System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting consumer data comprising purchase history, comparison and review history, and reviews; means for pre-processing the collected data; means for analyzing the pre-processed data to identify consumer needs; means for generating a new product idea based on the analysis; means for designing and fabricating a prototype based on the generated product idea; means for testing the prototype and collecting feedback from the consumer; means for analyzing the feedback and improving the product; and means for manufacturing and providing the improved product to the market.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] Conventional online shopping platforms have a wealth of data, such as consumer purchase data and reviews, but no established method exists for effectively utilizing this data to quickly develop products that meet consumer needs. Because the manufacturing process takes a long time, it is difficult to respond to changing consumer needs, and because the platform operator itself lacks manufacturing know-how, highly efficient product planning and manufacturing are difficult. The present invention aims to solve these problems by providing a system that effectively utilizes consumer data to quickly and effectively develop products that meet consumer needs. [Means for solving the problem]

[0005] The present invention provides a system that includes: means for collecting consumer data consisting of purchase history, comparison history, and reviews; means for preprocessing the collected data; means for analyzing the preprocessed data and identifying consumer needs; means for generating new product ideas using a generative AI based on the analysis results; means for designing and manufacturing prototypes based on the generated product ideas; means for testing the prototypes and collecting feedback from consumers; means for analyzing the feedback and improving the product; and means for manufacturing and offering the improved products to the market. Furthermore, by automatically collecting, preprocessing, and analyzing data, and generating product ideas using a generative AI, the system can improve process efficiency and respond quickly to consumer needs. Furthermore, the system includes means for anonymizing consumer data and ensuring privacy protection, allowing for more secure data utilization.

[0006] "Consumer Data" is data collected from a consumer's online activities, such as purchase history, shopping history, and reviews.

[0007] "Collection instruments" are mechanisms or software used to automatically collect consumer data from online shopping platforms.

[0008] "Preprocessing means" are procedures and software for organizing collected consumer data into a form suitable for analysis.

[0009] "Analytical tools" are algorithms and AI models that use pre-processed data to identify consumer needs and trends.

[0010] "Generative AI" refers to artificial intelligence techniques and algorithms that automatically generate new product ideas based on consumer data.

[0011] "Prototype design means" refers to design tools and software for creating actual product designs based on the product ideas generated by the generative AI.

[0012] "Prototype production means" refers to machines and procedures for producing physical prototypes based on the design drawings created by the design means.

[0013] A "testing tool" is a method or system for providing a manufactured prototype to consumers and collecting their usage and evaluation.

[0014] A "feedback collection tool" is software or a platform for collecting consumer feedback and opinions on prototypes.

[0015] "Improvement tools" are procedures and tools for improving prototypes and products based on collected feedback.

[0016] "Manufacturing means" refers to the machines and lines used to mass-produce products based on the final product specifications.

[0017] "Marketing means" refers to the mechanisms and procedures for selling manufactured goods on online shopping platforms.

[0018] "Anonymization methods" are methods or technologies used to remove personally identifiable information from collected consumer data and protect the privacy of that data. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The present invention is a system for quickly developing products that capture market needs by utilizing consumer data, and specific implementation details thereof will be described below.

[0041] System Embodiments

[0042] Consumer Data Collection

[0043] The server automatically collects consumer data (purchase history, comparison history, reviews) from online shopping platforms. It periodically pulls the data using APIs and stores it in a database. The data is anonymized to protect privacy.

[0044] Specific examples

[0045] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[0046] Data Preprocessing

[0047] The server preprocesses the collected data, specifically cleaning text data (such as reviews), deleting unnecessary data, and eliminating duplicates in purchase history data.

[0048] Specific examples

[0049] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[0050] Analyzing the data

[0051] The server inputs the preprocessed data into the AI ​​generator, which analyzes consumer needs and market trends. The AI ​​uses natural language processing technology to analyze the sentiment of reviews and identify popular products and their features based on purchase history.

[0052] Specific examples

[0053] The server performs a sentiment analysis of the reviews and discovers that many consumers highly praise the camera features of a particular smartphone.

[0054] Product idea generation

[0055] The server uses the generative AI to generate new product ideas based on the analysis results. The AI ​​considers specific parameters (price range, functionality, design, etc.) and provides product ideas that are desired by many consumers.

[0056] Specific examples

[0057] The generative AI will suggest "mid-priced smartphones equipped with high-performance cameras."

[0058] Prototype design and construction

[0059] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[0060] Specific examples

[0061] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[0062] Testing prototypes and gathering feedback

[0063] The server provides the prototype to the monitor consumers and collects their feedback, which includes opinions and evaluations of the consumers regarding the prototype.

[0064] Specific examples

[0065] The prototype will be distributed to 20 testers to collect feedback such as "The camera image quality is good, but the battery life is poor."

[0066] Analyzing feedback and improving products

[0067] The server analyzes the collected feedback and identifies necessary improvements, which the design team then uses to refine the prototype.

[0068] Specific examples

[0069] The design team designs an improved smartphone with increased battery capacity and improved power efficiency.

[0070] Manufacturing and bringing products to market

[0071] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[0072] Specific examples

[0073] The improved smartphone is mass-produced and begins selling on online platforms, where it is purchased by many consumers and receives positive reviews.

[0074] summary

[0075] By repeating these steps, the present invention is a system that maximizes the use of consumer data and enables the rapid planning and manufacturing of products that meet market needs, significantly shortening the lengthy conventional product development process and enabling rapid response to changing consumer needs.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] The server periodically collects consumers' purchase history, comparison shopping history, and reviews using the online shopping platform API. The collected data is stored in a database. When collecting the data, it is anonymized to prevent personal identification.

[0079] Step 2:

[0080] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters, as well as removing unnecessary columns in purchase history data and deleting duplicate data.

[0081] Step 3:

[0082] The server inputs the preprocessed data into the generation AI, which uses natural language processing (NLP) technology to analyze the sentiment of the reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history.

[0083] Step 4:

[0084] The server generates new product ideas based on the results of the analysis by the generative AI, which automatically creates multiple ideas by taking into account specific parameters (e.g., price range, functionality, design, etc.).

[0085] Step 5:

[0086] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[0087] Step 6:

[0088] A prototype device is produced based on the design drawings. The prototype is then assembled in the factory using the specified materials and parts. Once the prototype is complete, a quality check is carried out.

[0089] Step 7:

[0090] The server provides the prototype to selected test consumers and tests its usage. The test consumers use the prototype and send their impressions and evaluations to the server as feedback.

[0091] Step 8:

[0092] The server analyzes the collected feedback, identifies areas that need improvement based on consumer opinions and ratings, and generates improvement proposals based on those. These improvement proposals are provided as feedback to the design team.

[0093] Step 9:

[0094] The prototype device is redesigned based on the proposed improvements, new blueprints are created that reflect the improvements, and the device is sent back to the factory to produce an improved prototype.

[0095] Step 10:

[0096] The server then finalizes the improved final product specifications and sends manufacturing instructions to the factory, which then goes into mass production and mass-produces the product based on the finalized specifications.

[0097] Step 11:

[0098] The server lists the manufactured products on an online shopping platform and starts selling them, monitors sales, and optimizes marketing strategies as needed.

[0099] Conclusion

[0100] These are the specific processing steps of this system, which makes it possible to make maximum use of consumer data and quickly and efficiently develop and provide products that meet market needs.

[0101] Example 1

[0102] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0103] In the conventional product development process, it was difficult to quickly grasp consumer needs and then plan and manufacture new products based on those needs. Furthermore, data collection and analysis, product idea generation, and product improvement were all done manually, which was time-consuming and costly. This resulted in an inability to respond quickly to changing consumer needs, and a decline in market competitiveness.

[0104] 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.

[0105] In this invention, the server includes means for collecting consumer data from an online shopping platform, means for periodically obtaining the collected data using an API and storing it in a database, means for preprocessing the collected data and deleting unnecessary and duplicate data, means for analyzing the preprocessed data and identifying consumer needs and market trends, means for using a generative AI to generate new product ideas based on the analysis results, means for creating detailed blueprints based on the generated product ideas and designing and manufacturing prototypes, means for providing the prototypes to monitor consumers and collecting feedback, means for analyzing the collected feedback and improving the product, and means for determining final product specifications, manufacturing the improved product, and providing it to the market. This makes it possible to make maximum use of consumer data and efficiently plan, manufacture, and launch products that meet market needs quickly.

[0106] "Consumer data" refers to information, including consumer purchase history, comparison history, and reviews, that reflects consumer behavior and opinions.

[0107] An "online shopping platform" is a web-based service for selling and purchasing goods over the Internet.

[0108] An "API" is an interface that allows different software applications to communicate and a protocol for using specific services or functions.

[0109] "Data preprocessing" is the process of preparing collected raw data in an analyzable form, and includes tasks such as removing unnecessary and duplicate data and cleaning text data.

[0110] "Generative AI" refers to artificial intelligence that generates new content and ideas based on human instructions, particularly using natural language processing and machine learning techniques.

[0111] A "prototype" is a test product created to verify the design and performance of a final product, and is used to demonstrate and evaluate product designs.

[0112] "Feedback" refers to the evaluations and opinions collected from consumers who have used prototypes, and is information that is used to improve the product and determine its final specifications.

[0113] "Privacy protection" refers to measures to anonymize personal information from collected data so that individuals cannot be identified.

[0114] MODE FOR CARRYING OUT THE INVENTION

[0115] This invention is a system that uses consumer data to rapidly develop products that meet market needs. This system uses consumer data collected from online shopping platforms, generates new product ideas using generative AI, and designs, manufactures, and sells products based on those ideas.

[0116] Consumer Data Collection

[0117] The server periodically collects consumer data (purchase history, comparison shopping history, reviews) from the online shopping platform using APIs. The collected data is stored in a database and anonymized to protect privacy. Consumer data collection is performed using a scheduler that automates database updates and an anonymization tool.

[0118] As a specific example, consider a situation where a user purchases a home appliance from an online shopping platform, and the history and reviews of the purchase are collected by a server.

[0119] Data Preprocessing

[0120] The server pre-processes the collected data. Text data is cleaned by removing unnecessary symbols and tags, and duplicate purchase history data is deduplicated. This pre-processing uses text analysis tools and deduplication algorithms to convert the data into a format suitable for analysis.

[0121] For example, the server removes unnecessary symbols and duplicate data from the reviews and converts them into a format suitable for analysis.

[0122] Analyzing the data

[0123] The server inputs the preprocessed data into a generative AI model to analyze consumer needs and market trends. The generative AI model uses natural language processing technology to analyze the sentiment of reviews and extract popular products and their features from purchase history.

[0124] A specific example might be a situation where a server performs sentiment analysis of reviews and discovers that many consumers highly praise the camera features of a particular smartphone.

[0125] Product idea generation

[0126] The server generates new product ideas based on the analysis results provided by the generative AI, which considers parameters such as price range, functionality, and design to propose product ideas that will appeal to many consumers.

[0127] For example, the generative AI suggests a "mid-priced smartphone with a high-performance camera."

[0128] Prototype design and construction

[0129] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. It then uses the drawing to create a prototype and sends production instructions to the factory, where the prototype is actually produced.

[0130] For example, a design team might create a prototype smartphone that is lightweight and equipped with a high-performance camera.

[0131] Testing prototypes and gathering feedback

[0132] The server provides the prototype to the monitor consumers and collects feedback from the consumers, including their evaluation of the prototype and suggestions for improvement.

[0133] For example, you could distribute a prototype to 20 testers and collect feedback such as, "The camera image quality is good, but the battery life is poor."

[0134] Analyzing feedback and improving products

[0135] The server analyzes the collected feedback and identifies product improvements, which the design team uses to improve the prototype and send the improvements back to the factory.

[0136] As a concrete example, a design team designs an improved version of a smartphone with increased battery capacity and improved power efficiency.

[0137] Manufacturing and bringing products to market

[0138] The server finalizes the product specifications and sends manufacturing instructions to the factory, where the product is mass-produced and then made available for sale on the online shopping platform.

[0139] For example, an improved smartphone is mass-produced and launched for sale on an online platform, where it is purchased by many consumers and receives positive reviews.

[0140] Specific prompt examples

[0141] "Analyze the purchase history and reviews of home appliances on online platforms to generate ideas for the next product we should develop."

[0142] By repeating these steps, the present invention is a system that maximizes the use of consumer data and enables the rapid planning and manufacturing of products that meet market needs. This system significantly shortens the conventional product development process and makes it possible to respond quickly to changing consumer needs.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] Step 1: Collect consumer data

[0145] The server collects consumer data from online shopping platforms using APIs. Specifically, the server sends requests to API endpoints to obtain data such as purchase history, comparison history, and reviews.

[0146] Input: Consumer data retrieved from API endpoints

[0147] Output: Consumer data stored in a database

[0148] Specific behavior:

[0149] The server periodically runs scheduled tasks and sends API requests.

[0150] Receive the acquired data and process it using anonymization tools to protect privacy.

[0151] The anonymized data is stored in a database.

[0152] Step 2: Preprocessing the data

[0153] The server preprocesses the collected data: text data (such as reviews) is cleaned and unnecessary symbols and tags are removed, and purchase history data is deduplicated and converted into a format suitable for analysis.

[0154] Input: Raw data stored in a database

[0155] Output: Preprocessed data

[0156] Specific behavior:

[0157] The server uses text analysis tools to remove unnecessary symbols and tags from the reviews.

[0158] Use a duplicate data detection algorithm to remove duplicate purchase history.

[0159] Save the preprocessed data to a new database table.

[0160] Step 3: Analyze the data

[0161] The server inputs the preprocessed data into a generative AI model to analyze consumer needs and market trends. The generative AI model uses natural language processing technology to analyze the sentiment of reviews and extract popular products and their features from purchase history.

[0162] Input: Preprocessed data

[0163] Output: Analysis results

[0164] Specific behavior:

[0165] The server converts the preprocessed data into an input format for the generative AI model.

[0166] Input data into the generative AI model and wait for analysis to complete.

[0167] The analysis results are obtained and stored in a database.

[0168] Step 4: Generate product ideas

[0169] The server generates new product ideas based on the analysis results provided by the generative AI, which considers parameters such as price range, functionality, and design to propose product ideas that consumers desire.

[0170] Input: Analysis results

[0171] Output: Product idea

[0172] Specific behavior:

[0173] The server inputs prompts into the generative AI model based on the analysis results.

[0174] Evaluate the generated product ideas and extract feasible ideas.

[0175] The extracted ideas are stored in a database and notified to the design team.

[0176] Step 5: Design and build a prototype

[0177] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server, creates prototypes based on the drawings, and sends production instructions to the factory.

[0178] Input: Product idea

[0179] Output: Prototype blueprints and prototypes

[0180] Specific behavior:

[0181] The design team uses design software to create detailed blueprints.

[0182] Send the blueprint to the factory manufacturing system.

[0183] The factory produces prototypes based on the design drawings.

[0184] Step 6: Test the prototype and gather feedback

[0185] The server provides the prototype to the test consumers and collects their feedback, including their evaluation of the prototype and specific suggestions for improvement.

[0186] Input: Monitor consumer ratings and opinions

[0187] Output: Feedback data

[0188] Specific behavior:

[0189] The server provides the prototype to consumers who participate in the evaluation test.

[0190] The server collects feedback through online surveys and interviews.

[0191] Store the collected feedback in a database.

[0192] Step 7: Analyze feedback and improve the product

[0193] The server analyzes the collected feedback and identifies necessary improvements, which the design team then uses to refine the prototype.

[0194] Input: Feedback data

[0195] Output: Improvements and tweaks

[0196] Specific behavior:

[0197] The server analyzes the feedback data and identifies areas for improvement.

[0198] The server notifies the design team of improvements.

[0199] The design team modifies the design drawings based on the improvements and sends them back to the factory.

[0200] Step 8: Manufacture and market your product

[0201] The server finalizes the product specifications and sends manufacturing instructions to the factory, which then mass-produces the product and starts selling it on the online shopping platform.

[0202] Input: Final product specifications

[0203] Output: Commercially available product

[0204] Specific behavior:

[0205] The server sends the final product specifications to the factory.

[0206] The factory begins mass production and delivers the finished products to the warehouse.

[0207] The server uploads the product data to the online shopping platform and starts selling.

[0208] (Application example 1)

[0209] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0210] In the traditional product development process, it takes a long time and costs a lot of money to properly understand consumer needs and generate new product ideas based on them. Furthermore, even product recommendation systems that utilize consumer data often do not provide personalized recommendations, making it difficult to meet consumer expectations. Furthermore, protecting the privacy of collected consumer data is also a major issue. Therefore, an efficient system that solves these problems is needed.

[0211] 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.

[0212] In this invention, the server includes means for collecting consumer data consisting of purchase history, comparison history, and reviews, means for preprocessing the collected data, means for analyzing the preprocessed data and identifying consumer needs, means for a generative AI to generate new product ideas based on the analysis results, means for designing and manufacturing prototypes based on the generated product ideas, means for testing the prototypes and collecting feedback from consumers, means for analyzing the feedback and improving the products, means for manufacturing the improved products and providing them to the market, and means for personalizing product recommendations based on the collected data. This makes it possible to plan and manufacture products that meet market needs effectively in a short period of time, and to provide more personalized product recommendations.

[0213] "Consumer Data" refers to data consisting of purchase history, comparison history, and reviews.

[0214] "Means of collection" refers to mechanisms for automatically obtaining consumer data from online shopping platforms and other data sources.

[0215] "Preprocessing means" refers to a mechanism for cleaning collected data, removing unnecessary information, and converting it into a format suitable for analysis.

[0216] "Means of analysis" refers to the data analysis process to identify consumer needs based on collected and pre-processed data.

[0217] "Generative AI" refers to artificial intelligence technology that automatically generates new product ideas based on analysis results.

[0218] "Means of designing and producing prototypes" refers to the process of creating detailed design drawings based on the generated product ideas and producing prototypes.

[0219] "Means of testing prototypes and gathering feedback" refers to the process of providing prototypes to consumers and gathering their impressions and opinions.

[0220] "Means for analyzing feedback and improving the product" refers to the process of identifying improvements to the prototype based on the collected feedback and improving the design and functionality.

[0221] "Means of manufacturing and marketing" refers to the process of mass-producing an improved product and selling it to consumers.

[0222] "Means for personalizing product recommendations" refers to a system that recommends the most suitable products to each user based on collected consumer data.

[0223] The system for implementing this invention automates the process of collecting consumer data and quickly developing products that meet market needs. This system is primarily composed of a server, terminals, and users.

[0224] Server Functions and Processing

[0225] 1. Data Collection:

[0226] The server automatically collects consumer data, consisting of purchase history, comparison history, and reviews, from online shopping platforms and other data sources using APIs. The data is periodically pulled, anonymized to protect privacy, and stored in a database.

[0227] 2. Data Preprocessing:

[0228] The server preprocesses the collected data. Specifically, it cleans text data (such as reviews) and deletes unnecessary data. It also deduplicates purchase history data. This converts the data into a format suitable for analysis.

[0229] 3. Data Analysis:

[0230] The pre-processed data is then input into the generative AI, which uses natural language processing technology to analyze the sentiment of the reviews and identify popular products and their features based on purchase history. Based on the results of this analysis, consumer needs and market trends are identified.

[0231] 4. Product idea generation:

[0232] The server uses generative AI to generate new product ideas based on the analysis results. The AI ​​considers specific parameters (price range, functionality, design, etc.) and provides product ideas that are desired by many consumers.

[0233] Terminal functions and processing

[0234] 1. Prototype design and construction:

[0235] The terminal (such as the design team's computer) creates detailed design drawings based on the product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[0236] 2. Test the prototype and gather feedback:

[0237] The prototype is provided to test consumers, and the server collects their feedback, including their opinions and evaluations of the prototype.

[0238] Server feedback processing

[0239] 1. Feedback Analysis and Product Improvement:

[0240] The server analyzes the collected feedback and identifies necessary improvements. The design team then improves the prototype based on the feedback. For example, if the feedback is that the camera image quality is good but the battery life is poor, the team will increase the battery capacity and improve power efficiency.

[0241] 2. Manufacture and market the product:

[0242] The final product specifications are finalized and manufacturing instructions are sent to the factory, where mass production begins. The product is then sold on an online shopping platform, where it is purchased by many consumers and receives positive reviews.

[0243] Personalized product recommendations

[0244] The server personalizes product recommendations based on the collected data. It analyzes each user's purchase and browsing history to provide the functionality to recommend the most suitable products, improving the user experience and increasing sales.

[0245] Prompt Sentence Examples

[0246] For example, suppose you want to collect and analyze data about "smartwatches." Here are some example prompts to input to the generative AI:

[0247] Generate new product ideas based on the following popular items and sentiments: {'Smartwatch Model A': 123, 'Smartwatch Model B' : 95, 'Smartwatch Model C': 80} and [0.75, 0.6, -0.3, 0.9, 0.8]

[0248] Based on these prompts, the generative AI will provide new product ideas such as "a mid-priced smartwatch with advanced health management features."

[0249] As described above, the system of the present invention makes it possible to make maximum use of consumer data and quickly plan and manufacture products that meet market needs.

[0250] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0251] Step 1: Data collection

[0252] The server automatically collects consumer data, including purchase history, comparison history, and reviews, from online shopping platforms and other data sources using APIs, periodically sending API requests and storing the retrieved data in a database in JSON format.

[0253] Input: Raw data obtained via API

[0254] Output: Consumer data in JSON format

[0255] Step 2: Data Preprocessing

[0256] The server preprocesses the collected data. Specifically, it cleans the text data (reviews) and deletes unnecessary data. It also eliminates duplicates in the purchase history data and converts it into a format suitable for analysis.

[0257] Input: Consumer data in JSON format

[0258] Output: Cleaned dataset

[0259] Step 3: Data analysis

[0260] The server inputs the preprocessed data into the generative AI to analyze consumer needs and market trends. Specifically, it uses natural language processing technology to analyze the sentiment of reviews and identify popular products and their features based on purchase history.

[0261] Input: Cleaned dataset

[0262] Output: Analysis of consumer needs and market trends

[0263] Step 4: Product idea generation

[0264] The server uses a generative AI to generate new product ideas based on the analysis results. The AI ​​receives a prompt and generates new product ideas taking into account specific parameters (price range, functionality, design, etc.).

[0265] Input: Consumer needs and market trend analysis results, prompt text

[0266] Output: New product ideas

[0267] Step 5: Design and build a prototype

[0268] The terminal (such as the design team's computer) creates detailed design drawings based on the new product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[0269] Input: New product idea

[0270] Output: Prototype

[0271] Step 6: Test the prototype and gather feedback

[0272] The prototypes are provided to test consumers, and their feedback is collected by the server. Specifically, their impressions and evaluations of the product are collected in the form of questionnaires and reviews.

[0273] Input: Prototype

[0274] Output: Feedback data

[0275] Step 7: Analyze feedback and improve the product

[0276] The server analyzes the collected feedback data and identifies necessary improvements, which the design team then uses to refine the prototype, implementing specific improvements such as increasing battery capacity.

[0277] Input: Feedback data

[0278] Output: Improvements and New Designs

[0279] Step 8: Manufacture and market your product

[0280] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[0281] Input: Improved product specifications

[0282] Output: Products delivered to the market

[0283] Step 9: Personalize product recommendations

[0284] The server personalizes product recommendations based on the collected data, analyzing each user's purchase and browsing history to recommend the most suitable products, improving the user experience and increasing sales.

[0285] Input: User purchase history and browsing history

[0286] Output: Personalized product recommendations

[0287] 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.

[0288] The present invention combines a system that uses consumer data to rapidly develop products that capture market needs with an emotion engine that recognizes user emotions. Specific implementation details are described below.

[0289] System Embodiments

[0290] Consumer Data Collection

[0291] The server automatically collects consumer data (purchase history, comparison history, and reviews) from online shopping platforms. The collected data is stored in a database. When collecting the data, it is anonymized so that individuals cannot be identified.

[0292] Specific examples

[0293] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[0294] Data Preprocessing

[0295] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters. It also removes unnecessary columns from purchase history data and deletes duplicate data.

[0296] Specific examples

[0297] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[0298] Analyzing the data

[0299] The server inputs the preprocessed data into the generation AI and emotion engine. The generation AI uses natural language processing (NLP) technology to analyze the sentiment of reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history. The emotion engine identifies consumer sentiment from reviews.

[0300] Specific examples

[0301] The server performs sentiment analysis on the reviews and discovers that many consumers express positive sentiment, such as being "very satisfied," with the camera features of a particular smartphone.

[0302] Product idea generation

[0303] The server generates new product ideas based on the results of the generative AI and emotion engine analysis. The generative AI automatically creates multiple ideas, taking into account specific parameters (price range, functionality, design, etc.).

[0304] Specific examples

[0305] As a result of sentiment analysis, the generative AI proposes a product idea: a mid-priced smartphone equipped with a high-performance camera.

[0306] Prototype design and construction

[0307] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[0308] Specific examples

[0309] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[0310] Testing prototypes and gathering feedback

[0311] The server provides the prototype to the monitor consumers and collects their feedback. The feedback includes the consumers' opinions and evaluations of the prototype. The emotion engine also analyzes the feedback to identify the consumers' emotions.

[0312] Specific examples

[0313] The prototype is distributed to 20 testers and feedback is collected, such as "The camera image quality is good, but the battery life is poor." The emotion engine identifies positive and negative emotions from the testers' feedback.

[0314] Analyzing feedback and improving products

[0315] The server identifies necessary improvements based on the collected feedback and the emotion engine analysis, and the design team refines the prototype based on the feedback and emotion analysis.

[0316] Specific examples

[0317] The design team designs an improved smartphone with increased battery capacity and improved power efficiency.

[0318] Manufacturing and bringing products to market

[0319] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[0320] Specific examples

[0321] The improved smartphone is mass-produced and begins selling on online platforms, where it is purchased by many consumers and receives positive reviews.

[0322] summary

[0323] This invention is a system that combines consumer data with an emotion engine to enable product planning and manufacturing that more accurately reflects consumer emotions. By repeating these steps, it becomes possible to make the most of consumer data and quickly and efficiently develop and provide products that meet market needs.

[0324] The processing flow will be explained below.

[0325] Step 1:

[0326] The server periodically collects consumers' purchase history, comparison shopping history, and reviews using the online shopping platform API. The collected data is stored in a database. When collecting the data, it is anonymized to prevent personal identification.

[0327] Specific examples

[0328] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[0329] Step 2:

[0330] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters. It also removes unnecessary columns from purchase history data and deletes duplicate data.

[0331] Specific examples

[0332] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[0333] Step 3:

[0334] The server inputs the preprocessed data into the generation AI and emotion engine. The generation AI uses natural language processing (NLP) technology to analyze the sentiment of reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history. The emotion engine identifies consumer sentiment from reviews.

[0335] Specific examples

[0336] The server performs sentiment analysis on the reviews and discovers that many consumers express positive sentiment, such as being "very satisfied," with the camera features of a particular smartphone.

[0337] Step 4:

[0338] The server generates new product ideas based on the results of the generative AI and emotion engine analysis. The generative AI automatically creates multiple ideas, taking into account specific parameters (price range, functionality, design, etc.).

[0339] Specific examples

[0340] As a result of sentiment analysis, the generative AI proposes a product idea: a mid-priced smartphone equipped with a high-performance camera.

[0341] Step 5:

[0342] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[0343] Specific examples

[0344] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[0345] Step 6:

[0346] The server issues instructions to the factory to manufacture a prototype based on the design drawings. The factory assembles the prototype using the specified materials and parts. Once the prototype is completed, a quality check is performed.

[0347] Specific examples

[0348] At the factory, prototype smartphones pass quality checks and are ready for testing.

[0349] Step 7:

[0350] The server provides the prototype to selected monitor consumers and tests its usage. The users (monitor consumers) use the prototype and send their impressions and evaluations as feedback to the server. The emotion engine also analyzes the feedback and identifies the consumer's emotions.

[0351] Specific examples

[0352] The prototype is distributed to 20 testers and feedback is collected, such as "The camera image quality is good, but the battery life is poor." The emotion engine identifies positive and negative emotions from the testers' feedback.

[0353] Step 8:

[0354] The server identifies necessary improvements based on the collected feedback and the analysis results of the emotion engine. The design team improves the prototype based on the feedback and emotion analysis. A new improved design is created and another prototype is produced.

[0355] Specific examples

[0356] The design team designs an improved smartphone with increased battery capacity and improved power efficiency, and the factory builds prototypes of the improved version.

[0357] Step 9:

[0358] The server then finalizes the improved final product specifications and sends manufacturing instructions to the factory, which then goes into mass production and mass-produces the product based on the finalized specifications.

[0359] Specific examples

[0360] The improved smartphone will be mass-produced and made available for sale on online platforms.

[0361] Step 10:

[0362] The server lists the manufactured products on an online shopping platform and starts selling them, monitors sales, and optimizes marketing strategies as needed.

[0363] Specific examples

[0364] The product goes on sale on an online shopping platform, is purchased by many consumers, and receives positive reviews.

[0365] Example 2

[0366] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0367] In today's market, it is difficult to quickly and accurately grasp consumer needs and develop products that meet those needs. Furthermore, because product development is carried out without a detailed understanding of consumer sentiment, it is difficult to improve consumer satisfaction. Furthermore, there is a need for an efficient system that can properly collect and analyze consumer data and reflect it in product development.

[0368] 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.

[0369] In this invention, the server includes: means for collecting consumer data consisting of purchase history, comparison history, and reviews; means for preprocessing the collected data; means for analyzing the preprocessed data and identifying consumer needs; means for a generative AI to generate new product ideas based on the analysis results; means for designing and manufacturing prototypes based on the generated product ideas; means for testing the prototypes and collecting feedback from consumers; means for analyzing the feedback and improving the product; means for recognizing emotions from consumer reviews using an emotion engine and reflecting the results in improving product characteristics; and means for manufacturing the improved products and offering them to the market. This enables product development that reflects consumer data and emotion analysis in detail.

[0370] "Purchase history" is a record of data about products a consumer has purchased in the past.

[0371] A "comparison and consideration history" is a record of data showing the comparison and consideration process that a consumer undertakes before purchasing a product.

[0372] A "review" is a written evaluation or impression left by a consumer about a product they have purchased.

[0373] "Consumer Data" is information consisting of purchase history, comparison history, and reviews.

[0374] "Preprocessing" is the process of removing unnecessary information from collected data and converting it into a form suitable for analysis.

[0375] "Analysis" is the process of analyzing data in detail to extract patterns and useful information.

[0376] "Generative AI" is a system that uses artificial intelligence technology to automatically generate new product ideas.

[0377] A "product idea" is a proposal that summarizes the concept and features of a new product.

[0378] A "prototype" is a model that is actually designed and manufactured based on a generated product idea.

[0379] "Feedback" refers to opinions and evaluations collected from consumers regarding prototypes.

[0380] The "sentiment engine" is a system that analyzes the sentiment of consumer reviews and identifies positive or negative sentiment.

[0381] "Data anonymization" is the process of removing personally identifiable information from data to protect privacy.

[0382] MODE FOR CARRYING OUT THE INVENTION

[0383] The present invention combines a system that uses consumer data, including purchase history, comparison history, and reviews, to rapidly develop products that meet market needs with an emotion engine that recognizes consumer emotions. Specific implementation methods are described below.

[0384] 1. Consumer Data Collection

[0385] The server automatically collects consumer data such as purchase history, comparison history, and reviews from online shopping platforms through APIs, such as Amazon Web Services (AWS) or Google Cloud Platform (GCP), and retrieves the data using the Python requests library.

[0386] 2. Data Preprocessing

[0387] The server preprocesses the collected data by converting it into a data frame using Pandas (a Python library), removing punctuation and special characters from text data, deleting unnecessary columns, and removing duplicate data, converting the data into a format suitable for analysis.

[0388] 3. Data Analysis

[0389] The server inputs the preprocessed data into the generative AI and sentiment engine. It uses natural language processing (NLP) technologies such as BERT and GPT-3 to analyze the sentiment of reviews and analyze market trends from purchase history and comparison history data. The sentiment engine also uses tools such as Amazon Comprehend to identify consumer sentiment.

[0390] 4. Product idea generation

[0391] The server uses the generative AI to generate new product ideas based on the analysis results. It uses OpenAI's API and Hugging Face's Transformers to automatically create multiple product ideas based on specified parameters. For example, enter "Generate a new smartphone idea based on the following specifications: ..." as the prompt.

[0392] 5. Prototype design and construction

[0393] The terminal (such as the design team's PC) uses AutoCAD or SolidWorks to create detailed design drawings based on the product ideas received from the server. The design drawings include the specific specifications proposed by the generative AI, and a prototype is then produced based on these.

[0394] 6. Test the prototype and gather feedback

[0395] The server provides the prototype to the test consumers and collects their feedback using Google Forms or SurveyMonkey. The feedback form contains the consumers' opinions and impressions about the prototype, which are analyzed by an emotion engine to identify the consumers' emotions.

[0396] 7. Analyzing Feedback and Improving Products

[0397] The server analyzes the collected feedback and identifies areas for improvement in the product. Using Pandas and SciPy, it performs detailed analysis of the feedback data and identifies areas for improvement. It notifies the design team of the results and creates an improved version.

[0398] 8. Manufacturing and bringing products to market

[0399] The server finalizes the product specifications and sends manufacturing instructions to the factory using the ERP system, after which the products are mass-produced and made available for sale on online shopping platforms such as Shopify, bringing the products to market.

[0400] In this way, the present invention is a system that covers a whole series of processes from data collection to product development, feedback collection, product improvement, and final market release, and by introducing an emotion engine, it is possible to analyze consumer emotions in detail and improve product characteristics to reflect those emotions. This allows products that provide high consumer satisfaction to be released to the market quickly.

[0401] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0402] Program processing flow

[0403] Step 1: Collect consumer data

[0404] The server collects consumer data (purchase history, comparison history, and reviews) from the online shopping platform.

[0405] Input: API endpoint of online shopping platform

[0406] Data processing: Purchase history, comparison history, and reviews are obtained in JSON format and saved in a database

[0407] Output: Raw data stored in a database

[0408] Specific operation: Makes an API call using Python's requests library and saves the retrieved data to a database.

[0409] Step 2: Preprocessing the data

[0410] The server performs pre-processing on the collected data.

[0411] Input: Raw data in the database

[0412] Data processing: removing punctuation and special characters, deleting unnecessary columns, removing duplicate data

[0413] Output: Cleaned data

[0414] Specific behavior: Convert to a data frame using Pandas and perform data cleaning operations.

[0415] Step 3: Analyze the data

[0416] The server feeds the pre-processed data into the generative AI and emotion engine.

[0417] Input: Preprocessed data

[0418] Data processing: Using natural language processing technology to analyze the sentiment of reviews and understand market trends

[0419] Output: Sentiment analysis results and market trend data

[0420] What it does: Perform sentiment analysis and market trend analysis using BERT, GPT-3, and Amazon Comprehend.

[0421] Step 4: Generate product ideas

[0422] The server uses a generative AI to generate new product ideas based on the analysis results.

[0423] Input: Sentiment analysis results and market trend data

[0424] Data processing: Providing product recommendations based on specified parameters

[0425] Output: New product ideas

[0426] What it does: Uses OpenAI APIs and Hugging Face Transformers to generate product ideas based on a given prompt.

[0427] Step 5: Design and build a prototype

[0428] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server.

[0429] Input: New product idea

[0430] Data processing: Creating detailed blueprints using CAD software

[0431] Output: Prototype blueprints

[0432] Specific Tasks: Using AutoCAD and SolidWorks, you will create blueprints for the design team to bring product ideas to life.

[0433] Step 6: Test the prototype and gather feedback

[0434] The server provides the prototype to monitor consumers and collects their feedback.

[0435] Input: Prototype, Feedback Form

[0436] Data processing: Collecting consumer ratings and comments and analyzing their sentiment

[0437] Output: Aggregated feedback and sentiment analysis results

[0438] What it does: Collect feedback using Google Forms and SurveyMonkey, and perform sentiment analysis using Amazon Comprehend.

[0439] Step 7: Analyze feedback and improve the product

[0440] The server analyzes the collected feedback and identifies product improvements.

[0441] Input: Aggregated feedback and sentiment analysis results

[0442] Data processing: Analyzing feedback data and extracting areas for improvement

[0443] Output: List of improvements

[0444] What it does: Uses Pandas and SciPy to perform detailed analysis of feedback and inform the design team of improvements.

[0445] Step 8: Manufacture and market your product

[0446] The server determines the final product specifications and sends manufacturing instructions to the factory.

[0447] Input: List of improvements, final specifications

[0448] Data processing: Finalizing manufacturing instructions and preparing for market launch

[0449] Output: Produced products, on sale

[0450] What it does: Uses an ERP system to send production instructions to factories and starts selling on e-commerce platforms like Shopify.

[0451] The above specific steps will realize a series of processes from product development to market launch using consumer data.

[0452] (Application example 2)

[0453] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0454] In the past, it was difficult to utilize consumer data to quickly develop products that met market needs in the product development process. Furthermore, there was a lack of technology to understand the emotions of drivers and passengers in real time and adjust in-car navigation and entertainment accordingly. Under these circumstances, it was difficult to develop products that maximize consumer satisfaction and provide a safe and comfortable driving environment for drivers and passengers.

[0455] 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.

[0456] In this invention, the server includes means for collecting consumer data including purchase history, comparison history, and reviews, means for preprocessing the collected data, means for analyzing the preprocessed data and identifying consumer needs, means for a generative AI to generate new product ideas based on the analysis results, means for designing and manufacturing prototypes based on the generated product ideas, means for testing the prototypes and collecting feedback from consumers, means for analyzing the feedback and improving the product, means for manufacturing the improved product and providing it to the market, means for collecting emotional data of drivers and passengers, means for anonymizing the collected emotional data, and means for providing driving routes and entertainment based on the emotional data. This enables the development and provision of products that accurately reflect consumer emotions and needs, and a safe and comfortable driving experience that takes into account the emotions of drivers and passengers.

[0457] "Consumer Data" is information about consumer behavior and opinions, such as purchase history, comparison history, and reviews.

[0458] "Preprocessing" means removing unnecessary information from raw data and converting it into a form suitable for analysis.

[0459] "Analyzing" means using pre-processed data to extract information and patterns and make sense of them.

[0460] "Generative AI" is a technology that uses artificial intelligence algorithms to automatically generate new product ideas and proposals.

[0461] A "product idea" is a concept for a new product or service that is generated with consumer needs and emotions in mind.

[0462] A "prototype" is an early stage product that embodies a generated product idea.

[0463] "Feedback" refers to reaction information such as evaluations and opinions from consumers who have used the prototype.

[0464] "Improvement" means improving the product's specifications and features based on collected feedback.

[0465] "Emotion data" is information that indicates the emotional state of the driver or passengers, obtained from their faces, voices, etc.

[0466] "Navigation" refers to systems and functions that provide the optimal route to a destination.

[0467] "Entertainment" refers to content such as music and videos that provide enjoyment and satisfaction.

[0468] "Anonymization" is a method of removing or transforming personally identifiable information to protect privacy.

[0469] "Real-time" refers to the processing and provision of information immediately, without delay.

[0470] The present invention provides a system for more accurately grasping market needs and providing products by combining consumer data and emotion data. Specific embodiments of the system are described below.

[0471] Hardware and software used

[0472] The specific hardware and software used as servers and terminals include the following:

[0473] Hardware:

[0474] Camera: Used to recognize the faces of the driver and passengers.

[0475] Microphone: Used to collect audio data.

[0476] Computer: A server or PC for analyzing and storing data.

[0477] software:

[0478] OpenCV: A library for acquiring and processing camera images.

[0479] DeepFace: A library for facial expression analysis.

[0480] Librosa: A library for reading and parsing audio data.

[0481] NLP technologies: Libraries for natural language processing (e.g. spaCy).

[0482] AI generative model: An algorithm that uses generative AI to automatically generate new product ideas.

[0483] Data processing flow

[0484] 1. Data Collection:

[0485] The server collects consumer and emotional data from online shopping platforms and in-car sensors. Consumer data includes purchase history, comparison shopping history, and reviews, while emotional data includes facial expressions and voice recordings of drivers and passengers.

[0486] 2. Data preprocessing:

[0487] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters, deleting unnecessary parts from image data, and removing noise from audio data.

[0488] 3. Data Analysis:

[0489] The server analyzes the preprocessed data, using natural language processing (NLP) technology to analyze the sentiment of reviews, and analyzes market trends and the characteristics of popular products based on purchase history and comparison history. It also identifies the emotions of drivers and passengers through facial expression and voice analysis.

[0490] 4. Product idea generation and provision:

[0491] The server generates new product ideas using a generative AI model. Based on the analysis results, the generative AI automatically creates multiple ideas taking into account specific parameters (price range, functionality, design, etc.). It also provides driving directions and entertainment based on emotional data.

[0492] Specific examples

[0493] When a consumer purchases a home appliance on an online platform, the purchase history and reviews are collected on a server. Sentiment analysis of the reviews is performed and it is discovered that many consumers express positive emotions such as "very satisfied" with the features of a particular home appliance. Based on this result, the generative AI proposes a product idea for a "high-performance, cost-effective home appliance." At the same time, the system uses the in-car camera and microphone to collect the driver's facial expressions and voice. If it determines that the driver is nervous, it plays relaxing music and suggests a safe route.

[0494] Example prompt for a generative AI model:

[0495] "Suggest ideas for home appliances that consumers would be happy to purchase."

[0496] "If you sense a driver is nervous, suggest the most relaxing route."

[0497] "If passengers are bored, offer them music recommendations."

[0498] The above is a specific description of the "Mode for Carrying Out the Invention." The present invention enables highly accurate market response by combining consumer data and emotion data.

[0499] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0500] Step 1:

[0501] Collecting consumer and sentiment data

[0502] The server collects consumer and emotional data from online shopping platforms and in-car sensors. Input data includes purchase history, comparison shopping history, reviews, driver and passenger facial expressions, and voice. The output is the collected raw data. Specifically, the server uses an API to obtain purchase history and reviews from online shopping platforms, and uses the camera and microphone in the in-car sensors to capture driver and passenger emotional data.

[0503] Step 2:

[0504] Data Preprocessing

[0505] The server performs preprocessing on the collected data. The input is the raw data collected in step 1. Specific data processing includes removing punctuation and special characters from the text data and removing noise from the audio data. The output is cleaned data. Specifically, the text data is cleaned using regular expressions, and the audio data is denoised using Librosa.

[0506] Step 3:

[0507] Anonymizing Emotional Data

[0508] The server anonymizes the collected emotional data. The input is the emotional data preprocessed in step 2. Data calculation involves deleting or encrypting information that can identify a specific individual. The output is anonymized emotional data. Specific operations include removing features that can identify an individual from facial expression data and assigning an identification code to the analysis results of the voice data.

[0509] Step 4:

[0510] Data analysis

[0511] The server analyzes the preprocessed consumer data and sentiment data. The input is the cleaned and anonymized data obtained in steps 2 and 3. Specific data calculations include analyzing the sentiment of reviews using natural language processing techniques and analyzing market trends from purchase history and comparison history. The output is the analysis results. Operations include calculating sentiment scores based on specific keywords using an NLP library and extracting trend information from the database.

[0512] Step 5:

[0513] Product idea generation

[0514] The server uses the generative AI model to generate new product ideas based on the analysis results. The input is the analysis results from step 4. As a data calculation, the generative AI generates product ideas based on specific parameters (price, function, design, etc.). The output is the generated product idea. Specifically, the server inputs market trends and sentiment scores into the generative AI model, and generates product ideas based on the prompt text.

[0515] Step 6:

[0516] Prototype design and construction

[0517] The terminal (such as the design team's PC) creates detailed design drawings based on the product idea generated in step 5 and produces a prototype. The input is the generated product idea. As data calculation, a design drawing is created using CAD software and prototype production instructions are output. The output is production instructions and a prototype. As an operation, a detailed design is created using CAD software and prototype production instructions are sent to the factory.

[0518] Step 7:

[0519] Testing prototypes and gathering feedback

[0520] The server provides the prototype to test consumers and collects their feedback. The input is the test results of the test consumers. Specific data processing involves collecting evaluations and opinions from testers and analyzing them with an emotion engine. The output is feedback data. The system operates by collecting feedback through online forms and direct interviews, and analyzing the data with an emotion engine.

[0521] Step 8:

[0522] Feedback analysis and product improvement

[0523] The server analyzes the collected feedback and improves the product. The input is the feedback data from step 7. The data calculation analyzes the collected feedback and identifies necessary improvements. The output is improvement instructions. The operation analyzes the feedback data and integrates the sentiment score and user comments to derive improvement suggestions.

[0524] Step 9:

[0525] Manufacturing and bringing products to market

[0526] The server finalizes the product specifications and sends manufacturing instructions to the factory. The input is the improvement instructions from step 8. As a data calculation, it formulates a manufacturing plan and outputs manufacturing instructions. The output is a mass-produced product. As an operation, it instructs the manufacturing department on the production plan and starts selling the completed product on the online platform.

[0527] Step 10:

[0528] Providing driving directions and entertainment based on emotion data

[0529] The server provides optimal driving routes and entertainment based on the emotional data of the driver and passengers. The input is the emotional data collected in step 1. The data calculation involves analyzing the emotional data and selecting routes and content based on it. The output is the proposed route and entertainment. The operation involves selecting a route that will relax the driver based on the emotional data and selecting music and videos to provide.

[0530] The above is the flow of processing in the system that realizes the application example.

[0531] 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.

[0532] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0533] 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.

[0534] [Second embodiment]

[0535] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0536] 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.

[0537] 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).

[0538] 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.

[0539] 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.

[0540] 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).

[0541] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0542] 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.

[0543] 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.

[0544] 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.

[0545] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0546] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0547] The present invention is a system for quickly developing products that capture market needs by utilizing consumer data, and specific implementation details thereof will be described below.

[0548] System Embodiments

[0549] Consumer Data Collection

[0550] The server automatically collects consumer data (purchase history, comparison history, reviews) from online shopping platforms. It periodically pulls the data using APIs and stores it in a database. The data is anonymized to protect privacy.

[0551] Specific examples

[0552] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[0553] Data Preprocessing

[0554] The server preprocesses the collected data, specifically cleaning text data (such as reviews), deleting unnecessary data, and eliminating duplicates in purchase history data.

[0555] Specific examples

[0556] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[0557] Analyzing the data

[0558] The server inputs the preprocessed data into the AI ​​generator, which analyzes consumer needs and market trends. The AI ​​uses natural language processing technology to analyze the sentiment of reviews and identify popular products and their features based on purchase history.

[0559] Specific examples

[0560] The server performs a sentiment analysis of the reviews and discovers that many consumers highly praise the camera features of a particular smartphone.

[0561] Product idea generation

[0562] The server uses the generative AI to generate new product ideas based on the analysis results. The AI ​​considers specific parameters (price range, functionality, design, etc.) and provides product ideas that are desired by many consumers.

[0563] Specific examples

[0564] The generative AI will suggest "mid-priced smartphones equipped with high-performance cameras."

[0565] Prototype design and construction

[0566] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[0567] Specific examples

[0568] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[0569] Testing prototypes and gathering feedback

[0570] The server provides the prototype to the monitor consumers and collects their feedback, which includes opinions and evaluations of the consumers regarding the prototype.

[0571] Specific examples

[0572] The prototype will be distributed to 20 testers to collect feedback such as "The camera image quality is good, but the battery life is poor."

[0573] Analyzing feedback and improving products

[0574] The server analyzes the collected feedback and identifies necessary improvements, which the design team then uses to refine the prototype.

[0575] Specific examples

[0576] The design team designs an improved smartphone with increased battery capacity and improved power efficiency.

[0577] Manufacturing and bringing products to market

[0578] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[0579] Specific examples

[0580] The improved smartphone is mass-produced and begins selling on online platforms, where it is purchased by many consumers and receives positive reviews.

[0581] summary

[0582] By repeating these steps, the present invention is a system that maximizes the use of consumer data and enables the rapid planning and manufacturing of products that meet market needs, significantly shortening the lengthy conventional product development process and enabling rapid response to changing consumer needs.

[0583] The processing flow will be explained below.

[0584] Step 1:

[0585] The server periodically collects consumers' purchase history, comparison shopping history, and reviews using the online shopping platform API. The collected data is stored in a database. When collecting the data, it is anonymized to prevent personal identification.

[0586] Step 2:

[0587] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters, as well as removing unnecessary columns in purchase history data and deleting duplicate data.

[0588] Step 3:

[0589] The server inputs the preprocessed data into the generation AI, which uses natural language processing (NLP) technology to analyze the sentiment of the reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history.

[0590] Step 4:

[0591] The server generates new product ideas based on the results of the analysis by the generative AI, which automatically creates multiple ideas by taking into account specific parameters (e.g., price range, functionality, design, etc.).

[0592] Step 5:

[0593] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[0594] Step 6:

[0595] A prototype device is produced based on the design drawings. The prototype is then assembled in the factory using the specified materials and parts. Once the prototype is complete, a quality check is carried out.

[0596] Step 7:

[0597] The server provides the prototype to selected test consumers and tests its usage. The test consumers use the prototype and send their impressions and evaluations to the server as feedback.

[0598] Step 8:

[0599] The server analyzes the collected feedback, identifies areas that need improvement based on consumer opinions and ratings, and generates improvement proposals based on those. These improvement proposals are provided as feedback to the design team.

[0600] Step 9:

[0601] The prototype device is redesigned based on the proposed improvements, new blueprints are created that reflect the improvements, and the device is sent back to the factory to produce an improved prototype.

[0602] Step 10:

[0603] The server then finalizes the improved final product specifications and sends manufacturing instructions to the factory, which then goes into mass production and mass-produces the product based on the finalized specifications.

[0604] Step 11:

[0605] The server lists the manufactured products on an online shopping platform and starts selling them, monitors sales, and optimizes marketing strategies as needed.

[0606] Conclusion

[0607] These are the specific processing steps of this system, which makes it possible to make maximum use of consumer data and quickly and efficiently develop and provide products that meet market needs.

[0608] Example 1

[0609] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0610] In the conventional product development process, it was difficult to quickly grasp consumer needs and then plan and manufacture new products based on those needs. Furthermore, data collection and analysis, product idea generation, and product improvement were all done manually, which was time-consuming and costly. This resulted in an inability to respond quickly to changing consumer needs, and a decline in market competitiveness.

[0611] 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.

[0612] In this invention, the server includes means for collecting consumer data from an online shopping platform, means for periodically obtaining the collected data using an API and storing it in a database, means for preprocessing the collected data and deleting unnecessary and duplicate data, means for analyzing the preprocessed data and identifying consumer needs and market trends, means for using a generative AI to generate new product ideas based on the analysis results, means for creating detailed blueprints based on the generated product ideas and designing and manufacturing prototypes, means for providing the prototypes to monitor consumers and collecting feedback, means for analyzing the collected feedback and improving the product, and means for determining final product specifications, manufacturing the improved product, and providing it to the market. This makes it possible to make maximum use of consumer data and efficiently plan, manufacture, and launch products that meet market needs quickly.

[0613] "Consumer data" refers to information, including consumer purchase history, comparison history, and reviews, that reflects consumer behavior and opinions.

[0614] An "online shopping platform" is a web-based service for selling and purchasing goods over the Internet.

[0615] An "API" is an interface that allows different software applications to communicate and a protocol for using specific services or functions.

[0616] "Data preprocessing" is the process of preparing collected raw data in an analyzable form, and includes tasks such as removing unnecessary and duplicate data and cleaning text data.

[0617] "Generative AI" refers to artificial intelligence that generates new content and ideas based on human instructions, particularly using natural language processing and machine learning techniques.

[0618] A "prototype" is a test product created to verify the design and performance of a final product, and is used to demonstrate and evaluate product designs.

[0619] "Feedback" refers to the evaluations and opinions collected from consumers who have used prototypes, and is information that is used to improve the product and determine its final specifications.

[0620] "Privacy protection" refers to measures to anonymize personal information from collected data so that individuals cannot be identified.

[0621] MODE FOR CARRYING OUT THE INVENTION

[0622] This invention is a system that uses consumer data to rapidly develop products that meet market needs. This system uses consumer data collected from online shopping platforms, generates new product ideas using generative AI, and designs, manufactures, and sells products based on those ideas.

[0623] Consumer Data Collection

[0624] The server periodically collects consumer data (purchase history, comparison shopping history, reviews) from the online shopping platform using APIs. The collected data is stored in a database and anonymized to protect privacy. Consumer data collection is performed using a scheduler that automates database updates and an anonymization tool.

[0625] As a specific example, consider a situation where a user purchases a home appliance from an online shopping platform, and the history and reviews of the purchase are collected by a server.

[0626] Data Preprocessing

[0627] The server pre-processes the collected data. Text data is cleaned by removing unnecessary symbols and tags, and duplicate purchase history data is deduplicated. This pre-processing uses text analysis tools and deduplication algorithms to convert the data into a format suitable for analysis.

[0628] For example, the server removes unnecessary symbols and duplicate data from the reviews and converts them into a format suitable for analysis.

[0629] Analyzing the data

[0630] The server inputs the preprocessed data into a generative AI model to analyze consumer needs and market trends. The generative AI model uses natural language processing technology to analyze the sentiment of reviews and extract popular products and their features from purchase history.

[0631] A specific example might be a situation where a server performs sentiment analysis of reviews and discovers that many consumers highly praise the camera features of a particular smartphone.

[0632] Product idea generation

[0633] The server generates new product ideas based on the analysis results provided by the generative AI, which considers parameters such as price range, functionality, and design to propose product ideas that will appeal to many consumers.

[0634] For example, the generative AI suggests a "mid-priced smartphone with a high-performance camera."

[0635] Prototype design and construction

[0636] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. It then uses the drawing to create a prototype and sends production instructions to the factory, where the prototype is actually produced.

[0637] For example, a design team might create a prototype smartphone that is lightweight and equipped with a high-performance camera.

[0638] Testing prototypes and gathering feedback

[0639] The server provides the prototype to the monitor consumers and collects feedback from the consumers, including their evaluation of the prototype and suggestions for improvement.

[0640] For example, you could distribute a prototype to 20 testers and collect feedback such as, "The camera image quality is good, but the battery life is poor."

[0641] Analyzing feedback and improving products

[0642] The server analyzes the collected feedback and identifies product improvements, which the design team uses to improve the prototype and send the improvements back to the factory.

[0643] As a concrete example, a design team designs an improved version of a smartphone with increased battery capacity and improved power efficiency.

[0644] Manufacturing and bringing products to market

[0645] The server finalizes the product specifications and sends manufacturing instructions to the factory, where the product is mass-produced and then made available for sale on the online shopping platform.

[0646] For example, an improved smartphone is mass-produced and launched for sale on an online platform, where it is purchased by many consumers and receives positive reviews.

[0647] Specific prompt examples

[0648] "Analyze the purchase history and reviews of home appliances on online platforms to generate ideas for the next product we should develop."

[0649] By repeating these steps, the present invention is a system that maximizes the use of consumer data and enables the rapid planning and manufacturing of products that meet market needs. This system significantly shortens the conventional product development process and makes it possible to respond quickly to changing consumer needs.

[0650] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0651] Step 1: Collect consumer data

[0652] The server collects consumer data from online shopping platforms using APIs. Specifically, the server sends requests to API endpoints to obtain data such as purchase history, comparison history, and reviews.

[0653] Input: Consumer data retrieved from API endpoints

[0654] Output: Consumer data stored in a database

[0655] Specific behavior:

[0656] The server periodically runs scheduled tasks and sends API requests.

[0657] Receive the acquired data and process it using anonymization tools to protect privacy.

[0658] The anonymized data is stored in a database.

[0659] Step 2: Preprocessing the data

[0660] The server preprocesses the collected data: text data (such as reviews) is cleaned and unnecessary symbols and tags are removed, and purchase history data is deduplicated and converted into a format suitable for analysis.

[0661] Input: Raw data stored in a database

[0662] Output: Preprocessed data

[0663] Specific behavior:

[0664] The server uses text analysis tools to remove unnecessary symbols and tags from the reviews.

[0665] Use a duplicate data detection algorithm to remove duplicate purchase history.

[0666] Save the preprocessed data to a new database table.

[0667] Step 3: Analyze the data

[0668] The server inputs the preprocessed data into a generative AI model to analyze consumer needs and market trends. The generative AI model uses natural language processing technology to analyze the sentiment of reviews and extract popular products and their features from purchase history.

[0669] Input: Preprocessed data

[0670] Output: Analysis results

[0671] Specific behavior:

[0672] The server converts the preprocessed data into an input format for the generative AI model.

[0673] Input data into the generative AI model and wait for analysis to complete.

[0674] The analysis results are obtained and stored in a database.

[0675] Step 4: Generate product ideas

[0676] The server generates new product ideas based on the analysis results provided by the generative AI, which considers parameters such as price range, functionality, and design to propose product ideas that consumers desire.

[0677] Input: Analysis results

[0678] Output: Product idea

[0679] Specific behavior:

[0680] The server inputs prompts into the generative AI model based on the analysis results.

[0681] Evaluate the generated product ideas and extract feasible ideas.

[0682] The extracted ideas are stored in a database and notified to the design team.

[0683] Step 5: Design and build a prototype

[0684] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server, creates prototypes based on the drawings, and sends production instructions to the factory.

[0685] Input: Product idea

[0686] Output: Prototype blueprints and prototypes

[0687] Specific behavior:

[0688] The design team uses design software to create detailed blueprints.

[0689] Send the blueprint to the factory manufacturing system.

[0690] The factory produces prototypes based on the design drawings.

[0691] Step 6: Test the prototype and gather feedback

[0692] The server provides the prototype to the test consumers and collects their feedback, including their evaluation of the prototype and specific suggestions for improvement.

[0693] Input: Monitor consumer ratings and opinions

[0694] Output: Feedback data

[0695] Specific behavior:

[0696] The server provides the prototype to consumers who participate in the evaluation test.

[0697] The server collects feedback through online surveys and interviews.

[0698] Store the collected feedback in a database.

[0699] Step 7: Analyze feedback and improve the product

[0700] The server analyzes the collected feedback and identifies necessary improvements, which the design team then uses to refine the prototype.

[0701] Input: Feedback data

[0702] Output: Improvements and tweaks

[0703] Specific behavior:

[0704] The server analyzes the feedback data and identifies areas for improvement.

[0705] The server notifies the design team of improvements.

[0706] The design team modifies the design drawings based on the improvements and sends them back to the factory.

[0707] Step 8: Manufacture and market your product

[0708] The server finalizes the product specifications and sends manufacturing instructions to the factory, which then mass-produces the product and starts selling it on the online shopping platform.

[0709] Input: Final product specifications

[0710] Output: Commercially available product

[0711] Specific behavior:

[0712] The server sends the final product specifications to the factory.

[0713] The factory begins mass production and delivers the finished products to the warehouse.

[0714] The server uploads the product data to the online shopping platform and starts selling.

[0715] (Application example 1)

[0716] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0717] In the traditional product development process, it takes a long time and costs a lot of money to properly understand consumer needs and generate new product ideas based on them. Furthermore, even product recommendation systems that utilize consumer data often do not provide personalized recommendations, making it difficult to meet consumer expectations. Furthermore, protecting the privacy of collected consumer data is also a major issue. Therefore, an efficient system that solves these problems is needed.

[0718] 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.

[0719] In this invention, the server includes means for collecting consumer data consisting of purchase history, comparison history, and reviews, means for preprocessing the collected data, means for analyzing the preprocessed data and identifying consumer needs, means for a generative AI to generate new product ideas based on the analysis results, means for designing and manufacturing prototypes based on the generated product ideas, means for testing the prototypes and collecting feedback from consumers, means for analyzing the feedback and improving the products, means for manufacturing the improved products and providing them to the market, and means for personalizing product recommendations based on the collected data. This makes it possible to plan and manufacture products that meet market needs effectively in a short period of time, and to provide more personalized product recommendations.

[0720] "Consumer Data" refers to data consisting of purchase history, comparison history, and reviews.

[0721] "Means of collection" refers to mechanisms for automatically obtaining consumer data from online shopping platforms and other data sources.

[0722] "Preprocessing means" refers to a mechanism for cleaning collected data, removing unnecessary information, and converting it into a format suitable for analysis.

[0723] "Means of analysis" refers to the data analysis process to identify consumer needs based on collected and pre-processed data.

[0724] "Generative AI" refers to artificial intelligence technology that automatically generates new product ideas based on analysis results.

[0725] "Means of designing and producing prototypes" refers to the process of creating detailed design drawings based on the generated product ideas and producing prototypes.

[0726] "Means of testing prototypes and gathering feedback" refers to the process of providing prototypes to consumers and gathering their impressions and opinions.

[0727] "Means for analyzing feedback and improving the product" refers to the process of identifying improvements to the prototype based on the collected feedback and improving the design and functionality.

[0728] "Means of manufacturing and marketing" refers to the process of mass-producing an improved product and selling it to consumers.

[0729] "Means for personalizing product recommendations" refers to a system that recommends the most suitable products to each user based on collected consumer data.

[0730] The system for implementing this invention automates the process of collecting consumer data and quickly developing products that meet market needs. This system is primarily composed of a server, terminals, and users.

[0731] Server Functions and Processing

[0732] 1. Data Collection:

[0733] The server automatically collects consumer data, consisting of purchase history, comparison history, and reviews, from online shopping platforms and other data sources using APIs. The data is periodically pulled, anonymized to protect privacy, and stored in a database.

[0734] 2. Data Preprocessing:

[0735] The server preprocesses the collected data. Specifically, it cleans text data (such as reviews) and deletes unnecessary data. It also deduplicates purchase history data. This converts the data into a format suitable for analysis.

[0736] 3. Data Analysis:

[0737] The pre-processed data is then input into the generative AI, which uses natural language processing technology to analyze the sentiment of the reviews and identify popular products and their features based on purchase history. Based on the results of this analysis, consumer needs and market trends are identified.

[0738] 4. Product idea generation:

[0739] The server uses generative AI to generate new product ideas based on the analysis results. The AI ​​considers specific parameters (price range, functionality, design, etc.) and provides product ideas that are desired by many consumers.

[0740] Terminal functions and processing

[0741] 1. Prototype design and construction:

[0742] The terminal (such as the design team's computer) creates detailed design drawings based on the product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[0743] 2. Test the prototype and gather feedback:

[0744] The prototype is provided to test consumers, and the server collects their feedback, including their opinions and evaluations of the prototype.

[0745] Server feedback processing

[0746] 1. Feedback Analysis and Product Improvement:

[0747] The server analyzes the collected feedback and identifies necessary improvements. The design team then improves the prototype based on the feedback. For example, if the feedback is that the camera image quality is good but the battery life is poor, the team will increase the battery capacity and improve power efficiency.

[0748] 2. Manufacture and market the product:

[0749] The final product specifications are finalized and manufacturing instructions are sent to the factory, where mass production begins. The product is then sold on an online shopping platform, where it is purchased by many consumers and receives positive reviews.

[0750] Personalized product recommendations

[0751] The server personalizes product recommendations based on the collected data. It analyzes each user's purchase and browsing history to provide the functionality to recommend the most suitable products, improving the user experience and increasing sales.

[0752] Prompt Sentence Examples

[0753] For example, suppose you want to collect and analyze data about "smartwatches." Here are some example prompts to input to the generative AI:

[0754] Generate new product ideas based on the following popular items and sentiments: {'Smartwatch Model A': 123, 'Smartwatch Model B' : 95, 'Smartwatch Model C': 80} and [0.75, 0.6, -0.3, 0.9, 0.8]

[0755] Based on these prompts, the generative AI will provide new product ideas such as "a mid-priced smartwatch with advanced health management features."

[0756] As described above, the system of the present invention makes it possible to make maximum use of consumer data and quickly plan and manufacture products that meet market needs.

[0757] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0758] Step 1: Data collection

[0759] The server automatically collects consumer data, including purchase history, comparison history, and reviews, from online shopping platforms and other data sources using APIs, periodically sending API requests and storing the retrieved data in a database in JSON format.

[0760] Input: Raw data obtained via API

[0761] Output: Consumer data in JSON format

[0762] Step 2: Data Preprocessing

[0763] The server preprocesses the collected data. Specifically, it cleans the text data (reviews) and deletes unnecessary data. It also eliminates duplicates in the purchase history data and converts it into a format suitable for analysis.

[0764] Input: Consumer data in JSON format

[0765] Output: Cleaned dataset

[0766] Step 3: Data analysis

[0767] The server inputs the preprocessed data into the generative AI to analyze consumer needs and market trends. Specifically, it uses natural language processing technology to analyze the sentiment of reviews and identify popular products and their features based on purchase history.

[0768] Input: Cleaned dataset

[0769] Output: Analysis of consumer needs and market trends

[0770] Step 4: Product idea generation

[0771] The server uses a generative AI to generate new product ideas based on the analysis results. The AI ​​receives a prompt and generates new product ideas taking into account specific parameters (price range, functionality, design, etc.).

[0772] Input: Consumer needs and market trend analysis results, prompt text

[0773] Output: New product ideas

[0774] Step 5: Design and build a prototype

[0775] The terminal (such as the design team's computer) creates detailed design drawings based on the new product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[0776] Input: New product idea

[0777] Output: Prototype

[0778] Step 6: Test the prototype and gather feedback

[0779] The prototypes are provided to test consumers, and their feedback is collected by the server. Specifically, their impressions and evaluations of the product are collected in the form of questionnaires and reviews.

[0780] Input: Prototype

[0781] Output: Feedback data

[0782] Step 7: Analyze feedback and improve the product

[0783] The server analyzes the collected feedback data and identifies necessary improvements, which the design team then uses to refine the prototype, implementing specific improvements such as increasing battery capacity.

[0784] Input: Feedback data

[0785] Output: Improvements and New Designs

[0786] Step 8: Manufacture and market your product

[0787] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[0788] Input: Improved product specifications

[0789] Output: Products delivered to the market

[0790] Step 9: Personalize product recommendations

[0791] The server personalizes product recommendations based on the collected data, analyzing each user's purchase and browsing history to recommend the most suitable products, improving the user experience and increasing sales.

[0792] Input: User purchase history and browsing history

[0793] Output: Personalized product recommendations

[0794] 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.

[0795] The present invention combines a system that uses consumer data to rapidly develop products that capture market needs with an emotion engine that recognizes user emotions. Specific implementation details are described below.

[0796] System Embodiments

[0797] Consumer Data Collection

[0798] The server automatically collects consumer data (purchase history, comparison history, and reviews) from online shopping platforms. The collected data is stored in a database. When collecting the data, it is anonymized so that individuals cannot be identified.

[0799] Specific examples

[0800] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[0801] Data Preprocessing

[0802] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters. It also removes unnecessary columns from purchase history data and deletes duplicate data.

[0803] Specific examples

[0804] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[0805] Analyzing the data

[0806] The server inputs the preprocessed data into the generation AI and emotion engine. The generation AI uses natural language processing (NLP) technology to analyze the sentiment of reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history. The emotion engine identifies consumer sentiment from reviews.

[0807] Specific examples

[0808] The server performs sentiment analysis on the reviews and discovers that many consumers express positive sentiment, such as being "very satisfied," with the camera features of a particular smartphone.

[0809] Product idea generation

[0810] The server generates new product ideas based on the results of the generative AI and emotion engine analysis. The generative AI automatically creates multiple ideas, taking into account specific parameters (price range, functionality, design, etc.).

[0811] Specific examples

[0812] As a result of sentiment analysis, the generative AI proposes a product idea: a mid-priced smartphone equipped with a high-performance camera.

[0813] Prototype design and construction

[0814] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[0815] Specific examples

[0816] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[0817] Testing prototypes and gathering feedback

[0818] The server provides the prototype to the monitor consumers and collects their feedback. The feedback includes the consumers' opinions and evaluations of the prototype. The emotion engine also analyzes the feedback to identify the consumers' emotions.

[0819] Specific examples

[0820] The prototype is distributed to 20 testers and feedback is collected, such as "The camera image quality is good, but the battery life is poor." The emotion engine identifies positive and negative emotions from the testers' feedback.

[0821] Analyzing feedback and improving products

[0822] The server identifies necessary improvements based on the collected feedback and the emotion engine analysis, and the design team refines the prototype based on the feedback and emotion analysis.

[0823] Specific examples

[0824] The design team designs an improved smartphone with increased battery capacity and improved power efficiency.

[0825] Manufacturing and bringing products to market

[0826] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[0827] Specific examples

[0828] The improved smartphone is mass-produced and begins selling on online platforms, where it is purchased by many consumers and receives positive reviews.

[0829] summary

[0830] This invention is a system that combines consumer data with an emotion engine to enable product planning and manufacturing that more accurately reflects consumer emotions. By repeating these steps, it becomes possible to make the most of consumer data and quickly and efficiently develop and provide products that meet market needs.

[0831] The processing flow will be explained below.

[0832] Step 1:

[0833] The server periodically collects consumers' purchase history, comparison shopping history, and reviews using the online shopping platform API. The collected data is stored in a database. When collecting the data, it is anonymized to prevent personal identification.

[0834] Specific examples

[0835] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[0836] Step 2:

[0837] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters. It also removes unnecessary columns from purchase history data and deletes duplicate data.

[0838] Specific examples

[0839] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[0840] Step 3:

[0841] The server inputs the preprocessed data into the generation AI and emotion engine. The generation AI uses natural language processing (NLP) technology to analyze the sentiment of reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history. The emotion engine identifies consumer sentiment from reviews.

[0842] Specific examples

[0843] The server performs sentiment analysis on the reviews and discovers that many consumers express positive sentiment, such as being "very satisfied," with the camera features of a particular smartphone.

[0844] Step 4:

[0845] The server generates new product ideas based on the results of the generative AI and emotion engine analysis. The generative AI automatically creates multiple ideas, taking into account specific parameters (price range, functionality, design, etc.).

[0846] Specific examples

[0847] As a result of sentiment analysis, the generative AI proposes a product idea: a mid-priced smartphone equipped with a high-performance camera.

[0848] Step 5:

[0849] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[0850] Specific examples

[0851] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[0852] Step 6:

[0853] The server issues instructions to the factory to manufacture a prototype based on the design drawings. The factory assembles the prototype using the specified materials and parts. Once the prototype is completed, a quality check is performed.

[0854] Specific examples

[0855] At the factory, prototype smartphones pass quality checks and are ready for testing.

[0856] Step 7:

[0857] The server provides the prototype to selected monitor consumers and tests its usage. The users (monitor consumers) use the prototype and send their impressions and evaluations as feedback to the server. The emotion engine also analyzes the feedback and identifies the consumer's emotions.

[0858] Specific examples

[0859] The prototype is distributed to 20 testers and feedback is collected, such as "The camera image quality is good, but the battery life is poor." The emotion engine identifies positive and negative emotions from the testers' feedback.

[0860] Step 8:

[0861] The server identifies necessary improvements based on the collected feedback and the analysis results of the emotion engine. The design team improves the prototype based on the feedback and emotion analysis. A new improved design is created and another prototype is produced.

[0862] Specific examples

[0863] The design team designs an improved smartphone with increased battery capacity and improved power efficiency, and the factory builds prototypes of the improved version.

[0864] Step 9:

[0865] The server then finalizes the improved final product specifications and sends manufacturing instructions to the factory, which then goes into mass production and mass-produces the product based on the finalized specifications.

[0866] Specific examples

[0867] The improved smartphone will be mass-produced and made available for sale on online platforms.

[0868] Step 10:

[0869] The server lists the manufactured products on an online shopping platform and starts selling them, monitors sales, and optimizes marketing strategies as needed.

[0870] Specific examples

[0871] The product goes on sale on an online shopping platform, is purchased by many consumers, and receives positive reviews.

[0872] Example 2

[0873] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0874] In today's market, it is difficult to quickly and accurately grasp consumer needs and develop products that meet those needs. Furthermore, because product development is carried out without a detailed understanding of consumer sentiment, it is difficult to improve consumer satisfaction. Furthermore, there is a need for an efficient system that can properly collect and analyze consumer data and reflect it in product development.

[0875] 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.

[0876] In this invention, the server includes: means for collecting consumer data consisting of purchase history, comparison history, and reviews; means for preprocessing the collected data; means for analyzing the preprocessed data and identifying consumer needs; means for a generative AI to generate new product ideas based on the analysis results; means for designing and manufacturing prototypes based on the generated product ideas; means for testing the prototypes and collecting feedback from consumers; means for analyzing the feedback and improving the product; means for recognizing emotions from consumer reviews using an emotion engine and reflecting the results in improving product characteristics; and means for manufacturing the improved products and offering them to the market. This enables product development that reflects consumer data and emotion analysis in detail.

[0877] "Purchase history" is a record of data about products a consumer has purchased in the past.

[0878] A "comparison and consideration history" is a record of data showing the comparison and consideration process that a consumer undertakes before purchasing a product.

[0879] A "review" is a written evaluation or impression left by a consumer about a product they have purchased.

[0880] "Consumer Data" is information consisting of purchase history, comparison history, and reviews.

[0881] "Preprocessing" is the process of removing unnecessary information from collected data and converting it into a form suitable for analysis.

[0882] "Analysis" is the process of analyzing data in detail to extract patterns and useful information.

[0883] "Generative AI" is a system that uses artificial intelligence technology to automatically generate new product ideas.

[0884] A "product idea" is a proposal that summarizes the concept and features of a new product.

[0885] A "prototype" is a model that is actually designed and manufactured based on a generated product idea.

[0886] "Feedback" refers to opinions and evaluations collected from consumers regarding prototypes.

[0887] The "sentiment engine" is a system that analyzes the sentiment of consumer reviews and identifies positive or negative sentiment.

[0888] "Data anonymization" is the process of removing personally identifiable information from data to protect privacy.

[0889] MODE FOR CARRYING OUT THE INVENTION

[0890] The present invention combines a system that uses consumer data, including purchase history, comparison history, and reviews, to rapidly develop products that meet market needs with an emotion engine that recognizes consumer emotions. Specific implementation methods are described below.

[0891] 1. Consumer Data Collection

[0892] The server automatically collects consumer data such as purchase history, comparison history, and reviews from online shopping platforms through APIs, such as Amazon Web Services (AWS) or Google Cloud Platform (GCP), and retrieves the data using the Python requests library.

[0893] 2. Data Preprocessing

[0894] The server preprocesses the collected data by converting it into a data frame using Pandas (a Python library), removing punctuation and special characters from text data, deleting unnecessary columns, and removing duplicate data, converting the data into a format suitable for analysis.

[0895] 3. Data Analysis

[0896] The server inputs the preprocessed data into the generative AI and sentiment engine. It uses natural language processing (NLP) technologies such as BERT and GPT-3 to analyze the sentiment of reviews and analyze market trends from purchase history and comparison history data. The sentiment engine also uses tools such as Amazon Comprehend to identify consumer sentiment.

[0897] 4. Product idea generation

[0898] The server uses the generative AI to generate new product ideas based on the analysis results. It uses OpenAI's API and Hugging Face's Transformers to automatically create multiple product ideas based on specified parameters. For example, enter "Generate a new smartphone idea based on the following specifications: ..." as the prompt.

[0899] 5. Prototype design and construction

[0900] The terminal (such as the design team's PC) uses AutoCAD or SolidWorks to create detailed design drawings based on the product ideas received from the server. The design drawings include the specific specifications proposed by the generative AI, and a prototype is then produced based on these.

[0901] 6. Test the prototype and gather feedback

[0902] The server provides the prototype to the test consumers and collects their feedback using Google Forms or SurveyMonkey. The feedback form contains the consumers' opinions and impressions about the prototype, which are analyzed by an emotion engine to identify the consumers' emotions.

[0903] 7. Analyzing Feedback and Improving Products

[0904] The server analyzes the collected feedback and identifies areas for improvement in the product. Using Pandas and SciPy, it performs detailed analysis of the feedback data and identifies areas for improvement. It notifies the design team of the results and creates an improved version.

[0905] 8. Manufacturing and bringing products to market

[0906] The server finalizes the product specifications and sends manufacturing instructions to the factory using the ERP system, after which the products are mass-produced and made available for sale on online shopping platforms such as Shopify, bringing the products to market.

[0907] In this way, the present invention is a system that covers a whole series of processes from data collection to product development, feedback collection, product improvement, and final market release, and by introducing an emotion engine, it is possible to analyze consumer emotions in detail and improve product characteristics to reflect those emotions. This allows products that provide high consumer satisfaction to be released to the market quickly.

[0908] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0909] Program processing flow

[0910] Step 1: Collect consumer data

[0911] The server collects consumer data (purchase history, comparison history, and reviews) from the online shopping platform.

[0912] Input: API endpoint of online shopping platform

[0913] Data processing: Purchase history, comparison history, and reviews are obtained in JSON format and saved in a database

[0914] Output: Raw data stored in a database

[0915] Specific operation: Makes an API call using Python's requests library and saves the retrieved data to a database.

[0916] Step 2: Preprocessing the data

[0917] The server performs pre-processing on the collected data.

[0918] Input: Raw data in the database

[0919] Data processing: removing punctuation and special characters, deleting unnecessary columns, removing duplicate data

[0920] Output: Cleaned data

[0921] Specific behavior: Convert to a data frame using Pandas and perform data cleaning operations.

[0922] Step 3: Analyze the data

[0923] The server feeds the pre-processed data into the generative AI and emotion engine.

[0924] Input: Preprocessed data

[0925] Data processing: Using natural language processing technology to analyze the sentiment of reviews and understand market trends

[0926] Output: Sentiment analysis results and market trend data

[0927] What it does: Perform sentiment analysis and market trend analysis using BERT, GPT-3, and Amazon Comprehend.

[0928] Step 4: Generate product ideas

[0929] The server uses a generative AI to generate new product ideas based on the analysis results.

[0930] Input: Sentiment analysis results and market trend data

[0931] Data processing: Providing product recommendations based on specified parameters

[0932] Output: New product ideas

[0933] What it does: Uses OpenAI APIs and Hugging Face Transformers to generate product ideas based on a given prompt.

[0934] Step 5: Design and build a prototype

[0935] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server.

[0936] Input: New product idea

[0937] Data processing: Creating detailed blueprints using CAD software

[0938] Output: Prototype blueprints

[0939] Specific Tasks: Using AutoCAD and SolidWorks, you will create blueprints for the design team to bring product ideas to life.

[0940] Step 6: Test the prototype and gather feedback

[0941] The server provides the prototype to monitor consumers and collects their feedback.

[0942] Input: Prototype, Feedback Form

[0943] Data processing: Collecting consumer ratings and comments and analyzing their sentiment

[0944] Output: Aggregated feedback and sentiment analysis results

[0945] What it does: Collect feedback using Google Forms and SurveyMonkey, and perform sentiment analysis using Amazon Comprehend.

[0946] Step 7: Analyze feedback and improve the product

[0947] The server analyzes the collected feedback and identifies product improvements.

[0948] Input: Aggregated feedback and sentiment analysis results

[0949] Data processing: Analyzing feedback data and extracting areas for improvement

[0950] Output: List of improvements

[0951] What it does: Uses Pandas and SciPy to perform detailed analysis of feedback and inform the design team of improvements.

[0952] Step 8: Manufacture and market your product

[0953] The server determines the final product specifications and sends manufacturing instructions to the factory.

[0954] Input: List of improvements, final specifications

[0955] Data processing: Finalizing manufacturing instructions and preparing for market launch

[0956] Output: Produced products, on sale

[0957] What it does: Uses an ERP system to send production instructions to factories and starts selling on e-commerce platforms like Shopify.

[0958] The above specific steps will realize a series of processes from product development to market launch using consumer data.

[0959] (Application example 2)

[0960] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0961] In the past, it was difficult to utilize consumer data to quickly develop products that met market needs in the product development process. Furthermore, there was a lack of technology to understand the emotions of drivers and passengers in real time and adjust in-car navigation and entertainment accordingly. Under these circumstances, it was difficult to develop products that maximize consumer satisfaction and provide a safe and comfortable driving environment for drivers and passengers.

[0962] 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.

[0963] In this invention, the server includes means for collecting consumer data including purchase history, comparison history, and reviews, means for preprocessing the collected data, means for analyzing the preprocessed data and identifying consumer needs, means for a generative AI to generate new product ideas based on the analysis results, means for designing and manufacturing prototypes based on the generated product ideas, means for testing the prototypes and collecting feedback from consumers, means for analyzing the feedback and improving the product, means for manufacturing the improved product and providing it to the market, means for collecting emotional data of drivers and passengers, means for anonymizing the collected emotional data, and means for providing driving routes and entertainment based on the emotional data. This enables the development and provision of products that accurately reflect consumer emotions and needs, and a safe and comfortable driving experience that takes into account the emotions of drivers and passengers.

[0964] "Consumer Data" is information about consumer behavior and opinions, such as purchase history, comparison history, and reviews.

[0965] "Preprocessing" means removing unnecessary information from raw data and converting it into a form suitable for analysis.

[0966] "Analyzing" means using pre-processed data to extract information and patterns and make sense of them.

[0967] "Generative AI" is a technology that uses artificial intelligence algorithms to automatically generate new product ideas and proposals.

[0968] A "product idea" is a concept for a new product or service that is generated with consumer needs and emotions in mind.

[0969] A "prototype" is an early stage product that embodies a generated product idea.

[0970] "Feedback" refers to reaction information such as evaluations and opinions from consumers who have used the prototype.

[0971] "Improvement" means improving the product's specifications and features based on collected feedback.

[0972] "Emotion data" is information that indicates the emotional state of the driver or passengers, obtained from their faces, voices, etc.

[0973] "Navigation" refers to systems and functions that provide the optimal route to a destination.

[0974] "Entertainment" refers to content such as music and videos that provide enjoyment and satisfaction.

[0975] "Anonymization" is a method of removing or transforming personally identifiable information to protect privacy.

[0976] "Real-time" refers to the processing and provision of information immediately, without delay.

[0977] The present invention provides a system for more accurately grasping market needs and providing products by combining consumer data and emotion data. Specific embodiments of the system are described below.

[0978] Hardware and software used

[0979] The specific hardware and software used as servers and terminals include the following:

[0980] Hardware:

[0981] Camera: Used to recognize the faces of the driver and passengers.

[0982] Microphone: Used to collect audio data.

[0983] Computer: A server or PC for analyzing and storing data.

[0984] software:

[0985] OpenCV: A library for acquiring and processing camera images.

[0986] DeepFace: A library for facial expression analysis.

[0987] Librosa: A library for reading and parsing audio data.

[0988] NLP technologies: Libraries for natural language processing (e.g. spaCy).

[0989] AI generative model: An algorithm that uses generative AI to automatically generate new product ideas.

[0990] Data processing flow

[0991] 1. Data Collection:

[0992] The server collects consumer and emotional data from online shopping platforms and in-car sensors. Consumer data includes purchase history, comparison shopping history, and reviews, while emotional data includes facial expressions and voice recordings of drivers and passengers.

[0993] 2. Data preprocessing:

[0994] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters, deleting unnecessary parts from image data, and removing noise from audio data.

[0995] 3. Data Analysis:

[0996] The server analyzes the preprocessed data, using natural language processing (NLP) technology to analyze the sentiment of reviews, and analyzes market trends and the characteristics of popular products based on purchase history and comparison history. It also identifies the emotions of drivers and passengers through facial expression and voice analysis.

[0997] 4. Product idea generation and provision:

[0998] The server generates new product ideas using a generative AI model. Based on the analysis results, the generative AI automatically creates multiple ideas taking into account specific parameters (price range, functionality, design, etc.). It also provides driving directions and entertainment based on emotional data.

[0999] Specific examples

[1000] When a consumer purchases a home appliance on an online platform, the purchase history and reviews are collected on a server. Sentiment analysis of the reviews is performed and it is discovered that many consumers express positive emotions such as "very satisfied" with the features of a particular home appliance. Based on this result, the generative AI proposes a product idea for a "high-performance, cost-effective home appliance." At the same time, the system uses the in-car camera and microphone to collect the driver's facial expressions and voice. If it determines that the driver is nervous, it plays relaxing music and suggests a safe route.

[1001] Example prompt for a generative AI model:

[1002] "Suggest ideas for home appliances that consumers would be happy to purchase."

[1003] "If you sense a driver is nervous, suggest the most relaxing route."

[1004] "If passengers are bored, offer them music recommendations."

[1005] The above is a specific description of the "Mode for Carrying Out the Invention." The present invention enables highly accurate market response by combining consumer data and emotion data.

[1006] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1007] Step 1:

[1008] Collecting consumer and sentiment data

[1009] The server collects consumer and emotional data from online shopping platforms and in-car sensors. Input data includes purchase history, comparison shopping history, reviews, driver and passenger facial expressions, and voice. The output is the collected raw data. Specifically, the server uses an API to obtain purchase history and reviews from online shopping platforms, and uses the camera and microphone in the in-car sensors to capture driver and passenger emotional data.

[1010] Step 2:

[1011] Data Preprocessing

[1012] The server performs preprocessing on the collected data. The input is the raw data collected in step 1. Specific data processing includes removing punctuation and special characters from the text data and removing noise from the audio data. The output is cleaned data. Specifically, the text data is cleaned using regular expressions, and the audio data is denoised using Librosa.

[1013] Step 3:

[1014] Anonymizing Emotional Data

[1015] The server anonymizes the collected emotional data. The input is the emotional data preprocessed in step 2. Data calculation involves deleting or encrypting information that can identify a specific individual. The output is anonymized emotional data. Specific operations include removing features that can identify an individual from facial expression data and assigning an identification code to the analysis results of the voice data.

[1016] Step 4:

[1017] Data analysis

[1018] The server analyzes the preprocessed consumer data and sentiment data. The input is the cleaned and anonymized data obtained in steps 2 and 3. Specific data calculations include analyzing the sentiment of reviews using natural language processing techniques and analyzing market trends from purchase history and comparison history. The output is the analysis results. Operations include calculating sentiment scores based on specific keywords using an NLP library and extracting trend information from the database.

[1019] Step 5:

[1020] Product idea generation

[1021] The server uses the generative AI model to generate new product ideas based on the analysis results. The input is the analysis results from step 4. As a data calculation, the generative AI generates product ideas based on specific parameters (price, function, design, etc.). The output is the generated product idea. Specifically, the server inputs market trends and sentiment scores into the generative AI model, and generates product ideas based on the prompt text.

[1022] Step 6:

[1023] Prototype design and construction

[1024] The terminal (such as the design team's PC) creates detailed design drawings based on the product idea generated in step 5 and produces a prototype. The input is the generated product idea. As data calculation, a design drawing is created using CAD software and prototype production instructions are output. The output is production instructions and a prototype. As an operation, a detailed design is created using CAD software and prototype production instructions are sent to the factory.

[1025] Step 7:

[1026] Testing prototypes and gathering feedback

[1027] The server provides the prototype to test consumers and collects their feedback. The input is the test results of the test consumers. Specific data processing involves collecting evaluations and opinions from testers and analyzing them with an emotion engine. The output is feedback data. The system operates by collecting feedback through online forms and direct interviews, and analyzing the data with an emotion engine.

[1028] Step 8:

[1029] Feedback analysis and product improvement

[1030] The server analyzes the collected feedback and improves the product. The input is the feedback data from step 7. The data calculation analyzes the collected feedback and identifies necessary improvements. The output is improvement instructions. The operation analyzes the feedback data and integrates the sentiment score and user comments to derive improvement suggestions.

[1031] Step 9:

[1032] Manufacturing and bringing products to market

[1033] The server finalizes the product specifications and sends manufacturing instructions to the factory. The input is the improvement instructions from step 8. As a data calculation, it formulates a manufacturing plan and outputs manufacturing instructions. The output is a mass-produced product. As an operation, it instructs the manufacturing department on the production plan and starts selling the completed product on the online platform.

[1034] Step 10:

[1035] Providing driving directions and entertainment based on emotion data

[1036] The server provides optimal driving routes and entertainment based on the emotional data of the driver and passengers. The input is the emotional data collected in step 1. The data calculation involves analyzing the emotional data and selecting routes and content based on it. The output is the proposed route and entertainment. The operation involves selecting a route that will relax the driver based on the emotional data and selecting music and videos to provide.

[1037] The above is the flow of processing in the system that realizes the application example.

[1038] 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.

[1039] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1040] 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.

[1041] [Third embodiment]

[1042] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1043] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1044] 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).

[1045] 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.

[1046] 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.

[1047] 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).

[1048] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1049] 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.

[1050] 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.

[1051] 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.

[1052] 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.

[1053] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1054] The present invention is a system for quickly developing products that capture market needs by utilizing consumer data, and specific implementation details thereof will be described below.

[1055] System Embodiments

[1056] Consumer Data Collection

[1057] The server automatically collects consumer data (purchase history, comparison history, reviews) from online shopping platforms. It periodically pulls the data using APIs and stores it in a database. The data is anonymized to protect privacy.

[1058] Specific examples

[1059] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[1060] Data Preprocessing

[1061] The server preprocesses the collected data, specifically cleaning text data (such as reviews), deleting unnecessary data, and eliminating duplicates in purchase history data.

[1062] Specific examples

[1063] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[1064] Analyzing the data

[1065] The server inputs the preprocessed data into the AI ​​generator, which analyzes consumer needs and market trends. The AI ​​uses natural language processing technology to analyze the sentiment of reviews and identify popular products and their features based on purchase history.

[1066] Specific examples

[1067] The server performs a sentiment analysis of the reviews and discovers that many consumers highly praise the camera features of a particular smartphone.

[1068] Product idea generation

[1069] The server uses the generative AI to generate new product ideas based on the analysis results. The AI ​​considers specific parameters (price range, functionality, design, etc.) and provides product ideas that are desired by many consumers.

[1070] Specific examples

[1071] The generative AI will suggest "mid-priced smartphones equipped with high-performance cameras."

[1072] Prototype design and construction

[1073] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[1074] Specific examples

[1075] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[1076] Testing prototypes and gathering feedback

[1077] The server provides the prototype to the monitor consumers and collects their feedback, which includes opinions and evaluations of the consumers regarding the prototype.

[1078] Specific examples

[1079] The prototype will be distributed to 20 testers to collect feedback such as "The camera image quality is good, but the battery life is poor."

[1080] Analyzing feedback and improving products

[1081] The server analyzes the collected feedback and identifies necessary improvements, which the design team then uses to refine the prototype.

[1082] Specific examples

[1083] The design team designs an improved smartphone with increased battery capacity and improved power efficiency.

[1084] Manufacturing and bringing products to market

[1085] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[1086] Specific examples

[1087] The improved smartphone is mass-produced and begins selling on online platforms, where it is purchased by many consumers and receives positive reviews.

[1088] summary

[1089] By repeating these steps, the present invention is a system that maximizes the use of consumer data and enables the rapid planning and manufacturing of products that meet market needs, significantly shortening the lengthy conventional product development process and enabling rapid response to changing consumer needs.

[1090] The processing flow will be explained below.

[1091] Step 1:

[1092] The server periodically collects consumers' purchase history, comparison shopping history, and reviews using the online shopping platform API. The collected data is stored in a database. When collecting the data, it is anonymized to prevent personal identification.

[1093] Step 2:

[1094] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters, as well as removing unnecessary columns in purchase history data and deleting duplicate data.

[1095] Step 3:

[1096] The server inputs the preprocessed data into the generation AI, which uses natural language processing (NLP) technology to analyze the sentiment of the reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history.

[1097] Step 4:

[1098] The server generates new product ideas based on the results of the analysis by the generative AI, which automatically creates multiple ideas by taking into account specific parameters (e.g., price range, functionality, design, etc.).

[1099] Step 5:

[1100] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[1101] Step 6:

[1102] A prototype device is produced based on the design drawings. The prototype is then assembled in the factory using the specified materials and parts. Once the prototype is complete, a quality check is carried out.

[1103] Step 7:

[1104] The server provides the prototype to selected test consumers and tests its usage. The test consumers use the prototype and send their impressions and evaluations to the server as feedback.

[1105] Step 8:

[1106] The server analyzes the collected feedback, identifies areas that need improvement based on consumer opinions and ratings, and generates improvement proposals based on those. These improvement proposals are provided as feedback to the design team.

[1107] Step 9:

[1108] The prototype device is redesigned based on the proposed improvements, new blueprints are created that reflect the improvements, and the device is sent back to the factory to produce an improved prototype.

[1109] Step 10:

[1110] The server then finalizes the improved final product specifications and sends manufacturing instructions to the factory, which then goes into mass production and mass-produces the product based on the finalized specifications.

[1111] Step 11:

[1112] The server lists the manufactured products on an online shopping platform and starts selling them, monitors sales, and optimizes marketing strategies as needed.

[1113] Conclusion

[1114] These are the specific processing steps of this system, which makes it possible to make maximum use of consumer data and quickly and efficiently develop and provide products that meet market needs.

[1115] Example 1

[1116] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1117] In the conventional product development process, it was difficult to quickly grasp consumer needs and then plan and manufacture new products based on those needs. Furthermore, data collection and analysis, product idea generation, and product improvement were all done manually, which was time-consuming and costly. This resulted in an inability to respond quickly to changing consumer needs, and a decline in market competitiveness.

[1118] 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.

[1119] In this invention, the server includes means for collecting consumer data from an online shopping platform, means for periodically obtaining the collected data using an API and storing it in a database, means for preprocessing the collected data and deleting unnecessary and duplicate data, means for analyzing the preprocessed data and identifying consumer needs and market trends, means for using a generative AI to generate new product ideas based on the analysis results, means for creating detailed blueprints based on the generated product ideas and designing and manufacturing prototypes, means for providing the prototypes to monitor consumers and collecting feedback, means for analyzing the collected feedback and improving the product, and means for determining final product specifications, manufacturing the improved product, and providing it to the market. This makes it possible to make maximum use of consumer data and efficiently plan, manufacture, and launch products that meet market needs quickly.

[1120] "Consumer data" refers to information, including consumer purchase history, comparison history, and reviews, that reflects consumer behavior and opinions.

[1121] An "online shopping platform" is a web-based service for selling and purchasing goods over the Internet.

[1122] An "API" is an interface that allows different software applications to communicate and a protocol for using specific services or functions.

[1123] "Data preprocessing" is the process of preparing collected raw data in an analyzable form, and includes tasks such as removing unnecessary and duplicate data and cleaning text data.

[1124] "Generative AI" refers to artificial intelligence that generates new content and ideas based on human instructions, particularly using natural language processing and machine learning techniques.

[1125] A "prototype" is a test product created to verify the design and performance of a final product, and is used to demonstrate and evaluate product designs.

[1126] "Feedback" refers to the evaluations and opinions collected from consumers who have used prototypes, and is information that is used to improve the product and determine its final specifications.

[1127] "Privacy protection" refers to measures to anonymize personal information from collected data so that individuals cannot be identified.

[1128] MODE FOR CARRYING OUT THE INVENTION

[1129] This invention is a system that uses consumer data to rapidly develop products that meet market needs. This system uses consumer data collected from online shopping platforms, generates new product ideas using generative AI, and designs, manufactures, and sells products based on those ideas.

[1130] Consumer Data Collection

[1131] The server periodically collects consumer data (purchase history, comparison shopping history, reviews) from the online shopping platform using APIs. The collected data is stored in a database and anonymized to protect privacy. Consumer data collection is performed using a scheduler that automates database updates and an anonymization tool.

[1132] As a specific example, consider a situation where a user purchases a home appliance from an online shopping platform, and the history and reviews of the purchase are collected by a server.

[1133] Data Preprocessing

[1134] The server pre-processes the collected data. Text data is cleaned by removing unnecessary symbols and tags, and duplicate purchase history data is deduplicated. This pre-processing uses text analysis tools and deduplication algorithms to convert the data into a format suitable for analysis.

[1135] For example, the server removes unnecessary symbols and duplicate data from the reviews and converts them into a format suitable for analysis.

[1136] Analyzing the data

[1137] The server inputs the preprocessed data into a generative AI model to analyze consumer needs and market trends. The generative AI model uses natural language processing technology to analyze the sentiment of reviews and extract popular products and their features from purchase history.

[1138] A specific example might be a situation where a server performs sentiment analysis of reviews and discovers that many consumers highly praise the camera features of a particular smartphone.

[1139] Product idea generation

[1140] The server generates new product ideas based on the analysis results provided by the generative AI, which considers parameters such as price range, functionality, and design to propose product ideas that will appeal to many consumers.

[1141] For example, the generative AI suggests a "mid-priced smartphone with a high-performance camera."

[1142] Prototype design and construction

[1143] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. It then uses the drawing to create a prototype and sends production instructions to the factory, where the prototype is actually produced.

[1144] For example, a design team might create a prototype smartphone that is lightweight and equipped with a high-performance camera.

[1145] Testing prototypes and gathering feedback

[1146] The server provides the prototype to the monitor consumers and collects feedback from the consumers, including their evaluation of the prototype and suggestions for improvement.

[1147] For example, you could distribute a prototype to 20 testers and collect feedback such as, "The camera image quality is good, but the battery life is poor."

[1148] Analyzing feedback and improving products

[1149] The server analyzes the collected feedback and identifies product improvements, which the design team uses to improve the prototype and send the improvements back to the factory.

[1150] As a concrete example, a design team designs an improved version of a smartphone with increased battery capacity and improved power efficiency.

[1151] Manufacturing and bringing products to market

[1152] The server finalizes the product specifications and sends manufacturing instructions to the factory, where the product is mass-produced and then made available for sale on the online shopping platform.

[1153] For example, an improved smartphone is mass-produced and launched for sale on an online platform, where it is purchased by many consumers and receives positive reviews.

[1154] Specific prompt examples

[1155] "Analyze the purchase history and reviews of home appliances on online platforms to generate ideas for the next product we should develop."

[1156] By repeating these steps, the present invention is a system that maximizes the use of consumer data and enables the rapid planning and manufacturing of products that meet market needs. This system significantly shortens the conventional product development process and makes it possible to respond quickly to changing consumer needs.

[1157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1158] Step 1: Collect consumer data

[1159] The server collects consumer data from online shopping platforms using APIs. Specifically, the server sends requests to API endpoints to obtain data such as purchase history, comparison history, and reviews.

[1160] Input: Consumer data retrieved from API endpoints

[1161] Output: Consumer data stored in a database

[1162] Specific behavior:

[1163] The server periodically runs scheduled tasks and sends API requests.

[1164] Receive the acquired data and process it using anonymization tools to protect privacy.

[1165] The anonymized data is stored in a database.

[1166] Step 2: Preprocessing the data

[1167] The server preprocesses the collected data: text data (such as reviews) is cleaned and unnecessary symbols and tags are removed, and purchase history data is deduplicated and converted into a format suitable for analysis.

[1168] Input: Raw data stored in a database

[1169] Output: Preprocessed data

[1170] Specific behavior:

[1171] The server uses text analysis tools to remove unnecessary symbols and tags from the reviews.

[1172] Use a duplicate data detection algorithm to remove duplicate purchase history.

[1173] Save the preprocessed data to a new database table.

[1174] Step 3: Analyze the data

[1175] The server inputs the preprocessed data into a generative AI model to analyze consumer needs and market trends. The generative AI model uses natural language processing technology to analyze the sentiment of reviews and extract popular products and their features from purchase history.

[1176] Input: Preprocessed data

[1177] Output: Analysis results

[1178] Specific behavior:

[1179] The server converts the preprocessed data into an input format for the generative AI model.

[1180] Input data into the generative AI model and wait for analysis to complete.

[1181] The analysis results are obtained and stored in a database.

[1182] Step 4: Generate product ideas

[1183] The server generates new product ideas based on the analysis results provided by the generative AI, which considers parameters such as price range, functionality, and design to propose product ideas that consumers desire.

[1184] Input: Analysis results

[1185] Output: Product idea

[1186] Specific behavior:

[1187] The server inputs prompts into the generative AI model based on the analysis results.

[1188] Evaluate the generated product ideas and extract feasible ideas.

[1189] The extracted ideas are stored in a database and notified to the design team.

[1190] Step 5: Design and build a prototype

[1191] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server, creates prototypes based on the drawings, and sends production instructions to the factory.

[1192] Input: Product idea

[1193] Output: Prototype blueprints and prototypes

[1194] Specific behavior:

[1195] The design team uses design software to create detailed blueprints.

[1196] Send the blueprint to the factory manufacturing system.

[1197] The factory produces prototypes based on the design drawings.

[1198] Step 6: Test the prototype and gather feedback

[1199] The server provides the prototype to the test consumers and collects their feedback, including their evaluation of the prototype and specific suggestions for improvement.

[1200] Input: Monitor consumer ratings and opinions

[1201] Output: Feedback data

[1202] Specific behavior:

[1203] The server provides the prototype to consumers who participate in the evaluation test.

[1204] The server collects feedback through online surveys and interviews.

[1205] Store the collected feedback in a database.

[1206] Step 7: Analyze feedback and improve the product

[1207] The server analyzes the collected feedback and identifies necessary improvements, which the design team then uses to refine the prototype.

[1208] Input: Feedback data

[1209] Output: Improvements and tweaks

[1210] Specific behavior:

[1211] The server analyzes the feedback data and identifies areas for improvement.

[1212] The server notifies the design team of improvements.

[1213] The design team modifies the design drawings based on the improvements and sends them back to the factory.

[1214] Step 8: Manufacture and market your product

[1215] The server finalizes the product specifications and sends manufacturing instructions to the factory, which then mass-produces the product and starts selling it on the online shopping platform.

[1216] Input: Final product specifications

[1217] Output: Commercially available product

[1218] Specific behavior:

[1219] The server sends the final product specifications to the factory.

[1220] The factory begins mass production and delivers the finished products to the warehouse.

[1221] The server uploads the product data to the online shopping platform and starts selling.

[1222] (Application example 1)

[1223] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1224] In the traditional product development process, it takes a long time and costs a lot of money to properly understand consumer needs and generate new product ideas based on them. Furthermore, even product recommendation systems that utilize consumer data often do not provide personalized recommendations, making it difficult to meet consumer expectations. Furthermore, protecting the privacy of collected consumer data is also a major issue. Therefore, an efficient system that solves these problems is needed.

[1225] 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.

[1226] In this invention, the server includes means for collecting consumer data consisting of purchase history, comparison history, and reviews, means for preprocessing the collected data, means for analyzing the preprocessed data and identifying consumer needs, means for a generative AI to generate new product ideas based on the analysis results, means for designing and manufacturing prototypes based on the generated product ideas, means for testing the prototypes and collecting feedback from consumers, means for analyzing the feedback and improving the products, means for manufacturing the improved products and providing them to the market, and means for personalizing product recommendations based on the collected data. This makes it possible to plan and manufacture products that meet market needs effectively in a short period of time, and to provide more personalized product recommendations.

[1227] "Consumer Data" refers to data consisting of purchase history, comparison history, and reviews.

[1228] "Means of collection" refers to mechanisms for automatically obtaining consumer data from online shopping platforms and other data sources.

[1229] "Preprocessing means" refers to a mechanism for cleaning collected data, removing unnecessary information, and converting it into a format suitable for analysis.

[1230] "Means of analysis" refers to the data analysis process to identify consumer needs based on collected and pre-processed data.

[1231] "Generative AI" refers to artificial intelligence technology that automatically generates new product ideas based on analysis results.

[1232] "Means of designing and producing prototypes" refers to the process of creating detailed design drawings based on the generated product ideas and producing prototypes.

[1233] "Means of testing prototypes and gathering feedback" refers to the process of providing prototypes to consumers and gathering their impressions and opinions.

[1234] "Means for analyzing feedback and improving the product" refers to the process of identifying improvements to the prototype based on the collected feedback and improving the design and functionality.

[1235] "Means of manufacturing and marketing" refers to the process of mass-producing an improved product and selling it to consumers.

[1236] "Means for personalizing product recommendations" refers to a system that recommends the most suitable products to each user based on collected consumer data.

[1237] The system for implementing this invention automates the process of collecting consumer data and quickly developing products that meet market needs. This system is primarily composed of a server, terminals, and users.

[1238] Server Functions and Processing

[1239] 1. Data Collection:

[1240] The server automatically collects consumer data, consisting of purchase history, comparison history, and reviews, from online shopping platforms and other data sources using APIs. The data is periodically pulled, anonymized to protect privacy, and stored in a database.

[1241] 2. Data Preprocessing:

[1242] The server preprocesses the collected data. Specifically, it cleans text data (such as reviews) and deletes unnecessary data. It also deduplicates purchase history data. This converts the data into a format suitable for analysis.

[1243] 3. Data Analysis:

[1244] The pre-processed data is then input into the generative AI, which uses natural language processing technology to analyze the sentiment of the reviews and identify popular products and their features based on purchase history. Based on the results of this analysis, consumer needs and market trends are identified.

[1245] 4. Product idea generation:

[1246] The server uses generative AI to generate new product ideas based on the analysis results. The AI ​​considers specific parameters (price range, functionality, design, etc.) and provides product ideas that are desired by many consumers.

[1247] Terminal functions and processing

[1248] 1. Prototype design and construction:

[1249] The terminal (such as the design team's computer) creates detailed design drawings based on the product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[1250] 2. Test the prototype and gather feedback:

[1251] The prototype is provided to test consumers, and the server collects their feedback, including their opinions and evaluations of the prototype.

[1252] Server feedback processing

[1253] 1. Feedback Analysis and Product Improvement:

[1254] The server analyzes the collected feedback and identifies necessary improvements. The design team then improves the prototype based on the feedback. For example, if the feedback is that the camera image quality is good but the battery life is poor, the team will increase the battery capacity and improve power efficiency.

[1255] 2. Manufacture and market the product:

[1256] The final product specifications are finalized and manufacturing instructions are sent to the factory, where mass production begins. The product is then sold on an online shopping platform, where it is purchased by many consumers and receives positive reviews.

[1257] Personalized product recommendations

[1258] The server personalizes product recommendations based on the collected data. It analyzes each user's purchase and browsing history to provide the functionality to recommend the most suitable products, improving the user experience and increasing sales.

[1259] Prompt Sentence Examples

[1260] For example, suppose you want to collect and analyze data about "smartwatches." Here are some example prompts to input to the generative AI:

[1261] Generate new product ideas based on the following popular items and sentiments: {'Smartwatch Model A': 123, 'Smartwatch Model B' : 95, 'Smartwatch Model C': 80} and [0.75, 0.6, -0.3, 0.9, 0.8]

[1262] Based on these prompts, the generative AI will provide new product ideas such as "a mid-priced smartwatch with advanced health management features."

[1263] As described above, the system of the present invention makes it possible to make maximum use of consumer data and quickly plan and manufacture products that meet market needs.

[1264] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1265] Step 1: Data collection

[1266] The server automatically collects consumer data, including purchase history, comparison history, and reviews, from online shopping platforms and other data sources using APIs, periodically sending API requests and storing the retrieved data in a database in JSON format.

[1267] Input: Raw data obtained via API

[1268] Output: Consumer data in JSON format

[1269] Step 2: Data Preprocessing

[1270] The server preprocesses the collected data. Specifically, it cleans the text data (reviews) and deletes unnecessary data. It also eliminates duplicates in the purchase history data and converts it into a format suitable for analysis.

[1271] Input: Consumer data in JSON format

[1272] Output: Cleaned dataset

[1273] Step 3: Data analysis

[1274] The server inputs the preprocessed data into the generative AI to analyze consumer needs and market trends. Specifically, it uses natural language processing technology to analyze the sentiment of reviews and identify popular products and their features based on purchase history.

[1275] Input: Cleaned dataset

[1276] Output: Analysis of consumer needs and market trends

[1277] Step 4: Product idea generation

[1278] The server uses a generative AI to generate new product ideas based on the analysis results. The AI ​​receives a prompt and generates new product ideas taking into account specific parameters (price range, functionality, design, etc.).

[1279] Input: Consumer needs and market trend analysis results, prompt text

[1280] Output: New product ideas

[1281] Step 5: Design and build a prototype

[1282] The terminal (such as the design team's computer) creates detailed design drawings based on the new product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[1283] Input: New product idea

[1284] Output: Prototype

[1285] Step 6: Test the prototype and gather feedback

[1286] The prototypes are provided to test consumers, and their feedback is collected by the server. Specifically, their impressions and evaluations of the product are collected in the form of questionnaires and reviews.

[1287] Input: Prototype

[1288] Output: Feedback data

[1289] Step 7: Analyze feedback and improve the product

[1290] The server analyzes the collected feedback data and identifies necessary improvements, which the design team then uses to refine the prototype, implementing specific improvements such as increasing battery capacity.

[1291] Input: Feedback data

[1292] Output: Improvements and New Designs

[1293] Step 8: Manufacture and market your product

[1294] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[1295] Input: Improved product specifications

[1296] Output: Products delivered to the market

[1297] Step 9: Personalize product recommendations

[1298] The server personalizes product recommendations based on the collected data, analyzing each user's purchase and browsing history to recommend the most suitable products, improving the user experience and increasing sales.

[1299] Input: User purchase history and browsing history

[1300] Output: Personalized product recommendations

[1301] 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.

[1302] The present invention combines a system that uses consumer data to rapidly develop products that capture market needs with an emotion engine that recognizes user emotions. Specific implementation details are described below.

[1303] System Embodiments

[1304] Consumer Data Collection

[1305] The server automatically collects consumer data (purchase history, comparison history, and reviews) from online shopping platforms. The collected data is stored in a database. When collecting the data, it is anonymized so that individuals cannot be identified.

[1306] Specific examples

[1307] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[1308] Data Preprocessing

[1309] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters. It also removes unnecessary columns from purchase history data and deletes duplicate data.

[1310] Specific examples

[1311] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[1312] Analyzing the data

[1313] The server inputs the preprocessed data into the generation AI and emotion engine. The generation AI uses natural language processing (NLP) technology to analyze the sentiment of reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history. The emotion engine identifies consumer sentiment from reviews.

[1314] Specific examples

[1315] The server performs sentiment analysis on the reviews and discovers that many consumers express positive sentiment, such as being "very satisfied," with the camera features of a particular smartphone.

[1316] Product idea generation

[1317] The server generates new product ideas based on the results of the generative AI and emotion engine analysis. The generative AI automatically creates multiple ideas, taking into account specific parameters (price range, functionality, design, etc.).

[1318] Specific examples

[1319] As a result of sentiment analysis, the generative AI proposes a product idea: a mid-priced smartphone equipped with a high-performance camera.

[1320] Prototype design and construction

[1321] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[1322] Specific examples

[1323] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[1324] Testing prototypes and gathering feedback

[1325] The server provides the prototype to the monitor consumers and collects their feedback. The feedback includes the consumers' opinions and evaluations of the prototype. The emotion engine also analyzes the feedback to identify the consumers' emotions.

[1326] Specific examples

[1327] The prototype is distributed to 20 testers and feedback is collected, such as "The camera image quality is good, but the battery life is poor." The emotion engine identifies positive and negative emotions from the testers' feedback.

[1328] Analyzing feedback and improving products

[1329] The server identifies necessary improvements based on the collected feedback and the emotion engine analysis, and the design team refines the prototype based on the feedback and emotion analysis.

[1330] Specific examples

[1331] The design team designs an improved smartphone with increased battery capacity and improved power efficiency.

[1332] Manufacturing and bringing products to market

[1333] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[1334] Specific examples

[1335] The improved smartphone is mass-produced and begins selling on online platforms, where it is purchased by many consumers and receives positive reviews.

[1336] summary

[1337] This invention is a system that combines consumer data with an emotion engine to enable product planning and manufacturing that more accurately reflects consumer emotions. By repeating these steps, it becomes possible to make the most of consumer data and quickly and efficiently develop and provide products that meet market needs.

[1338] The processing flow will be explained below.

[1339] Step 1:

[1340] The server periodically collects consumers' purchase history, comparison shopping history, and reviews using the online shopping platform API. The collected data is stored in a database. When collecting the data, it is anonymized to prevent personal identification.

[1341] Specific examples

[1342] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[1343] Step 2:

[1344] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters. It also removes unnecessary columns from purchase history data and deletes duplicate data.

[1345] Specific examples

[1346] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[1347] Step 3:

[1348] The server inputs the preprocessed data into the generation AI and emotion engine. The generation AI uses natural language processing (NLP) technology to analyze the sentiment of reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history. The emotion engine identifies consumer sentiment from reviews.

[1349] Specific examples

[1350] The server performs sentiment analysis on the reviews and discovers that many consumers express positive sentiment, such as being "very satisfied," with the camera features of a particular smartphone.

[1351] Step 4:

[1352] The server generates new product ideas based on the results of the generative AI and emotion engine analysis. The generative AI automatically creates multiple ideas, taking into account specific parameters (price range, functionality, design, etc.).

[1353] Specific examples

[1354] As a result of sentiment analysis, the generative AI proposes a product idea: a mid-priced smartphone equipped with a high-performance camera.

[1355] Step 5:

[1356] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[1357] Specific examples

[1358] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[1359] Step 6:

[1360] The server issues instructions to the factory to manufacture a prototype based on the design drawings. The factory assembles the prototype using the specified materials and parts. Once the prototype is completed, a quality check is performed.

[1361] Specific examples

[1362] At the factory, prototype smartphones pass quality checks and are ready for testing.

[1363] Step 7:

[1364] The server provides the prototype to selected monitor consumers and tests its usage. The users (monitor consumers) use the prototype and send their impressions and evaluations as feedback to the server. The emotion engine also analyzes the feedback and identifies the consumer's emotions.

[1365] Specific examples

[1366] The prototype is distributed to 20 testers and feedback is collected, such as "The camera image quality is good, but the battery life is poor." The emotion engine identifies positive and negative emotions from the testers' feedback.

[1367] Step 8:

[1368] The server identifies necessary improvements based on the collected feedback and the analysis results of the emotion engine. The design team improves the prototype based on the feedback and emotion analysis. A new improved design is created and another prototype is produced.

[1369] Specific examples

[1370] The design team designs an improved smartphone with increased battery capacity and improved power efficiency, and the factory builds prototypes of the improved version.

[1371] Step 9:

[1372] The server then finalizes the improved final product specifications and sends manufacturing instructions to the factory, which then goes into mass production and mass-produces the product based on the finalized specifications.

[1373] Specific examples

[1374] The improved smartphone will be mass-produced and made available for sale on online platforms.

[1375] Step 10:

[1376] The server lists the manufactured products on an online shopping platform and starts selling them, monitors sales, and optimizes marketing strategies as needed.

[1377] Specific examples

[1378] The product goes on sale on an online shopping platform, is purchased by many consumers, and receives positive reviews.

[1379] Example 2

[1380] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1381] In today's market, it is difficult to quickly and accurately grasp consumer needs and develop products that meet those needs. Furthermore, because product development is carried out without a detailed understanding of consumer sentiment, it is difficult to improve consumer satisfaction. Furthermore, there is a need for an efficient system that can properly collect and analyze consumer data and reflect it in product development.

[1382] 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.

[1383] In this invention, the server includes: means for collecting consumer data consisting of purchase history, comparison history, and reviews; means for preprocessing the collected data; means for analyzing the preprocessed data and identifying consumer needs; means for a generative AI to generate new product ideas based on the analysis results; means for designing and manufacturing prototypes based on the generated product ideas; means for testing the prototypes and collecting feedback from consumers; means for analyzing the feedback and improving the product; means for recognizing emotions from consumer reviews using an emotion engine and reflecting the results in improving product characteristics; and means for manufacturing the improved products and offering them to the market. This enables product development that reflects consumer data and emotion analysis in detail.

[1384] "Purchase history" is a record of data about products a consumer has purchased in the past.

[1385] A "comparison and consideration history" is a record of data showing the comparison and consideration process that a consumer undertakes before purchasing a product.

[1386] A "review" is a written evaluation or impression left by a consumer about a product they have purchased.

[1387] "Consumer Data" is information consisting of purchase history, comparison history, and reviews.

[1388] "Preprocessing" is the process of removing unnecessary information from collected data and converting it into a form suitable for analysis.

[1389] "Analysis" is the process of analyzing data in detail to extract patterns and useful information.

[1390] "Generative AI" is a system that uses artificial intelligence technology to automatically generate new product ideas.

[1391] A "product idea" is a proposal that summarizes the concept and features of a new product.

[1392] A "prototype" is a model that is actually designed and manufactured based on a generated product idea.

[1393] "Feedback" refers to opinions and evaluations collected from consumers regarding prototypes.

[1394] The "sentiment engine" is a system that analyzes the sentiment of consumer reviews and identifies positive or negative sentiment.

[1395] "Data anonymization" is the process of removing personally identifiable information from data to protect privacy.

[1396] MODE FOR CARRYING OUT THE INVENTION

[1397] The present invention combines a system that uses consumer data, including purchase history, comparison history, and reviews, to rapidly develop products that meet market needs with an emotion engine that recognizes consumer emotions. Specific implementation methods are described below.

[1398] 1. Consumer Data Collection

[1399] The server automatically collects consumer data such as purchase history, comparison history, and reviews from online shopping platforms through APIs, such as Amazon Web Services (AWS) or Google Cloud Platform (GCP), and retrieves the data using the Python requests library.

[1400] 2. Data Preprocessing

[1401] The server preprocesses the collected data by converting it into a data frame using Pandas (a Python library), removing punctuation and special characters from text data, deleting unnecessary columns, and removing duplicate data, converting the data into a format suitable for analysis.

[1402] 3. Data Analysis

[1403] The server inputs the preprocessed data into the generative AI and sentiment engine. It uses natural language processing (NLP) technologies such as BERT and GPT-3 to analyze the sentiment of reviews and analyze market trends from purchase history and comparison history data. The sentiment engine also uses tools such as Amazon Comprehend to identify consumer sentiment.

[1404] 4. Product idea generation

[1405] The server uses the generative AI to generate new product ideas based on the analysis results. It uses OpenAI's API and Hugging Face's Transformers to automatically create multiple product ideas based on specified parameters. For example, enter "Generate a new smartphone idea based on the following specifications: ..." as the prompt.

[1406] 5. Prototype design and construction

[1407] The terminal (such as the design team's PC) uses AutoCAD or SolidWorks to create detailed design drawings based on the product ideas received from the server. The design drawings include the specific specifications proposed by the generative AI, and a prototype is then produced based on these.

[1408] 6. Test the prototype and gather feedback

[1409] The server provides the prototype to the test consumers and collects their feedback using Google Forms or SurveyMonkey. The feedback form contains the consumers' opinions and impressions about the prototype, which are analyzed by an emotion engine to identify the consumers' emotions.

[1410] 7. Analyzing Feedback and Improving Products

[1411] The server analyzes the collected feedback and identifies areas for improvement in the product. Using Pandas and SciPy, it performs detailed analysis of the feedback data and identifies areas for improvement. It notifies the design team of the results and creates an improved version.

[1412] 8. Manufacturing and bringing products to market

[1413] The server finalizes the product specifications and sends manufacturing instructions to the factory using the ERP system, after which the products are mass-produced and made available for sale on online shopping platforms such as Shopify, bringing the products to market.

[1414] In this way, the present invention is a system that covers a whole series of processes from data collection to product development, feedback collection, product improvement, and final market release, and by introducing an emotion engine, it is possible to analyze consumer emotions in detail and improve product characteristics to reflect those emotions. This allows products that provide high consumer satisfaction to be released to the market quickly.

[1415] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1416] Program processing flow

[1417] Step 1: Collect consumer data

[1418] The server collects consumer data (purchase history, comparison history, and reviews) from the online shopping platform.

[1419] Input: API endpoint of online shopping platform

[1420] Data processing: Purchase history, comparison history, and reviews are obtained in JSON format and saved in a database

[1421] Output: Raw data stored in a database

[1422] Specific operation: Makes an API call using Python's requests library and saves the retrieved data to a database.

[1423] Step 2: Preprocessing the data

[1424] The server performs pre-processing on the collected data.

[1425] Input: Raw data in the database

[1426] Data processing: removing punctuation and special characters, deleting unnecessary columns, removing duplicate data

[1427] Output: Cleaned data

[1428] Specific behavior: Convert to a data frame using Pandas and perform data cleaning operations.

[1429] Step 3: Analyze the data

[1430] The server feeds the pre-processed data into the generative AI and emotion engine.

[1431] Input: Preprocessed data

[1432] Data processing: Using natural language processing technology to analyze the sentiment of reviews and understand market trends

[1433] Output: Sentiment analysis results and market trend data

[1434] What it does: Perform sentiment analysis and market trend analysis using BERT, GPT-3, and Amazon Comprehend.

[1435] Step 4: Generate product ideas

[1436] The server uses a generative AI to generate new product ideas based on the analysis results.

[1437] Input: Sentiment analysis results and market trend data

[1438] Data processing: Providing product recommendations based on specified parameters

[1439] Output: New product ideas

[1440] What it does: Uses OpenAI APIs and Hugging Face Transformers to generate product ideas based on a given prompt.

[1441] Step 5: Design and build a prototype

[1442] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server.

[1443] Input: New product idea

[1444] Data processing: Creating detailed blueprints using CAD software

[1445] Output: Prototype blueprints

[1446] Specific Tasks: Using AutoCAD and SolidWorks, you will create blueprints for the design team to bring product ideas to life.

[1447] Step 6: Test the prototype and gather feedback

[1448] The server provides the prototype to monitor consumers and collects their feedback.

[1449] Input: Prototype, Feedback Form

[1450] Data processing: Collecting consumer ratings and comments and analyzing their sentiment

[1451] Output: Aggregated feedback and sentiment analysis results

[1452] What it does: Collect feedback using Google Forms and SurveyMonkey, and perform sentiment analysis using Amazon Comprehend.

[1453] Step 7: Analyze feedback and improve the product

[1454] The server analyzes the collected feedback and identifies product improvements.

[1455] Input: Aggregated feedback and sentiment analysis results

[1456] Data processing: Analyzing feedback data and extracting areas for improvement

[1457] Output: List of improvements

[1458] What it does: Uses Pandas and SciPy to perform detailed analysis of feedback and inform the design team of improvements.

[1459] Step 8: Manufacture and market your product

[1460] The server determines the final product specifications and sends manufacturing instructions to the factory.

[1461] Input: List of improvements, final specifications

[1462] Data processing: Finalizing manufacturing instructions and preparing for market launch

[1463] Output: Produced products, on sale

[1464] What it does: Uses an ERP system to send production instructions to factories and starts selling on e-commerce platforms like Shopify.

[1465] The above specific steps will realize a series of processes from product development to market launch using consumer data.

[1466] (Application example 2)

[1467] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1468] In the past, it was difficult to utilize consumer data to quickly develop products that met market needs in the product development process. Furthermore, there was a lack of technology to understand the emotions of drivers and passengers in real time and adjust in-car navigation and entertainment accordingly. Under these circumstances, it was difficult to develop products that maximize consumer satisfaction and provide a safe and comfortable driving environment for drivers and passengers.

[1469] 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.

[1470] In this invention, the server includes means for collecting consumer data including purchase history, comparison history, and reviews, means for preprocessing the collected data, means for analyzing the preprocessed data and identifying consumer needs, means for a generative AI to generate new product ideas based on the analysis results, means for designing and manufacturing prototypes based on the generated product ideas, means for testing the prototypes and collecting feedback from consumers, means for analyzing the feedback and improving the product, means for manufacturing the improved product and providing it to the market, means for collecting emotional data of drivers and passengers, means for anonymizing the collected emotional data, and means for providing driving routes and entertainment based on the emotional data. This enables the development and provision of products that accurately reflect consumer emotions and needs, and a safe and comfortable driving experience that takes into account the emotions of drivers and passengers.

[1471] "Consumer Data" is information about consumer behavior and opinions, such as purchase history, comparison history, and reviews.

[1472] "Preprocessing" means removing unnecessary information from raw data and converting it into a form suitable for analysis.

[1473] "Analyzing" means using pre-processed data to extract information and patterns and make sense of them.

[1474] "Generative AI" is a technology that uses artificial intelligence algorithms to automatically generate new product ideas and proposals.

[1475] A "product idea" is a concept for a new product or service that is generated with consumer needs and emotions in mind.

[1476] A "prototype" is an early stage product that embodies a generated product idea.

[1477] "Feedback" refers to reaction information such as evaluations and opinions from consumers who have used the prototype.

[1478] "Improvement" means improving the product's specifications and features based on collected feedback.

[1479] "Emotion data" is information that indicates the emotional state of the driver or passengers, obtained from their faces, voices, etc.

[1480] "Navigation" refers to systems and functions that provide the optimal route to a destination.

[1481] "Entertainment" refers to content such as music and videos that provide enjoyment and satisfaction.

[1482] "Anonymization" is a method of removing or transforming personally identifiable information to protect privacy.

[1483] "Real-time" refers to the processing and provision of information immediately, without delay.

[1484] The present invention provides a system for more accurately grasping market needs and providing products by combining consumer data and emotion data. Specific embodiments of the system are described below.

[1485] Hardware and software used

[1486] The specific hardware and software used as servers and terminals include the following:

[1487] Hardware:

[1488] Camera: Used to recognize the faces of the driver and passengers.

[1489] Microphone: Used to collect audio data.

[1490] Computer: A server or PC for analyzing and storing data.

[1491] software:

[1492] OpenCV: A library for acquiring and processing camera images.

[1493] DeepFace: A library for facial expression analysis.

[1494] Librosa: A library for reading and parsing audio data.

[1495] NLP technologies: Libraries for natural language processing (e.g. spaCy).

[1496] AI generative model: An algorithm that uses generative AI to automatically generate new product ideas.

[1497] Data processing flow

[1498] 1. Data Collection:

[1499] The server collects consumer and emotional data from online shopping platforms and in-car sensors. Consumer data includes purchase history, comparison shopping history, and reviews, while emotional data includes facial expressions and voice recordings of drivers and passengers.

[1500] 2. Data preprocessing:

[1501] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters, deleting unnecessary parts from image data, and removing noise from audio data.

[1502] 3. Data Analysis:

[1503] The server analyzes the preprocessed data, using natural language processing (NLP) technology to analyze the sentiment of reviews, and analyzes market trends and the characteristics of popular products based on purchase history and comparison history. It also identifies the emotions of drivers and passengers through facial expression and voice analysis.

[1504] 4. Product idea generation and provision:

[1505] The server generates new product ideas using a generative AI model. Based on the analysis results, the generative AI automatically creates multiple ideas taking into account specific parameters (price range, functionality, design, etc.). It also provides driving directions and entertainment based on emotional data.

[1506] Specific examples

[1507] When a consumer purchases a home appliance on an online platform, the purchase history and reviews are collected on a server. Sentiment analysis of the reviews is performed and it is discovered that many consumers express positive emotions such as "very satisfied" with the features of a particular home appliance. Based on this result, the generative AI proposes a product idea for a "high-performance, cost-effective home appliance." At the same time, the system uses the in-car camera and microphone to collect the driver's facial expressions and voice. If it determines that the driver is nervous, it plays relaxing music and suggests a safe route.

[1508] Example prompt for a generative AI model:

[1509] "Suggest ideas for home appliances that consumers would be happy to purchase."

[1510] "If you sense a driver is nervous, suggest the most relaxing route."

[1511] "If passengers are bored, offer them music recommendations."

[1512] The above is a specific description of the "Mode for Carrying Out the Invention." The present invention enables highly accurate market response by combining consumer data and emotion data.

[1513] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1514] Step 1:

[1515] Collecting consumer and sentiment data

[1516] The server collects consumer and emotional data from online shopping platforms and in-car sensors. Input data includes purchase history, comparison shopping history, reviews, driver and passenger facial expressions, and voice. The output is the collected raw data. Specifically, the server uses an API to obtain purchase history and reviews from online shopping platforms, and uses the camera and microphone in the in-car sensors to capture driver and passenger emotional data.

[1517] Step 2:

[1518] Data Preprocessing

[1519] The server performs preprocessing on the collected data. The input is the raw data collected in step 1. Specific data processing includes removing punctuation and special characters from the text data and removing noise from the audio data. The output is cleaned data. Specifically, the text data is cleaned using regular expressions, and the audio data is denoised using Librosa.

[1520] Step 3:

[1521] Anonymizing Emotional Data

[1522] The server anonymizes the collected emotional data. The input is the emotional data preprocessed in step 2. Data calculation involves deleting or encrypting information that can identify a specific individual. The output is anonymized emotional data. Specific operations include removing features that can identify an individual from facial expression data and assigning an identification code to the analysis results of the voice data.

[1523] Step 4:

[1524] Data analysis

[1525] The server analyzes the preprocessed consumer data and sentiment data. The input is the cleaned and anonymized data obtained in steps 2 and 3. Specific data calculations include analyzing the sentiment of reviews using natural language processing techniques and analyzing market trends from purchase history and comparison history. The output is the analysis results. Operations include calculating sentiment scores based on specific keywords using an NLP library and extracting trend information from the database.

[1526] Step 5:

[1527] Product idea generation

[1528] The server uses the generative AI model to generate new product ideas based on the analysis results. The input is the analysis results from step 4. As a data calculation, the generative AI generates product ideas based on specific parameters (price, function, design, etc.). The output is the generated product idea. Specifically, the server inputs market trends and sentiment scores into the generative AI model, and generates product ideas based on the prompt text.

[1529] Step 6:

[1530] Prototype design and construction

[1531] The terminal (such as the design team's PC) creates detailed design drawings based on the product idea generated in step 5 and produces a prototype. The input is the generated product idea. As data calculation, a design drawing is created using CAD software and prototype production instructions are output. The output is production instructions and a prototype. As an operation, a detailed design is created using CAD software and prototype production instructions are sent to the factory.

[1532] Step 7:

[1533] Testing prototypes and gathering feedback

[1534] The server provides the prototype to test consumers and collects their feedback. The input is the test results of the test consumers. Specific data processing involves collecting evaluations and opinions from testers and analyzing them with an emotion engine. The output is feedback data. The system operates by collecting feedback through online forms and direct interviews, and analyzing the data with an emotion engine.

[1535] Step 8:

[1536] Feedback analysis and product improvement

[1537] The server analyzes the collected feedback and improves the product. The input is the feedback data from step 7. The data calculation analyzes the collected feedback and identifies necessary improvements. The output is improvement instructions. The operation analyzes the feedback data and integrates the sentiment score and user comments to derive improvement suggestions.

[1538] Step 9:

[1539] Manufacturing and bringing products to market

[1540] The server finalizes the product specifications and sends manufacturing instructions to the factory. The input is the improvement instructions from step 8. As a data calculation, it formulates a manufacturing plan and outputs manufacturing instructions. The output is a mass-produced product. As an operation, it instructs the manufacturing department on the production plan and starts selling the completed product on the online platform.

[1541] Step 10:

[1542] Providing driving directions and entertainment based on emotion data

[1543] The server provides optimal driving routes and entertainment based on the emotional data of the driver and passengers. The input is the emotional data collected in step 1. The data calculation involves analyzing the emotional data and selecting routes and content based on it. The output is the proposed route and entertainment. The operation involves selecting a route that will relax the driver based on the emotional data and selecting music and videos to provide.

[1544] The above is the flow of processing in the system that realizes the application example.

[1545] 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.

[1546] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1547] 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.

[1548] [Fourth embodiment]

[1549] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1550] 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.

[1551] 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).

[1552] 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.

[1553] 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.

[1554] 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).

[1555] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1556] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1557] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1558] 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.

[1559] 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.

[1560] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1561] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1562] The present invention is a system for quickly developing products that capture market needs by utilizing consumer data, and specific implementation details thereof will be described below.

[1563] System Embodiments

[1564] Consumer Data Collection

[1565] The server automatically collects consumer data (purchase history, comparison history, reviews) from online shopping platforms. It periodically pulls the data using APIs and stores it in a database. The data is anonymized to protect privacy.

[1566] Specific examples

[1567] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[1568] Data Preprocessing

[1569] The server preprocesses the collected data, specifically cleaning text data (such as reviews), deleting unnecessary data, and eliminating duplicates in purchase history data.

[1570] Specific examples

[1571] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[1572] Analyzing the data

[1573] The server inputs the preprocessed data into the AI ​​generator, which analyzes consumer needs and market trends. The AI ​​uses natural language processing technology to analyze the sentiment of reviews and identify popular products and their features based on purchase history.

[1574] Specific examples

[1575] The server performs a sentiment analysis of the reviews and discovers that many consumers highly praise the camera features of a particular smartphone.

[1576] Product idea generation

[1577] The server uses the generative AI to generate new product ideas based on the analysis results. The AI ​​considers specific parameters (price range, functionality, design, etc.) and provides product ideas that are desired by many consumers.

[1578] Specific examples

[1579] The generative AI will suggest "mid-priced smartphones equipped with high-performance cameras."

[1580] Prototype design and construction

[1581] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[1582] Specific examples

[1583] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[1584] Testing prototypes and gathering feedback

[1585] The server provides the prototype to the monitor consumers and collects their feedback, which includes opinions and evaluations of the consumers regarding the prototype.

[1586] Specific examples

[1587] The prototype will be distributed to 20 testers to collect feedback such as "The camera image quality is good, but the battery life is poor."

[1588] Analyzing feedback and improving products

[1589] The server analyzes the collected feedback and identifies necessary improvements, which the design team then uses to refine the prototype.

[1590] Specific examples

[1591] The design team designs an improved smartphone with increased battery capacity and improved power efficiency.

[1592] Manufacturing and bringing products to market

[1593] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[1594] Specific examples

[1595] The improved smartphone is mass-produced and begins selling on online platforms, where it is purchased by many consumers and receives positive reviews.

[1596] summary

[1597] By repeating these steps, the present invention is a system that maximizes the use of consumer data and enables the rapid planning and manufacturing of products that meet market needs, significantly shortening the lengthy conventional product development process and enabling rapid response to changing consumer needs.

[1598] The processing flow will be explained below.

[1599] Step 1:

[1600] The server periodically collects consumers' purchase history, comparison shopping history, and reviews using the online shopping platform API. The collected data is stored in a database. When collecting the data, it is anonymized to prevent personal identification.

[1601] Step 2:

[1602] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters, as well as removing unnecessary columns in purchase history data and deleting duplicate data.

[1603] Step 3:

[1604] The server inputs the preprocessed data into the generation AI, which uses natural language processing (NLP) technology to analyze the sentiment of the reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history.

[1605] Step 4:

[1606] The server generates new product ideas based on the results of the analysis by the generative AI, which automatically creates multiple ideas by taking into account specific parameters (e.g., price range, functionality, design, etc.).

[1607] Step 5:

[1608] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[1609] Step 6:

[1610] A prototype device is produced based on the design drawings. The prototype is then assembled in the factory using the specified materials and parts. Once the prototype is complete, a quality check is carried out.

[1611] Step 7:

[1612] The server provides the prototype to selected test consumers and tests its usage. The test consumers use the prototype and send their impressions and evaluations to the server as feedback.

[1613] Step 8:

[1614] The server analyzes the collected feedback, identifies areas that need improvement based on consumer opinions and ratings, and generates improvement proposals based on those. These improvement proposals are provided as feedback to the design team.

[1615] Step 9:

[1616] The prototype device is redesigned based on the proposed improvements, new blueprints are created that reflect the improvements, and the device is sent back to the factory to produce an improved prototype.

[1617] Step 10:

[1618] The server then finalizes the improved final product specifications and sends manufacturing instructions to the factory, which then goes into mass production and mass-produces the product based on the finalized specifications.

[1619] Step 11:

[1620] The server lists the manufactured products on an online shopping platform and starts selling them, monitors sales, and optimizes marketing strategies as needed.

[1621] Conclusion

[1622] These are the specific processing steps of this system, which makes it possible to make maximum use of consumer data and quickly and efficiently develop and provide products that meet market needs.

[1623] Example 1

[1624] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1625] In the conventional product development process, it was difficult to quickly grasp consumer needs and then plan and manufacture new products based on those needs. Furthermore, data collection and analysis, product idea generation, and product improvement were all done manually, which was time-consuming and costly. This resulted in an inability to respond quickly to changing consumer needs, and a decline in market competitiveness.

[1626] 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.

[1627] In this invention, the server includes means for collecting consumer data from an online shopping platform, means for periodically obtaining the collected data using an API and storing it in a database, means for preprocessing the collected data and deleting unnecessary and duplicate data, means for analyzing the preprocessed data and identifying consumer needs and market trends, means for using a generative AI to generate new product ideas based on the analysis results, means for creating detailed blueprints based on the generated product ideas and designing and manufacturing prototypes, means for providing the prototypes to monitor consumers and collecting feedback, means for analyzing the collected feedback and improving the product, and means for determining final product specifications, manufacturing the improved product, and providing it to the market. This makes it possible to make maximum use of consumer data and efficiently plan, manufacture, and launch products that meet market needs quickly.

[1628] "Consumer data" refers to information, including consumer purchase history, comparison history, and reviews, that reflects consumer behavior and opinions.

[1629] An "online shopping platform" is a web-based service for selling and purchasing goods over the Internet.

[1630] An "API" is an interface that allows different software applications to communicate and a protocol for using specific services or functions.

[1631] "Data preprocessing" is the process of preparing collected raw data in an analyzable form, and includes tasks such as removing unnecessary and duplicate data and cleaning text data.

[1632] "Generative AI" refers to artificial intelligence that generates new content and ideas based on human instructions, particularly using natural language processing and machine learning techniques.

[1633] A "prototype" is a test product created to verify the design and performance of a final product, and is used to demonstrate and evaluate product designs.

[1634] "Feedback" refers to the evaluations and opinions collected from consumers who have used prototypes, and is information that is used to improve the product and determine its final specifications.

[1635] "Privacy protection" refers to measures to anonymize personal information from collected data so that individuals cannot be identified.

[1636] MODE FOR CARRYING OUT THE INVENTION

[1637] This invention is a system that uses consumer data to rapidly develop products that meet market needs. This system uses consumer data collected from online shopping platforms, generates new product ideas using generative AI, and designs, manufactures, and sells products based on those ideas.

[1638] Consumer Data Collection

[1639] The server periodically collects consumer data (purchase history, comparison shopping history, reviews) from the online shopping platform using APIs. The collected data is stored in a database and anonymized to protect privacy. Consumer data collection is performed using a scheduler that automates database updates and an anonymization tool.

[1640] As a specific example, consider a situation where a user purchases a home appliance from an online shopping platform, and the history and reviews of the purchase are collected by a server.

[1641] Data Preprocessing

[1642] The server pre-processes the collected data. Text data is cleaned by removing unnecessary symbols and tags, and duplicate purchase history data is deduplicated. This pre-processing uses text analysis tools and deduplication algorithms to convert the data into a format suitable for analysis.

[1643] For example, the server removes unnecessary symbols and duplicate data from the reviews and converts them into a format suitable for analysis.

[1644] Analyzing the data

[1645] The server inputs the preprocessed data into a generative AI model to analyze consumer needs and market trends. The generative AI model uses natural language processing technology to analyze the sentiment of reviews and extract popular products and their features from purchase history.

[1646] A specific example might be a situation where a server performs sentiment analysis of reviews and discovers that many consumers highly praise the camera features of a particular smartphone.

[1647] Product idea generation

[1648] The server generates new product ideas based on the analysis results provided by the generative AI, which considers parameters such as price range, functionality, and design to propose product ideas that will appeal to many consumers.

[1649] For example, the generative AI suggests a "mid-priced smartphone with a high-performance camera."

[1650] Prototype design and construction

[1651] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. It then uses the drawing to create a prototype and sends production instructions to the factory, where the prototype is actually produced.

[1652] For example, a design team might create a prototype smartphone that is lightweight and equipped with a high-performance camera.

[1653] Testing prototypes and gathering feedback

[1654] The server provides the prototype to the monitor consumers and collects feedback from the consumers, including their evaluation of the prototype and suggestions for improvement.

[1655] For example, you could distribute a prototype to 20 testers and collect feedback such as, "The camera image quality is good, but the battery life is poor."

[1656] Analyzing feedback and improving products

[1657] The server analyzes the collected feedback and identifies product improvements, which the design team uses to improve the prototype and send the improvements back to the factory.

[1658] As a concrete example, a design team designs an improved version of a smartphone with increased battery capacity and improved power efficiency.

[1659] Manufacturing and bringing products to market

[1660] The server finalizes the product specifications and sends manufacturing instructions to the factory, where the product is mass-produced and then made available for sale on the online shopping platform.

[1661] For example, an improved smartphone is mass-produced and launched for sale on an online platform, where it is purchased by many consumers and receives positive reviews.

[1662] Specific prompt examples

[1663] "Analyze the purchase history and reviews of home appliances on online platforms to generate ideas for the next product we should develop."

[1664] By repeating these steps, the present invention is a system that maximizes the use of consumer data and enables the rapid planning and manufacturing of products that meet market needs. This system significantly shortens the conventional product development process and makes it possible to respond quickly to changing consumer needs.

[1665] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1666] Step 1: Collect consumer data

[1667] The server collects consumer data from online shopping platforms using APIs. Specifically, the server sends requests to API endpoints to obtain data such as purchase history, comparison history, and reviews.

[1668] Input: Consumer data retrieved from API endpoints

[1669] Output: Consumer data stored in a database

[1670] Specific behavior:

[1671] The server periodically runs scheduled tasks and sends API requests.

[1672] Receive the acquired data and process it using anonymization tools to protect privacy.

[1673] The anonymized data is stored in a database.

[1674] Step 2: Preprocessing the data

[1675] The server preprocesses the collected data: text data (such as reviews) is cleaned and unnecessary symbols and tags are removed, and purchase history data is deduplicated and converted into a format suitable for analysis.

[1676] Input: Raw data stored in a database

[1677] Output: Preprocessed data

[1678] Specific behavior:

[1679] The server uses text analysis tools to remove unnecessary symbols and tags from the reviews.

[1680] Use a duplicate data detection algorithm to remove duplicate purchase history.

[1681] Save the preprocessed data to a new database table.

[1682] Step 3: Analyze the data

[1683] The server inputs the preprocessed data into a generative AI model to analyze consumer needs and market trends. The generative AI model uses natural language processing technology to analyze the sentiment of reviews and extract popular products and their features from purchase history.

[1684] Input: Preprocessed data

[1685] Output: Analysis results

[1686] Specific behavior:

[1687] The server converts the preprocessed data into an input format for the generative AI model.

[1688] Input data into the generative AI model and wait for analysis to complete.

[1689] The analysis results are obtained and stored in a database.

[1690] Step 4: Generate product ideas

[1691] The server generates new product ideas based on the analysis results provided by the generative AI, which considers parameters such as price range, functionality, and design to propose product ideas that consumers desire.

[1692] Input: Analysis results

[1693] Output: Product idea

[1694] Specific behavior:

[1695] The server inputs prompts into the generative AI model based on the analysis results.

[1696] Evaluate the generated product ideas and extract feasible ideas.

[1697] The extracted ideas are stored in a database and notified to the design team.

[1698] Step 5: Design and build a prototype

[1699] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server, creates prototypes based on the drawings, and sends production instructions to the factory.

[1700] Input: Product idea

[1701] Output: Prototype blueprints and prototypes

[1702] Specific behavior:

[1703] The design team uses design software to create detailed blueprints.

[1704] Send the blueprint to the factory manufacturing system.

[1705] The factory produces prototypes based on the design drawings.

[1706] Step 6: Test the prototype and gather feedback

[1707] The server provides the prototype to the test consumers and collects their feedback, including their evaluation of the prototype and specific suggestions for improvement.

[1708] Input: Monitor consumer ratings and opinions

[1709] Output: Feedback data

[1710] Specific behavior:

[1711] The server provides the prototype to consumers who participate in the evaluation test.

[1712] The server collects feedback through online surveys and interviews.

[1713] Store the collected feedback in a database.

[1714] Step 7: Analyze feedback and improve the product

[1715] The server analyzes the collected feedback and identifies necessary improvements, which the design team then uses to refine the prototype.

[1716] Input: Feedback data

[1717] Output: Improvements and tweaks

[1718] Specific behavior:

[1719] The server analyzes the feedback data and identifies areas for improvement.

[1720] The server notifies the design team of improvements.

[1721] The design team modifies the design drawings based on the improvements and sends them back to the factory.

[1722] Step 8: Manufacture and market your product

[1723] The server finalizes the product specifications and sends manufacturing instructions to the factory, which then mass-produces the product and starts selling it on the online shopping platform.

[1724] Input: Final product specifications

[1725] Output: Commercially available product

[1726] Specific behavior:

[1727] The server sends the final product specifications to the factory.

[1728] The factory begins mass production and delivers the finished products to the warehouse.

[1729] The server uploads the product data to the online shopping platform and starts selling.

[1730] (Application example 1)

[1731] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1732] In the traditional product development process, it takes a long time and costs a lot of money to properly understand consumer needs and generate new product ideas based on them. Furthermore, even product recommendation systems that utilize consumer data often do not provide personalized recommendations, making it difficult to meet consumer expectations. Furthermore, protecting the privacy of collected consumer data is also a major issue. Therefore, an efficient system that solves these problems is needed.

[1733] 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.

[1734] In this invention, the server includes means for collecting consumer data consisting of purchase history, comparison history, and reviews, means for preprocessing the collected data, means for analyzing the preprocessed data and identifying consumer needs, means for a generative AI to generate new product ideas based on the analysis results, means for designing and manufacturing prototypes based on the generated product ideas, means for testing the prototypes and collecting feedback from consumers, means for analyzing the feedback and improving the products, means for manufacturing the improved products and providing them to the market, and means for personalizing product recommendations based on the collected data. This makes it possible to plan and manufacture products that meet market needs effectively in a short period of time, and to provide more personalized product recommendations.

[1735] "Consumer Data" refers to data consisting of purchase history, comparison history, and reviews.

[1736] "Means of collection" refers to mechanisms for automatically obtaining consumer data from online shopping platforms and other data sources.

[1737] "Preprocessing means" refers to a mechanism for cleaning collected data, removing unnecessary information, and converting it into a format suitable for analysis.

[1738] "Means of analysis" refers to the data analysis process to identify consumer needs based on collected and pre-processed data.

[1739] "Generative AI" refers to artificial intelligence technology that automatically generates new product ideas based on analysis results.

[1740] "Means of designing and producing prototypes" refers to the process of creating detailed design drawings based on the generated product ideas and producing prototypes.

[1741] "Means of testing prototypes and gathering feedback" refers to the process of providing prototypes to consumers and gathering their impressions and opinions.

[1742] "Means for analyzing feedback and improving the product" refers to the process of identifying improvements to the prototype based on the collected feedback and improving the design and functionality.

[1743] "Means of manufacturing and marketing" refers to the process of mass-producing an improved product and selling it to consumers.

[1744] "Means for personalizing product recommendations" refers to a system that recommends the most suitable products to each user based on collected consumer data.

[1745] The system for implementing this invention automates the process of collecting consumer data and quickly developing products that meet market needs. This system is primarily composed of a server, terminals, and users.

[1746] Server Functions and Processing

[1747] 1. Data Collection:

[1748] The server automatically collects consumer data, consisting of purchase history, comparison history, and reviews, from online shopping platforms and other data sources using APIs. The data is periodically pulled, anonymized to protect privacy, and stored in a database.

[1749] 2. Data Preprocessing:

[1750] The server preprocesses the collected data. Specifically, it cleans text data (such as reviews) and deletes unnecessary data. It also deduplicates purchase history data. This converts the data into a format suitable for analysis.

[1751] 3. Data Analysis:

[1752] The pre-processed data is then input into the generative AI, which uses natural language processing technology to analyze the sentiment of the reviews and identify popular products and their features based on purchase history. Based on the results of this analysis, consumer needs and market trends are identified.

[1753] 4. Product idea generation:

[1754] The server uses generative AI to generate new product ideas based on the analysis results. The AI ​​considers specific parameters (price range, functionality, design, etc.) and provides product ideas that are desired by many consumers.

[1755] Terminal functions and processing

[1756] 1. Prototype design and construction:

[1757] The terminal (such as the design team's computer) creates detailed design drawings based on the product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[1758] 2. Test the prototype and gather feedback:

[1759] The prototype is provided to test consumers, and the server collects their feedback, including their opinions and evaluations of the prototype.

[1760] Server feedback processing

[1761] 1. Feedback Analysis and Product Improvement:

[1762] The server analyzes the collected feedback and identifies necessary improvements. The design team then improves the prototype based on the feedback. For example, if the feedback is that the camera image quality is good but the battery life is poor, the team will increase the battery capacity and improve power efficiency.

[1763] 2. Manufacture and market the product:

[1764] The final product specifications are finalized and manufacturing instructions are sent to the factory, where mass production begins. The product is then sold on an online shopping platform, where it is purchased by many consumers and receives positive reviews.

[1765] Personalized product recommendations

[1766] The server personalizes product recommendations based on the collected data. It analyzes each user's purchase and browsing history to provide the functionality to recommend the most suitable products, improving the user experience and increasing sales.

[1767] Prompt Sentence Examples

[1768] For example, suppose you want to collect and analyze data about "smartwatches." Here are some example prompts to input to the generative AI:

[1769] Generate new product ideas based on the following popular items and sentiments: {'Smartwatch Model A': 123, 'Smartwatch Model B' : 95, 'Smartwatch Model C': 80} and [0.75, 0.6, -0.3, 0.9, 0.8]

[1770] Based on these prompts, the generative AI will provide new product ideas such as "a mid-priced smartwatch with advanced health management features."

[1771] As described above, the system of the present invention makes it possible to make maximum use of consumer data and quickly plan and manufacture products that meet market needs.

[1772] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1773] Step 1: Data collection

[1774] The server automatically collects consumer data, including purchase history, comparison history, and reviews, from online shopping platforms and other data sources using APIs, periodically sending API requests and storing the retrieved data in a database in JSON format.

[1775] Input: Raw data obtained via API

[1776] Output: Consumer data in JSON format

[1777] Step 2: Data Preprocessing

[1778] The server preprocesses the collected data. Specifically, it cleans the text data (reviews) and deletes unnecessary data. It also eliminates duplicates in the purchase history data and converts it into a format suitable for analysis.

[1779] Input: Consumer data in JSON format

[1780] Output: Cleaned dataset

[1781] Step 3: Data analysis

[1782] The server inputs the preprocessed data into the generative AI to analyze consumer needs and market trends. Specifically, it uses natural language processing technology to analyze the sentiment of reviews and identify popular products and their features based on purchase history.

[1783] Input: Cleaned dataset

[1784] Output: Analysis of consumer needs and market trends

[1785] Step 4: Product idea generation

[1786] The server uses a generative AI to generate new product ideas based on the analysis results. The AI ​​receives a prompt and generates new product ideas taking into account specific parameters (price range, functionality, design, etc.).

[1787] Input: Consumer needs and market trend analysis results, prompt text

[1788] Output: New product ideas

[1789] Step 5: Design and build a prototype

[1790] The terminal (such as the design team's computer) creates detailed design drawings based on the new product ideas received from the server and produces prototypes. The production instructions are sent to the factory, where the prototypes are actually produced.

[1791] Input: New product idea

[1792] Output: Prototype

[1793] Step 6: Test the prototype and gather feedback

[1794] The prototypes are provided to test consumers, and their feedback is collected by the server. Specifically, their impressions and evaluations of the product are collected in the form of questionnaires and reviews.

[1795] Input: Prototype

[1796] Output: Feedback data

[1797] Step 7: Analyze feedback and improve the product

[1798] The server analyzes the collected feedback data and identifies necessary improvements, which the design team then uses to refine the prototype, implementing specific improvements such as increasing battery capacity.

[1799] Input: Feedback data

[1800] Output: Improvements and New Designs

[1801] Step 8: Manufacture and market your product

[1802] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[1803] Input: Improved product specifications

[1804] Output: Products delivered to the market

[1805] Step 9: Personalize product recommendations

[1806] The server personalizes product recommendations based on the collected data, analyzing each user's purchase and browsing history to recommend the most suitable products, improving the user experience and increasing sales.

[1807] Input: User purchase history and browsing history

[1808] Output: Personalized product recommendations

[1809] 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.

[1810] The present invention combines a system that uses consumer data to rapidly develop products that capture market needs with an emotion engine that recognizes user emotions. Specific implementation details are described below.

[1811] System Embodiments

[1812] Consumer Data Collection

[1813] The server automatically collects consumer data (purchase history, comparison history, and reviews) from online shopping platforms. The collected data is stored in a database. When collecting the data, it is anonymized so that individuals cannot be identified.

[1814] Specific examples

[1815] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[1816] Data Preprocessing

[1817] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters. It also removes unnecessary columns from purchase history data and deletes duplicate data.

[1818] Specific examples

[1819] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[1820] Analyzing the data

[1821] The server inputs the preprocessed data into the generation AI and emotion engine. The generation AI uses natural language processing (NLP) technology to analyze the sentiment of reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history. The emotion engine identifies consumer sentiment from reviews.

[1822] Specific examples

[1823] The server performs sentiment analysis on the reviews and discovers that many consumers express positive sentiment, such as being "very satisfied," with the camera features of a particular smartphone.

[1824] Product idea generation

[1825] The server generates new product ideas based on the results of the generative AI and emotion engine analysis. The generative AI automatically creates multiple ideas, taking into account specific parameters (price range, functionality, design, etc.).

[1826] Specific examples

[1827] As a result of sentiment analysis, the generative AI proposes a product idea: a mid-priced smartphone equipped with a high-performance camera.

[1828] Prototype design and construction

[1829] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[1830] Specific examples

[1831] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[1832] Testing prototypes and gathering feedback

[1833] The server provides the prototype to the monitor consumers and collects their feedback. The feedback includes the consumers' opinions and evaluations of the prototype. The emotion engine also analyzes the feedback to identify the consumers' emotions.

[1834] Specific examples

[1835] The prototype is distributed to 20 testers and feedback is collected, such as "The camera image quality is good, but the battery life is poor." The emotion engine identifies positive and negative emotions from the testers' feedback.

[1836] Analyzing feedback and improving products

[1837] The server identifies necessary improvements based on the collected feedback and the emotion engine analysis, and the design team refines the prototype based on the feedback and emotion analysis.

[1838] Specific examples

[1839] The design team designs an improved smartphone with increased battery capacity and improved power efficiency.

[1840] Manufacturing and bringing products to market

[1841] The server finalizes the product specifications and sends manufacturing instructions to the factory, where mass production takes place, and then the product is made available for sale on the online shopping platform.

[1842] Specific examples

[1843] The improved smartphone is mass-produced and begins selling on online platforms, where it is purchased by many consumers and receives positive reviews.

[1844] summary

[1845] This invention is a system that combines consumer data with an emotion engine to enable product planning and manufacturing that more accurately reflects consumer emotions. By repeating these steps, it becomes possible to make the most of consumer data and quickly and efficiently develop and provide products that meet market needs.

[1846] The processing flow will be explained below.

[1847] Step 1:

[1848] The server periodically collects consumers' purchase history, comparison shopping history, and reviews using the online shopping platform API. The collected data is stored in a database. When collecting the data, it is anonymized to prevent personal identification.

[1849] Specific examples

[1850] A user purchases a home appliance on an online platform, and the history and reviews are collected on the server.

[1851] Step 2:

[1852] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters. It also removes unnecessary columns from purchase history data and deletes duplicate data.

[1853] Specific examples

[1854] The server removes unnecessary symbols and duplicate data from the review and converts it into a format suitable for analysis.

[1855] Step 3:

[1856] The server inputs the preprocessed data into the generation AI and emotion engine. The generation AI uses natural language processing (NLP) technology to analyze the sentiment of reviews and analyze market trends and the characteristics of popular products based on purchase history and comparison history. The emotion engine identifies consumer sentiment from reviews.

[1857] Specific examples

[1858] The server performs sentiment analysis on the reviews and discovers that many consumers express positive sentiment, such as being "very satisfied," with the camera features of a particular smartphone.

[1859] Step 4:

[1860] The server generates new product ideas based on the results of the generative AI and emotion engine analysis. The generative AI automatically creates multiple ideas, taking into account specific parameters (price range, functionality, design, etc.).

[1861] Specific examples

[1862] As a result of sentiment analysis, the generative AI proposes a product idea: a mid-priced smartphone equipped with a high-performance camera.

[1863] Step 5:

[1864] The terminal (such as the design team's PC) creates a detailed design drawing based on the product idea received from the server. The design drawing includes the specific specifications proposed by the generative AI. The design team then sends instructions to the factory to create a prototype based on this drawing.

[1865] Specific examples

[1866] A design team creates a prototype smartphone that is lightweight and equipped with a high-performance camera.

[1867] Step 6:

[1868] The server issues instructions to the factory to manufacture a prototype based on the design drawings. The factory assembles the prototype using the specified materials and parts. Once the prototype is completed, a quality check is performed.

[1869] Specific examples

[1870] At the factory, prototype smartphones pass quality checks and are ready for testing.

[1871] Step 7:

[1872] The server provides the prototype to selected monitor consumers and tests its usage. The users (monitor consumers) use the prototype and send their impressions and evaluations as feedback to the server. The emotion engine also analyzes the feedback and identifies the consumer's emotions.

[1873] Specific examples

[1874] The prototype is distributed to 20 testers and feedback is collected, such as "The camera image quality is good, but the battery life is poor." The emotion engine identifies positive and negative emotions from the testers' feedback.

[1875] Step 8:

[1876] The server identifies necessary improvements based on the collected feedback and the analysis results of the emotion engine. The design team improves the prototype based on the feedback and emotion analysis. A new improved design is created and another prototype is produced.

[1877] Specific examples

[1878] The design team designs an improved smartphone with increased battery capacity and improved power efficiency, and the factory builds prototypes of the improved version.

[1879] Step 9:

[1880] The server then finalizes the improved final product specifications and sends manufacturing instructions to the factory, which then goes into mass production and mass-produces the product based on the finalized specifications.

[1881] Specific examples

[1882] The improved smartphone will be mass-produced and made available for sale on online platforms.

[1883] Step 10:

[1884] The server lists the manufactured products on an online shopping platform and starts selling them, monitors sales, and optimizes marketing strategies as needed.

[1885] Specific examples

[1886] The product goes on sale on an online shopping platform, is purchased by many consumers, and receives positive reviews.

[1887] Example 2

[1888] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1889] In today's market, it is difficult to quickly and accurately grasp consumer needs and develop products that meet those needs. Furthermore, because product development is carried out without a detailed understanding of consumer sentiment, it is difficult to improve consumer satisfaction. Furthermore, there is a need for an efficient system that can properly collect and analyze consumer data and reflect it in product development.

[1890] 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.

[1891] In this invention, the server includes: means for collecting consumer data consisting of purchase history, comparison history, and reviews; means for preprocessing the collected data; means for analyzing the preprocessed data and identifying consumer needs; means for a generative AI to generate new product ideas based on the analysis results; means for designing and manufacturing prototypes based on the generated product ideas; means for testing the prototypes and collecting feedback from consumers; means for analyzing the feedback and improving the product; means for recognizing emotions from consumer reviews using an emotion engine and reflecting the results in improving product characteristics; and means for manufacturing the improved products and offering them to the market. This enables product development that reflects consumer data and emotion analysis in detail.

[1892] "Purchase history" is a record of data about products a consumer has purchased in the past.

[1893] A "comparison and consideration history" is a record of data showing the comparison and consideration process that a consumer undertakes before purchasing a product.

[1894] A "review" is a written evaluation or impression left by a consumer about a product they have purchased.

[1895] "Consumer Data" is information consisting of purchase history, comparison history, and reviews.

[1896] "Preprocessing" is the process of removing unnecessary information from collected data and converting it into a form suitable for analysis.

[1897] "Analysis" is the process of analyzing data in detail to extract patterns and useful information.

[1898] "Generative AI" is a system that uses artificial intelligence technology to automatically generate new product ideas.

[1899] A "product idea" is a proposal that summarizes the concept and features of a new product.

[1900] A "prototype" is a model that is actually designed and manufactured based on a generated product idea.

[1901] "Feedback" refers to opinions and evaluations collected from consumers regarding prototypes.

[1902] The "sentiment engine" is a system that analyzes the sentiment of consumer reviews and identifies positive or negative sentiment.

[1903] "Data anonymization" is the process of removing personally identifiable information from data to protect privacy.

[1904] MODE FOR CARRYING OUT THE INVENTION

[1905] The present invention combines a system that uses consumer data, including purchase history, comparison history, and reviews, to rapidly develop products that meet market needs with an emotion engine that recognizes consumer emotions. Specific implementation methods are described below.

[1906] 1. Consumer Data Collection

[1907] The server automatically collects consumer data such as purchase history, comparison history, and reviews from online shopping platforms through APIs, such as Amazon Web Services (AWS) or Google Cloud Platform (GCP), and retrieves the data using the Python requests library.

[1908] 2. Data Preprocessing

[1909] The server preprocesses the collected data by converting it into a data frame using Pandas (a Python library), removing punctuation and special characters from text data, deleting unnecessary columns, and removing duplicate data, converting the data into a format suitable for analysis.

[1910] 3. Data Analysis

[1911] The server inputs the preprocessed data into the generative AI and sentiment engine. It uses natural language processing (NLP) technologies such as BERT and GPT-3 to analyze the sentiment of reviews and analyze market trends from purchase history and comparison history data. The sentiment engine also uses tools such as Amazon Comprehend to identify consumer sentiment.

[1912] 4. Product idea generation

[1913] The server uses the generative AI to generate new product ideas based on the analysis results. It uses OpenAI's API and Hugging Face's Transformers to automatically create multiple product ideas based on specified parameters. For example, enter "Generate a new smartphone idea based on the following specifications: ..." as the prompt.

[1914] 5. Prototype design and construction

[1915] The terminal (such as the design team's PC) uses AutoCAD or SolidWorks to create detailed design drawings based on the product ideas received from the server. The design drawings include the specific specifications proposed by the generative AI, and a prototype is then produced based on these.

[1916] 6. Test the prototype and gather feedback

[1917] The server provides the prototype to the test consumers and collects their feedback using Google Forms or SurveyMonkey. The feedback form contains the consumers' opinions and impressions about the prototype, which are analyzed by an emotion engine to identify the consumers' emotions.

[1918] 7. Analyzing Feedback and Improving Products

[1919] The server analyzes the collected feedback and identifies areas for improvement in the product. Using Pandas and SciPy, it performs detailed analysis of the feedback data and identifies areas for improvement. It notifies the design team of the results and creates an improved version.

[1920] 8. Manufacturing and bringing products to market

[1921] The server finalizes the product specifications and sends manufacturing instructions to the factory using the ERP system, after which the products are mass-produced and made available for sale on online shopping platforms such as Shopify, bringing the products to market.

[1922] In this way, the present invention is a system that covers a whole series of processes from data collection to product development, feedback collection, product improvement, and final market release, and by introducing an emotion engine, it is possible to analyze consumer emotions in detail and improve product characteristics to reflect those emotions. This allows products that provide high consumer satisfaction to be released to the market quickly.

[1923] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1924] Program processing flow

[1925] Step 1: Collect consumer data

[1926] The server collects consumer data (purchase history, comparison history, and reviews) from the online shopping platform.

[1927] Input: API endpoint of online shopping platform

[1928] Data processing: Purchase history, comparison history, and reviews are obtained in JSON format and saved in a database

[1929] Output: Raw data stored in a database

[1930] Specific operation: Makes an API call using Python's requests library and saves the retrieved data to a database.

[1931] Step 2: Preprocessing the data

[1932] The server performs pre-processing on the collected data.

[1933] Input: Raw data in the database

[1934] Data processing: removing punctuation and special characters, deleting unnecessary columns, removing duplicate data

[1935] Output: Cleaned data

[1936] Specific behavior: Convert to a data frame using Pandas and perform data cleaning operations.

[1937] Step 3: Analyze the data

[1938] The server feeds the pre-processed data into the generative AI and emotion engine.

[1939] Input: Preprocessed data

[1940] Data processing: Using natural language processing technology to analyze the sentiment of reviews and understand market trends

[1941] Output: Sentiment analysis results and market trend data

[1942] What it does: Perform sentiment analysis and market trend analysis using BERT, GPT-3, and Amazon Comprehend.

[1943] Step 4: Generate product ideas

[1944] The server uses a generative AI to generate new product ideas based on the analysis results.

[1945] Input: Sentiment analysis results and market trend data

[1946] Data processing: Providing product recommendations based on specified parameters

[1947] Output: New product ideas

[1948] What it does: Uses OpenAI APIs and Hugging Face Transformers to generate product ideas based on a given prompt.

[1949] Step 5: Design and build a prototype

[1950] The terminal (such as the design team's PC) creates detailed design drawings based on the product ideas received from the server.

[1951] Input: New product idea

[1952] Data processing: Creating detailed blueprints using CAD software

[1953] Output: Prototype blueprints

[1954] Specific Tasks: Using AutoCAD and SolidWorks, you will create blueprints for the design team to bring product ideas to life.

[1955] Step 6: Test the prototype and gather feedback

[1956] The server provides the prototype to monitor consumers and collects their feedback.

[1957] Input: Prototype, Feedback Form

[1958] Data processing: Collecting consumer ratings and comments and analyzing their sentiment

[1959] Output: Aggregated feedback and sentiment analysis results

[1960] What it does: Collect feedback using Google Forms and SurveyMonkey, and perform sentiment analysis using Amazon Comprehend.

[1961] Step 7: Analyze feedback and improve the product

[1962] The server analyzes the collected feedback and identifies product improvements.

[1963] Input: Aggregated feedback and sentiment analysis results

[1964] Data processing: Analyzing feedback data and extracting areas for improvement

[1965] Output: List of improvements

[1966] What it does: Uses Pandas and SciPy to perform detailed analysis of feedback and inform the design team of improvements.

[1967] Step 8: Manufacture and market your product

[1968] The server determines the final product specifications and sends manufacturing instructions to the factory.

[1969] Input: List of improvements, final specifications

[1970] Data processing: Finalizing manufacturing instructions and preparing for market launch

[1971] Output: Produced products, on sale

[1972] What it does: Uses an ERP system to send production instructions to factories and starts selling on e-commerce platforms like Shopify.

[1973] The above specific steps will realize a series of processes from product development to market launch using consumer data.

[1974] (Application example 2)

[1975] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1976] In the past, it was difficult to utilize consumer data to quickly develop products that met market needs in the product development process. Furthermore, there was a lack of technology to understand the emotions of drivers and passengers in real time and adjust in-car navigation and entertainment accordingly. Under these circumstances, it was difficult to develop products that maximize consumer satisfaction and provide a safe and comfortable driving environment for drivers and passengers.

[1977] 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.

[1978] In this invention, the server includes means for collecting consumer data including purchase history, comparison history, and reviews, means for preprocessing the collected data, means for analyzing the preprocessed data and identifying consumer needs, means for a generative AI to generate new product ideas based on the analysis results, means for designing and manufacturing prototypes based on the generated product ideas, means for testing the prototypes and collecting feedback from consumers, means for analyzing the feedback and improving the product, means for manufacturing the improved product and providing it to the market, means for collecting emotional data of drivers and passengers, means for anonymizing the collected emotional data, and means for providing driving routes and entertainment based on the emotional data. This enables the development and provision of products that accurately reflect consumer emotions and needs, and a safe and comfortable driving experience that takes into account the emotions of drivers and passengers.

[1979] "Consumer Data" is information about consumer behavior and opinions, such as purchase history, comparison history, and reviews.

[1980] "Preprocessing" means removing unnecessary information from raw data and converting it into a form suitable for analysis.

[1981] "Analyzing" means using pre-processed data to extract information and patterns and make sense of them.

[1982] "Generative AI" is a technology that uses artificial intelligence algorithms to automatically generate new product ideas and proposals.

[1983] A "product idea" is a concept for a new product or service that is generated with consumer needs and emotions in mind.

[1984] A "prototype" is an early stage product that embodies a generated product idea.

[1985] "Feedback" refers to reaction information such as evaluations and opinions from consumers who have used the prototype.

[1986] "Improvement" means improving the product's specifications and features based on collected feedback.

[1987] "Emotion data" is information that indicates the emotional state of the driver or passengers, obtained from their faces, voices, etc.

[1988] "Navigation" refers to systems and functions that provide the optimal route to a destination.

[1989] "Entertainment" refers to content such as music and videos that provide enjoyment and satisfaction.

[1990] "Anonymization" is a method of removing or transforming personally identifiable information to protect privacy.

[1991] "Real-time" refers to the processing and provision of information immediately, without delay.

[1992] The present invention provides a system for more accurately grasping market needs and providing products by combining consumer data and emotion data. Specific embodiments of the system are described below.

[1993] Hardware and software used

[1994] The specific hardware and software used as servers and terminals include the following:

[1995] Hardware:

[1996] Camera: Used to recognize the faces of the driver and passengers.

[1997] Microphone: Used to collect audio data.

[1998] Computer: A server or PC for analyzing and storing data.

[1999] software:

[2000] OpenCV: A library for acquiring and processing camera images.

[2001] DeepFace: A library for facial expression analysis.

[2002] Librosa: A library for reading and parsing audio data.

[2003] NLP technologies: Libraries for natural language processing (e.g. spaCy).

[2004] AI generative model: An algorithm that uses generative AI to automatically generate new product ideas.

[2005] Data processing flow

[2006] 1. Data Collection:

[2007] The server collects consumer and emotional data from online shopping platforms and in-car sensors. Consumer data includes purchase history, comparison shopping history, and reviews, while emotional data includes facial expressions and voice recordings of drivers and passengers.

[2008] 2. Data preprocessing:

[2009] The server preprocesses the collected data, specifically cleaning text data (such as reviews) and removing punctuation and special characters, deleting unnecessary parts from image data, and removing noise from audio data.

[2010] 3. Data Analysis:

[2011] The server analyzes the preprocessed data, using natural language processing (NLP) technology to analyze the sentiment of reviews, and analyzes market trends and the characteristics of popular products based on purchase history and comparison history. It also identifies the emotions of drivers and passengers through facial expression and voice analysis.

[2012] 4. Product idea generation and provision:

[2013] The server generates new product ideas using a generative AI model. Based on the analysis results, the generative AI automatically creates multiple ideas taking into account specific parameters (price range, functionality, design, etc.). It also provides driving directions and entertainment based on emotional data.

[2014] Specific examples

[2015] When a consumer purchases a home appliance on an online platform, the purchase history and reviews are collected on a server. Sentiment analysis of the reviews is performed and it is discovered that many consumers express positive emotions such as "very satisfied" with the features of a particular home appliance. Based on this result, the generative AI proposes a product idea for a "high-performance, cost-effective home appliance." At the same time, the system uses the in-car camera and microphone to collect the driver's facial expressions and voice. If it determines that the driver is nervous, it plays relaxing music and suggests a safe route.

[2016] Example prompt for a generative AI model:

[2017] "Suggest ideas for home appliances that consumers would be happy to purchase."

[2018] "If you sense a driver is nervous, suggest the most relaxing route."

[2019] "If passengers are bored, offer them music recommendations."

[2020] The above is a specific description of the "Mode for Carrying Out the Invention." The present invention enables highly accurate market response by combining consumer data and emotion data.

[2021] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2022] Step 1:

[2023] Collecting consumer and sentiment data

[2024] The server collects consumer and emotional data from online shopping platforms and in-car sensors. Input data includes purchase history, comparison shopping history, reviews, driver and passenger facial expressions, and voice. The output is the collected raw data. Specifically, the server uses an API to obtain purchase history and reviews from online shopping platforms, and uses the camera and microphone in the in-car sensors to capture driver and passenger emotional data.

[2025] Step 2:

[2026] Data Preprocessing

[2027] The server performs preprocessing on the collected data. The input is the raw data collected in step 1. Specific data processing includes removing punctuation and special characters from the text data and removing noise from the audio data. The output is cleaned data. Specifically, the text data is cleaned using regular expressions, and the audio data is denoised using Librosa.

[2028] Step 3:

[2029] Anonymizing Emotional Data

[2030] The server anonymizes the collected emotional data. The input is the emotional data preprocessed in step 2. Data calculation involves deleting or encrypting information that can identify a specific individual. The output is anonymized emotional data. Specific operations include removing features that can identify an individual from facial expression data and assigning an identification code to the analysis results of the voice data.

[2031] Step 4:

[2032] Data analysis

[2033] The server analyzes the preprocessed consumer data and sentiment data. The input is the cleaned and anonymized data obtained in steps 2 and 3. Specific data calculations include analyzing the sentiment of reviews using natural language processing techniques and analyzing market trends from purchase history and comparison history. The output is the analysis results. Operations include calculating sentiment scores based on specific keywords using an NLP library and extracting trend information from the database.

[2034] Step 5:

[2035] Product idea generation

[2036] The server uses the generative AI model to generate new product ideas based on the analysis results. The input is the analysis results from step 4. As a data calculation, the generative AI generates product ideas based on specific parameters (price, function, design, etc.). The output is the generated product idea. Specifically, the server inputs market trends and sentiment scores into the generative AI model, and generates product ideas based on the prompt text.

[2037] Step 6:

[2038] Prototype design and construction

[2039] The terminal (such as the design team's PC) creates detailed design drawings based on the product idea generated in step 5 and produces a prototype. The input is the generated product idea. As data calculation, a design drawing is created using CAD software and prototype production instructions are output. The output is production instructions and a prototype. As an operation, a detailed design is created using CAD software and prototype production instructions are sent to the factory.

[2040] Step 7:

[2041] Testing prototypes and gathering feedback

[2042] The server provides the prototype to test consumers and collects their feedback. The input is the test results of the test consumers. Specific data processing involves collecting evaluations and opinions from testers and analyzing them with an emotion engine. The output is feedback data. The system operates by collecting feedback through online forms and direct interviews, and analyzing the data with an emotion engine.

[2043] Step 8:

[2044] Feedback analysis and product improvement

[2045] The server analyzes the collected feedback and improves the product. The input is the feedback data from step 7. The data calculation analyzes the collected feedback and identifies necessary improvements. The output is improvement instructions. The operation analyzes the feedback data and integrates the sentiment score and user comments to derive improvement suggestions.

[2046] Step 9:

[2047] Manufacturing and bringing products to market

[2048] The server finalizes the product specifications and sends manufacturing instructions to the factory. The input is the improvement instructions from step 8. As a data calculation, it formulates a manufacturing plan and outputs manufacturing instructions. The output is a mass-produced product. As an operation, it instructs the manufacturing department on the production plan and starts selling the completed product on the online platform.

[2049] Step 10:

[2050] Providing driving directions and entertainment based on emotion data

[2051] The server provides optimal driving routes and entertainment based on the emotional data of the driver and passengers. The input is the emotional data collected in step 1. The data calculation involves analyzing the emotional data and selecting routes and content based on it. The output is the proposed route and entertainment. The operation involves selecting a route that will relax the driver based on the emotional data and selecting music and videos to provide.

[2052] The above is the flow of processing in the system that realizes the application example.

[2053] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2054] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2055] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2056] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2057] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2058] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half...

Claims

1. a means of collecting consumer data consisting of purchase history, comparison history, and reviews; a means for pre-processing the collected data; A means of analyzing the pre-processed data to identify consumer needs; A means for the generative AI to generate new product ideas based on the analysis results; A means of designing and producing prototypes based on the generated product ideas; a means of testing prototypes and gathering feedback from consumers; A means to analyze feedback and improve the product; a means of producing and offering to market the improved product; A system including:

2. The system according to claim 1, characterized in that data collection, preprocessing, analysis, and product idea generation using generation AI are all performed automatically.

3. 10. The system of claim 1, further comprising means for anonymizing consumer data to ensure privacy.

Images