[1951] Step 7:

[1952] The server feeds back the evaluation results to the user terminal.

[1953] Input: Evaluation result

[1954] Output: Evaluation results displayed on the user's terminal

[1955] Specific operation: The server sends the evaluation results to the user's terminal, and the user can check the results on the terminal.

[1956] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1957] The data generation model 58 is a so-called generative AI (Artificial Intelligence).

[1958] An example of a data generation model58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generative AIs. Data generation models 58

[1959] , 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 the data format of voice data, text data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1960] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1961] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1962] [Fourth embodiment]

[1963] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1964] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1965] 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).

[1966] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1967] 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.

[1968] 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).

[1969] 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.

[1970] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by contro...

Claims

1. A means for providing a prompt to the generative AI model to instruct the model on market research; means for collecting market data output from the generative AI model; A means for analyzing competitive products using the market data; A means for generating a new product concept based on the competing products; and a means for evaluating the new product concept. system.

2. The generating means generates the new product concept based on at least one of purchase data and review data of users; The evaluating means evaluates whether the new product concept has an advantage over the competing products. The system of claim 1 .

3. means for collecting emotion data using an emotion engine that recognizes an emotion of a user; the providing means provides the prompt sentence to the generative AI model based on the emotion data. The system of claim 1 .

Images